Health State Prediction Research Of Rotating Machinery Based On Quantum Process Neural Network

Rotating machinery is widely used in industry,with the rapid development of the rotating machinery to the large-scale and integrated direction,the structure of the equipment becomes more and more complex,and its operating state is paid more and more attention.Through the prediction of the health status of rotating machinery,faults can be found in time and the safety,utilization and reliability of rotating machinery can be improved.Therefore,it is very important to study the health status of rotating machinery.This paper according to the problems of rotating machinery under complex working conditions and nonlinear time-varying characteristics,the noise reduction method,global prediction model and integrated prediction model of vibration data are studied.A time-frequency matrix SVD de-noising method based on correlation coefficient is proposed,which eliminates the influence of strong background noise on the selection of singular values,and realizes adaptive selection of signal reconstruction order.The method is applied to the rolling bearing health state signal,and the effectiveness of the method is proved by noise reduction results.Aiming at the inadaptability of current network model in the field of rotating machinery,a quantum process neural network model based on controlled H gate is proposed,which realizes parallel processing of model information and multidimensional adjustment of network parameters,and avoid the process neural network in the function fitting and basis function expansion process error.The performance prediction of the rolling bearing shows that the quantum process neural network based on controlled H gate has good prediction precision.Aiming at the problem that the model of a single global model is complex and difficult to optimize,an integrated prediction model based on GA-Ada Boost.RT is proposed.The process neuralnetwork and discrete input process neural network are used as weak learning machine to construct ensemble prediction model.The prediction results of the rolling bearing health state show that the comprehensive prediction model constructed by the simple structure weak learning mechanism has better prediction effect than the single global model.Based on the above research results and combined with the advantages of VC++ and Matlab software,a health monitoring system for rotating machinery is developed.The prediction of the health state of rotating machinery,which can shorten the maintenance time,reduce maintenance costs,improve equipment utilization,maintainability and reliability,avoid the occurrence of disastrous accidents.It is of great theoretical significance and practical value to expand and enrich the health prediction methods of rotating machinery.