Research On Intelligent Algorithm Optimization Of Flexible Job Shop Green Scheduling Based On Knowledge Graph

The goal of carbon peaking and carbon neutrality in China has accelerated the transformation and upgrading of manufacturing intelligence and information technology to green and lean.In the context of double carbon,workshop energysaving scheduling,as a balance between energy consumption and emission reduction and production,has become an important topic in the field of intelligent manufacturing.By optimizing the scheduling scheme in the shop scheduling process,the energy consumption waste and machine load in the production process can be reduced,and the goal of carbon peak carbon neutrality can be achieved.In the workshop production,there are unexpected situations such as machine failure and personnel departure.To respond quickly to these unexpected situations and implement the best scheduling scheme has a significant impact on order completion time,energy consumption and machine load.Based on the project of National Natural Science Foundation of China,this paper studies the knowledge graph and scheduling method of flexible job shop around the problem of production scheduling in intelligent job shop,and takes a fixture manufacturing workshop as an example to verify the proposed scheduling method.The main research work of this thesis is as follows:(1)Aiming at the complex problem of hierarchical and structural relationship of flexible job shop scheduling knowledge,a multi-level flexible job shop knowledge graph is constructed.The knowledge ontology of workpiece design,workpiece task,process,material,machine and personnel in job shop is constructed to express the knowledge and relationship of flexible job shop.The knowledge graph of the flexible job shop is constructed by combining the model layer with the information of the knowledge and data of the job shop.The multidimensional information matrix of the scheduling method is generated by the mapping rules of multidimensional information matrix to ensure the accuracy and timeliness of the data transmitted by the knowledge graph.(2)An improved Golden Jackal Algorithm(LSGJO)is proposed to solve the problem of high dimensionality and complexity of flexible job shop scheduling.The algorithm improves the global searching ability of the scheduling problem by adding dynamic lens imaging learning strategy,double golden helix location updating strategy and increasing the diversity of the population.Compared with11 benchmark algorithms on 49 classical functions,the results of Wilcoxon rank sum test and Friedman calculus analysis show that LSGJO algorithm achieves excellent results.(3)For the flexible job shop scheduling problem,the scheduling model based on completion time,energy consumption and mechanical load is established by using two-stage coding method.Mixed population initialization method and three kinds of neighborhood search based on critical path are adopted to enhance the local search ability of the algorithm.Taking a fixture manufacturing workshop as the research object,taking completion time,energy consumption and machine load as the optimization objectives,the proposed dynamic knowledge graph and optimization algorithm are verified.