Modelling and application of joint maintenance grouping and workload smoothing for an automotive plant

Abstract

In the maintenance optimisation framework, grouping maintenance is a promising solution for maintenance planning of multi-component systems, in which maintenance activities are performed together to reduce maintenance costs. One of the most widely identified challenges in real applications of grouping maintenance is that it may disturb the maintenance workload balance (smoothness), causing many difficulties in production and/or labour scheduling and inventory management. In this study, we propose a joint optimisation approach for maintenance grouping and workload balancing to address the above challenge. First, a mathematical model of the joint optimisation problem was derived. A multi-objective grouping optimisation approach based on the Weighted Sum model and Genetic Algorithm was implemented to determine the Pareto-optimal grouping solution. The proposed approach was applied to a real case study of an automotive plant comprising 40 production lines with 1090 components. The results highlighted the advantages, effectiveness, and flexibility of the proposed maintenance approach in real-world applications.

Keywords:

• Maintenance grouping
• workload smoothing
• automotive maintenance
• multi-objective genetic algorithm
• multi-component system

Data availability statement (DAS)

Due to the nature of this research, participants of this study did not agree for their data to be shared publicly, so supporting data is unavailable.

Disclosure statement

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

Notes

1 A partition of a set X, which is defined as a set of nonempty subsets of X such that every element x in X is in exactly one of these subsets (Halmos 2017) (i.e. X is a disjoint union of the subsets)

Additional information

Funding

This research is partially supported by the Vietnamese Ministry of Education and Training under the “Research and develop models to predict the safety and lifespan of coastal and island infrastructures using artificial intelligence and condition monitoring” project, number B2021-GHA-03.

Notes on contributors

Minh-Tuan Truong

Minh-Tuan Truong obtained a Master's degree in System Optimization and Security from the University of Technology of Troyes, France in 2014. In November 2018, Tuan-TRUONG joined the Research Center for Automatic Control (CRAN) at the University of Lorraine, where he also collaborated with the CEA Tech Grenoble to pursue his Ph.D. degree. Throughout his doctoral studies, Tuan-TRUONG engaged in numerous projects related to microelectronic devices, accelerated testing design, reliability modeling, and maintenance. Currently, Tuan-TRUONG serves as a RAM (Reliability, Availability, Maintainability) engineer at Hitachi Astemo France. In this role, he focuses on an R&D project centered around the brake-by-wire system. With his knowledge and experience, Tuan-TRUONG plays a vital role in ensuring the reliability, availability, and maintainability of this innovative technology.

Hai-Canh Vu

Hai Canh Vu is currently an Assistant Professor of Reliability Engineering and Data Science at the Roberval laboratory, at the University of Technology of Compiègne, France. He received an Engineering degree in Electrical systems in 2007 in Vietnam. He obtained a master's degree and a Ph.D. in Optimization and security of industrial systems at the University of Technology of Troyes, France in 2015. His research deals with Maintenance optimisation of complex systems, Prognostics and Health Management (PHM), and other applications of Machine learning/Deep learning in the industry.

Phuc Do

Phuc Do Dr. is currently Associate Professor at Lorraine University (UL/CRAN laboratory) since 2011. He received his PhD in systems optimisation and dependability in 2008 from Troyes University of Technology (France). He defended his HDR (Habilitation à diriger des recherches) in 2019 on the subject of ‘towards a prescriptive maintenance for cyber physical production system’. So, his research interests include stochastic modelling for reliability prognostic, optimisation of maintenance decision-making. He is strongly involved in ESREL, PHM society and MIMAR communities. He has many international collaborations (UK, Norways, Brazil, US, Canada, Vietnam, Hongkong). He already supervised 8 Ph. D. students (+ 4 in progress) and 7 master's degree on PHM and predictive maintenance. He is co-guest editor of several Special Issue for different journal such as Reliability Engineering System Safety, Journal of Risk and Reliability, Autonomous Intelligent Systems, Pesquisa Operacional. Phuc Do is associated Editor of two international journals: Safety and Reliability (Francis & Taylor); Autonomous Intelligent Systems (Springer), co-chair of the 9th, 10th, 11th and 12th International Conference on Modelling in Industrial Maintenance and Reliability. He served as IPC member of various IEEE, IFAC, ESREL, PHM, ICSRS, SRSE conferences. He has published over 90 research publications in international journals (i.e. RESS, IEEE Transactions on Reliability) and conferences. Phuc Do is involved as actor but also as scientific leader in many contracts with industry such as RENAULT, AccelorMittal, CEA, SECTOR, EODev, Feedgy but also in national or European projects (e.g. COFECUB, H2020 AI -- PROFICIENT, Nuclear Reactor, MODAPTO).

