Remaining useful life prediction of rolling bearings based on TCN-MSA
Open Access
- 15 November 2023
- journal article
- research article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (2) , 025125
Abstract
As a pivotal element within the drive system of mechanical equipment, the remaining useful life (RUL) of rolling bearings not only dictates the lifespan of the equipment’s drive system but also the overall machine. An inaccurate prediction of the RUL of rolling bearings could hinder the formulation of maintenance strategies and lead to a chain of failures stemming from bearing malfunction, culminating in potentially catastrophic accidents. This paper designs a novel temporal convolutional network-multi-head self-attention (TCN-MSA) model for predicting the RUL of rolling bearings. This model considers the intricate non-linearity and complexity of mechanical equipment systems. It captures long-term dependencies using the causally inflated convolutional structure within the temporal convolutional network (TCN) and simultaneously extracts features from the frequency domain signal. Subsequently, by employing the multi-head self-attention (MSA) mechanism, the model discerns the significance of different features throughout the degradation process of rolling bearings by analyzing global information. The final prediction for rolling bearings’ RUL has been successfully attained. To underline the excellence of the method presented in this paper, a comparative analysis was performed with existing methods, such as convolutional neural network, gate recurrent unit, and TCN. The results highlight that the model designed in this paper surpasses other existing methods in predicting the RUL of rolling bearings, demonstrating superior prediction accuracy and robust generalization capability.Keywords
Funding Information
- Science and Technology Planning Project of Inner Mongolia of China (2021GG0346)
- National Natural Science Foundation of China (52365019)
- Natural Science Foundation of Inner Mongolia Autonomous Region (2023MS05030)
- Basic Scientific Research Business Expenses of Inner Mongolia Directly Affiliated Universities (JY20220004)
This publication has 32 references indexed in Scilit:
- Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanismMeasurement, 2021
- Reliability analysis of a floating offshore wind turbine using Bayesian NetworksOcean Engineering, 2020
- Gated Dual Attention Unit Neural Networks for Remaining Useful Life Prediction of Rolling BearingsIEEE Transactions on Industrial Informatics, 2020
- Remaining useful life prediction using multi-scale deep convolutional neural networkApplied Soft Computing, 2020
- Deep separable convolutional network for remaining useful life prediction of machineryMechanical Systems and Signal Processing, 2019
- Remaining useful life estimation using a bidirectional recurrent neural network based autoencoder schemeMechanical Systems and Signal Processing, 2019
- Gated recurrent unit based recurrent neural network for remaining useful life prediction of nonlinear deterioration processReliability Engineering & System Safety, 2019
- A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element BearingsIEEE Transactions on Reliability, 2018
- Multi-bearing remaining useful life collaborative prediction: A deep learning approachJournal of Manufacturing Systems, 2017
- An Optimal Sample Data Usage Strategy to Minimize Overfitting and Underfitting Effects in Regression Tree Models Based on Remotely-Sensed DataRemote Sensing, 2016