Circular Twain - Reference Implementations Wiki - User contributions [en-gb]

Main Page

2025-05-06T10:04:49Z

Admin ugqr649i:

Welcome to the CircularTwain project's portfolio of reference implementations wiki.

This wiki serves as live documentation for collecting technologies and reference implementations of AI related to manufacturing business cases, with a focus on circularity and sustainability aspects. The presented implementations derive from both from open source initiatives and the consortium's partners’ background.

== Getting started ==
* Browse through the [[AI portfolio of reference implementations]]
* Browse through the [[solutions for circularity Data Space implementations]]
* Visit the [https://www.circular-twain-project.eu: CircularTwain H2020 Project Official Website]

D.16: XAI for Unstructured Data

2025-04-28T09:52:15Z

Admin ugqr649i:

• '''Short Description''': The XAI for unstructured data is a software component that provides an explanation on how the object detecion algorithm is working in the form of heatmap. The output of the XAI for unstructured data (heatmap) shows the zones of the image that the algorithm is using for detecting and classifying a certain object. The software needs the AI model (NN) and the image to show how the model is behaving. It provides a REST API for uploading the image.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': Neural Networks

• '''Related technologies''': N.A

• '''Applicable Research Area''': Explainable AI

• '''Applicable Technical Category''': Machine learning

• '''License Information''': Open Source license

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

D.16: XAI for Unstructured Data

2025-04-28T09:52:08Z

Admin ugqr649i:

• '''Short Description''': The XAI for unstructured data is a software component that provides an explanation on how the object detecion algorithm is working in the form of heatmap. The output of the XAI for unstructured data (heatmap) shows the zones of the image that the algorithm is using for detecting and classifying a certain object. The software needs the AI model (NN) and the image to show how the model is behaving. It provides a REST API for uploading the image.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': Neural Networks

• '''Related technologies''': N.A

• '''Applicable Research Area''': Explainable Ai

• '''Applicable Technical Category''': Machine learning

• '''License Information''': Open Source license

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

D.15: Product Digital Twin

2025-04-28T09:50:45Z

Admin ugqr649i:

• '''Short Description''': The Product Digital Twin (DT) plays a crucial role in fostering sustainability and facilitating remanufacturing, demanufacturing, and recycling processes while prioritizing sustainability and eco-friendly product design within a Circular Economy environment. It is utilizing Asset Administration Shell (AAS) for specifications and Eclipse BaSyx for implementation, the Product DT enables comprehensive monitoring and management of product lifecycles. It tracks the usage, performance, and condition of products, enhancing the resource efficiency. Furthermore, it integrates a data management and processing component, leveraging TensorFlow services for data analytics. Leveraging this data, AI algorithms, are promoting eco-friendly product design and supporting a sustainable Circular Economy by maximizing resource recovery and minimizing waste.

The Product Digital Twin (DT) encompasses various technical elements to ensure its functionality and interoperability.

• Standards and Protocols: The Product DT adheres to industry standards and protocols to ensure compatibility and seamless integration with existing systems. This includes standards such as Asset Administration Shell (AAS), which provides a standardized approach to describe and manage assets in a digitalized environment. Additionally, protocols like MQTT (Message Queuing Telemetry Transport) are used for efficient and reliable communication between the Product DT and other components of the Circular Economy ecosystem.

• APIs (Application Programming Interfaces): The Product DT offers well-defined APIs, following the AAS specifications, to facilitate interaction with external systems and applications. These APIs allow developers to access and manipulate data stored in the Product DT, enabling functionalities such as querying product specifications, monitoring performance metrics, and triggering maintenance tasks.

• Data Management and Processing Component: The Product DT includes a data management and processing component responsible for handling data generated by the Product DT. TensorFlow services are integrated to enable advanced data analytics, including machine learning algorithms for predictive maintenance and eco-friendly product design.

• Integration with Eclipse BaSyx: Eclipse BaSyx serves as the implementation framework for the Product DT, providing tools and libraries for developing and deploying Digital Twin solutions. The Product DT leverages BaSyx's capabilities to model and execute Digital Twins, enabling seamless integration with the Circular Economy ecosystem.

• '''Reference, URL''': https://www.netcompany-intrasoft.com/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': N.A

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': N.A

• '''License Information''': N.A

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

D.14: Process Digital Twin

2025-04-28T09:49:46Z

Admin ugqr649i:

• '''Short Description''': The Process Digital Twin (DT) is a virtual representation of a process that incorporates real-time data together with other forms of AI to analyze the system behaviour, performance, and outcomes. Therefore, the Process DT can be seen as a higher-level AI-enabled AAS that ingests from other AASs deployed in the production line and other DTs (Product and Person/Human). This “newer” AAS is especially designed to collect, preprocess data and execute AI/ML models for computing answers, insights, optimizations, while solving “circular manufacturing” problems.
The Process DT has been developed by using the AAS as technological background. This means that it provides the same REST API, the "data image" of the process is built by using the AAS's metamodel. And event-based communication (using MQTT) is supported. Since it needs to collect and send data to other AAS that are part of the process, then an orchestrator has been embedded. The orchestrator is using the behaviour tree mathematical model for creating, defining, managing and executing complex tasks. Finally, an embedded AI engine has been developed to allow the exectution of Neural Networks developed using TensorFlow.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': Neural Networks

• '''Related technologies''': Tensorflow

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information''': Open Source license

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

B.12: Object Detection and Classification for PC Components

2025-04-28T09:48:53Z

Admin ugqr649i:

• '''Short Description''': Advanced Object Detection and Classification Module: Incorporates pretrained neural network models for precise object detection and classification, embedded within the process Digital Twin, utilizing NOVAAS technology for optimal performance. The system integrates the YOLO v5 model for advanced object detection and classification within the Digital Twin software, using NOVASS technology. It employs industry standards, protocols, and APIs for seamless execution and interoperability, offering precise object recognition and improved decision-making across sectors.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': Neural Networks

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': Computer Vision

• '''License Information''': Copyright

• '''Related to circularity and sustainability''': Yes

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.13: NOVAAS

2025-04-28T09:47:34Z

Admin ugqr649i:

