Laboratoire D'automatique et Productique

his study focuses on proposing a new architecture that combines cloud computing, deep learning, and artificial intelligence to provide solutions for flow shop scheduling problems. Currently, cloud computing is an active research field in production engineering due to its two main advantages: computing power and knowledge sharing. The aim of this study is to improve the productivity of modern factories, as well as the efficiency and profitability of industrial operations. Our research activities primarily focus on maintenance and modern industrial scheduling, which is a relatively new research area in artificial intelligence. Hybrid approaches based on multi-agent systems (MAS) on one hand, and the use of emergent methods such as Genetic Algorithms (GA) and Artificial Immune System (AIS) algorithms on the other, are explored to better integrate systematic preventive maintenance policies into scheduling workshops. The objective is to minimize execution times during the scheduling process. Flow shop scheduling, considering sequence setup time, is another research focus in our work, where we apply various artificial intelligence approaches and techniques. To evaluate our proposals, we will use datasets from multiple industrial systems.