Mechanical equipment residual life prediction method for optimizing BiLSTM based on DRSN and sparrow search

Abstract

The invention relates to a mechanical equipment residual life prediction method for optimizing BiLSTM based on DRSN and sparrow search, and belongs to the field of mechanical equipment monitoring. Firstly, self-adaptive feature learning is carried out on an original signal by utilizing DRSN without priori knowledge, an attention mechanism and a soft thresholding structure of the network can effectively eliminate influences of noise related features, and degradation features of mechanical equipment are excavated to construct health indexes; then, a residual life prediction model is constructed by utilizing a BiLSTM network, and the parameters are optimized by adopting a sparrow search algorithm aiming at the problem that the number of neurons and the learning rate of a hidden layer of the BiLSTM are difficult to set; and after health indexes extracted by the DRSN are smoothed, normalized life is used as a label and input into the optimized BiLSTM prediction model, and residual life prediction of the mechanical equipment is completed.

Description

technical field [0001] The invention belongs to the field of mechanical equipment monitoring, and relates to a method for predicting the remaining life of mechanical equipment based on DRSN and sparrow search optimization BiLSTM. Background technique [0002] At this stage, predictive maintenance of mechanical equipment is necessary. Che Yujiao et al. used the KPCA method to integrate the time domain, frequency domain and time-frequency domain characteristics of vibration signals to characterize the degradation state of mechanical equipment (Che Yujiao, Chen Yunxia, ​​Cui Yuxuan. Application research of KPCA and improved LSTM in the prediction of rolling bearing residual life [J]. Journal of Electronic Measurement and Instrumentation, 2021,35(02):109-114.). SOUALHI uses Hilbert-Huang Transform to extract degraded features from vibration signals (SoualhiA, MedjaherK, Zerhouni N.Bearing Health monitoring based on Hilbert-Huang Transform, Support Vector Machine and Regression[...

AI Technical Summary

Problems solved by technology

However, with the increase of the number of layers of the deep learning model, the problems of model degradation and overfitting will appear. At the same time, the vibration signal of mechanical equipment will contain a lot of noise due to the influence of the environment during the acquisition process. These network structures are difficult to capture. Degradation information of mechanical equipment in noisy environment

Long-short-term memory (LSTM) solves the problem of gradient dissipation and explosion. It has advantages in predicting the remaining service life and can get good prediction results, but there is a problem that it cannot make full use of sequence information, and the BiLSTM network model can make full use of the context. The data is predicted and has been applied in the field of time series prediction. Compared with the ordinary convolutional neural network, the bidirectional long short-term memory network (BiLSTM) has achieved higher prediction accuracy.

However, there is still the problem that the learning rate and the number of neurons in the hidden layer are difficult to determine

Images