• '''Short Description''': NOVAAS is an open source implementation of the RAMI4.0 Asset Administration Shell concept. The Asset Administration Shell (AAS) is a key concept within the context of the Industrial Internet of Things (IIoT) and Industry 4.0. It is a standardized framework for describing and managing industrial assets and their digital representations (i.e., a “data image” of the asset) in a way that enables seamless interoperability between various components and systems in industrial environments. The AAS is used to digitalize any physical asset in order to be integrated seamlessly into and I4.0 compliant system. In the context of Circular TwAIn NOVAAS will be used for designing and developing I4.0 compatible Digital Twins. Moreover, NOVAAS can be used to run AI algorithms at the edge for several applications such as quality inspection, predictive maintenance, dashboarding etc.
NOVAAS is currently compliant with the V2 specification of the AAS, the development team is working on giving support to the newer V3 specification of the AAS. The tool is implemented using the next-generation software development principles, i.e., using low/no code platforms, microservices and APIs and containers. The tool is containerised using Docker. Latest version of the tool is available on GitLab as Open Source repository (both source code and image). NOVAAS provides a REST API for retrieving data and send commands to the asset. Event-based communication (using MQTT standard) is also supported and used in the context of Circular TwAIn.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''':Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': N.A

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative Ai

• '''Applicable Technical Category''': N.A

• '''License Information''': Open Source

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

D.12: Mechanical Recycling Digital Twin

2025-04-28T09:31:44Z

Admin ugqr649i:

• '''Short Description''': An innovative process Digital Twin which implements an AI driven algorithm for optimization of recycling treatment parameters. AI driven algorithm for optimization of treatment parameters for LIBs recycling.

• '''Reference, URL''': https://www.polimi.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular Twain

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': N.A

• '''Applicable Technical Category''': N.A

• '''License Information''': N.A

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Battery Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

B.11: LIB Cells Health State Digital Twin

2025-04-28T09:30:20Z

Admin ugqr649i:

• '''Short Description''': An innovative process DT which implements AI tools for the characterization of the Li-ion batteries state-of-health. AI driven engineering method for the characterization of the LIBs State-of-health.

• '''Reference, URL''': https://www.polimi.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': N.A

• '''Applicable Technical Category''': N.A

• '''License Information''': N.A

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Battery Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

D.11: Hybrid Digital Twin

2025-04-28T09:29:19Z

Admin ugqr649i:

• '''Short Description''': Hybrid Digital Twin (DT) is an advanced tool designed for the process industry, particularly in sectors like petrochemicals and energy. Its primary utility lies in combining a data-driven Digital Twin model with physical process models. This integration enables it to leverage data from various sources, including control systems like DCS and SCADA, and apply AI analytics for predictive capabilities and system monitoring. The Hybrid DT is crucial for understanding and optimizing complex industrial processes, enhancing decision-making, and predicting system performance. It assists in monitoring usage, energy consumption, and emissions, and plays a key role in predictive maintenance and process optimization. This technology is particularly valuable in managing and optimizing the lifecycle of process plants and in aiding the digital transformation of factories.
Hybrid Digital Twin (Hybrid DT) encompasses the integration of various standards, protocols, and APIs to ensure effective and secure data handling. This integration typically includes:

• Integrating advanced AI and machine learning algorithms for predictive analytics and process optimization.

• Application Programming Interfaces (APIs) for interoperability, enabling the Hybrid DT to interact with different software systems,Aspen and MATLAB, and platforms for data analysis and process optimization.

• Utilizing industry-standard communication protocols like OPC UA and Modbus to facilitate data exchange between the Hybrid DT, Aspen models, control systems (DCS and SCADA), and MATLAB.

• Incorporating robust security measures to protect sensitive data and system integrity.

• Ensuring compatibility with various industrial data standards for seamless data acquisition and integration.

Finally it supports many relevant standards on ISO/IECD and ISO/IEC.

• '''Reference, URL''': https://www.teknopar.com.tr/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': As A Service

• '''AI Breadth''': ML

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': Other

• '''License Information''': Copyright

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Petrochemical industry and Energy sector

Go back to the '''[[AI portfolio of reference implementations]]'''

B.10: Disassembly Digital Twin

2025-04-28T09:21:23Z

Admin ugqr649i:

• '''Short Description''': The Disassembly Digital Twin is an innovative process DT which executes machine learning aided disassembly algorithm for the execution of battery disassembly operations.

• '''Reference, URL''': https://www.polimi.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': AI Services

• '''License Information''': N.A

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Battery Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

B.9: Decision Support System

2025-04-28T09:20:40Z

Admin ugqr649i:

• '''Short Description''': The Decision Support System (DSS) manages an extended Digital Battery Passport imposing an economic overlayer to dynamically estimate the value of the battery for recycling and remanufacturing. The tool exploits AI to merge data available on the battery in terms of materials composition and state-of-health, with data characterizing the market quotations to obtain a decision support system which guides operational choices in function of the most profitable expected scenario.

• '''Reference, URL''': https://www.cobat.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': As a Service

• '''AI Breadth''': ML

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': AI Services

• '''License Information''': N.A

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Battery Manufacturers, Battery Recyclers

Go back to the '''[[AI portfolio of reference implementations]]'''

B.10: Disassembly Digital Twin

2025-04-28T09:11:15Z

Admin ugqr649i:

• '''Short Description''': The Disassembly Digital Twin is an innovative process DT which executes machine learning aided disassembly algorithm for the execution of battery disassembly operations.

• '''Reference, URL''': https://www.polimi.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': AI Services

• '''License Information''':

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Battery Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

A17: FA³ST AAS for Circular Economy

2025-04-28T09:08:29Z

Admin ugqr649i:

• '''Short Description''':

• '''Reference, URL''':

• '''Applicable Business Category''':

• '''Application in relevant Projects/Initiatives''':

• '''Asset Type''':

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information''':

• '''Related to circularity and sustainability''':

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

A13: AI Aided Disassembly Planner

2025-04-28T09:08:15Z

Admin ugqr649i:

• '''Short Description''': This tool will provide a plan for the optimal disassemble of electronic consumables (PCs) based on the observation of the overall components considering the colaborative working of one operator and one robotic arm. The complete tool will consist on AI models for part recognition with semantic segmentation capabilities. Based on confidence rates, the system will assume part of the disassembly tasks as doable and other as to be delegated. Based on these constrictions, additional data extracted from a diagnosis tool and hardware availability for disassemble (robot) a plan will be delivered with a set of actions and associated coordinates to be delivered to the robotics system responsible for disassembly. A text-based report to explain the plan will be delivered to the operator from which he/she can infer what to do in collaboration with the robot.

