A joint chance constrained optimization algorithm with robust reconstruction for multi-echelon and multi-period closed-loop manufacturing adjustable system design under multi-source uncertainty

Abstract

The complex electronic assembly scheduling problem under uncertainty poses a new challenge. The joint chance constraint programming method based on robust reconstruction is used to hedge the endogenous and external uncertainty in the closed-loop manufacturing scheduling model of multi-echelon and multi-product electronic assembly process under multi-source uncertainty in this study. The numerical cases of electronic factory in assembly and closed-loop manufacturing mode are studied, the sensitivity of cost to different types of uncertain parameters is analyzed. The results show that different types of uncertainty have different effects on economic benefits, and endogenous uncertainty has a greater impact on manufacturing costs. Decision makers can adjust the adjustable parameters according to external policies and economic situation to control the conservatism and economic benefits of the scheme, and at the same time reduce the demand for uncertain data and improve the efficiency of solution. The model provides a new sustainable production method for electronic assembly manufacturing practitioners, and makes the best production decision when weighing economic benefits and risks.