Fusing physics-based and deep learning models for prognostics. Arias Chao, M., Kulkarni, C., Goebel, K., & Fink, O. Reliability Engineering & System Safety, 217:107961, January, 2022. ![Fusing physics-based and deep learning models for prognostics [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Physics-based and data-driven models for remaining useful lifetime (RUL) prediction typically suffer from two major challenges that limit their applicability to complex real-world domains: (1) the incompleteness of physics-based models and (2) the limited representativeness of the training dataset for data-driven models. Combining the advantages of these two approaches while overcoming some of their limitations, we propose a novel hybrid framework for fusing the information from physics-based performance models with deep learning algorithms for prognostics of complex safety-critical systems. In the proposed framework, we use physics-based performance models to infer unobservable model parameters related to a system’s components health by solving a calibration problem. These parameters are subsequently combined with sensor readings and used as input to a deep neural network, thereby generating a data-driven prognostics model with physics-augmented features. The performance of the hybrid framework is evaluated on an extensive case study comprising run-to-failure degradation trajectories from a fleet of nine turbofan engines under real flight conditions. The experimental results show that the hybrid framework outperforms purely data-driven approaches by extending the prediction horizon by nearly 127%. Furthermore, it requires less training data and is less sensitive to the limited representativeness of the dataset as compared to purely data-driven approaches. Furthermore, we demonstrated the feasibility of the proposed framework on the original CMAPSS dataset, thereby confirming its superior performance.
@article{arias_chao_fusing_2022,
title = {Fusing physics-based and deep learning models for prognostics},
volume = {217},
issn = {0951-8320},
url = {https://www.sciencedirect.com/science/article/pii/S0951832021004725},
doi = {10.1016/j.ress.2021.107961},
abstract = {Physics-based and data-driven models for remaining useful lifetime (RUL) prediction typically suffer from two major challenges that limit their applicability to complex real-world domains: (1) the incompleteness of physics-based models and (2) the limited representativeness of the training dataset for data-driven models. Combining the advantages of these two approaches while overcoming some of their limitations, we propose a novel hybrid framework for fusing the information from physics-based performance models with deep learning algorithms for prognostics of complex safety-critical systems. In the proposed framework, we use physics-based performance models to infer unobservable model parameters related to a system’s components health by solving a calibration problem. These parameters are subsequently combined with sensor readings and used as input to a deep neural network, thereby generating a data-driven prognostics model with physics-augmented features. The performance of the hybrid framework is evaluated on an extensive case study comprising run-to-failure degradation trajectories from a fleet of nine turbofan engines under real flight conditions. The experimental results show that the hybrid framework outperforms purely data-driven approaches by extending the prediction horizon by nearly 127\%. Furthermore, it requires less training data and is less sensitive to the limited representativeness of the dataset as compared to purely data-driven approaches. Furthermore, we demonstrated the feasibility of the proposed framework on the original CMAPSS dataset, thereby confirming its superior performance.},
language = {en},
urldate = {2021-11-15},
journal = {Reliability Engineering \& System Safety},
author = {Arias Chao, Manuel and Kulkarni, Chetan and Goebel, Kai and Fink, Olga},
month = jan,
year = {2022},
keywords = {CMAPSS, Deep learning, Hybrid model, Prognostics},
pages = {107961},
}
Downloads: 0
{"_id":"3hTeBDSNwqG2u9gP9","bibbaseid":"ariaschao-kulkarni-goebel-fink-fusingphysicsbasedanddeeplearningmodelsforprognostics-2022","author_short":["Arias Chao, M.","Kulkarni, C.","Goebel, K.","Fink, O."],"bibdata":{"bibtype":"article","type":"article","title":"Fusing physics-based and deep learning models for prognostics","volume":"217","issn":"0951-8320","url":"https://www.sciencedirect.com/science/article/pii/S0951832021004725","doi":"10.1016/j.ress.2021.107961","abstract":"Physics-based and data-driven models for remaining useful lifetime (RUL) prediction typically suffer from two major challenges that limit their applicability to complex real-world domains: (1) the incompleteness of physics-based models and (2) the limited representativeness of the training dataset for data-driven models. Combining the advantages