A generalized diffusion model for remaining useful life prediction with uncertainty
Abstract Forecasting the remaining useful life (RUL) is a crucial aspect of prognostics and health management (PHM), which has garnered significant attention in academic and industrial domains in recent decades. The accurate prediction of RUL relies on the creation of an appropriate degradation mode...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-01-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01773-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861500324872192 |
|---|---|
| author | Bincheng Wen Xin Zhao Xilang Tang Mingqing Xiao Haizhen Zhu Jianfeng Li |
| author_facet | Bincheng Wen Xin Zhao Xilang Tang Mingqing Xiao Haizhen Zhu Jianfeng Li |
| author_sort | Bincheng Wen |
| collection | DOAJ |
| description | Abstract Forecasting the remaining useful life (RUL) is a crucial aspect of prognostics and health management (PHM), which has garnered significant attention in academic and industrial domains in recent decades. The accurate prediction of RUL relies on the creation of an appropriate degradation model for the system. In this paper, a general representation of diffusion process models with three sources of uncertainty for RUL estimation is constructed. According to time-space transformation, the analytic equations that approximate the RUL probability distribution function (PDF) are inferred. The results demonstrate that the proposed model is more general, covering several existing simplified cases. The parameters of the model are then calculated utilizing an adaptive technique based on the Kalman filter and expectation maximization with Rauch-Tung-Striebel (KF-EM-RTS). KF-EM-RTS can adaptively estimate and update unknown parameters, overcoming the limits of strong Markovian nature of diffusion model. Linear and nonlinear degradation datasets from real working environments are used to validate the proposed model. The experiments indicate that the proposed model can achieve accurate RUL estimation results. |
| format | Article |
| id | doaj-art-c204cb04f96b4dd3b86dc25a22b07d26 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-c204cb04f96b4dd3b86dc25a22b07d262025-02-09T13:01:02ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-01-0111212110.1007/s40747-024-01773-wA generalized diffusion model for remaining useful life prediction with uncertaintyBincheng Wen0Xin Zhao1Xilang Tang2Mingqing Xiao3Haizhen Zhu4Jianfeng Li5ATS Lab, Air Force Engineering UniversityATS Lab, Air Force Engineering UniversityEquipment Management and UAV Engineering College, Air Force Engineering UniversityATS Lab, Air Force Engineering UniversityATS Lab, Air Force Engineering UniversityBeijing Aeronautical Technology Research CenterAbstract Forecasting the remaining useful life (RUL) is a crucial aspect of prognostics and health management (PHM), which has garnered significant attention in academic and industrial domains in recent decades. The accurate prediction of RUL relies on the creation of an appropriate degradation model for the system. In this paper, a general representation of diffusion process models with three sources of uncertainty for RUL estimation is constructed. According to time-space transformation, the analytic equations that approximate the RUL probability distribution function (PDF) are inferred. The results demonstrate that the proposed model is more general, covering several existing simplified cases. The parameters of the model are then calculated utilizing an adaptive technique based on the Kalman filter and expectation maximization with Rauch-Tung-Striebel (KF-EM-RTS). KF-EM-RTS can adaptively estimate and update unknown parameters, overcoming the limits of strong Markovian nature of diffusion model. Linear and nonlinear degradation datasets from real working environments are used to validate the proposed model. The experiments indicate that the proposed model can achieve accurate RUL estimation results.https://doi.org/10.1007/s40747-024-01773-wRemaining useful lifeKalman filterGeneral diffusion modelPrognostic |
| spellingShingle | Bincheng Wen Xin Zhao Xilang Tang Mingqing Xiao Haizhen Zhu Jianfeng Li A generalized diffusion model for remaining useful life prediction with uncertainty Complex & Intelligent Systems Remaining useful life Kalman filter General diffusion model Prognostic |
| title | A generalized diffusion model for remaining useful life prediction with uncertainty |
| title_full | A generalized diffusion model for remaining useful life prediction with uncertainty |
| title_fullStr | A generalized diffusion model for remaining useful life prediction with uncertainty |
| title_full_unstemmed | A generalized diffusion model for remaining useful life prediction with uncertainty |
| title_short | A generalized diffusion model for remaining useful life prediction with uncertainty |
| title_sort | generalized diffusion model for remaining useful life prediction with uncertainty |
| topic | Remaining useful life Kalman filter General diffusion model Prognostic |
| url | https://doi.org/10.1007/s40747-024-01773-w |
| work_keys_str_mv | AT binchengwen ageneralizeddiffusionmodelforremainingusefullifepredictionwithuncertainty AT xinzhao ageneralizeddiffusionmodelforremainingusefullifepredictionwithuncertainty AT xilangtang ageneralizeddiffusionmodelforremainingusefullifepredictionwithuncertainty AT mingqingxiao ageneralizeddiffusionmodelforremainingusefullifepredictionwithuncertainty AT haizhenzhu ageneralizeddiffusionmodelforremainingusefullifepredictionwithuncertainty AT jianfengli ageneralizeddiffusionmodelforremainingusefullifepredictionwithuncertainty AT binchengwen generalizeddiffusionmodelforremainingusefullifepredictionwithuncertainty AT xinzhao generalizeddiffusionmodelforremainingusefullifepredictionwithuncertainty AT xilangtang generalizeddiffusionmodelforremainingusefullifepredictionwithuncertainty AT mingqingxiao generalizeddiffusionmodelforremainingusefullifepredictionwithuncertainty AT haizhenzhu generalizeddiffusionmodelforremainingusefullifepredictionwithuncertainty AT jianfengli generalizeddiffusionmodelforremainingusefullifepredictionwithuncertainty |