Research on Job Shop Scheduling Algorithm of Intelligent Manufacturing Based on Machine Learning

Abstract

Intelligent manufacturing can partially replace the mental work of human beings in the manufacturing process, making production intelligent, efficient and personalized, which is the development trend of manufacturing industry in the future. By organically combining process planning with dynamic optimal scheduling based on cycle and event drive, the integrated system can adapt to the complex environmental changes in the continuous machining process and efficiently complete the real-time processing, thus reducing the redesign of large-scale processes caused by unexpected events. The diploid hybrid genetic algorithm is introduced into the dynamic shop scheduling operation, so that the dynamic production scheduling and control functions in the integrated model can be realized. Under the constraints of multi workpiece machining process, the process and machine are matrix coded respectively. The selection, crossover and mutation operations corresponding to the coding method are designed, and the retention operator is added to retain the optimal individual in each generation of population. The combination of rule-based and Simulation Based Job Shop scheduling system and expert system makes the intelligent scheduling system widely used. The machine learning principle is applied to the genetic algorithm to solve the job shop scheduling problem, so that each chromosome in the initial population has a high fitness value, so that the evolutionary process can be stable after a few iterations, and the loss of the optimal solution is avoided.