Prediction of the Remaining Useful Life of Bearings Through CNN-Bi-LSTM-Based Domain Adaptation Model

Predicting the remaining useful life (RUL) of mechanical bearings is crucial in the industry. Estimating the RUL enables the assessment of health bearing, maintenance planning, and significant cost reduction, thereby fostering industrial development. Existing models rely on traditional feature engin...

Full description

Saved in:
Bibliographic Details
Main Authors: Feifan Li, Zhuoheng Dai, Lei Jiang, Chanfei Song, Caiming Zhong, Yingna Chen
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/21/6906
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846173101902004224
author Feifan Li
Zhuoheng Dai
Lei Jiang
Chanfei Song
Caiming Zhong
Yingna Chen
author_facet Feifan Li
Zhuoheng Dai
Lei Jiang
Chanfei Song
Caiming Zhong
Yingna Chen
author_sort Feifan Li
collection DOAJ
description Predicting the remaining useful life (RUL) of mechanical bearings is crucial in the industry. Estimating the RUL enables the assessment of health bearing, maintenance planning, and significant cost reduction, thereby fostering industrial development. Existing models rely on traditional feature engineering with feature changes because operating conditions pose a major challenge to the generalization of RUL prediction models. This study focuses on neural network-based feature engineering and the downstream prediction of the RUL, eliminating the need for specific prior knowledge and simplifying the development and maintenance of models. Initially, a convolutional neural network (CNN) model is employed for feature engineering. Subsequently, a bidirectional long short-term memory network (Bi-LSTM) model is used to capture the time-series degradation characteristics of the engineered features and predict the RUL through regression. Finally, the study examines the influence of operating conditions in the model and integrates domain adaptation to minimize differences in feature distribution, thereby enhancing the model’s generalizability for the RUL prediction.
format Article
id doaj-art-68ac72fb73bf4ff8943cda14fa0d1325
institution Kabale University
issn 1424-8220
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-68ac72fb73bf4ff8943cda14fa0d13252024-11-08T14:41:23ZengMDPI AGSensors1424-82202024-10-012421690610.3390/s24216906Prediction of the Remaining Useful Life of Bearings Through CNN-Bi-LSTM-Based Domain Adaptation ModelFeifan Li0Zhuoheng Dai1Lei Jiang2Chanfei Song3Caiming Zhong4Yingna Chen5School of Information Engineering, College of Science & Technology, Ningbo University, Ningbo 315000, ChinaSchool of Information Engineering, College of Science & Technology, Ningbo University, Ningbo 315000, ChinaSchool of Information Engineering, College of Science & Technology, Ningbo University, Ningbo 315000, ChinaSchool of Information Engineering, College of Science & Technology, Ningbo University, Ningbo 315000, ChinaSchool of Information Engineering, College of Science & Technology, Ningbo University, Ningbo 315000, ChinaSchool of Information Engineering, College of Science & Technology, Ningbo University, Ningbo 315000, ChinaPredicting the remaining useful life (RUL) of mechanical bearings is crucial in the industry. Estimating the RUL enables the assessment of health bearing, maintenance planning, and significant cost reduction, thereby fostering industrial development. Existing models rely on traditional feature engineering with feature changes because operating conditions pose a major challenge to the generalization of RUL prediction models. This study focuses on neural network-based feature engineering and the downstream prediction of the RUL, eliminating the need for specific prior knowledge and simplifying the development and maintenance of models. Initially, a convolutional neural network (CNN) model is employed for feature engineering. Subsequently, a bidirectional long short-term memory network (Bi-LSTM) model is used to capture the time-series degradation characteristics of the engineered features and predict the RUL through regression. Finally, the study examines the influence of operating conditions in the model and integrates domain adaptation to minimize differences in feature distribution, thereby enhancing the model’s generalizability for the RUL prediction.https://www.mdpi.com/1424-8220/24/21/6906bearingRULCNNBi-LSTMdomain adaptation
spellingShingle Feifan Li
Zhuoheng Dai
Lei Jiang
Chanfei Song
Caiming Zhong
Yingna Chen
Prediction of the Remaining Useful Life of Bearings Through CNN-Bi-LSTM-Based Domain Adaptation Model
Sensors
bearing
RUL
CNN
Bi-LSTM
domain adaptation
title Prediction of the Remaining Useful Life of Bearings Through CNN-Bi-LSTM-Based Domain Adaptation Model
title_full Prediction of the Remaining Useful Life of Bearings Through CNN-Bi-LSTM-Based Domain Adaptation Model
title_fullStr Prediction of the Remaining Useful Life of Bearings Through CNN-Bi-LSTM-Based Domain Adaptation Model
title_full_unstemmed Prediction of the Remaining Useful Life of Bearings Through CNN-Bi-LSTM-Based Domain Adaptation Model
title_short Prediction of the Remaining Useful Life of Bearings Through CNN-Bi-LSTM-Based Domain Adaptation Model
title_sort prediction of the remaining useful life of bearings through cnn bi lstm based domain adaptation model
topic bearing
RUL
CNN
Bi-LSTM
domain adaptation
url https://www.mdpi.com/1424-8220/24/21/6906
work_keys_str_mv AT feifanli predictionoftheremainingusefullifeofbearingsthroughcnnbilstmbaseddomainadaptationmodel
AT zhuohengdai predictionoftheremainingusefullifeofbearingsthroughcnnbilstmbaseddomainadaptationmodel
AT leijiang predictionoftheremainingusefullifeofbearingsthroughcnnbilstmbaseddomainadaptationmodel
AT chanfeisong predictionoftheremainingusefullifeofbearingsthroughcnnbilstmbaseddomainadaptationmodel
AT caimingzhong predictionoftheremainingusefullifeofbearingsthroughcnnbilstmbaseddomainadaptationmodel
AT yingnachen predictionoftheremainingusefullifeofbearingsthroughcnnbilstmbaseddomainadaptationmodel