Design And Implementation Of Dynamic Target Efficient APS Algorithm In Cloud Manufacturing Environment

In the context of "Cloud Manufacturing","Industry 4.0" and "Made in China 2025",digitalization and intelligent transformation is the only way for Chinese enterprises to develop.Advanced planning and scheduling(APS)system based on cloud environment is one of the key technologies for enterprises to enhance their digital capabilities,promote enterprises to go to the cloud,help enterprises realize intelligent manufacturing,and enhance their core competitiveness.This thesis mainly studies the workshop scheduling problem in APS system under the cloud manufacturing environment.In the cloud manufacturing environment,the traditional workshop scheduling has changed in scheduling goals and resources,and new problems have arisen.That is,the cloud workshop is oriented to different companies,different production methods,and different process flows.The constraint indicators and optimization goals of each company's orders are dynamically changing and highly differentiated,and efficient execution in the cloud is required.In order to solve the above problems,the main work of this thesis is as follows:1.Aiming at how the production workshop efficiently processes a large number of orders from the cloud service platform,comprehensively analyzes the various indicators that affect order reception,and proposes a comprehensive order evaluation model based on the gray correlation analysis method.Calculate the gray correlation degree of the order on the cloud platform and conduct an effective comprehensive evaluation.At the same time,several ways of inserting orders on the cloud platform are given.According to the calculation results and the way of inserting orders,the orders from the cloud service platform are preprocessed,which improves the processing efficiency.2.Aiming at the constraints and optimization goals of the dynamic changes of the workshop,comprehensively analyze the common constraints and optimization goals of different order companies in different production environments.Based on this,a unified scheduling model is constructed under multiple constraints,with the maximum completion time,the penalty cost of delay,the total machine load and the minimum machine load as the goal.An improved non-dominated sorting algorithm(NSGA-II)is proposed,and population initialization based on combination strategy,improved elite strategy dynamic update of the elite solution set and improved Pareto ranking method are designed.Finally,the actual production data of a garment factory in Zhuzhou City under the cloud environment verifies the practicability of the algorithm;in addition,standard calculation examples are used to verify the superiority of the improved algorithm in this thesis.3.Based on the above two points,a cloud-based APS system is designed and developed for small and medium-sized enterprises,which realizes data cloud storage,quickly responds to the diverse needs of customers,visualized factory production,and efficient cloud collaboration,which improves the production efficiency of enterprises.Through the research and application of APS in the cloud manufacturing environment,it provides a new idea to promote the digitalization and intelligent transformation of manufacturing industry.