Predictive Model Evaluation for PHM
In the past decades, machine learning techniques or algorithms, particularly, classifiers have been widely applied to various real-world applications such as PHM. In developing high-performance classifiers, or machine learning-based models, i.e. predictive model for PHM, the predictive model evaluat...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Prognostics and Health Management Society
2014-06-01
|
| Series: | International Journal of Prognostics and Health Management |
| Subjects: | |
| Online Access: | https://papers.phmsociety.org/index.php/ijphm/article/view/2238 |
| _version_ | 1819027343392374784 |
|---|---|
| author | Chunsheng Yang Yanni Zou Jie Liu Kyle R Mulligan |
| author_facet | Chunsheng Yang Yanni Zou Jie Liu Kyle R Mulligan |
| author_sort | Chunsheng Yang |
| collection | DOAJ |
| description | In the past decades, machine learning techniques or algorithms, particularly, classifiers have been widely applied to various real-world applications such as PHM. In developing high-performance classifiers, or machine learning-based models, i.e. predictive model for PHM, the predictive model evaluation remains a challenge. Generic methods such as accuracy may not fully meet the needs of models evaluation for prognostic applications. This paper addresses this issue from the point of view of PHM systems. Generic methods are first reviewed while outlining their limitations or deficiencies with respect to PHM. Then, two approaches developed for evaluating predictive models are presented with emphasis on specificities and requirements of PHM. A case of real prognostic application is studies to demonstrate the usefulness of two proposed methods for predictive model evaluation. We argue that predictive models for PHM must be evaluated not only using generic methods, but also domain-oriented approaches in order to deploy the models in real-world applications. |
| first_indexed | 2024-12-21T05:40:58Z |
| format | Article |
| id | doaj.art-b0c39518165042b096cba1cf9d5a2606 |
| institution | Directory Open Access Journal |
| issn | 2153-2648 2153-2648 |
| language | English |
| last_indexed | 2024-12-21T05:40:58Z |
| publishDate | 2014-06-01 |
| publisher | The Prognostics and Health Management Society |
| record_format | Article |
| series | International Journal of Prognostics and Health Management |
| spelling | doaj.art-b0c39518165042b096cba1cf9d5a26062022-12-21T19:14:15ZengThe Prognostics and Health Management SocietyInternational Journal of Prognostics and Health Management2153-26482153-26482014-06-0152doi:10.36001/ijphm.2014.v5i2.2238Predictive Model Evaluation for PHMChunsheng Yang0Yanni Zou1Jie Liu2Kyle R Mulligan3National Research Council Canada, Ottawa, Ontario K1A 0R6, CanadaJiujiang University, Jiangxi, ChinaDept. of Mechanical and Aerospace Eng., Carleton University, Ottawa, ON, K1S 5B6, Canada4GAUS, Dept. of Mechanical Engineering, Université de Sherbrooke, Sherbrooke, QC, J1K 2R1, CanadaIn the past decades, machine learning techniques or algorithms, particularly, classifiers have been widely applied to various real-world applications such as PHM. In developing high-performance classifiers, or machine learning-based models, i.e. predictive model for PHM, the predictive model evaluation remains a challenge. Generic methods such as accuracy may not fully meet the needs of models evaluation for prognostic applications. This paper addresses this issue from the point of view of PHM systems. Generic methods are first reviewed while outlining their limitations or deficiencies with respect to PHM. Then, two approaches developed for evaluating predictive models are presented with emphasis on specificities and requirements of PHM. A case of real prognostic application is studies to demonstrate the usefulness of two proposed methods for predictive model evaluation. We argue that predictive models for PHM must be evaluated not only using generic methods, but also domain-oriented approaches in order to deploy the models in real-world applications.https://papers.phmsociety.org/index.php/ijphm/article/view/2238prognosticsprognostics and health management (phm)binary classifiermachine learning algorithmsgeneric methodstime to failurepredictive models evaluation |
| spellingShingle | Chunsheng Yang Yanni Zou Jie Liu Kyle R Mulligan Predictive Model Evaluation for PHM International Journal of Prognostics and Health Management prognostics prognostics and health management (phm) binary classifier machine learning algorithms generic methods time to failure predictive models evaluation |
| title | Predictive Model Evaluation for PHM |
| title_full | Predictive Model Evaluation for PHM |
| title_fullStr | Predictive Model Evaluation for PHM |
| title_full_unstemmed | Predictive Model Evaluation for PHM |
| title_short | Predictive Model Evaluation for PHM |
| title_sort | predictive model evaluation for phm |
| topic | prognostics prognostics and health management (phm) binary classifier machine learning algorithms generic methods time to failure predictive models evaluation |
| url | https://papers.phmsociety.org/index.php/ijphm/article/view/2238 |
| work_keys_str_mv | AT chunshengyang predictivemodelevaluationforphm AT yannizou predictivemodelevaluationforphm AT jieliu predictivemodelevaluationforphm AT kylermulligan predictivemodelevaluationforphm |