• '''Reference, URL''': https://www.aimen.es/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': Computer Vision

• '''License Information''': Open Source License

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

D.16: XAI for Unstructured Data

2025-04-28T09:07:47Z

Admin ugqr649i:

• '''Short Description''': The XAI for unstructured data is a software component that provides an explanation on how the object detecion algorithm is working in the form of heatmap. The output of the XAI for unstructured data (heatmap) shows the zones of the image that the algorithm is using for detecting and classifying a certain object. The software needs the AI model (NN) and the image to show how the model is behaving. It provides a REST API for uploading the image.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information''': Open Source license

• '''Related to circularity and sustainability''':

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.15: Product Digital Twin

2025-04-28T09:07:37Z

Admin ugqr649i:

• '''Short Description''': The Product Digital Twin (DT) plays a crucial role in fostering sustainability and facilitating remanufacturing, demanufacturing, and recycling processes while prioritizing sustainability and eco-friendly product design within a Circular Economy environment. It is utilizing Asset Administration Shell (AAS) for specifications and Eclipse BaSyx for implementation, the Product DT enables comprehensive monitoring and management of product lifecycles. It tracks the usage, performance, and condition of products, enhancing the resource efficiency. Furthermore, it integrates a data management and processing component, leveraging TensorFlow services for data analytics. Leveraging this data, AI algorithms, are promoting eco-friendly product design and supporting a sustainable Circular Economy by maximizing resource recovery and minimizing waste.

The Product Digital Twin (DT) encompasses various technical elements to ensure its functionality and interoperability.

• Standards and Protocols: The Product DT adheres to industry standards and protocols to ensure compatibility and seamless integration with existing systems. This includes standards such as Asset Administration Shell (AAS), which provides a standardized approach to describe and manage assets in a digitalized environment. Additionally, protocols like MQTT (Message Queuing Telemetry Transport) are used for efficient and reliable communication between the Product DT and other components of the Circular Economy ecosystem.

• APIs (Application Programming Interfaces): The Product DT offers well-defined APIs, following the AAS specifications, to facilitate interaction with external systems and applications. These APIs allow developers to access and manipulate data stored in the Product DT, enabling functionalities such as querying product specifications, monitoring performance metrics, and triggering maintenance tasks.

• Data Management and Processing Component: The Product DT includes a data management and processing component responsible for handling data generated by the Product DT. TensorFlow services are integrated to enable advanced data analytics, including machine learning algorithms for predictive maintenance and eco-friendly product design.

• Integration with Eclipse BaSyx: Eclipse BaSyx serves as the implementation framework for the Product DT, providing tools and libraries for developing and deploying Digital Twin solutions. The Product DT leverages BaSyx's capabilities to model and execute Digital Twins, enabling seamless integration with the Circular Economy ecosystem.

• '''Reference, URL''': https://www.netcompany-intrasoft.com/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information''':

• '''Related to circularity and sustainability''':

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.14: Process Digital Twin

2025-04-28T09:07:24Z

Admin ugqr649i:

• '''Short Description''': The Process Digital Twin (DT) is a virtual representation of a process that incorporates real-time data together with other forms of AI to analyze the system behaviour, performance, and outcomes. Therefore, the Process DT can be seen as a higher-level AI-enabled AAS that ingests from other AASs deployed in the production line and other DTs (Product and Person/Human). This “newer” AAS is especially designed to collect, preprocess data and execute AI/ML models for computing answers, insights, optimizations, while solving “circular manufacturing” problems.
The Process DT has been developed by using the AAS as technological background. This means that it provides the same REST API, the "data image" of the process is built by using the AAS's metamodel. And event-based communication (using MQTT) is supported. Since it needs to collect and send data to other AAS that are part of the process, then an orchestrator has been embedded. The orchestrator is using the behaviour tree mathematical model for creating, defining, managing and executing complex tasks. Finally, an embedded AI engine has been developed to allow the exectution of Neural Networks developed using TensorFlow.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML, Neural Networks

• '''Learning Ability''':

• '''Related technologies''': Tensorflow

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information''': Open Source license

• '''Related to circularity and sustainability''':

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.13: NOVAAS

2025-04-28T09:07:13Z

Admin ugqr649i:

• '''Short Description''': NOVAAS is an open source implementation of the RAMI4.0 Asset Administration Shell concept. The Asset Administration Shell (AAS) is a key concept within the context of the Industrial Internet of Things (IIoT) and Industry 4.0. It is a standardized framework for describing and managing industrial assets and their digital representations (i.e., a “data image” of the asset) in a way that enables seamless interoperability between various components and systems in industrial environments. The AAS is used to digitalize any physical asset in order to be integrated seamlessly into and I4.0 compliant system. In the context of Circular TwAIn NOVAAS will be used for designing and developing I4.0 compatible Digital Twins. Moreover, NOVAAS can be used to run AI algorithms at the edge for several applications such as quality inspection, predictive maintenance, dashboarding etc.
NOVAAS is currently compliant with the V2 specification of the AAS, the development team is working on giving support to the newer V3 specification of the AAS. The tool is implemented using the next-generation software development principles, i.e., using low/no code platforms, microservices and APIs and containers. The tool is containerised using Docker. Latest version of the tool is available on GitLab as Open Source repository (both source code and image). NOVAAS provides a REST API for retrieving data and send commands to the asset. Event-based communication (using MQTT standard) is also supported and used in the context of Circular TwAIn.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''':yers, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information''': Copyright

• '''Related to circularity and sustainability''': Yes

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.12: Mechanical Recycling Digital Twin

2025-04-28T09:07:02Z

Admin ugqr649i:

• '''Short Description''': An innovative process Digital Twin which implements an AI driven algorithm for optimization of recycling treatment parameters. AI driven algorithm for optimization of treatment parameters for LIBs recycling.

