Research On Multi Objective Flexible Job Shop Scheduling Problem Based On Complex Network

In today's rapid development of science and technology,more and more fields and profession is undergoing rapid change.Renewal and upgrading of products goes faster and faster,and the period of product cycle goes shorter and shorter,and the demand of people also shows a trend of diversification.In today's high-speed production,how to adjust the indicators of production and schedule the production effectively to reduce the costs and improve the efficiency has become a key element of existence and improvement of market competitiveness of manufacturing.With the progress of science and technology,and the complex degree of industrial production is becoming higher than before.Meanwhile,the progress of production tend to be more intelligent.Under the background of big data and “Made in China2025”,industrial production is transforming to data-driven.The application of transducer and computer technology provides us a large number of available data and digital management mode.In order to solve the problems in diverse manufacturing procedure,this paper will combine multi-objective flexible workshop scheduling problem with complex networks,establish the material-process network model,analyze the characteristics and the structure and causes of the network.In this model,we used the ant colony algorithm to solve the problem of multi-objective flexible workshop scheduling,and analyzed the combination of its results and the network structure features.Under the workshop circumstances of a high level of automation and digitization degree,the optimization of shop scheduling is also transforming to digitization.On the basis of the material-process model,this paper improved the model further,established a complex network model based on data with the aid of Apriori algorithm,and tested its accuracy.The model used a variety of data generated in the production process furthest,effectively expressed the connection between the various data,transformed multi-objective optimization into multiple node parameter optimization.