Artificial Intelligence for improved PROduction efFICIEncy, quality and maiNTenance

Informazioni relative al progetto

AI-PROFICIENT

ID dell’accordo di sovvenzione: 957391

DOI

10.3030/957391

Progetto chiuso

Data della firma CE 2 Luglio 2020

Data di avvio 1 Novembre 2020

Data di completamento 31 Ottobre 2023

Finanziato da

• INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT)

Costo totale

€ 5 467 698,75

Contributo UE

€ 5 467 698,75

Coordinato da

UNIVERSITE DE LORRAINE
France

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (25)

AI-PROFICIENT clustering and networking

Report on the AIPROFICIENT clustering and networking activities with short assessment of impact

Integration with AI4EU's AI on-demand platform

Report on building upon the result of AI4EU project and reuse of key AI enablers data source and AI services

Validation analysis of demonstration scenarios

Report detailing the results from data collection and analysis from the pilot sites during validation period based on D61 methodology

Project identity kit and communication material

Guidelines about the project identity and web channels, and communication material published (initial version).

AI-PROFICIENT hybrid models and digital twins first version (state of the art, designing and specification)

Report on state of the art design and specification of digital twins physical modelling and simulation of manufacturing processes selected for demonstration activities

Final public project report

Report of AIPROFICIENTs activities decisions results conclusions

System integration and deployment

Report summarising WP achievements related to system integration deployment

User experience evaluation

Report on the evaluation of the user experience and recommendation for future improvements of humanmachine interaction

Semantic data model for integrated digital twins

Report on semantic data model developments and strategy for smart data fusion and interlinking of digital twins

Smart components and local AI at system edge

Report summarising WP achievements related to smart components and local AI at the system edge

Best practices and lessons learnt

Analysis of the demonstration results lessons learnt at the pilot sites after deployment of AIPROFICIENT and a best practice guide for future deployments

Legal and ethical requirements for human-machine interaction

Report on identification of legal and ethical issues at pilot sites and specification of AIPROFICIENT strategy for humanmachine interaction

AI-PROFICIENT approach for XAI

Report on the techniques deployed to improve the explainability and transparency of AI enabled recommendation and decision support

Standardization activities of AI-PROFICIENT

Report on standardization activities in terms of data interfacing and humanmachine interaction

Project identity kit and communication material (final version)

Report on guidelines about the project identity and web channels and communication material published final version updated with results

AI-PROFICIENT validation methodology (final version)

Report on methodology for validation of demonstration results LCA and ethical aspects in each pilot site

Pilot-specific demonstration scenarios

Based on D11 and D12 report will present the full set of demo scenarios technical and functional aspects to be deployed in the pilots

Future scenario based decision making

Report on the AI tools and mechanisms deployed to enable predictive decisionmaking and selflearning capabilities specification design and implementation

Human-machine interaction and feedback mechanisms (Design and specification)

Report on specificationdesign of reinforcement learning mechanisms based on the human knowledge and feedback

AI-PROFICIENT ethical recommendations

Report on the ethical recommendations of AI PROFICIENT and instantiation of HLEG guidelines to manufacturing domain

Human-machine interaction, explainable AI and shop-floor feedback

Report summarising WP achievements related to HMIs XAIs and shopfloor feedback

AI-PROFICIENT system architecture

Report on the architectural design of the AI PROFICIENT serviceoriented solution and the underlying AI services and tools

Communication middleware and IIoT interoperability (Design and specification)

Report on specificationdesign of the serviceoriented communication middleware and interoperability

Roadmap for dissemination and communication first release

List of planned activities, their description, place, date and specific target audiences as well as the partners responsible.

AI-PROFICIENT validation methodology (preliminary version)

Report on methodology for validation of demonstration results LCA and ethical aspects in each pilot site

Other (4)

Predictive AI for process quality assurance

Algorithms for data-driven predictive AI analytics developed for improved quality, and fault and incident detection in underlying processes

System-level proactive maintenance strategy

Algorithms for system-level proactive maintenance strategies and KPIs

Local AI for proactive maintenance support

Algorithms for prognostics applied to manufacturing assets and components.

Predictive AI analytics for component self-diagnostics

Algorithms for component self-diagnostics and fault identification at system edge.

Pubblicazioni

Conference proceedings (12)

Learning representations with end-to-end models for improved remaining useful life prognostic

Autori: Alaaeddine CHAOUB, Alexandre VOISIN, Christophe CERISARA, and Benoıt IUNG
Pubblicato in: Proceedings of the 6th European Conference of the Prognostics and Health Management Society, Numero VOL. 6 NO. 1 (2021), 2021, Pagina/e 97-104, ISBN 978-1-936263-34-9
Editore: PHM Society
DOI: 10.36001/phme.2021.v6i1.2785

Internet of Things Platform Architecture for Smart Factories

Autori: Lazar Berbakov and Nikola Tomasevic
Pubblicato in: Fourth International Balkan Conference on Communications and Networking BalkanCom 2021, 2021
Editore: Fourth International Balkan Conference on Communications and Networking BalkanCom 2021

Can Ontologies help making Machine Learning Systems Accountable?