• '''Reference, URL''': https://www.polimi.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular Twain

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information''':

• '''Related to circularity and sustainability''': Yes

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.11: Hybrid Digital Twin

2025-04-28T09:06:39Z

Admin ugqr649i:

• '''Short Description''': Hybrid Digital Twin (DT) is an advanced tool designed for the process industry, particularly in sectors like petrochemicals and energy. Its primary utility lies in combining a data-driven Digital Twin model with physical process models. This integration enables it to leverage data from various sources, including control systems like DCS and SCADA, and apply AI analytics for predictive capabilities and system monitoring. The Hybrid DT is crucial for understanding and optimizing complex industrial processes, enhancing decision-making, and predicting system performance. It assists in monitoring usage, energy consumption, and emissions, and plays a key role in predictive maintenance and process optimization. This technology is particularly valuable in managing and optimizing the lifecycle of process plants and in aiding the digital transformation of factories.
Hybrid Digital Twin (Hybrid DT) encompasses the integration of various standards, protocols, and APIs to ensure effective and secure data handling. This integration typically includes:

• Integrating advanced AI and machine learning algorithms for predictive analytics and process optimization.

• Application Programming Interfaces (APIs) for interoperability, enabling the Hybrid DT to interact with different software systems,Aspen and MATLAB, and platforms for data analysis and process optimization.

• Utilizing industry-standard communication protocols like OPC UA and Modbus to facilitate data exchange between the Hybrid DT, Aspen models, control systems (DCS and SCADA), and MATLAB.

• Incorporating robust security measures to protect sensitive data and system integrity.

• Ensuring compatibility with various industrial data standards for seamless data acquisition and integration.

Finally it supports many relevant standards on ISO/IECD and ISO/IEC.

• '''Reference, URL''': https://www.teknopar.com.tr/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': As A Service

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information''': Copyright

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Petrochemical industry and energy sector

Go back to the '''[[AI portfolio of reference implementations]]'''

D.10: Human Digital Twin

2025-04-28T09:06:28Z

Admin ugqr649i:

D.7: Behaviour Tree Editor

2025-04-28T09:06:06Z

Admin ugqr649i:

• '''Short Description''': The Behaviour Tree Editor is a web-based editor that allows orchestration and supervision based on the behaviour tree concept. The Behaviour Tree editor, built on rete.js, offers a visual programming interface for designing and monitoring Behavior Trees, crucial for managing autonomous agents. It supports embedding in various platforms due to its flexible rete.js foundation. The editor facilitates intuitive, drag-and-drop interaction, adhering to user experience standards. It provides real-time feedback for behavior tree creation and execution, enhancing usability and efficiency. The editor's API allows for seamless integration with existing systems, ensuring broad applicability. Additionally, its design ensures compatibility and interoperability with various standards and protocols in software development.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': N.A

• '''Learning Ability''': N.A

• '''Related technologies''':N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': Optimisation

• '''License Information''': Open Source

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Manufacturers and Quality Control Professionals, Educational Institutions and Students.

Go back to the '''[[AI portfolio of reference implementations]]'''

D.6: AutoML Tool

2025-04-28T09:05:38Z

Admin ugqr649i:

• '''Short Description''': The AutoML Tool is designed for domain users who are not experts in machine learning. It provides an easy-to-use, wizard-like interface for covering every step of data-driven machine learning. Users can upload data, create ad hoc queries, and perform preprocessing tasks such as normalization and standardization. It allows users to train and test machine learning algorithms, compare models using various metrics, and save the best-performing models. The goal is to make machine learning approachable and useful for operators and managers in the process industry, enabling them to use AI for process optimization without requiring in-depth technical knowledge of data science. The AutoML Tool is a framework that includes a graphical user interface for data preprocessing, model training, and testing. It supports data upload from databases or CSV files and uses customizable filters for data selection. Metrics such as F1 score, Area Under the Curve, and confusion matrices are used for model comparison. The system likely adheres to relevant data standards and uses common protocols and APIs for data handling and model deployment. AutoML Tool's optimization algorithms create a closed-loop system. This allows for continuously refining the model and control strategy based on real-time data feedback. The AutoML Tool supports relevant standards in ISO/IEC.

• '''Reference, URL''': https://www.teknopar.com.tr/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''':Yers - Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': N.A.

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': Machine Learning

• '''License Information''': N.A

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Operators and Factory Managers

Go back to the '''[[AI portfolio of reference implementations]]'''

C.7: EthicalML

2025-04-28T09:05:21Z

Admin ugqr649i:

• '''Short Description''':
A repository containing a curated list of open source libraries for production machine learning

• '''Reference, URL''': https://github.com/EthicalML/awesome-production-machine-learning

• '''Relevant Domain/Industry''': Research

• '''Application in relevant Projects/Initiatives''': N.A

• '''Asset Type''': Other, Repository of libraries

• '''AI Breadth''': XAI.

• '''Learning Ability''': N.A.

• '''Related technologies''': sk-learn, pytorch, keras, tensorflow

• '''Applicable Research Area''': Verifiable AI

• '''Applicable Technical Category''': Machine Learning

• '''License Information''': Multiple (mostly MIT)

• '''Related to circularity and sustainability''': No

• '''Audience''': Developers

Go back to the '''[[AI portfolio of reference implementations]]'''

B.13: Waste Management Best Practices

2025-04-28T09:04:50Z

Admin ugqr649i:

• '''Short Description''': Redesign of operational standards in the segregation of waste in the light of AI tools and collaborative robotics, thus increasing the recovery of critical materials, reducing costs and creating added value. It updates the current intructions to adjust to emerging technologies. The results are presented in the form of an updated protocol to provide workers and waste management companies with instructions to maximize the advantages of AI and collaborative robotics.

• '''Reference, URL''': https://www.recyclia.es/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Other

• '''AI Breadth''': N/A

• '''Learning Ability''': N/A

• '''Related technologies''': N/A

• '''Applicable Research Area''': Other

• '''Applicable Technical Category''': Optimisation

• '''License Information''': Open-source license

• '''Related to circularity and sustainability''': Yes

• '''Audience''': WEEE, managers, dismantlers, and recyclers

Go back to the '''[[AI portfolio of reference implementations]]'''

B.12: Object Detection and Classification for PC Components

2025-04-28T09:04:40Z

Admin ugqr649i:

• '''Short Description''': Advanced Object Detection and Classification Module: Incorporates pretrained neural network models for precise object detection and classification, embedded within the process Digital Twin, utilizing NOVAAS technology for optimal performance. The system integrates the YOLO v5 model for advanced object detection and classification within the Digital Twin software, using NOVASS technology. It employs industry standards, protocols, and APIs for seamless execution and interoperability, offering precise object recognition and improved decision-making across sectors.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information''': Copyright

• '''Related to circularity and sustainability''': Yes

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

B.11: LIB Cells Health State Digital Twin

2025-04-28T09:04:31Z

Admin ugqr649i:

• '''Short Description''': An innovative process DT which implements AI tools for the characterization of the Li-ion batteries state-of-health. AI driven engineering method for the characterization of the LIBs State-of-health.

