Pub Date : 2013-06-24DOI: 10.1109/ICPHM.2013.6621458
P. Lall, Ryan Lowe, K. Goebel
In an effort to meet reliability requirements for long term human presence in space without the need for resupply, a new interconnect for grid array packages has been developed. The interconnect utilizes beryllium copper springs which are 0.05 inches in height as interconnects between the package and PCB. These novel interconnects are known as micro coil springs (MCS). The configuration is approximately the same height as copper column interconnects, but has increased compliance compared to traditional column interconnects. Because the interconnect is still in the design stage, the feasibility of integrating prognostic health management capability into the interconnect is being studied. Failure prognostics, or the prediction of impending failure for individual components, would help ensure the reliability of systems deployed on long duration space missions and provide warnings of potential failure with adequate time to formulate contingency plans. Prognostic monitoring circuitry, prediction algorithms, and performance validation are discussed for micro coil packages subjected to JDEC standard drop testing.
{"title":"Prognostic health monitoring for a micro-coil spring interconnect subjected to drop impacts","authors":"P. Lall, Ryan Lowe, K. Goebel","doi":"10.1109/ICPHM.2013.6621458","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621458","url":null,"abstract":"In an effort to meet reliability requirements for long term human presence in space without the need for resupply, a new interconnect for grid array packages has been developed. The interconnect utilizes beryllium copper springs which are 0.05 inches in height as interconnects between the package and PCB. These novel interconnects are known as micro coil springs (MCS). The configuration is approximately the same height as copper column interconnects, but has increased compliance compared to traditional column interconnects. Because the interconnect is still in the design stage, the feasibility of integrating prognostic health management capability into the interconnect is being studied. Failure prognostics, or the prediction of impending failure for individual components, would help ensure the reliability of systems deployed on long duration space missions and provide warnings of potential failure with adequate time to formulate contingency plans. Prognostic monitoring circuitry, prediction algorithms, and performance validation are discussed for micro coil packages subjected to JDEC standard drop testing.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128844968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-24DOI: 10.1109/ICPHM.2013.6621423
Jinjiang Wang, R. Gao
For bearing remaining life prognosis, past research has investigated deterministic material fatigue crack growth models such as Paris law and Newman model. Due to the inherent stochastic nature of defect propagation and varying operating conditions, the accuracy of such models has shown to be limited. This paper addresses this challenge by presenting a stochastic modeling approach, based on interacting multiple models and particle filter. Experiments were conducted on a customized bearing test rig to demonstrate the effectiveness of the developed method. Comparison between the developed method and the traditional particle filter has shown that the developed method improves the accuracy in bearing remaining life prediction.
{"title":"Multiple model particle filtering for bearing life prognosis","authors":"Jinjiang Wang, R. Gao","doi":"10.1109/ICPHM.2013.6621423","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621423","url":null,"abstract":"For bearing remaining life prognosis, past research has investigated deterministic material fatigue crack growth models such as Paris law and Newman model. Due to the inherent stochastic nature of defect propagation and varying operating conditions, the accuracy of such models has shown to be limited. This paper addresses this challenge by presenting a stochastic modeling approach, based on interacting multiple models and particle filter. Experiments were conducted on a customized bearing test rig to demonstrate the effectiveness of the developed method. Comparison between the developed method and the traditional particle filter has shown that the developed method improves the accuracy in bearing remaining life prediction.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121818335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-24DOI: 10.1109/ICPHM.2013.6621439
K. Park, B. Youn, J. Yoon, Chao Hu, H. Kim, Y. Bae
A power generator, one of the most critical components in power plant, could experience unexpected series system failures, resulting in substantial maintenance and societal cost. This paper proposes a new health diagnostics method for water-cooled power generator windings against moisture absorption. The main idea of the proposed diagnostics method is a Directional Mahalanobis Distance (DMD) based on the correlation matrix of health data. In this study capacitance data measured from a winding insulator is referred to as health data. It is an indirect measure of moisture absorption in power generator windings by water leakage. Data from ten generators, of which each has 42 windings, are used for demonstration of the proposed health diagnostics method for power generator windings.
