{"title":"退化建模和预测的数据级迁移学习","authors":"Amirhossein Fallahdizcheh, Chao Wang","doi":"10.1080/00224065.2022.2081103","DOIUrl":null,"url":null,"abstract":"Abstract The typical way to conduct data-driven prognosis is to train a degradation model with historical data, then apply the model to predict failure for in-service units. Most existing works assume the historical data and in-service data are from the same process. In practice, however, different but related processes can share similar degradation patterns. Thus, the historical data from these processes are expected to provide useful prognosis information for each other. In this article, we propose a data-level transfer learning framework to extract useful and shared information from different processes to benefit the prognosis of in-service units. In this framework, the degradation data in each process is modeled by a mixed effects model. To facilitate the information sharing among different mixed effects models, a hierarchical Bayesian structure is proposed to model and connect the distributions of mixed effects in different mixed models. Because the degradation paths in different processes are rarely the same, the dimension of the mixed effects/regressor in each process can be different. To handle this issue, we propose a tailored linear transformation to marginalize or expand the distributions of mixed effects in different degradation processes to achieve consistent dimensions. The transferred information is finally incorporated with the degradation data from in-service units to conduct prognosis. The proposed method is validated and compared with various benchmarks in extensive numerical studies and two case studies. The results show the proposed method can successfully transfer useful information in different processes to benefit the prognosis.","PeriodicalId":54769,"journal":{"name":"Journal of Quality Technology","volume":"100 1","pages":"140 - 162"},"PeriodicalIF":2.6000,"publicationDate":"2022-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Data-level transfer learning for degradation modeling and prognosis\",\"authors\":\"Amirhossein Fallahdizcheh, Chao Wang\",\"doi\":\"10.1080/00224065.2022.2081103\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract The typical way to conduct data-driven prognosis is to train a degradation model with historical data, then apply the model to predict failure for in-service units. Most existing works assume the historical data and in-service data are from the same process. In practice, however, different but related processes can share similar degradation patterns. Thus, the historical data from these processes are expected to provide useful prognosis information for each other. In this article, we propose a data-level transfer learning framework to extract useful and shared information from different processes to benefit the prognosis of in-service units. In this framework, the degradation data in each process is modeled by a mixed effects model. To facilitate the information sharing among different mixed effects models, a hierarchical Bayesian structure is proposed to model and connect the distributions of mixed effects in different mixed models. Because the degradation paths in different processes are rarely the same, the dimension of the mixed effects/regressor in each process can be different. To handle this issue, we propose a tailored linear transformation to marginalize or expand the distributions of mixed effects in different degradation processes to achieve consistent dimensions. The transferred information is finally incorporated with the degradation data from in-service units to conduct prognosis. The proposed method is validated and compared with various benchmarks in extensive numerical studies and two case studies. The results show the proposed method can successfully transfer useful information in different processes to benefit the prognosis.\",\"PeriodicalId\":54769,\"journal\":{\"name\":\"Journal of Quality Technology\",\"volume\":\"100 1\",\"pages\":\"140 - 162\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2022-06-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Quality Technology\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1080/00224065.2022.2081103\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, INDUSTRIAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Quality Technology","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1080/00224065.2022.2081103","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, INDUSTRIAL","Score":null,"Total":0}
Data-level transfer learning for degradation modeling and prognosis
Abstract The typical way to conduct data-driven prognosis is to train a degradation model with historical data, then apply the model to predict failure for in-service units. Most existing works assume the historical data and in-service data are from the same process. In practice, however, different but related processes can share similar degradation patterns. Thus, the historical data from these processes are expected to provide useful prognosis information for each other. In this article, we propose a data-level transfer learning framework to extract useful and shared information from different processes to benefit the prognosis of in-service units. In this framework, the degradation data in each process is modeled by a mixed effects model. To facilitate the information sharing among different mixed effects models, a hierarchical Bayesian structure is proposed to model and connect the distributions of mixed effects in different mixed models. Because the degradation paths in different processes are rarely the same, the dimension of the mixed effects/regressor in each process can be different. To handle this issue, we propose a tailored linear transformation to marginalize or expand the distributions of mixed effects in different degradation processes to achieve consistent dimensions. The transferred information is finally incorporated with the degradation data from in-service units to conduct prognosis. The proposed method is validated and compared with various benchmarks in extensive numerical studies and two case studies. The results show the proposed method can successfully transfer useful information in different processes to benefit the prognosis.
期刊介绍:
The objective of Journal of Quality Technology is to contribute to the technical advancement of the field of quality technology by publishing papers that emphasize the practical applicability of new techniques, instructive examples of the operation of existing techniques and results of historical researches. Expository, review, and tutorial papers are also acceptable if they are written in a style suitable for practicing engineers.
Sample our Mathematics & Statistics journals, sign in here to start your FREE access for 14 days