• '''Reference, URL''': https://www.polimi.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information''':

• '''Related to circularity and sustainability''': Yes

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

B.9: Decision Support System

2025-04-28T09:04:14Z

Admin ugqr649i:

• '''Short Description''': The Decision Support System (DSS) manages an extended Digital Battery Passport imposing an economic overlayer to dynamically estimate the value of the battery for recycling and remanufacturing. The tool exploits AI to merge data available on the battery in terms of materials composition and state-of-health, with data characterizing the market quotations to obtain a decision support system which guides operational choices in function of the most profitable expected scenario.

• '''Reference, URL''': https://www.cobat.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': As a Service

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information''':

• '''Related to circularity and sustainability''': Yes

• '''Audience''':Battery Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

B.10: Disassembly Digital Twin

2025-04-28T09:03:55Z

Admin ugqr649i:

• '''Short Description''': The Disassembly Digital Twin is an innovative process DT which executes machine learning aided disassembly algorithm for the execution of battery disassembly operations.

• '''Reference, URL''': https://www.polimi.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': AI Services

• '''License Information''':

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Battery Manufacrturers

Go back to the '''[[AI portfolio of reference implementations]]'''

D.9: Collaborative Environment for AI Developments

2025-04-28T09:03:36Z

Admin ugqr649i:

• '''Short Description''': Provides a real-time collaborative development environment to experiment new Explainable Artificial Intelligence modules based both on real-time and historical data. Compatibility with the main communication protocols, data model, security, data governance, open-source standards (i.e. ISO/IEC 22989, ISO/IEC 23053, ISO/IEC FDIS 23894, ISO/IEC TS 4213, ISO/IEC 5259 2, ISO/IEC 5259 3, ISO/IEC 5259 4,ISO/IEC 5338, ISO/IEC 5339, ISO/IEC 5469, ISO/IEC 23894, ISO/IEC 24027, ISO/IEC 24029 1, ISO/IEC 24029 2, ISO/IEC 24668, ISO/IEC).

• '''Reference, URL''': https://www.eng.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': N.A

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': Other

• '''License Information''': Open Source license

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Data scientists

Go back to the '''[[AI portfolio of reference implementations]]'''

D.8: Circular TwAIn Ontology Library

2025-04-28T08:56:57Z

Admin ugqr649i:

• '''Short Description''': The Circular TwAIn Ontology Library is a collection of ontologies organized in a hierarchical import structure that defines data models and terminologies to represent materials, products, processes, and assets required by the Circular TwAIn's Pilots. Compatible with the open-source semantic web technologies proposed by W3C (RDF, OWL, SPARQL, etc.).

• '''Reference, URL''': https://github.com/Circular-TwAIn/CircularTwAIn-Ontology-Library

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Library

• '''AI Breadth''': N.A

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': Other

• '''Applicable Technical Category''': Other

• '''License Information''': Opens Source license

• '''Related to circularity and sustainability''':

• '''Audience''': Researchers & Innovators, Industry & Market

Go back to the '''[[AI portfolio of reference implementations]]'''

A16: Best Practices (IT Equipment Recovery)

2025-04-28T08:56:03Z

Admin ugqr649i:

• '''Short Description''': Redesign of technical processes in the refurbishment of IT equipment with the use of AI tools, thereby increasing the recovery of second-hand equipment, critical components and materials, reducing costs and creating added value. The results are presented in the form of updated technical instructions to provide electrical and electronic waste management companies and workers, where the focus is on reuse through the advantages of AI.

• '''Reference, URL''': https://revertia.com/en/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''':Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': N.A

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': Optimisation

• '''License Information''': N.A

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Electrical and Electronic waste management companies and workers

Go back to the '''[[AI portfolio of reference implementations]]'''

D.7: Behaviour Tree Editor

2025-04-28T08:50:19Z

Admin ugqr649i:

• '''Short Description''': The Behaviour Tree Editor is a web-based editor that allows orchestration and supervision based on the behaviour tree concept. The Behaviour Tree editor, built on rete.js, offers a visual programming interface for designing and monitoring Behavior Trees, crucial for managing autonomous agents. It supports embedding in various platforms due to its flexible rete.js foundation. The editor facilitates intuitive, drag-and-drop interaction, adhering to user experience standards. It provides real-time feedback for behavior tree creation and execution, enhancing usability and efficiency. The editor's API allows for seamless integration with existing systems, ensuring broad applicability. Additionally, its design ensures compatibility and interoperability with various standards and protocols in software development.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': N.A

• '''Learning Ability''': N.A

• '''Related technologies''':N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': Optimisation

• '''License Information: Proprietary license''': Open Source

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Manufacturers and Quality Control Professionals, Educational Institutions and Students.

Go back to the '''[[AI portfolio of reference implementations]]'''

D.6: AutoML Tool

2025-04-28T08:44:52Z

Admin ugqr649i:

• '''Short Description''': The AutoML Tool is designed for domain users who are not experts in machine learning. It provides an easy-to-use, wizard-like interface for covering every step of data-driven machine learning. Users can upload data, create ad hoc queries, and perform preprocessing tasks such as normalization and standardization. It allows users to train and test machine learning algorithms, compare models using various metrics, and save the best-performing models. The goal is to make machine learning approachable and useful for operators and managers in the process industry, enabling them to use AI for process optimization without requiring in-depth technical knowledge of data science. The AutoML Tool is a framework that includes a graphical user interface for data preprocessing, model training, and testing. It supports data upload from databases or CSV files and uses customizable filters for data selection. Metrics such as F1 score, Area Under the Curve, and confusion matrices are used for model comparison. The system likely adheres to relevant data standards and uses common protocols and APIs for data handling and model deployment. AutoML Tool's optimization algorithms create a closed-loop system. This allows for continuously refining the model and control strategy based on real-time data feedback. The AutoML Tool supports relevant standards in ISO/IEC.

