IMT Atlantique, internationally recognised for the quality of its research, is a leading general engineering school under the aegis of the Ministry of Industry and Digital Technology, ranked in the three main international rankings (THE, SHANGHAI, QS).
Located on three campuses, Brest, Nantes and Rennes, IMT Atlantique aims to combine digital technology and energy to transform society and industry through training, research and innovation. It aims to be the leading French higher education and research institution in this field on an international scale. With 290 researchers and permanent lecturers, 1000 publications and 18 M€ of contracts, it supervises 2300 students each year and its training courses are based on cutting-edge research carried out within 6 joint research units: GEPEA, IRISA, LATIM, LABSTICC, LS2N and SUBATECH.
We are looking for a postdoc to work on assembly line balancing within the H2020 European funded ASSISTANT project. The ASSISTANT (LeArning and robuSt deciSIon SupporT systems for agile mANufacTuring environments) consortium is composed of eleven academic and industrial partners combining key skills in artificial intelligence, optimization, manufacturing, industrial engineering, edge computing and robotics. ASSISTANT aims to create intelligent digital twins through the joint use of machine learning (ML), optimization, simulation and domain models. The resulting tools will design and operate complex collaborative and reconfigurable production systems based on data collected from various sources such as IoT devices. ASSISTANT will experiment this methodology on a significant panel of use cases selected for their relevance in the current context of the digital transformation of production in major manufacturing sectors undergoing rapid transformations like energy, industrial equipment, and automotive sectors which already make extensive use of digital twins. ASSISTANT targets a significant increase in flexibility and reactivity, product/process quality, and in the robustness of manufacturing systems, by integrating human and machine intelligence in a sustainable learning relationship.
The job will be located on the campus of IMT Atlantique in Nantes, France. The recruited person will be member of the MODELIS team wich is part of the Optimization and Decision Support group of the Department of Automation, Production, and Computer Science. The team focuses on the design and optimization of production systems, logistic and transport networks, planning and scheduling of production activities, and risk management for industrial systems and services.
The selected candidate will work on the workpackage 3 that aims to develop optimization approaches for assembly line balancing with equipment selection. The objective of the postdoc is to design a highly dynamic mixed-model assembly line where tasks can be dynamically assigned to stations at each takt, workers and robots can move among stations at the end of each takt. The design decisions include the number of workers to hire and their skills as well as the positions of fixed equipment. The line should be able to adapt to various uncertain events, such as a tool or machine breakdown, a task lasting longer than expected, blocked conveyor, … Therefore, the model to design the line must include operational decisions where the
line is reconfigured in real time to face these disturbances. The postdoc will formulate the operational problem as an MDP and integrated this MDP with the assembly line balancing model. To solve large size instances efficiently of the considered model, we will rely on adaptive robust optimization, or approximate dynamic programming. To increase the accuracy of the optimization model, we will investigate the possibility to learn the performance of a process plan and its reconfiguration policy from historical or simulated data. We will use AI methods to analyze the data, evaluate the specific process plans (decision problem). The goal is to develop AI techniques predict the quality and efficiency of a process plan and its reconfiguration policy. The resulting prediction model will be included into the optimization algorithm to find a process plan that respect the takt time, quality requirements, and other KPIs.
PhD in operations research or computer science or Applied mathematics or industrial engineering.