{"title":"Health diagnostics of water-cooled power generator stator windings using a Directional Mahalanobis Distance (DMD)","authors":"K. Park, B. Youn, J. Yoon, Chao Hu, H. Kim, Y. Bae","doi":"10.1109/ICPHM.2013.6621439","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621439","url":null,"abstract":"A power generator, one of the most critical components in power plant, could experience unexpected series system failures, resulting in substantial maintenance and societal cost. This paper proposes a new health diagnostics method for water-cooled power generator windings against moisture absorption. The main idea of the proposed diagnostics method is a Directional Mahalanobis Distance (DMD) based on the correlation matrix of health data. In this study capacitance data measured from a winding insulator is referred to as health data. It is an indirect measure of moisture absorption in power generator windings by water leakage. Data from ten generators, of which each has 42 windings, are used for demonstration of the proposed health diagnostics method for power generator windings.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"181 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132834174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-24DOI: 10.1109/ICPHM.2013.6621459
D. Lau, J. Liu, S. Majumdar, B. Nandy, M. St-Hilaire, C. S. Yang
One of the problems with the current practices in the various domains of facility management is that each facility is managed by its stake holder in isolation from the management of other similar facilities. However, with the advent of new technologies such as cloud computing, we have an opportunity to unify the management of multiple geographically dispersed facilities. To that end, this paper presents our joint research efforts on cloud-based smart facility management. More precisely, we present a cloud-based platform in order to manage sensor-based bridge infrastructures and smart machinery. Although the paper focuses on these two applications, the proposed cloud-based platform is designed to support/manage a multitude of smart facilities.
{"title":"A cloud-based approach for smart facilities management","authors":"D. Lau, J. Liu, S. Majumdar, B. Nandy, M. St-Hilaire, C. S. Yang","doi":"10.1109/ICPHM.2013.6621459","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621459","url":null,"abstract":"One of the problems with the current practices in the various domains of facility management is that each facility is managed by its stake holder in isolation from the management of other similar facilities. However, with the advent of new technologies such as cloud computing, we have an opportunity to unify the management of multiple geographically dispersed facilities. To that end, this paper presents our joint research efforts on cloud-based smart facility management. More precisely, we present a cloud-based platform in order to manage sensor-based bridge infrastructures and smart machinery. Although the paper focuses on these two applications, the proposed cloud-based platform is designed to support/manage a multitude of smart facilities.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127508196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-24DOI: 10.1109/ICPHM.2013.6621416
Linxia Liao, Radu Pavel
One of the important roles of prognostics health management (PHM) is to predict the time to failure of a system in order to avoid unexpected downtime and optimize maintenance activities. Although many attempts to predict time to failure have been reported in the literature, there are still challenges related to data availability and methodology. In addition, there is significant variation from case to case due to complexity of system usage and failure modes. This paper reveals various aspects related to such challenges experienced while applying a novel predictive technology to a spindle test-bed. The goal was to evaluate the ability of the technology to predict the remaining useful life of a bearing with seeded faults. Testing has been conducted to reveal the effectiveness of signal processing, health modeling and prediction techniques. While conducting the evaluation tests, besides some well-known bearing failure modes, an unusual case was recorded. This atypical bearing failure mode created a new challenge for the predictive technology being investigated, which prompted the development of an advanced feature discovering methodology using genetic programming. This new methodology and the technology evaluation results obtained for both the well-known and the atypical failure modes will be discussed in the paper. In addition, the paper will describe the test-bed and instrumentation approach, the data acquisition system and the experimental design for testing and validation of the technology.