of these two approaches while overcoming some of their limitations, we propose a novel hybrid framework for fusing the information from physics-based performance models with deep learning algorithms for prognostics of complex safety-critical systems. In the proposed framework, we use physics-based performance models to infer unobservable model parameters related to a system’s components health by solving a calibration problem. These parameters are subsequently combined with sensor readings and used as input to a deep neural network, thereby generating a data-driven prognostics model with physics-augmented features. The performance of the hybrid framework is evaluated on an extensive case study comprising run-to-failure degradation trajectories from a fleet of nine turbofan engines under real flight conditions. The experimental results show that the hybrid framework outperforms purely data-driven approaches by extending the prediction horizon by nearly 127%. Furthermore, it requires less training data and is less sensitive to the limited representativeness of the dataset as compared to purely data-driven approaches. Furthermore, we demonstrated the feasibility of the proposed framework on the original CMAPSS dataset, thereby confirming its superior performance.","language":"en","urldate":"2021-11-15","journal":"Reliability Engineering & System Safety","author":[{"propositions":[],"lastnames":["Arias","Chao"],"firstnames":["Manuel"],"suffixes":[]},{"propositions":[],"lastnames":["Kulkarni"],"firstnames":["Chetan"],"suffixes":[]},{"propositions":[],"lastnames":["Goebel"],"firstnames":["Kai"],"suffixes":[]},{"propositions":[],"lastnames":["Fink"],"firstnames":["Olga"],"suffixes":[]}],"month":"January","year":"2022","keywords":"CMAPSS, Deep learning, Hybrid model, Prognostics","pages":"107961","bibtex":"@article{arias_chao_fusing_2022,\n\ttitle = {Fusing physics-based and deep learning models for prognostics},\n\tvolume = {217},\n\tissn = {0951-8320},\n\turl = {https://www.sciencedirect.com/science/article/pii/S0951832021004725},\n\tdoi = {10.1016/j.ress.2021.107961},\n\tabstract = {Physics-based and data-driven models for remaining useful lifetime (RUL) prediction typically suffer from two major challenges that limit their applicability to complex real-world domains: (1) the incompleteness of physics-based models and (2) the limited representativeness of the training dataset for data-driven models. Combining the advantages of these two approaches while overcoming some of their limitations, we propose a novel hybrid framework for fusing the information from physics-based performance models with deep learning algorithms for prognostics of complex safety-critical systems. In the proposed framework, we use physics-based performance models to infer unobservable model parameters related to a system’s components health by solving a calibration problem. These parameters are subsequently combined with sensor readings and used as input to a deep neural network, thereby generating a data-driven prognostics model with physics-augmented features. The performance of the hybrid framework is evaluated on an extensive case study comprising run-to-failure degradation trajectories from a fleet of nine turbofan engines under real flight conditions. The experimental results show that the hybrid framework outperforms purely data-driven approaches by extending the prediction horizon by nearly 127\\%. Furthermore, it requires less training data and is less sensitive to the limited representativeness of the dataset as compared to purely data-driven approaches. Furthermore, we demonstrated the feasibility of the proposed framework on the original CMAPSS dataset, thereby confirming its superior performance.},\n\tlanguage = {en},\n\turldate = {2021-11-15},\n\tjournal = {Reliability Engineering \\& System Safety},\n\tauthor = {Arias Chao, Manuel and Kulkarni, Chetan and Goebel, Kai and Fink, Olga},\n\tmonth = jan,\n\tyear = {2022},\n\tkeywords = {CMAPSS, Deep learning, Hybrid model, Prognostics},\n\tpages = {107961},\n}\n\n","author_short":["Arias Chao, M.","Kulkarni, C.","Goebel, K.","Fink, O."],"key":"arias_chao_fusing_2022","id":"arias_chao_fusing_2022","bibbaseid":"ariaschao-kulkarni-goebel-fink-fusingphysicsbasedanddeeplearningmodelsforprognostics-2022","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S0951832021004725"},"keyword":["CMAPSS","Deep learning","Hybrid model","Prognostics"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["XJ7Gu6aiNbAiJAjbw","XvjRDbrMBW2XJY3p9","3C6BKwtiX883bctx4","5THezwiL4FyF8mm4G","RktFJE9cDa98BRLZF","qpxPuYKLChgB7ox6D","PfM5iniYHEthCfQDH","NusJZ4NnCo9bYMpvf","iwKepCrWBps7ojhDx"],"keywords":["cmapss","deep learning","hybrid model","prognostics"],"search_terms":["fusing","physics","based","deep","learning","models","prognostics","arias chao","kulkarni","goebel","fink"],"title":"Fusing physics-based and deep learning models for prognostics","year":2022}