Convolutional Neural Networks—Long Short-Term Memory—Attention: A Novel Model for Wear State Prediction Based on Oil Monitoring Data
Wear state prediction based on oil monitoring technology enables the early identification of potential wear and failure risks of friction pairs, facilitating optimized equipment maintenance and extended service life. However, the complexity of lubricating oil monitoring data often poses challenges i...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Lubricants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4442/13/7/306 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849733007076753408 |
|---|---|
| author | Ying Du Hui Wei Tao Shao Shishuai Chen Jianlei Wang Chunguo Zhou Yanchao Zhang |
| author_facet | Ying Du Hui Wei Tao Shao Shishuai Chen Jianlei Wang Chunguo Zhou Yanchao Zhang |
| author_sort | Ying Du |
| collection | DOAJ |
| description | Wear state prediction based on oil monitoring technology enables the early identification of potential wear and failure risks of friction pairs, facilitating optimized equipment maintenance and extended service life. However, the complexity of lubricating oil monitoring data often poses challenges in extracting discriminative features, limiting the accuracy of wear state prediction. To address this, a CNN–LSTM–Attention network is specially constructed for predicting wear state, which hierarchically integrates convolutional neural networks (CNNs) for spatial feature extraction, long short-term memory (LSTM) networks for temporal dynamics modeling, and self-attention mechanisms for adaptive feature refinement. The proposed architecture implements a three-stage computational pipeline. Initially, the CNN performs hierarchical extraction of localized patterns from multi-sensor tribological signals. Subsequently, the self-attention mechanism conducts adaptive recalibration of feature saliency, prioritizing diagnostically critical feature channels. Ultimately, bidirectional LSTM establishes cross-cyclic temporal dependencies, enabling cascaded fully connected layers with Gaussian activation to generate probabilistic wear state estimations. Experimental results demonstrate that the proposed model not only achieves superior predictive accuracy but also exhibits robust stability, offering a reliable solution for condition monitoring and predictive maintenance in industrial applications. |
| format | Article |
| id | doaj-art-d5ffd1ebcaf346ff98d92349e2c8accc |
| institution | DOAJ |
| issn | 2075-4442 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Lubricants |
| spelling | doaj-art-d5ffd1ebcaf346ff98d92349e2c8accc2025-08-20T03:08:09ZengMDPI AGLubricants2075-44422025-07-0113730610.3390/lubricants13070306Convolutional Neural Networks—Long Short-Term Memory—Attention: A Novel Model for Wear State Prediction Based on Oil Monitoring DataYing Du0Hui Wei1Tao Shao2Shishuai Chen3Jianlei Wang4Chunguo Zhou5Yanchao Zhang6School of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaSchool of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, ChinaWear state prediction based on oil monitoring technology enables the early identification of potential wear and failure risks of friction pairs, facilitating optimized equipment maintenance and extended service life. However, the complexity of lubricating oil monitoring data often poses challenges in extracting discriminative features, limiting the accuracy of wear state prediction. To address this, a CNN–LSTM–Attention network is specially constructed for predicting wear state, which hierarchically integrates convolutional neural networks (CNNs) for spatial feature extraction, long short-term memory (LSTM) networks for temporal dynamics modeling, and self-attention mechanisms for adaptive feature refinement. The proposed architecture implements a three-stage computational pipeline. Initially, the CNN performs hierarchical extraction of localized patterns from multi-sensor tribological signals. Subsequently, the self-attention mechanism conducts adaptive recalibration of feature saliency, prioritizing diagnostically critical feature channels. Ultimately, bidirectional LSTM establishes cross-cyclic temporal dependencies, enabling cascaded fully connected layers with Gaussian activation to generate probabilistic wear state estimations. Experimental results demonstrate that the proposed model not only achieves superior predictive accuracy but also exhibits robust stability, offering a reliable solution for condition monitoring and predictive maintenance in industrial applications.https://www.mdpi.com/2075-4442/13/7/306lubricating oilconvolutional neural networks (CNN)long short-term memory (LSTM)wear state prediction |
| spellingShingle | Ying Du Hui Wei Tao Shao Shishuai Chen Jianlei Wang Chunguo Zhou Yanchao Zhang Convolutional Neural Networks—Long Short-Term Memory—Attention: A Novel Model for Wear State Prediction Based on Oil Monitoring Data Lubricants lubricating oil convolutional neural networks (CNN) long short-term memory (LSTM) wear state prediction |
| title | Convolutional Neural Networks—Long Short-Term Memory—Attention: A Novel Model for Wear State Prediction Based on Oil Monitoring Data |
| title_full | Convolutional Neural Networks—Long Short-Term Memory—Attention: A Novel Model for Wear State Prediction Based on Oil Monitoring Data |
| title_fullStr | Convolutional Neural Networks—Long Short-Term Memory—Attention: A Novel Model for Wear State Prediction Based on Oil Monitoring Data |
| title_full_unstemmed | Convolutional Neural Networks—Long Short-Term Memory—Attention: A Novel Model for Wear State Prediction Based on Oil Monitoring Data |
| title_short | Convolutional Neural Networks—Long Short-Term Memory—Attention: A Novel Model for Wear State Prediction Based on Oil Monitoring Data |
| title_sort | convolutional neural networks long short term memory attention a novel model for wear state prediction based on oil monitoring data |
| topic | lubricating oil convolutional neural networks (CNN) long short-term memory (LSTM) wear state prediction |
| url | https://www.mdpi.com/2075-4442/13/7/306 |
| work_keys_str_mv | AT yingdu convolutionalneuralnetworkslongshorttermmemoryattentionanovelmodelforwearstatepredictionbasedonoilmonitoringdata AT huiwei convolutionalneuralnetworkslongshorttermmemoryattentionanovelmodelforwearstatepredictionbasedonoilmonitoringdata AT taoshao convolutionalneuralnetworkslongshorttermmemoryattentionanovelmodelforwearstatepredictionbasedonoilmonitoringdata AT shishuaichen convolutionalneuralnetworkslongshorttermmemoryattentionanovelmodelforwearstatepredictionbasedonoilmonitoringdata AT jianleiwang convolutionalneuralnetworkslongshorttermmemoryattentionanovelmodelforwearstatepredictionbasedonoilmonitoringdata AT chunguozhou convolutionalneuralnetworkslongshorttermmemoryattentionanovelmodelforwearstatepredictionbasedonoilmonitoringdata AT yanchaozhang convolutionalneuralnetworkslongshorttermmemoryattentionanovelmodelforwearstatepredictionbasedonoilmonitoringdata |