• '''Reference, URL''': https://www.teknopar.com.tr/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''':Yers - Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': N.A.

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': Machine Learning

• '''License Information'': N.A

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Operators and Factory Managers

Go back to the '''[[AI portfolio of reference implementations]]'''

D.6: AutoML Tool

2025-04-28T08:44:45Z

Admin ugqr649i:

• '''Short Description''': The AutoML Tool is designed for domain users who are not experts in machine learning. It provides an easy-to-use, wizard-like interface for covering every step of data-driven machine learning. Users can upload data, create ad hoc queries, and perform preprocessing tasks such as normalization and standardization. It allows users to train and test machine learning algorithms, compare models using various metrics, and save the best-performing models. The goal is to make machine learning approachable and useful for operators and managers in the process industry, enabling them to use AI for process optimization without requiring in-depth technical knowledge of data science. The AutoML Tool is a framework that includes a graphical user interface for data preprocessing, model training, and testing. It supports data upload from databases or CSV files and uses customizable filters for data selection. Metrics such as F1 score, Area Under the Curve, and confusion matrices are used for model comparison. The system likely adheres to relevant data standards and uses common protocols and APIs for data handling and model deployment. AutoML Tool's optimization algorithms create a closed-loop system. This allows for continuously refining the model and control strategy based on real-time data feedback. The AutoML Tool supports relevant standards in ISO/IEC.

• '''Reference, URL''': https://www.teknopar.com.tr/

• '''Applicable Business Category''': MAnufacturing

• '''Application in relevant Projects/Initiatives''':Yers - Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': N.A.

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': Machine Learning

• '''License Information'': N.A

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Operators and Factory Managers

Go back to the '''[[AI portfolio of reference implementations]]'''

A14: Anomaly Detection Module for PETRO Industry

2025-04-28T08:15:39Z

Admin ugqr649i:

• '''Short Description''': The AI Anomaly Detection models consume the sensorial data that describe the operations of the manufacting process. The models are capable of identifying abnormal behaviours of the involved assets. The solution supports many relevant standards in the field: ISO/IEC 22989, ISO/IEC 23053, RDF, RDFS, OWL, JSON, JSON-LD, HTTP, ETSI SAI 002, ETSI SAI 005.

• '''Reference, URL''': https://www.core-innovation.com/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''' Machine Learning:

• '''License Information: Proprietary license''': Copyright

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

A13: AI Aided Disassembly Planner

2025-04-28T08:05:24Z

Admin ugqr649i:

• '''Short Description''': This tool will provide a plan for the optimal disassemble of electronic consumables (PCs) based on the observation of the overall components considering the colaborative working of one operator and one robotic arm. The complete tool will consist on AI models for part recognition with semantic segmentation capabilities. Based on confidence rates, the system will assume part of the disassembly tasks as doable and other as to be delegated. Based on these constrictions, additional data extracted from a diagnosis tool and hardware availability for disassemble (robot) a plan will be delivered with a set of actions and associated coordinates to be delivered to the robotics system responsible for disassembly. A text-based report to explain the plan will be delivered to the operator from which he/she can infer what to do in collaboration with the robot.

• '''Reference, URL''': https://www.aimen.es/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML

• '''Learning Ability''': N.A

• '''Related technologies''': N.A

• '''Applicable Research Area''': Collaborative AI

• '''Applicable Technical Category''': Computer Vision

• '''License Information: Proprietary license''': Open Source License

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Manufacturers

Go back to the '''[[AI portfolio of reference implementations]]'''

16: Product DT/DS/DPP Integration Enablers

2025-04-28T07:48:17Z

Admin ugqr649i:

• '''Purpose/Short Description''': The integrated solution of Product Digital Twins (DT), Data Spaces (DS), and Digital Product Passport (DPP) within the CircularTwAIn aimes at fostering sustainability and eco-friendly product design, particularly in WEEE and BATTERY use cases.

• '''Applicable Data Spaces Building Block''': Data Value Creation

• '''Reference, URL''': https://www.netcompany-intrasoft.com/

• '''Challenge addressed''': Foster sustainability and eco-friendly product design, particularly in WEEE and BATTERY use cases.

• '''Applicable Business area''': Manufacturing, Process Industry

• '''Affected Stakeholders''': Researchers, Innovators

• '''Key components''': "Asset Administration Shell (AAS),
Eclipse Dataspace Components (EDC)"

• '''Metrics/KPIs''': N.A.

• '''Completion Date''': Ongoing

Go back to the '''[[Solutions for circularity Data Space implementations]]'''

16: Product DT/DS/DPP Integration Enablers

2025-04-28T07:48:03Z

Admin ugqr649i:

• '''Purpose/Short Description''': The integrated solution of Product Digital Twins (DT), Data Spaces (DS), and Digital Product Passport (DPP) within the CircularTwAIn aimes at fostering sustainability and eco-friendly product design, particularly in WEEE and BATTERY use cases.

• '''Applicable Data Spaces Building Block''': Data Value Creation

• '''Reference, URL''': https://www.netcompany-intrasoft.com/

• '''Challenge addressed''': Foster sustainability and eco-friendly product design, particularly in WEEE and BATTERY use cases.

• '''Applicable Business area''': Manufacturing, Process Industry

• '''Affected Stakeholders''': Researchers, Innovators

• '''Key components''': "Asset Administration Shell (AAS)
Eclipse Dataspace Components (EDC)"

• '''Metrics/KPIs''': N.A.

• '''Completion Date''': Ongoing

Go back to the '''[[Solutions for circularity Data Space implementations]]'''

15: Data Space Lab

2025-04-08T08:55:54Z

Admin ugqr649i:

• '''Purpose/Short Description''': TECNALIA DS LAB addresses the challenges of manufacturing sector digitalization and, in particular, lack of data due to sovereignty risks, connection to external repositories, lack of failure data, data monetization. TEC DS LAB proposes the access to equipment data and manufacturing services (including circular/sustainable services) in a structured and standardized way so both service and data consumers can easily access them. Going deep in the details, standards like AAS, DPP, RAMI, IDS will be applied, and the connection with existing Data Spaces like GAIA-X or CATENA-X will be also implemented.

