Remaining Useful Life Prediction Model for Rolling Bearings Based on MFPE–MACNN

Abstract

Aiming to resolve the problem of redundant information concerning rolling bearing degradation characteristics and to tackle the difficulty faced by convolutional deep learning models in learning feature information in complex time series, a prediction model for remaining useful life based on multiscale fusion permutation entropy (MFPE) and a multiscale convolutional attention neural network (MACNN) is proposed. The original signal of the rolling bearing was extracted and decomposed by resonance sparse decomposition to obtain the high-resonance and low-resonance components. The multiscale permutation entropy of the low-resonance component was calculated. Moreover, the locally linear-embedding algorithm was used for dimensionality reduction to remove redundant information. The multiscale convolution module was constructed to learn the feature information at different time scales. The attention module was used to fuse the feature information and input it into the remaining useful life prediction module for evaluation. The appropriate network structure and parameter configuration were determined, and a multiscale convolutional attention neural network was designed to determine the remaining useful life prediction model. The results show that the method demonstrates effectiveness and superiority in degrading the feature information representation and improving the remaining useful life prediction accuracy compared with other models.

A novel exponential degradation approach for predicting the remaining useful life of roadheader bearings

“…In general, our method has obvious advantages, which can predict the RUL of cutting bearings dynamically and accurately. To further illustrate the effectiveness of the proposed method, the performance of the proposed method is compared with that of the other three methods (SSDM, LSMM, MCNM) [23,27] and [28]. Figure 13 shows the comparison results.…”

“…However, the data used in the experiment are a publicly available bearing data set, and the accuracy of LSMM may be low due to the high noise in the actual experiment. Wang et al [28] proposed the RUL prediction model based on the multiscale fusion permutation entropy and a multiscale convolutional attention neural network (MCNM), and the effectiveness and accuracy of the improved RUL prediction were demonstrated by the Cincinnati open data. To accurately predict the remaining service life of roadheader bearings, a new exponential degradation method based on Bayesian optimization is proposed in this study.…”

A novel method for online prediction of the remaining useful life of rolling bearings based on wavelet power spectrogram and Transformer structure

“…The rapid development of IoT technology has caused an explosion of data, bringing new opportunities and challenges to the field of machine health monitoring [2,14]. With the development of computer technology and deep learning, various algorithms of deep learning are continuously being applied to the prognostics and health management (PHM) of mechanical equipment, whose powerful network structure for capturing potential data characteristics in massive data is well suited to improve the predictive performance of the models.…”