Autori: Iker Esnaola-Gonzalez
Pubblicato in: Proceedings of the Workshop on Data meets Applied Ontologies in Explainable AI (DAO-XAI 2021), CEUR, Numero Volume 2998, 2021
Editore: 3rd International Workshop on Data meets Applied Ontologies
DOI: 10.13140/rg.2.2.29339.18722

Ethical Internal Logistics 4.0: Observations and Suggestions from a Working Internal Logistics Case

Autori: Marc M. Anderson & Karën Fort
Pubblicato in: Studies in Computational Intelligence book serie, Numero volume 1083, 2023, Pagina/e 317-328, ISSN 1860-9503
Editore: Springer International Publishing
DOI: 10.1007/978-3-031-24291-5_25

Artificial-Intelligence-Based Maintenance Scheduling for Complex Systems with Multiple Dependencies

Autori: Nguyen, V.-T., Do, P., & Voisin, A.
Pubblicato in: PHM Society European Conference, Numero 7(1), 2022, Pagina/e 586–589, ISBN 978-1-936263-36-3
Editore: PHM Society
DOI: 10.36001/phme.2022.v7i1.3294

Some Ethical Reflections on the EU AI Act

Autori: Marc M. Anderson
Pubblicato in: IAIL 2022: 1st International Workshop on Imagining the AI Landscape After the AI Act, Numero 3221, 2022, ISSN 1613-0073
Editore: IAIL 2022

Weighted-QMIX-based optimization for maintenance decision-making of multi-component systems

Autori: Van-Thai Nguyen, Phuc Do, Alexandre Voisin, and Benoit Iung
Pubblicato in: Proceedings of the 7th European Conference of the Prognostics and Health Management Society 2022, Numero 7(1), 2022, Pagina/e 360-367, ISBN 978-1-936263-36-3
Editore: PHM Society
DOI: 10.36001/phme.2022.v7i1.3319

Deep Learning Representation Pre-training for Industry 4.0

Autori: Chaoub, A., Cerisara, C., Voisin, A., & Iung, B.
Pubblicato in: Proceedings of the 7th European Conference of the Prognostics and Health Management Society 2022, Numero 7(1), 2022, Pagina/e 571-573, ISBN 978-1-936263-36-3
Editore: PHM Society
DOI: 10.36001/phme.2022.v7i1.2784

On the use of reinforcement learning for maintenance decision-making of multi-state component systems with imperfect maintenance

Autori: Van-Thai NGUYEN, Phuc DO, Alexandre VOISIN and Benoit IUNG
Pubblicato in: Proceedings of the 31st European Safety and Reliability Conference, Numero 2021, 2021, Pagina/e 2142-2149
Editore: Research Publishing
DOI: 10.3850/978-981-18-2016-8304-cd

Towards interpreting deep learning models for industry 4.0 with gated mixture of experts

Autori: Alaaeddine Chaoub, Christophe Cerisara, Alexandre Voisin, Benoît Iung
Pubblicato in: 30th European Signal Processing Conference, EUSIPCO 2022, Aug 2022, Belgrade, Serbia, 2022
Editore: EUSIPCO 2022

Divide, Propagate and Conquer: Splitting a Complex Diagnosis Problem for Early Detection of Faults in a Manufacturing Production Line

Autori: Kerman Lopez de Calle - Etxabe, Meritxell Gomez - Omella and Eider Garate - Perez
Pubblicato in: Proceedings of the European Conference of the PHM Society 2021, Numero VOL.6 No.1, published: 2021-06-29, 2021, Pagina/e 543-551, ISBN 978-1-936263-34-9
Editore: EUROPEAN CONFERENCE OF THE PROGNOSTICS AND HEALTH MANAGEMENT SOCIETY

Towards a Circular Rotating Blade Wear Assessment Digital Twin for Manufacturing Lines

Autori: López de Calle - Etxabe Kerman, Garate - Perez Eider, Arnaiz Aitor
Pubblicato in: IFAC PapersOnLine 55-2, Numero 2022, 2022, Pagina/e 561–566
Editore: Elsevier
DOI: 10.1016/j.ifacol.2022.04.253

Peer reviewed articles (4)

FIDES: An ontology-based approach for making machine learning systems accountable

Autori: Izaskun Fernandez, Cristina Aceta, Eduardo Gilabert, Iker Esnaola-Gonzalez
Pubblicato in: Journal of Web Semantics, Numero 79, 2023, ISSN 1570-8268
Editore: Elsevier BV
DOI: 10.1016/j.websem.2023.100808

Artificial-intelligence-based maintenance decision-making and optimization for multi-state component systems

Autori: Van-Thai Nguyen, Phuc Do, Alexandre Vosin, Benoit Iung
Pubblicato in: Reliability Engineering & System Safety, Numero 228, 2022, Pagina/e 108757, ISSN 0951-8320
Editore: Elsevier BV
DOI: 10.1016/j.ress.2022.108757

From the ground up: developing a practical ethical methodology for integrating AI into industry

Autori: Marc M. Anderson & Karën Fort
Pubblicato in: AI & SOCIETY volume, Numero 38, 2023, Pagina/e 631-645
Editore: Springer
DOI: 10.1007/s00146-022-01531-x

Human Where? A New Scale Defining Human Involvement in Technology Communities from an Ethical Standpoint”

Autori: Anderson, Marc, and Karën Fort
Pubblicato in: International Review of Information Ethics, Numero Vol. 31 (08/2022), 2022, Pagina/e 1-12, ISSN 2563-5638
Editore: Univ. of Alberta, Canada
DOI: 10.29173/irie477

Thesis and dissertations (1)

Optimisation de la maintenance basée sur l'intelligence artificielle pour des systèmes à dépendances multiples

Autori: Nguyen, Van-Thai
Pubblicato in: https://hal.univ-lorraine.fr/tel-04205243, Numero 2, 2023
Editore: Université de Lorraine