Research On Data-driven Active Remanufacturing Scheme Decision Of In-service Electromechanical Products

The deep integration of modern engineering information technology and digital technology not only speeds up the replacement speed of in-service mechanical and electrical products,but also realizes the leap-forward development of the quality and performance of mechanical and electrical products.However,due to the great uncertainty of the service status and recovery quality of mechanical and electrical products,the traditional remanufacturing industry is faced with problems such as low remanufacturing efficiency,low quality of remanufactured products and difficult to form industrialization development.Active remanufacturing,as one of the best industrial models to extend the service life of in-service mechanical and electrical products,deeply explore the potential value of in-service mechanical and electrical products,and achieve green and sustainable development of manufacturing economy,environment,and social benefits,has attracted much attention in recent years.With the multi-dimensional integration of networking,digitization,and informatization in the manufacturing industry,how to scientifically and reasonably utilize the multi life cycle manufacturing,service,and failure feature data of in-service mechanical and electrical products,and adopt modern remanufacturing engineering technology to achieve active remanufacturing scheme decision-making that maximizes the ecological benefits of the multi life cycle of in-service mechanical and electrical products has become a research focus.Therefore,this article is based on the national fund project "Research on the Theory and Method of Intelligent Upgrading Design of Waste Mechanical and Electrical Products Based on Multi attribute Life Customization(52075396)",to study the active remanufacturing scheme decision-making of data-driven in-service mechanical and electrical products for maximizing ecological benefits in multiple life cycles,and establish a data-driven active remanufacturing scheme decision-making of in-service mechanical and electrical products.This provides data and theoretical basis for optimizing the matching and performance upgrading of active remanufacturing components for in-service electromechanical products,and forms a systematic and intelligent decision-making mechanism for active remanufacturing solutions for in-service electromechanical products.Firstly,conduct a complete machine analysis of in-service electromechanical products,obtain their key components and performance parameter indicators,and construct a quality evaluation system;By using intelligent detection technology to detect key parameters and failure features,a database of failure features for in-service mechanical and electrical product components is constructed to achieve real-time storage,transmission,and sharing of key parameters.This provides data support for quality grading of in-service mechanical and electrical product components,optimal accuracy matching of active remanufacturing components,and decision-making of active remanufacturing plans in the later stage.Secondly,based on the expert knowledge model based on practical experience and the multi life cycle data of in-service mechanical and electrical products,the basic model of quality grading of in-service mechanical and electrical components is constructed.Considering the impact of in-service mechanical and electrical products’ service characteristics and performance upgrading constraints on quality grading,the quality grading optimization model of mechanical components based on particle swarm optimization algorithm is constructed to provide a theoretical basis for achieving optimal matching of active remanufactured components and upgrading product performance for in-service electromechanical products.Then,starting from the overall quality and cost of active remanufacturing mechanical and electrical products,the impact of factors such as performance upgrading and dimensional accuracy on the overall quality of active remanufacturing mechanical and electrical products was analyzed.A multi-dimensional collaborative evolution algorithm is adopted to establish an optimization model for the selection of components in active remanufacturing products that considers dimensional accuracy.This provides a data support and sharing platform for the active remanufacturing upgrading and performance optimization of in-service mechanical and electrical products.Thirdly,from the aspects of active remanufacturing costs,pollution emissions,quality value and social benefits of electromechanical products in service,the data characteristics of multiple life cycles of electromechanical products in service,the optimal precision matching characteristics of parts quality and active remanufacturing parts are analyzed.The entropy weight analysis method and semi supervised learning algorithm are combined to establish a decision-making model of active remanufacturing scheme of electromechanical products in service considering multiple life cycles.This provides methods and practical support for achieving intelligent and efficient enterprise based active remanufacturing production of in-service mechanical and electrical products.Finally,taking the active remanufacturing of the in-service machine tool CA6180 as an example,the quality characteristics and optimal accuracy matching of its active remanufacturing components were comprehensively analyzed,and the optimal active remanufacturing plan for maximizing the ecological benefits of the multiple life cycles of the in-service machine tool was obtained,verifying the feasibility of the model proposed in this paper.