A Dual-LSTM Framework Combining Change Point Detection and Remaining Useful Life Prediction. Shi, Z. & Chehade, A. Reliability Engineering & System Safety, October, 2020. ![A Dual-LSTM Framework Combining Change Point Detection and Remaining Useful Life Prediction [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Remaining Useful Life (RUL) prediction is a key task of Condition-based Maintenance (CBM). The massive data collected from multiple sensors enables monitoring the complex systems in near real-time. However, such multiple sensors data environments pose a challenging task of combining the sensor data to infer the quality and RUL of the system. To address this task, we propose a Dual-LSTM framework that leverages Long-Short Term Memory (LSTM) for degradation analysis and RUL prediction. The Dual-LSTM relaxes the strong assumption of the fixed change point and detects the uncertain change point unit by unit at first. Then, the Dual-LSTM predicts the health index beyond the change point which can be leveraged to calculate the RUL. The proposed Dual-LSTM (i) achieves real-time high-precision RUL prediction by connecting the change point detection and RUL prediction with the health index construction, (ii) introduces a novel one-dimension health index function, (iii) leverages historical information to achieve detection and prediction tasks by characterizing both long and short-term dependencies of sensor signals through LSTM network. The effectiveness of the proposed Dual-LSTM framework is validated and compared to state-of-art benchmark methods on two publicly available turbofan engine degradation datasets.
@article{shi_dual-lstm_2020,
title = {A {Dual}-{LSTM} {Framework} {Combining} {Change} {Point} {Detection} and {Remaining} {Useful} {Life} {Prediction}},
issn = {0951-8320},
url = {http://www.sciencedirect.com/science/article/pii/S0951832020307572},
doi = {10.1016/j.ress.2020.107257},
abstract = {Remaining Useful Life (RUL) prediction is a key task of Condition-based Maintenance (CBM). The massive data collected from multiple sensors enables monitoring the complex systems in near real-time. However, such multiple sensors data environments pose a challenging task of combining the sensor data to infer the quality and RUL of the system. To address this task, we propose a Dual-LSTM framework that leverages Long-Short Term Memory (LSTM) for degradation analysis and RUL prediction. The Dual-LSTM relaxes the strong assumption of the fixed change point and detects the uncertain change point unit by unit at first. Then, the Dual-LSTM predicts the health index beyond the change point which can be leveraged to calculate the RUL. The proposed Dual-LSTM (i) achieves real-time high-precision RUL prediction by connecting the change point detection and RUL prediction with the health index construction, (ii) introduces a novel one-dimension health index function, (iii) leverages historical information to achieve detection and prediction tasks by characterizing both long and short-term dependencies of sensor signals through LSTM network. The effectiveness of the proposed Dual-LSTM framework is validated and compared to state-of-art benchmark methods on two publicly available turbofan engine degradation datasets.},
language = {en},
urldate = {2020-10-05},
journal = {Reliability Engineering \& System Safety},
author = {Shi, Zunya and Chehade, Abdallah},
month = oct,
year = {2020},
keywords = {Change point detection, Long short-term memory, Neural networks, Prognosis, Remaining useful life, Sensor fusion},
pages = {107257},
}
Downloads: 0
{"_id":"NY5fhDAje3n5Zw735","bibbaseid":"shi-chehade-aduallstmframeworkcombiningchangepointdetectionandremainingusefullifeprediction-2020","authorIDs":["eMSQX2qxTgpfmSCQW"],"author_short":["Shi, Z.","Chehade, A."],"bibdata":{"bibtype":"article","type":"article","title":"A Dual-LSTM Framework Combining Change Point Detection and Remaining Useful Life Prediction","issn":"0951-8320","url":"http://www.sciencedirect.com/science/article/pii/S0951832020307572","doi":"10.1016/j.ress.2020.107257","abstract":"Remaining Useful Life (RUL) prediction is a key task of Condition-based Maintenance (CBM). The massive data collected from multiple sensors enables monitoring the complex systems in near real-time. However, such multiple sensors data environments pose a challenging task of combining the sensor data to infer the quality and RUL of the system. To address this task, we propose a Dual-LSTM framework that leverages