Google scholar: https://scholar.google.co.uk/phucdo

Benoit Iung

Benoît Iung is full Professor of Prognostics and Health Management (PHM) at Lorraine University (France). He conducts research at the Nancy Research Centre for Automatic Control (CRAN, CNRS UMR 7039) where he is co-managing today a research group on Sustainable Industrial System Engineering (about 60 people). His research and teaching areas are related to advance maintenance engineering, PHM, predictive maintenance technologies, condition monitoring, cyber-physical production system (CPPS) and Industry of the Future. In relation to these topics he took scientific responsibility for the participation of CRAN in a lot of national, European (i.e. REMAFEX, DYNAMITE) and international projects, for example, with China (i.e. EIAM-IPE, CENNET), Chile (i.e. iMaPla) and Brazil (i.e. COFECUB frame). He is now the coordinator of the European project AI-PROFICIENT (call ICT-38; 2020–2023; AI for Manufacturing). He has numerous collaborations with industry in the frame of Convention for Research Programme (mainly in France with EDF, CEA, RENAULT, ARCELORMITTAL, SEW USOCOME) and served until 2018, as responsible of a common Lab called PHM-FACTORY with PREDICT company (ANR LabCOM). He is now the IFAC CC5 chair (2020–2023) addressing Cyber-Physical Manufacturing Enterprises issues and was previously the chair of the IFAC TC5.1 (2017–2020). He was until 2014 the chair of the IFAC WG A-MEST on advanced maintenance, and until 2020, the chair of the ESRA TC on Manufacturing. He is a French CIRP fellow since 2017, a PHM society fellow from 2018, a founding Fellow to the ISEAM and to the European IAM Academic and Research Network, a nominated member of the IFAC TC 5.3. He had also a guest position in the NSF research centre for IMS (Univ. of Cincinnati; until end of 2017) and is currently Visiting Professor (Foreigner expert project) at Tongji University (Shanghai, China). He serves as project manager on ‘Industry of the Future’ for the University of Lorraine since 2016 which allows him to be involved in EFFRA and A.SPIRE European associations. Benoît Iung has (co)-authored over 220 scientific papers and several books including the first e-maintenance book in Springer. He developed several keynote speeches on PHM, Predictive maintenance/control in international conferences and attended as reviewer, faculty opponent or examiner for a lot of Ph. D. and ‘docent’ defenses in France and in Europe (UK, Belgium, Netherlands, Norway, Spain, Sweden, Germany and Italy). He has supervised until now 23 Ph. D. Students (3 in progress). He served as IPC member of various IEEE, CIRP and IFAC conferences and developed expertise/reviewing for European Commission and EiT in the frame of H2020 / Horizon Europe from 2015. He is also monitoring expert for EC and included in the FWO Review College (panels 2023–2025). He is cited, since 2019, in the ‘Top 2% Scientistic’ from the publicly available database of 100,000 top-scientists (up-dated science-wide author databases of standardised citation indicators). He is an Editor of the IFAC Journal of Systems and Control. Benoît IUNG received his B.S., M.S. and Ph.D. in Automatic Control, Manufacturing Engineering and Automation Engineering, respectively, from Lorraine University, and an accreditation to be research supervisor (2002) from this same University. https://scholar.google.com/citations?user=8OZNIrUAAAAJ&hl=en.

https://www.linkedin.com/in/benoit-iung-25a78817/?originalSubdomain=fr

Alexandre Voisin

Alexandre Voisin is Associate Professor at Université de lorraine (France). He conducts his research activities at the Research Center for Automatic Control of Nancy (CRAN-UMR 7039) laboratory. He received his Ph. D degree in Electrical Engineering in 1999. Alexandre current research interests deal with Predictive Maintenance & PHM including health monitoring of complex systems, system prognostic and decision making in a predictive maintenance framework and the role of maintenance in sustainable manufacturing. He leads dependability and PHM&Maintenance research group (around 15 researchers) and participate and co-ordinate several national and European R&D projects.