A data-driven model for scheduling and sequencing tasks in industry 4.0 compliant production systems with flow shop

The issue of scheduling flow shop is always an important issue in all industries and factories, which undergoes fundamental changes with the emergence of different paradigms. This article aimed to analyze the problem of scheduling and determining the sequence of tasks in production systems with flow shop according to the components of the industry4.0. For this purpose, a data-driven model and its integration with meta-heuristic hybrid algorithms are presented to solve the problem. In the first step the problem model is designed and to deal with uncertainty the data-driven robust optimization approach has been used for the first time in flow shop problems. The important parameters of the model were estimated using SARIMA and SVR algorithms, and then the problem model was solved using hybrid algorithms, and the findings showed that LP-GA-SA algorithm has the best performance. The main innovation of this article is to present a data-driven optimization approach and use the SVR algorithm in parameter estimation and investigate the impact of industry4.0 on flow shop optimization. The findings show that the use of robotics and AI from Industry 4.0 in the flow shop will improve the execution time and costs in the long run. The two main issues that Industry 4.0 directly affects the workshop flow are the learning coefficient and the deterioration rate. The increase in the learning coefficient that is obtained due to the use of Industry 4.0 technologies improves all the target functions. It also minimizes the deterioration effect, which again improves the target functions.