Cross Layer Optimal Scheduling Of Networked Collaborative Manufacturing System

The networked collaborative manufacturing system is a highly integrated intelligent manufacturing model.Its collaborative layer has a big data integrated knowledge base and service functions such as knowledge reasoning,data mining,and information interaction.But,at present,most of the energy efficiency scheduling optimization methods use computing resources in the optimization process are limited to the edge layers such as the enterprise layer and the workshop layer.There is a lack of research on optimal scheduling that utilizes the system’s collaborative layer knowledge base and services to further improve energy efficiency.In addition,the production process of the networked collaborative manufacturing system has the characteristics of flexible manufacturing,multi-factory collaborative production,that make energy efficiency analysis and optimization extremely difficult.Therefore,the research on optimized scheduling of networked collaborative manufacturing systems across the collaboration layer and the edge layer is of great significance.This paper studies the energy efficiency optimization problem of single job-shop and distributed multi-factories in the networked collaborative manufacturing system,and proposes the corresponding algorithm,which has achieved good optimization scheduling effects.The main works are as follows:(1)Analyze the information flow and energy flow characteristics,main control factors,and external interference of the networked collaborative manufacturing system,and face the goal of energy efficiency optimization control.Aiming at the real-time scheduling of independent manufacturing workshops at the edge level and the virtual resource optimization scheduling problem of cloud networked distributed multi-factory collaborative manufacturing,the corresponding optimization models are established respectively,and the cross-layer collaboration mechanism is established.(2)Aiming at the energy efficiency optimization problem of a single job shop,a scheduling optimization method that combines case-based reasoning and hybrid group intelligence is proposed.Under the framework of particle swarm optimization algorithm,this method integrates genetic algorithm crossover mutation operator,and based on the characteristics of the scheduling problem,the ternary representation method is used to convert the historical scheduling case information resources in the collaborative layer knowledge base into a digital representation to perform similarity calculations,and then introduce it into the supplementary individual generation process after the population screening of the scheduling optimization algorithm to improve the diversity in the later iteration process.The effectiveness of the method is verified by simulation and analysis.(3)Aiming at the problem of energy efficiency optimization in distributed multi-factories,a Gaussian particle swarm optimization nested optimization algorithm fused with ID3 decision tree is proposed.In this algorithm,the off-site factory is regarded as an independent processing unit,the order allocation optimization of the processing unit is regarded as the outer layer of nested optimization,and the scheduling optimization is regarded as the inner layer.At the same time,the elite retention strategy is introduced,and ID3 decision tree technology is integrated into the outer optimization particle generation process to reduce the randomness in the outer optimization process.Finally,the effectiveness of the method is verified by simulation experiments.(4)Based on the above theoretical research and the actual needs of the factory,the front-end visualization page is built using Thymeleaf and other front-end technologies.At the same time,the logic functions of the back-end application modules are developed using Spring Boot,Mybatis,Hadoop and other big data microservice information technologies,and the developed system is applied to a machine tool factory in wuxi to achieve a good optimal scheduling effect.