Remaining Useful Life Prediction Method for Stochastic Degrading Devices Considering Predictive Maintenance

Predictive maintenance, recognized as an effective health management strategy for extending the lifetime of devices, has emerged as a hot research topic in recent years. A general method is to execute two separate steps: data-driven remaining useful life (RUL) prediction and a maintenance strategy....

Full description

Saved in:
Bibliographic Details
Main Authors: Qing Dong, Hong Pei, Changhua Hu, Jianfei Zheng, Dangbo Du
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/4/1218
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850080128871170048
author Qing Dong
Hong Pei
Changhua Hu
Jianfei Zheng
Dangbo Du
author_facet Qing Dong
Hong Pei
Changhua Hu
Jianfei Zheng
Dangbo Du
author_sort Qing Dong
collection DOAJ
description Predictive maintenance, recognized as an effective health management strategy for extending the lifetime of devices, has emerged as a hot research topic in recent years. A general method is to execute two separate steps: data-driven remaining useful life (RUL) prediction and a maintenance strategy. However, among the numerous studies that conducted maintenance and replacement activities based on the results of RUL prediction, little attention has been paid to the impact of preventive maintenance on sensor-based monitoring data, which further affects the RUL for repairable degrading devices. In this paper, an adaptive RUL prediction method is proposed for repairable degrading devices in order to improve the accuracy of prediction results and achieve adaptability to future degradation processes. Firstly, a phased degradation model based on an adaptive Wiener process is established, taking into account the impact of imperfect maintenance. Meanwhile, integrating the impact of maintenance activities on the degradation rate and state, the probability distribution of RUL can be derived based on the concept of first hitting time (FHT). Secondly, a method is proposed for model parameter identification and updating that incorporates the individual variation among devices, integrating maximum likelihood estimation and Bayesian inference. Finally, the effectiveness of the RUL prediction method is ultimately validated through numerical simulation and its application to repairable gyroscope degradation data.
format Article
id doaj-art-725c9c8b34fa4a87b32b83965dfcfcdb
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-725c9c8b34fa4a87b32b83965dfcfcdb2025-08-20T02:45:01ZengMDPI AGSensors1424-82202025-02-01254121810.3390/s25041218Remaining Useful Life Prediction Method for Stochastic Degrading Devices Considering Predictive MaintenanceQing Dong0Hong Pei1Changhua Hu2Jianfei Zheng3Dangbo Du4The Department of Automation, Rocket Force University of Engineering, Xi’an 710025, ChinaThe Department of Automation, Rocket Force University of Engineering, Xi’an 710025, ChinaThe Department of Automation, Rocket Force University of Engineering, Xi’an 710025, ChinaThe Department of Automation, Rocket Force University of Engineering, Xi’an 710025, ChinaThe Department of Automation, Rocket Force University of Engineering, Xi’an 710025, ChinaPredictive maintenance, recognized as an effective health management strategy for extending the lifetime of devices, has emerged as a hot research topic in recent years. A general method is to execute two separate steps: data-driven remaining useful life (RUL) prediction and a maintenance strategy. However, among the numerous studies that conducted maintenance and replacement activities based on the results of RUL prediction, little attention has been paid to the impact of preventive maintenance on sensor-based monitoring data, which further affects the RUL for repairable degrading devices. In this paper, an adaptive RUL prediction method is proposed for repairable degrading devices in order to improve the accuracy of prediction results and achieve adaptability to future degradation processes. Firstly, a phased degradation model based on an adaptive Wiener process is established, taking into account the impact of imperfect maintenance. Meanwhile, integrating the impact of maintenance activities on the degradation rate and state, the probability distribution of RUL can be derived based on the concept of first hitting time (FHT). Secondly, a method is proposed for model parameter identification and updating that incorporates the individual variation among devices, integrating maximum likelihood estimation and Bayesian inference. Finally, the effectiveness of the RUL prediction method is ultimately validated through numerical simulation and its application to repairable gyroscope degradation data.https://www.mdpi.com/1424-8220/25/4/1218predictive maintenanceremaining useful liferepairable degrading devicesimperfect maintenanceadaptive Wienersensor-based monitoring
spellingShingle Qing Dong
Hong Pei
Changhua Hu
Jianfei Zheng
Dangbo Du
Remaining Useful Life Prediction Method for Stochastic Degrading Devices Considering Predictive Maintenance
Sensors
predictive maintenance
remaining useful life
repairable degrading devices
imperfect maintenance
adaptive Wiener
sensor-based monitoring
title Remaining Useful Life Prediction Method for Stochastic Degrading Devices Considering Predictive Maintenance
title_full Remaining Useful Life Prediction Method for Stochastic Degrading Devices Considering Predictive Maintenance
title_fullStr Remaining Useful Life Prediction Method for Stochastic Degrading Devices Considering Predictive Maintenance
title_full_unstemmed Remaining Useful Life Prediction Method for Stochastic Degrading Devices Considering Predictive Maintenance
title_short Remaining Useful Life Prediction Method for Stochastic Degrading Devices Considering Predictive Maintenance
title_sort remaining useful life prediction method for stochastic degrading devices considering predictive maintenance
topic predictive maintenance
remaining useful life
repairable degrading devices
imperfect maintenance
adaptive Wiener
sensor-based monitoring
url https://www.mdpi.com/1424-8220/25/4/1218
work_keys_str_mv AT qingdong remainingusefullifepredictionmethodforstochasticdegradingdevicesconsideringpredictivemaintenance
AT hongpei remainingusefullifepredictionmethodforstochasticdegradingdevicesconsideringpredictivemaintenance
AT changhuahu remainingusefullifepredictionmethodforstochasticdegradingdevicesconsideringpredictivemaintenance
AT jianfeizheng remainingusefullifepredictionmethodforstochasticdegradingdevicesconsideringpredictivemaintenance
AT dangbodu remainingusefullifepredictionmethodforstochasticdegradingdevicesconsideringpredictivemaintenance