The ASSISTANT project: AI for high level decisions in manufacturing

Abstract

This paper outlines the main idea and approach of the H2020 ASSISTANT (LeArning and robuSt deciSIon SupporT systems for agile mANufacTuring environments) project. ASSISTANT is aimed at the investigation of AI-based tools for adaptive manufacturing environments, and focuses on the development of a set of digital twins for integration with, management of, and decision support for production planning and control. The ASSISTANT tools are based on the approach of extending generative design, an established methodology for product design, to a broader set of manufacturing decision making processes; and to make use of machine learning, optimisation, and simulation techniques to produce executable models capable of ethical reasoning and data-driven decision making for manufacturing systems. Combining human control and accountable AI, the ASSISTANT toolsets span a wide range of manufacturing processes and time scales, including process planning, production planning, scheduling, and real-time control. They are designed to be adaptable and applicable in a both general and specific manufacturing environments.

Keywords:

• Artificial intelligence
• data analytics
• digital twins
• reconfigurable manufacturing systems
• process and production planning
• scheduling and real-time control

Acknowledgments

The authors extend their gratitude to all academic and industrial participants in the project.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

The article is conceptual one, no specific data was used, the article present new concepts and approaches for development of decision aid in manufacturing systems, based on Artificial Intelligence techniques, optimisation, generative design and data fabrics.

Additional information

Funding

This work is funded by the ASSISTANT, European project, under the framework program Horizon 2020, ICT-38-2020, Artificial intelligence for manufacturing, [grant agreement number 101000165].

Notes on contributors

G. Castañé

Gabriel González Castañé holds a PhD in Computer Science and Technology on the topic of agent modelling and simulation of energy models and computing resources and after he fished moved to Dublin City University leading a simulation work package in a EU project. When it finished, he moved to the University College of Cork, into the Center of Unified Computing as technical coordinator of another EU project. Next, was working in several industrial projects with optimisation and business units on the Insight-Centre where he moved to lead the development of the European AI ecosystem in the AI4EU project. He participated as a task force for the European Commission on the deep dives for the creation of the Trustworthy AI guidelines and the High-level expert group on AI. Currently he is part of the Executive Board of 2 networks of excellence on AI – TAILOR and HumanE AI Net – technical coordinator of a matchmaking project for the AI on demand platform and chairing several working groups on Digital Innovation Hub networks, communications and services for the portal of the AI on demand. His interests are simulation, self organising architectures, distributed computing, digital ecosystems, fairness and the applicability of responsible AI to computing.

A. Dolgui

Alexandre Dolgui is an IISE Fellow, Distinguished Professor, and the Head of Automation, Production and Computer Sciences Department at the IMT Atlantique, France. His research focuses on manufacturing line design, production planning and supply chain optimisation. His main results are based on the exact mathematical programming methods and their intelligent coupling with heuristics and metaheuristics algorithms. He is the co-author of 5 books and 275 refereed journal articles. He is the Editor-in-Chief of the International Journal of Production Research, and an Area Editor of Computers & Industrial Engineering. He is Member of the Editorial Boards for 27 other journals, including the International Journal of Production Economics. He is an Active Fellow of the European Academy for Industrial Management, Member of the Board of the International Foundation for Production Research, former Chair of IFAC TC on Manufacturing Modelling for Management and Control (2011–2017, currently a vice chair), Member of IFIP WG 5.7 Advances in Production Management Systems, Chairman of International Program Committees for major international conferences in the domain (MIM, INCOM, IESM, MOSIM, etc).

N. Kousi

Niki Kousi (female) owns a Diploma (Degree Master of Science) in Mechanical Engineering and Aeronautics from the University of Patras, Greece and a PhD in Engineering of the Department of Mechanical Engineering and Aeronautics, University of Patras. She worked as a Research Engineer for the Laboratory for Manufacturing Systems and Automation (LMS), in the Department of Mechanical Engineering and Aeronautics from November 2014 to present. Her research interest and activities are, among other, (a) the design and deployment of industrial robotic applications for reconfiguration factories, (b) the use of Digital Twins for flexible robotic assembly lines, (c) the use of simulation tools for performance assessment of production systems using stationary/mobile robots, (d) the design of methods for Human Robot collaborative applications task planning and orchestration. She has been involved in numerous research EU funded projects including AUTORECON, ROBO-PARTNER, SYMBIO-TIC, THOMAS, TRINITY, DIMOFAC, ODIN. She has more than twenty (20) scientific articles published in international conferences and journals.

B. Meyers

Bart Meyers is a research engineer at Flanders Make, a Flemish research centre for the manufacturing industry. He works on data, information and knowledge modelling in the context of digitisation and Industry 4.0, specifically on the use of knowledge graphs for manufacturing. Bart Meyers holds a PhD in Computer Science from the University of Antwerp, and has a background in systems engineering, software engineering, model-driven engineering, and domain modelling. He has worked on several projects with academia and industry, local and European, related to modelling and leveraging knowledge.

S. Thevenin

Simon Thevenin is an assistant professor in the Automation, Production, and Computer Sciences Department at the IMT Atlantique, France. He received a Ph.D. from the University of Geneva in 2015 for his work on metaheuristics to solve scheduling problems in production systems. His current research interests focus on optimisation methods for production management, including production scheduling, production planning, and manufacturing line design.

E. Vyhmeister

Eduardo Vyhmeister is a highly experienced Researcher/Academic with the formation in Chemical Engineering field. Currently focussing in AI and AI ethical considerations. Proven experience in project management (which have considered environmental, economic, productive, and/or social aspects) in fields of Computer Science and Chemical Engineering. Currently working at the University College Cork (Insight Research Centre) in industrial-funded projects related to data engineering, machine learning, and UI design.

P-O. Östberg

P-O Östberg is an Associate Professor at Umeå University and the founder and CTO of BiTi Innovations, a spin-off from the Autonomous Distributed Systems Laboratory at Umeå University, Sweden. He has more than 15 years postgraduate experience of both academic research and industry work, and has held (visiting and staff) researcher positions at several universities including Uppsala University, Sweden, Karolinska Institutet, Sweden, Ulm University, Germany, and the Lawrence Berkeley National Laboratory at the University of California, Berkeley, USA. He has worked in the Swedish government's strategic eScience research initiative eSSENCE as well as in several high profile framework projects funded by the EU in the FP7 and H2020 programmes and the Swedish national research council (VR). His research interests are centred around distributed computing resource management and the use of machine learning, simulation, and optimisation techniques to construct AI systems for planning and scheduling.