Knowledge Driven Machine Learning Towards Interpretable Intelligent Prognostics and Health Management: Review and Case Study
Abstract Despite significant progress in the Prognostics and Health Management (PHM) domain using pattern learning systems from data, machine learning (ML) still faces challenges related to limited generalization and weak interpretability. A promising approach to overcoming these challenges is to em...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Chinese Journal of Mechanical Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s10033-024-01173-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594911720898560 |
|---|---|
| author | Ruqiang Yan Zheng Zhou Zuogang Shang Zhiying Wang Chenye Hu Yasong Li Yuangui Yang Xuefeng Chen Robert X. Gao |
| author_facet | Ruqiang Yan Zheng Zhou Zuogang Shang Zhiying Wang Chenye Hu Yasong Li Yuangui Yang Xuefeng Chen Robert X. Gao |
| author_sort | Ruqiang Yan |
| collection | DOAJ |
| description | Abstract Despite significant progress in the Prognostics and Health Management (PHM) domain using pattern learning systems from data, machine learning (ML) still faces challenges related to limited generalization and weak interpretability. A promising approach to overcoming these challenges is to embed domain knowledge into the ML pipeline, enhancing the model with additional pattern information. In this paper, we review the latest developments in PHM, encapsulated under the concept of Knowledge Driven Machine Learning (KDML). We propose a hierarchical framework to define KDML in PHM, which includes scientific paradigms, knowledge sources, knowledge representations, and knowledge embedding methods. Using this framework, we examine current research to demonstrate how various forms of knowledge can be integrated into the ML pipeline and provide roadmap to specific usage. Furthermore, we present several case studies that illustrate specific implementations of KDML in the PHM domain, including inductive experience, physical model, and signal processing. We analyze the improvements in generalization capability and interpretability that KDML can achieve. Finally, we discuss the challenges, potential applications, and usage recommendations of KDML in PHM, with a particular focus on the critical need for interpretability to ensure trustworthy deployment of artificial intelligence in PHM. |
| format | Article |
| id | doaj-art-7e1aefdd409b41a28337dc421df0e5a1 |
| institution | Kabale University |
| issn | 2192-8258 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Chinese Journal of Mechanical Engineering |
| spelling | doaj-art-7e1aefdd409b41a28337dc421df0e5a12025-01-19T12:12:54ZengSpringerOpenChinese Journal of Mechanical Engineering2192-82582025-01-0138113110.1186/s10033-024-01173-8Knowledge Driven Machine Learning Towards Interpretable Intelligent Prognostics and Health Management: Review and Case StudyRuqiang Yan0Zheng Zhou1Zuogang Shang2Zhiying Wang3Chenye Hu4Yasong Li5Yuangui Yang6Xuefeng Chen7Robert X. Gao8State Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong UniversityState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong UniversityState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong UniversityState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong UniversityState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong UniversityState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong UniversityState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong UniversityState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong UniversityDepartment of Mechanical and Aerospace Engineering, Case Western Reserve UniversityAbstract Despite significant progress in the Prognostics and Health Management (PHM) domain using pattern learning systems from data, machine learning (ML) still faces challenges related to limited generalization and weak interpretability. A promising approach to overcoming these challenges is to embed domain knowledge into the ML pipeline, enhancing the model with additional pattern information. In this paper, we review the latest developments in PHM, encapsulated under the concept of Knowledge Driven Machine Learning (KDML). We propose a hierarchical framework to define KDML in PHM, which includes scientific paradigms, knowledge sources, knowledge representations, and knowledge embedding methods. Using this framework, we examine current research to demonstrate how various forms of knowledge can be integrated into the ML pipeline and provide roadmap to specific usage. Furthermore, we present several case studies that illustrate specific implementations of KDML in the PHM domain, including inductive experience, physical model, and signal processing. We analyze the improvements in generalization capability and interpretability that KDML can achieve. Finally, we discuss the challenges, potential applications, and usage recommendations of KDML in PHM, with a particular focus on the critical need for interpretability to ensure trustworthy deployment of artificial intelligence in PHM.https://doi.org/10.1186/s10033-024-01173-8PHMKnowledge driven machine learningSignal processingPhysics informedInterpretability |
| spellingShingle | Ruqiang Yan Zheng Zhou Zuogang Shang Zhiying Wang Chenye Hu Yasong Li Yuangui Yang Xuefeng Chen Robert X. Gao Knowledge Driven Machine Learning Towards Interpretable Intelligent Prognostics and Health Management: Review and Case Study Chinese Journal of Mechanical Engineering PHM Knowledge driven machine learning Signal processing Physics informed Interpretability |
| title | Knowledge Driven Machine Learning Towards Interpretable Intelligent Prognostics and Health Management: Review and Case Study |
| title_full | Knowledge Driven Machine Learning Towards Interpretable Intelligent Prognostics and Health Management: Review and Case Study |
| title_fullStr | Knowledge Driven Machine Learning Towards Interpretable Intelligent Prognostics and Health Management: Review and Case Study |
| title_full_unstemmed | Knowledge Driven Machine Learning Towards Interpretable Intelligent Prognostics and Health Management: Review and Case Study |
| title_short | Knowledge Driven Machine Learning Towards Interpretable Intelligent Prognostics and Health Management: Review and Case Study |
| title_sort | knowledge driven machine learning towards interpretable intelligent prognostics and health management review and case study |
| topic | PHM Knowledge driven machine learning Signal processing Physics informed Interpretability |
| url | https://doi.org/10.1186/s10033-024-01173-8 |
| work_keys_str_mv | AT ruqiangyan knowledgedrivenmachinelearningtowardsinterpretableintelligentprognosticsandhealthmanagementreviewandcasestudy AT zhengzhou knowledgedrivenmachinelearningtowardsinterpretableintelligentprognosticsandhealthmanagementreviewandcasestudy AT zuogangshang knowledgedrivenmachinelearningtowardsinterpretableintelligentprognosticsandhealthmanagementreviewandcasestudy AT zhiyingwang knowledgedrivenmachinelearningtowardsinterpretableintelligentprognosticsandhealthmanagementreviewandcasestudy AT chenyehu knowledgedrivenmachinelearningtowardsinterpretableintelligentprognosticsandhealthmanagementreviewandcasestudy AT yasongli knowledgedrivenmachinelearningtowardsinterpretableintelligentprognosticsandhealthmanagementreviewandcasestudy AT yuanguiyang knowledgedrivenmachinelearningtowardsinterpretableintelligentprognosticsandhealthmanagementreviewandcasestudy AT xuefengchen knowledgedrivenmachinelearningtowardsinterpretableintelligentprognosticsandhealthmanagementreviewandcasestudy AT robertxgao knowledgedrivenmachinelearningtowardsinterpretableintelligentprognosticsandhealthmanagementreviewandcasestudy |