• '''Applicable Data Spaces Building Block''': Data Sovereignty & Trust

• '''Reference, URL''': https://www.tecnalia.com/

• '''Challenge addressed''': TECNALIA DS LAB addresses the challenges of manufacturing sector digitalization and, in particular, lack of data due to sovereignty risks, connection to external repositories, lack of failure data, data monetization.

• '''Applicable Business area''': Manufacturing

• '''Affected Stakeholders''': Data providers, Data consumers, Researchers & Innovators

• '''Key components''':

• '''Metrics/KPIs''': N.A.

• '''Completion Date''': Ongoing

Go back to the '''[[Solutions for circularity Data Space implementations]]'''

D.16: XAI for Unstructured Data

2025-04-08T08:52:14Z

Admin ugqr649i:

• '''Short Description''': The XAI for unstructured data is a software component that provides an explanation on how the object detecion algorithm is working in the form of heatmap. The output of the XAI for unstructured data (heatmap) shows the zones of the image that the algorithm is using for detecting and classifying a certain object. The software needs the AI model (NN) and the image to show how the model is behaving. It provides a REST API for uploading the image.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information: Proprietary license''': Open Source license

• '''Related to circularity and sustainability''':

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.15: Product Digital Twin

2025-04-08T08:50:35Z

Admin ugqr649i:

• '''Short Description''': The Product Digital Twin (DT) plays a crucial role in fostering sustainability and facilitating remanufacturing, demanufacturing, and recycling processes while prioritizing sustainability and eco-friendly product design within a Circular Economy environment. It is utilizing Asset Administration Shell (AAS) for specifications and Eclipse BaSyx for implementation, the Product DT enables comprehensive monitoring and management of product lifecycles. It tracks the usage, performance, and condition of products, enhancing the resource efficiency. Furthermore, it integrates a data management and processing component, leveraging TensorFlow services for data analytics. Leveraging this data, AI algorithms, are promoting eco-friendly product design and supporting a sustainable Circular Economy by maximizing resource recovery and minimizing waste.

The Product Digital Twin (DT) encompasses various technical elements to ensure its functionality and interoperability.

• Standards and Protocols: The Product DT adheres to industry standards and protocols to ensure compatibility and seamless integration with existing systems. This includes standards such as Asset Administration Shell (AAS), which provides a standardized approach to describe and manage assets in a digitalized environment. Additionally, protocols like MQTT (Message Queuing Telemetry Transport) are used for efficient and reliable communication between the Product DT and other components of the Circular Economy ecosystem.

• APIs (Application Programming Interfaces): The Product DT offers well-defined APIs, following the AAS specifications, to facilitate interaction with external systems and applications. These APIs allow developers to access and manipulate data stored in the Product DT, enabling functionalities such as querying product specifications, monitoring performance metrics, and triggering maintenance tasks.

• Data Management and Processing Component: The Product DT includes a data management and processing component responsible for handling data generated by the Product DT. TensorFlow services are integrated to enable advanced data analytics, including machine learning algorithms for predictive maintenance and eco-friendly product design.

• Integration with Eclipse BaSyx: Eclipse BaSyx serves as the implementation framework for the Product DT, providing tools and libraries for developing and deploying Digital Twin solutions. The Product DT leverages BaSyx's capabilities to model and execute Digital Twins, enabling seamless integration with the Circular Economy ecosystem.

• '''Reference, URL''': https://www.netcompany-intrasoft.com/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information: Proprietary license''':

• '''Related to circularity and sustainability''':

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.15: Product Digital Twin

2025-04-08T08:50:03Z

Admin ugqr649i:

• '''Short Description''': The Product Digital Twin (DT) plays a crucial role in fostering sustainability and facilitating remanufacturing, demanufacturing, and recycling processes while prioritizing sustainability and eco-friendly product design within a Circular Economy environment. It is utilizing Asset Administration Shell (AAS) for specifications and Eclipse BaSyx for implementation, the Product DT enables comprehensive monitoring and management of product lifecycles. It tracks the usage, performance, and condition of products, enhancing the resource efficiency. Furthermore, it integrates a data management and processing component, leveraging TensorFlow services for data analytics. Leveraging this data, AI algorithms, are promoting eco-friendly product design and supporting a sustainable Circular Economy by maximizing resource recovery and minimizing waste.

The Product Digital Twin (DT) encompasses various technical elements to ensure its functionality and interoperability.

- Standards and Protocols: The Product DT adheres to industry standards and protocols to ensure compatibility and seamless integration with existing systems. This includes standards such as Asset Administration Shell (AAS), which provides a standardized approach to describe and manage assets in a digitalized environment. Additionally, protocols like MQTT (Message Queuing Telemetry Transport) are used for efficient and reliable communication between the Product DT and other components of the Circular Economy ecosystem.

- APIs (Application Programming Interfaces): The Product DT offers well-defined APIs, following the AAS specifications, to facilitate interaction with external systems and applications. These APIs allow developers to access and manipulate data stored in the Product DT, enabling functionalities such as querying product specifications, monitoring performance metrics, and triggering maintenance tasks.

- Data Management and Processing Component: The Product DT includes a data management and processing component responsible for handling data generated by the Product DT. TensorFlow services are integrated to enable advanced data analytics, including machine learning algorithms for predictive maintenance and eco-friendly product design.

- Integration with Eclipse BaSyx: Eclipse BaSyx serves as the implementation framework for the Product DT, providing tools and libraries for developing and deploying Digital Twin solutions. The Product DT leverages BaSyx's capabilities to model and execute Digital Twins, enabling seamless integration with the Circular Economy ecosystem.

