Remaining useful life prediction for equipment based on RF-BiLSTM
The prediction technology of remaining useful life has received a lot attention to ensure the reliability and stability of complex mechanical equipment. Due to the large-scale, non-linear, and high-dimensional characteristics of monitoring data, machine learning does not need an exact physical model...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
AIP Publishing LLC
2022-11-01
|
Series: | AIP Advances |
Online Access: | http://dx.doi.org/10.1063/5.0125885 |
_version_ | 1797947434792386560 |
---|---|
author | Zhiqiang Wu Zhenxi Wang Huihui Wei Jianji Ren Yongliang Yuan Taijie Wang Wenxian Duan Hefan Wei Shukai Wang |
author_facet | Zhiqiang Wu Zhenxi Wang Huihui Wei Jianji Ren Yongliang Yuan Taijie Wang Wenxian Duan Hefan Wei Shukai Wang |
author_sort | Zhiqiang Wu |
collection | DOAJ |
description | The prediction technology of remaining useful life has received a lot attention to ensure the reliability and stability of complex mechanical equipment. Due to the large-scale, non-linear, and high-dimensional characteristics of monitoring data, machine learning does not need an exact physical model and prior expert knowledge. It has robust data processing ability, which shows a broad prospect in the field of life prediction of complex mechanical and electrical equipment. Therefore, a remaining useful life prediction algorithm based on Random Forest and Bi-directional Long Short-Term Memory (RF-BiLSTM) is proposed. In the RF-BiLSTM algorithm, RF is utilized to extract health indicators that reflect the life of the equipment. On this basis, a BiLSTM neural network is used to predict the residual life of the device. The effectiveness and advanced performance of RF-BiLSTM are verified in commercial modular aviation propulsion system datasets. The experimental results show that the RMSE of the RF-BiLSTM is 0.3892, which is 47.96%, 84.81%, 38.89%, and 86.53% lower than that of LSTM, SVR, XGBoost, and AdaBoost, respectively. It is verified that RF-BiLSTM can effectively improve the prediction accuracy of the remaining useful life of complex mechanical and electrical equipment, and it has certain application value. |
first_indexed | 2024-04-10T21:27:51Z |
format | Article |
id | doaj.art-f815b85a34eb4264bf4ea6000bd3ddc2 |
institution | Directory Open Access Journal |
issn | 2158-3226 |
language | English |
last_indexed | 2024-04-10T21:27:51Z |
publishDate | 2022-11-01 |
publisher | AIP Publishing LLC |
record_format | Article |
series | AIP Advances |
spelling | doaj.art-f815b85a34eb4264bf4ea6000bd3ddc22023-01-19T16:29:03ZengAIP Publishing LLCAIP Advances2158-32262022-11-011211115209115209-810.1063/5.0125885Remaining useful life prediction for equipment based on RF-BiLSTMZhiqiang Wu0Zhenxi Wang1Huihui Wei2Jianji Ren3Yongliang Yuan4Taijie Wang5Wenxian Duan6Hefan Wei7Shukai Wang8College of Computer Science and Technology, Henan Polytechnic University, Jiaozuo 454000, ChinaCollege of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaCollege of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaCollege of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Mechanical and Power Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaShenyang Institute of Automation (SIA), Chinese Academy of Sciences, Shenyang 110000, ChinaState Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130022, ChinaCollege of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaCollege of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaThe prediction technology of remaining useful life has received a lot attention to ensure the reliability and stability of complex mechanical equipment. Due to the large-scale, non-linear, and high-dimensional characteristics of monitoring data, machine learning does not need an exact physical model and prior expert knowledge. It has robust data processing ability, which shows a broad prospect in the field of life prediction of complex mechanical and electrical equipment. Therefore, a remaining useful life prediction algorithm based on Random Forest and Bi-directional Long Short-Term Memory (RF-BiLSTM) is proposed. In the RF-BiLSTM algorithm, RF is utilized to extract health indicators that reflect the life of the equipment. On this basis, a BiLSTM neural network is used to predict the residual life of the device. The effectiveness and advanced performance of RF-BiLSTM are verified in commercial modular aviation propulsion system datasets. The experimental results show that the RMSE of the RF-BiLSTM is 0.3892, which is 47.96%, 84.81%, 38.89%, and 86.53% lower than that of LSTM, SVR, XGBoost, and AdaBoost, respectively. It is verified that RF-BiLSTM can effectively improve the prediction accuracy of the remaining useful life of complex mechanical and electrical equipment, and it has certain application value.http://dx.doi.org/10.1063/5.0125885 |
spellingShingle | Zhiqiang Wu Zhenxi Wang Huihui Wei Jianji Ren Yongliang Yuan Taijie Wang Wenxian Duan Hefan Wei Shukai Wang Remaining useful life prediction for equipment based on RF-BiLSTM AIP Advances |
title | Remaining useful life prediction for equipment based on RF-BiLSTM |
title_full | Remaining useful life prediction for equipment based on RF-BiLSTM |
title_fullStr | Remaining useful life prediction for equipment based on RF-BiLSTM |
title_full_unstemmed | Remaining useful life prediction for equipment based on RF-BiLSTM |
title_short | Remaining useful life prediction for equipment based on RF-BiLSTM |
title_sort | remaining useful life prediction for equipment based on rf bilstm |
url | http://dx.doi.org/10.1063/5.0125885 |
work_keys_str_mv | AT zhiqiangwu remainingusefullifepredictionforequipmentbasedonrfbilstm AT zhenxiwang remainingusefullifepredictionforequipmentbasedonrfbilstm AT huihuiwei remainingusefullifepredictionforequipmentbasedonrfbilstm AT jianjiren remainingusefullifepredictionforequipmentbasedonrfbilstm AT yongliangyuan remainingusefullifepredictionforequipmentbasedonrfbilstm AT taijiewang remainingusefullifepredictionforequipmentbasedonrfbilstm AT wenxianduan remainingusefullifepredictionforequipmentbasedonrfbilstm AT hefanwei remainingusefullifepredictionforequipmentbasedonrfbilstm AT shukaiwang remainingusefullifepredictionforequipmentbasedonrfbilstm |