Research And Implementation Of Flexible Scheduling Algorithm For Intelligent Manufacturing

With the rapid development of industrial internet technology,intelligent manufacturing industry has gradually developed into the national economic pillar.China’s traditional manufacturing industry has begun to slowly transform to intelligent manufacturing industry.In the process of manufacturing industry transformation,manufacturing enterprises are also facing fierce market competition.Therefore,enterprises need to improve the production efficiency and diversification of products,and then stand firm in the competition by meeting the personalized needs of customers.Job shop scheduling is an important factor in the production process of enterprises.Excellent scheduling scheme can bring high-efficiency and low-cost workshop benefits to enterprises,which has become the needs of enterprises.Through the research on job shop scheduling,it is found that it is still a hot issue in industrial engineering,which has very important engineering practical value and theoretical significance.The main work of this paper is as follows:(1)This paper describes the single objective and multi-objective flexible job shop scheduling problem(FJSP),puts forward the corresponding constraints according to the problem description of single objective and multi-objective FJSP,and establishes their respective mathematical models under the corresponding constraints.(2)The algorithm of minimizing the maximum completion time in single objective FJSP is studied,and an improved genetic algorithm is proposed based on the original genetic algorithm.In the coding stage,the double-layer coding method is adopted;In order to improve the quality of the initial population,the initialization strategy of the combination of global search,local search and random selection is adopted;In order to prevent excellent individuals from being eliminated,tournament method and elite retention strategy are adopted in the selection operation;The nonlinear adjusted sadaptive operator is introduced to improve the probability of crossover and mutation,and then supplement the evolutionary ability of the improved genetic algorithm.An international benchmark example is used to verify the effectiveness of the improved genetic algorithm.(3)The algorithm of multi-objective FJSP with the goal of minimum completion time,minimum machine load and minimum total machine load is studied.The improved genetic algorithm and simulated annealing algorithm in this paper are combined,and an improved genetic simulated annealing algorithm is proposed based on the original genetic simulated annealing algorithm.In the coding stage,the double segment coding method is adopted;A two population model is designed in the operation of population initialization,selection,crossover and mutation.The two populations adopt different initialization and genetic operation methods to increase the diversity of the population;In the cooling stage,a non-homogeneous cooling strategy is introduced,which can better control the convergence speed of the algorithm.The international benchmark example is used to simulate the multi-objective FJSP.The simulation results of multiple target values verify the effectiveness and feasibility of the improved genetic simulated annealing algorithm in this paper.(3)After the demand analysis of the production process of the job shop,a flexible scheduling system based on the scheduling module and the combination of multiple functional modules is designed and implemented.