Bearing Remaining Useful Life Prediction Based on CICAE and ResConv1D-LSTM

Bearings play a critical role in industrial machinery, and accurate predictions of the remaining useful life (RUL) of bearings are essential for ensuring the safe operation of rotating equipment. However, traditional autoencoders and CNN-based approaches tend to assign equal weights to all feature c...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on instrumentation and measurement Vol. 74; p. 1
Main Authors: Qin, Yi, Zhao, Yihang, Zhuo, Yi'an, Chai, Yi, Yang, Zhenli, Mao, Yongfang
Format: Journal Article
Language:English
Published: New York IEEE 01.01.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Autoencoders
Bearing remaining useful life
Channels
CICAE
Computer architecture
Constraints
Convolution
Decoding
Deep learning
Degradation
Entropy (Information theory)
Feature extraction
Life prediction
Logic gates
Long short term memory
Machine learning
Predictive models
ResConv1DLSTM
RUL prediction
Training
Useful life
ISSN:0018-9456, 1557-9662
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Bearings play a critical role in industrial machinery, and accurate predictions of the remaining useful life (RUL) of bearings are essential for ensuring the safe operation of rotating equipment. However, traditional autoencoders and CNN-based approaches tend to assign equal weights to all feature channels for degradation feature extraction, which inevitably leads to the critical degradation characteristics being obscured by noise or characteristics of other channels. Moreover, the additive operation of traditional residual connection inherently limits the inter-block coordination, leading to redundant feature learning and constrained hierarchical representation capacity. To address these limitations, a novel two-stage deep learning framework is proposed. In the first stage, a Channel-information-constrained autoencoder (CICAE) develops an information entropy-based constraint to focus on the degradation-relevant channels while suppressing irrelevant ones. In the second stage, a ResConv1D-LSTM network integrates multi-scale convolutional blocks for progressive residual learning with several LSTM layers for temporal modeling, so as to comprehensively characterize the degradation trend, and then multiple fully connected layers are designed for RUL prediction. Experimental results demonstrate that the proposed bearing RUL prediction method outperforms existing approaches and is applicable in real-world scenarios.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2025.3597620