Long-Short Term Memory (LSTM) for degradation analysis and RUL prediction. The Dual-LSTM relaxes the strong assumption of the fixed change point and detects the uncertain change point unit by unit at first. Then, the Dual-LSTM predicts the health index beyond the change point which can be leveraged to calculate the RUL. The proposed Dual-LSTM (i) achieves real-time high-precision RUL prediction by connecting the change point detection and RUL prediction with the health index construction, (ii) introduces a novel one-dimension health index function, (iii) leverages historical information to achieve detection and prediction tasks by characterizing both long and short-term dependencies of sensor signals through LSTM network. The effectiveness of the proposed Dual-LSTM framework is validated and compared to state-of-art benchmark methods on two publicly available turbofan engine degradation datasets.","language":"en","urldate":"2020-10-05","journal":"Reliability Engineering & System Safety","author":[{"propositions":[],"lastnames":["Shi"],"firstnames":["Zunya"],"suffixes":[]},{"propositions":[],"lastnames":["Chehade"],"firstnames":["Abdallah"],"suffixes":[]}],"month":"October","year":"2020","keywords":"Change point detection, Long short-term memory, Neural networks, Prognosis, Remaining useful life, Sensor fusion","pages":"107257","bibtex":"@article{shi_dual-lstm_2020,\n\ttitle = {A {Dual}-{LSTM} {Framework} {Combining} {Change} {Point} {Detection} and {Remaining} {Useful} {Life} {Prediction}},\n\tissn = {0951-8320},\n\turl = {http://www.sciencedirect.com/science/article/pii/S0951832020307572},\n\tdoi = {10.1016/j.ress.2020.107257},\n\tabstract = {Remaining Useful Life (RUL) prediction is a key task of Condition-based Maintenance (CBM). The massive data collected from multiple sensors enables monitoring the complex systems in near real-time. However, such multiple sensors data environments pose a challenging task of combining the sensor data to infer the quality and RUL of the system. To address this task, we propose a Dual-LSTM framework that leverages Long-Short Term Memory (LSTM) for degradation analysis and RUL prediction. The Dual-LSTM relaxes the strong assumption of the fixed change point and detects the uncertain change point unit by unit at first. Then, the Dual-LSTM predicts the health index beyond the change point which can be leveraged to calculate the RUL. The proposed Dual-LSTM (i) achieves real-time high-precision RUL prediction by connecting the change point detection and RUL prediction with the health index construction, (ii) introduces a novel one-dimension health index function, (iii) leverages historical information to achieve detection and prediction tasks by characterizing both long and short-term dependencies of sensor signals through LSTM network. The effectiveness of the proposed Dual-LSTM framework is validated and compared to state-of-art benchmark methods on two publicly available turbofan engine degradation datasets.},\n\tlanguage = {en},\n\turldate = {2020-10-05},\n\tjournal = {Reliability Engineering \\& System Safety},\n\tauthor = {Shi, Zunya and Chehade, Abdallah},\n\tmonth = oct,\n\tyear = {2020},\n\tkeywords = {Change point detection, Long short-term memory, Neural networks, Prognosis, Remaining useful life, Sensor fusion},\n\tpages = {107257},\n}\n\n","author_short":["Shi, Z.","Chehade, A."],"key":"shi_dual-lstm_2020","id":"shi_dual-lstm_2020","bibbaseid":"shi-chehade-aduallstmframeworkcombiningchangepointdetectionandremainingusefullifeprediction-2020","role":"author","urls":{"Paper":"http://www.sciencedirect.com/science/article/pii/S0951832020307572"},"keyword":["Change point detection","Long short-term memory","Neural networks","Prognosis","Remaining useful life","Sensor fusion"],"metadata":{"authorlinks":{"chehade, a":"https://bibbase.org/service/mendeley/ceb22f87-8e17-3a73-8ac5-df584316b424"}}},"bibtype":"article","creationDate":"2020-10-04T16:04:56.912Z","downloads":0,"keywords":["change point detection","long short-term memory","neural networks","prognosis","remaining useful life","sensor fusion"],"search_terms":["dual","lstm","framework","combining","change","point","detection","remaining","useful","life","prediction","shi","chehade"],"title":"A Dual-LSTM Framework Combining Change Point Detection and Remaining Useful Life Prediction","year":2020,"biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["6gzRpwJ4xiXr4kmTA","ya2CyA73rpZseyrZ8","yanwtMpCcFaHzRwWb","iwKepCrWBps7ojhDx"]}