• '''Reference, URL''': https://www.netcompany-intrasoft.com/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information: Proprietary license''':

• '''Related to circularity and sustainability''':

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.14: Process Digital Twin

2025-04-08T08:49:07Z

Admin ugqr649i:

• '''Short Description''': The Process Digital Twin (DT) is a virtual representation of a process that incorporates real-time data together with other forms of AI to analyze the system behaviour, performance, and outcomes. Therefore, the Process DT can be seen as a higher-level AI-enabled AAS that ingests from other AASs deployed in the production line and other DTs (Product and Person/Human). This “newer” AAS is especially designed to collect, preprocess data and execute AI/ML models for computing answers, insights, optimizations, while solving “circular manufacturing” problems.
The Process DT has been developed by using the AAS as technological background. This means that it provides the same REST API, the "data image" of the process is built by using the AAS's metamodel. And event-based communication (using MQTT) is supported. Since it needs to collect and send data to other AAS that are part of the process, then an orchestrator has been embedded. The orchestrator is using the behaviour tree mathematical model for creating, defining, managing and executing complex tasks. Finally, an embedded AI engine has been developed to allow the exectution of Neural Networks developed using TensorFlow.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''': ML, Neural Networks

• '''Learning Ability''':

• '''Related technologies''': Tensorflow

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information: Proprietary license''': Open Source license

• '''Related to circularity and sustainability''':

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

B.12: Object Detection and Classification for PC Components

2025-04-08T08:47:22Z

Admin ugqr649i:

• '''Short Description''': Advanced Object Detection and Classification Module: Incorporates pretrained neural network models for precise object detection and classification, embedded within the process Digital Twin, utilizing NOVAAS technology for optimal performance. The system integrates the YOLO v5 model for advanced object detection and classification within the Digital Twin software, using NOVASS technology. It employs industry standards, protocols, and APIs for seamless execution and interoperability, offering precise object recognition and improved decision-making across sectors.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information: Proprietary license''': Copyright

• '''Related to circularity and sustainability''': Yes

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.13: NOVAAS

2025-04-08T08:45:01Z

Admin ugqr649i:

• '''Short Description''': NOVAAS is an open source implementation of the RAMI4.0 Asset Administration Shell concept. The Asset Administration Shell (AAS) is a key concept within the context of the Industrial Internet of Things (IIoT) and Industry 4.0. It is a standardized framework for describing and managing industrial assets and their digital representations (i.e., a “data image” of the asset) in a way that enables seamless interoperability between various components and systems in industrial environments. The AAS is used to digitalize any physical asset in order to be integrated seamlessly into and I4.0 compliant system. In the context of Circular TwAIn NOVAAS will be used for designing and developing I4.0 compatible Digital Twins. Moreover, NOVAAS can be used to run AI algorithms at the edge for several applications such as quality inspection, predictive maintenance, dashboarding etc.
NOVAAS is currently compliant with the V2 specification of the AAS, the development team is working on giving support to the newer V3 specification of the AAS. The tool is implemented using the next-generation software development principles, i.e., using low/no code platforms, microservices and APIs and containers. The tool is containerised using Docker. Latest version of the tool is available on GitLab as Open Source repository (both source code and image). NOVAAS provides a REST API for retrieving data and send commands to the asset. Event-based communication (using MQTT standard) is also supported and used in the context of Circular TwAIn.

• '''Reference, URL''': https://www.uninova.pt/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''':yers, Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information: Proprietary license''': Copyright

• '''Related to circularity and sustainability''': Yes

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.12: Mechanical Recycling Digital Twin

2025-04-08T08:39:14Z

Admin ugqr649i:

• '''Short Description''': An innovative process Digital Twin which implements an AI driven algorithm for optimization of recycling treatment parameters. AI driven algorithm for optimization of treatment parameters for LIBs recycling.

• '''Reference, URL''': https://www.polimi.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular Twain

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information: Proprietary license''':

• '''Related to circularity and sustainability''': Yes

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

B.11: LIB Cells Health State Digital Twin

2025-04-08T08:38:04Z

Admin ugqr649i:

• '''Short Description''': An innovative process DT which implements AI tools for the characterization of the Li-ion batteries state-of-health. AI driven engineering method for the characterization of the LIBs State-of-health.

• '''Reference, URL''': https://www.polimi.it/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes Circular TwAIn

• '''Asset Type''': Executable

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information: Proprietary license''':

• '''Related to circularity and sustainability''': Yes

• '''Audience''':

Go back to the '''[[AI portfolio of reference implementations]]'''

D.11: Hybrid Digital Twin

2025-04-08T08:36:48Z

Admin ugqr649i:

• '''Short Description''': Hybrid Digital Twin (DT) is an advanced tool designed for the process industry, particularly in sectors like petrochemicals and energy. Its primary utility lies in combining a data-driven Digital Twin model with physical process models. This integration enables it to leverage data from various sources, including control systems like DCS and SCADA, and apply AI analytics for predictive capabilities and system monitoring. The Hybrid DT is crucial for understanding and optimizing complex industrial processes, enhancing decision-making, and predicting system performance. It assists in monitoring usage, energy consumption, and emissions, and plays a key role in predictive maintenance and process optimization. This technology is particularly valuable in managing and optimizing the lifecycle of process plants and in aiding the digital transformation of factories.
Hybrid Digital Twin (Hybrid DT) encompasses the integration of various standards, protocols, and APIs to ensure effective and secure data handling. This integration typically includes:

• Integrating advanced AI and machine learning algorithms for predictive analytics and process optimization.

• Application Programming Interfaces (APIs) for interoperability, enabling the Hybrid DT to interact with different software systems,Aspen and MATLAB, and platforms for data analysis and process optimization.

• Utilizing industry-standard communication protocols like OPC UA and Modbus to facilitate data exchange between the Hybrid DT, Aspen models, control systems (DCS and SCADA), and MATLAB.

• Incorporating robust security measures to protect sensitive data and system integrity.

• Ensuring compatibility with various industrial data standards for seamless data acquisition and integration.

Finally it supports many relevant standards on ISO/IECD and ISO/IEC.

• '''Reference, URL''': https://www.teknopar.com.tr/

• '''Applicable Business Category''': Manufacturing

• '''Application in relevant Projects/Initiatives''': Yes, Circular TwAIn

• '''Asset Type''': As A Service

• '''AI Breadth''':

• '''Learning Ability''':

• '''Related technologies''':

• '''Applicable Research Area''':

• '''Applicable Technical Category''':

• '''License Information: Proprietary license''': Copyright

• '''Related to circularity and sustainability''': Yes

• '''Audience''': Petrochemical industry and energy sector

Go back to the '''[[AI portfolio of reference implementations]]'''