Research And Application Of Machining Workshop Rescheduling Problem Based On Improved Genetic Algorithm

With the proposal and implementation of “Made in China 2025” and “German Industry 4.0”,the future manufacturing industry will continue to advance along the road of “Multi-varieties Small-batches,custom-made”.In this context,discrete production models will affect the production scheduling of manufacturing enterprises.In general,the machining workshop needs to process multiple workpieces at the same time.Each workpiece has one or more processes.Each process can be processed on one or more machines,and the time for processing one process varies with the processing machine.In reality,the production environment of the machine shop often encounters a variety of dynamic interference factors,resulting in the failure of the initial scheduling scheme,which seriously affects the normal production of the machining workshop.When such problems occur,a new scheduling plan must be regenerated in a timely manner to minimize the loss of the enterprises.Therefore,it is of great academic and practical value to study the rescheduling problem of machining workshop.Firstly,an improved genetic algorithm introduced into machine learning technology is proposed under the basic framework of NGSA-II algorithm.The algorithm has made the following three improvements:The initial population database are generated by three initial modes: random initial,active scheduling combined with scheduling rules and no delay scheduling.A new operator,learning operator,is proposed to accelerate the evolution of the population and maintain the diversity of the population,so that the population can converge to the approximate solution or the optimal solution at a faster rate,while reducing the number of population iterations.The SOFM algorithm and the SVM algorithm are used to update a certain number of outstanding individuals generated by the NGSA-II algorithm in each iteration to the population database in real time,which strengthens the guiding role of the learning operator in the iterative evolution of the NGSA-II algorithm.Secondly,through the in-depth study and analysis of the machining workshop scheduling problem,the multi-objective scheduling model of the machining workshop is established.The simulation experiments are carried out for several standard examples.The improved genetic algorithm designed for solving the machining workshop scheduling problem is verified.Effectiveness and superiority.Thirdly,based on the in-depth study of the rescheduling problem in the machining workshop,using the rolling window technology and the hybrid drive rescheduling strategy,several common dynamic interference event-driven rescheduling strategies and periodic rescheduling strategies in the machining workshop are studied.And an example of the enterprise is selected to carry out the simulation experiment,which verifies the effectiveness and superiority of the improved genetic algorithm designed in this paper to solve the machining workshop rescheduling problem.Finally,based on the MES developed by the research group,a machining workshop scheduling management information system is designed and developed,which is divided into three functional modules: basic data management,dispatch data management and dispatch optimization management,and is tested in a machining workshop,and the trial application works well.