Remaining Useful Life Prediction With Fusing Failure Time Data and Field Degradation Data With Random Effects
Accurate remaining useful life (RUL) prediction has a great significance to improve the reliability and safety for key equipment. However, it often occur imperfect or even no prior degradation information in practical application for the existing RUL prediction methods, which could produce predictio...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8876626/ |
| _version_ | 1819175867040923648 |
|---|---|
| author | Shengjin Tang Xiaodong Xu Chuanqiang Yu Xiaoyan Sun Hongdong Fan Xiao-Sheng Si |
| author_facet | Shengjin Tang Xiaodong Xu Chuanqiang Yu Xiaoyan Sun Hongdong Fan Xiao-Sheng Si |
| author_sort | Shengjin Tang |
| collection | DOAJ |
| description | Accurate remaining useful life (RUL) prediction has a great significance to improve the reliability and safety for key equipment. However, it often occur imperfect or even no prior degradation information in practical application for the existing RUL prediction methods, which could produce prediction error. To solve this issue, this paper proposes a two-step RUL prediction method based on Wiener processes with reasonably fusing the failure time data and field degradation data. First, we obtain some interesting natures of parameters estimation based on the basic linear Wiener process. These natures explain the relationship between the parameters estimation results and the feature of degradation data, i.e. item sample numbers, detection time and detect frequency, and give the basis regarding how to reasonably fuse the failure time data and field degradation data. Second, under the Bayesian framework, we further propose a two-step method by fusing the failure time data and field degradation data with considering the random effects based on the proposed natures of parameters estimation. In this method, we propose an EM algorithm to estimate the mean and variance drift parameter of Wiener processes by the failure time data. Next, we generalize this two-step RUL prediction method to the nonlinear Wiener process. Last, we use two case studies to demonstrate the usefulness and superiority of the proposed method. |
| first_indexed | 2024-12-22T21:01:41Z |
| format | Article |
| id | doaj.art-4274dd03447b4cf99cbdab9b7498ba1b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T21:01:41Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4274dd03447b4cf99cbdab9b7498ba1b2022-12-21T18:12:49ZengIEEEIEEE Access2169-35362020-01-018119641197810.1109/ACCESS.2019.29482638876626Remaining Useful Life Prediction With Fusing Failure Time Data and Field Degradation Data With Random EffectsShengjin Tang0https://orcid.org/0000-0003-2480-4188Xiaodong Xu1Chuanqiang Yu2https://orcid.org/0000-0001-5525-1104Xiaoyan Sun3Hongdong Fan4https://orcid.org/0000-0002-3532-9741Xiao-Sheng Si5https://orcid.org/0000-0001-5226-9923High-Tech Institute of Xi’an, Xi’an, ChinaHigh-Tech Institute of Xi’an, Xi’an, ChinaHigh-Tech Institute of Xi’an, Xi’an, ChinaHigh-Tech Institute of Xi’an, Xi’an, ChinaHigh-Tech Institute of Xi’an, Xi’an, ChinaHigh-Tech Institute of Xi’an, Xi’an, ChinaAccurate remaining useful life (RUL) prediction has a great significance to improve the reliability and safety for key equipment. However, it often occur imperfect or even no prior degradation information in practical application for the existing RUL prediction methods, which could produce prediction error. To solve this issue, this paper proposes a two-step RUL prediction method based on Wiener processes with reasonably fusing the failure time data and field degradation data. First, we obtain some interesting natures of parameters estimation based on the basic linear Wiener process. These natures explain the relationship between the parameters estimation results and the feature of degradation data, i.e. item sample numbers, detection time and detect frequency, and give the basis regarding how to reasonably fuse the failure time data and field degradation data. Second, under the Bayesian framework, we further propose a two-step method by fusing the failure time data and field degradation data with considering the random effects based on the proposed natures of parameters estimation. In this method, we propose an EM algorithm to estimate the mean and variance drift parameter of Wiener processes by the failure time data. Next, we generalize this two-step RUL prediction method to the nonlinear Wiener process. Last, we use two case studies to demonstrate the usefulness and superiority of the proposed method.https://ieeexplore.ieee.org/document/8876626/Remaining useful life predictionwiener processesfusingfailure time datafield degradation datarandom effects |
| spellingShingle | Shengjin Tang Xiaodong Xu Chuanqiang Yu Xiaoyan Sun Hongdong Fan Xiao-Sheng Si Remaining Useful Life Prediction With Fusing Failure Time Data and Field Degradation Data With Random Effects IEEE Access Remaining useful life prediction wiener processes fusing failure time data field degradation data random effects |
| title | Remaining Useful Life Prediction With Fusing Failure Time Data and Field Degradation Data With Random Effects |
| title_full | Remaining Useful Life Prediction With Fusing Failure Time Data and Field Degradation Data With Random Effects |
| title_fullStr | Remaining Useful Life Prediction With Fusing Failure Time Data and Field Degradation Data With Random Effects |
| title_full_unstemmed | Remaining Useful Life Prediction With Fusing Failure Time Data and Field Degradation Data With Random Effects |
| title_short | Remaining Useful Life Prediction With Fusing Failure Time Data and Field Degradation Data With Random Effects |
| title_sort | remaining useful life prediction with fusing failure time data and field degradation data with random effects |
| topic | Remaining useful life prediction wiener processes fusing failure time data field degradation data random effects |
| url | https://ieeexplore.ieee.org/document/8876626/ |
| work_keys_str_mv | AT shengjintang remainingusefullifepredictionwithfusingfailuretimedataandfielddegradationdatawithrandomeffects AT xiaodongxu remainingusefullifepredictionwithfusingfailuretimedataandfielddegradationdatawithrandomeffects AT chuanqiangyu remainingusefullifepredictionwithfusingfailuretimedataandfielddegradationdatawithrandomeffects AT xiaoyansun remainingusefullifepredictionwithfusingfailuretimedataandfielddegradationdatawithrandomeffects AT hongdongfan remainingusefullifepredictionwithfusingfailuretimedataandfielddegradationdatawithrandomeffects AT xiaoshengsi remainingusefullifepredictionwithfusingfailuretimedataandfielddegradationdatawithrandomeffects |