Fault diagnosis and sustainable remanufacturing of complex equipment under uncertain conditions

Complex equipment system has the characteristics of time-varying, hierarchy, certain redundancy, and limited fault diagnosis experience, which makes it difficult for traditional diagnosis methods to meet its diagnosis and maintenance requirements. In order to improve the accuracy and efficiency of fault diagnosis for large-scale complex equipment, an intelligent fault diagnosis method is proposed. In this paper, the problem of fault diagnosis and sustainable remanufacturing of complex equipment under uncertain conditions is studied. Big data analysis and machine learning technology are applied to fault prediction diagnosis of equipment operation process, and fault information is mined from big data of complex equipment operation characteristics to realize rapid diagnosis of operation faults. The error between the natural frequency of low-speed complex equipment obtained by numerical simulation and the natural frequency calculated by finite element method is less than 5%. By comparing them, the accuracy of fault description is proved. We make full use of network technology, give full play to its advantages of wide coverage and resource sharing, and establish a network monitoring and fault diagnosis system, which can realize various software and hardware resource sharing, multi-machine redundant backup, and parallel processing.