Big Data Analysis and Scheduling Optimization System Oriented Assembly Process for Complex Equipment

Abstract

Traditionally, the data generated in the manufacturing process is not under full use for management decisions, so it is difficult to achieve the decision optimization in a manufacturing system level. The analysis of the big data with uncertain information that influences the assembly objectives can be helpful to improve the capacity of resisting the disturbance of the scheduling system and realize the optimal production. This paper focuses on the analysis and utilization of assembly big data in the manufacturing process and studies the key technologies of big data analysis and assembly scheduling optimization for complex equipment. A big data analysis and scheduling optimization system is proposed to solve the assembly service execution decision for complex equipment. It proposes to analyze the assembly big data and make decisions with uncertain information by locally linear embedding, adaptive boosting, support vector machine, and D-S evidence theory. In order to explore the influence pattern of assembly task and environment on assembly efficiency, the neural industrial engineering is proposed to be introduced into human error prediction based on physiological big data. Finally, the variable metric clustering of assembly tasks can be provided to ensure the maximization of assembly efficiency and the production balance. The proposed system can effectively handle the dynamic and uncertain information in the assembly, and get better overall scheduling optimization of the assembly system. The support technologies presented in this paper can provide a good theoretical foundation and application reference for big data decision to be used in manufacturing optimization.