{"title":"Machinery time to failure prediction - Case study and lesson learned for a spindle bearing application","authors":"Linxia Liao, Radu Pavel","doi":"10.1109/ICPHM.2013.6621416","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621416","url":null,"abstract":"One of the important roles of prognostics health management (PHM) is to predict the time to failure of a system in order to avoid unexpected downtime and optimize maintenance activities. Although many attempts to predict time to failure have been reported in the literature, there are still challenges related to data availability and methodology. In addition, there is significant variation from case to case due to complexity of system usage and failure modes. This paper reveals various aspects related to such challenges experienced while applying a novel predictive technology to a spindle test-bed. The goal was to evaluate the ability of the technology to predict the remaining useful life of a bearing with seeded faults. Testing has been conducted to reveal the effectiveness of signal processing, health modeling and prediction techniques. While conducting the evaluation tests, besides some well-known bearing failure modes, an unusual case was recorded. This atypical bearing failure mode created a new challenge for the predictive technology being investigated, which prompted the development of an advanced feature discovering methodology using genetic programming. This new methodology and the technology evaluation results obtained for both the well-known and the atypical failure modes will be discussed in the paper. In addition, the paper will describe the test-bed and instrumentation approach, the data acquisition system and the experimental design for testing and validation of the technology.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"141 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130924512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-24DOI: 10.1109/ICPHM.2013.6621436
Yan Ning, P. Sandborn, M. Pecht
Prognostics and health management (PHM) is an enabling discipline consisting of technologies and methods to assess the reliability of a product in its actual life cycle conditions and evaluate its remaining useful life. This paper presents the application of PHM methods as a proactive and predictive means to enable new warranty approaches. Warranty service is typically performed after the occurrence of failure. However, with the implementation of the predictive and proactive warranty strategies enabled by PHM, companies can make decisions for warranty returns up front. The prognostics-based warranty models developed in this paper include part-based warranty return, lifetime warranty, and customized extended warranty, and a case study of warranty validation and user abuse detection is also provided. The results of this work can increase the competitiveness of businesses by reshaping their warranty policies, improving their maintenance practices under warranty, and reducing their warranty costs.
{"title":"Prognostics-based product warranties","authors":"Yan Ning, P. Sandborn, M. Pecht","doi":"10.1109/ICPHM.2013.6621436","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621436","url":null,"abstract":"Prognostics and health management (PHM) is an enabling discipline consisting of technologies and methods to assess the reliability of a product in its actual life cycle conditions and evaluate its remaining useful life. This paper presents the application of PHM methods as a proactive and predictive means to enable new warranty approaches. Warranty service is typically performed after the occurrence of failure. However, with the implementation of the predictive and proactive warranty strategies enabled by PHM, companies can make decisions for warranty returns up front. The prognostics-based warranty models developed in this paper include part-based warranty return, lifetime warranty, and customized extended warranty, and a case study of warranty validation and user abuse detection is also provided. The results of this work can increase the competitiveness of businesses by reshaping their warranty policies, improving their maintenance practices under warranty, and reducing their warranty costs.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122112700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-24DOI: 10.1109/ICPHM.2013.6621421
J. Yoon, B. Youn, K. Park, Wook-ryun Lee
A power transformer is one of the main components in a power plant and transformer failure may provoke power plant shut-down with significant capital loss. Many techniques of vibration-based health diagnostics have been developed in order to prevent mechanical failures of the transformer. Vibration-based health diagnostics results are generally sensitive to the number of sensors and their locations. This study aims at developing robust health diagnostics for two dominant mechanical failure mechanisms of the transformer. Based upon the characteristics of transformer vibration, robust health indices were developed using sensitivity analysis. This study employed 33 transformers and each with 36~48 accelerometers for demonstration purpose. It is concluded that the proposed health index are suitable for robust health diagnostics and fault identification of power transformers.
{"title":"Vibration-based robust health diagnostics for mechanical failure modes of power transformers","authors":"J. Yoon, B. Youn, K. Park, Wook-ryun Lee","doi":"10.1109/ICPHM.2013.6621421","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621421","url":null,"abstract":"A power transformer is one of the main components in a power plant and transformer failure may provoke power plant shut-down with significant capital loss. Many techniques of vibration-based health diagnostics have been developed in order to prevent mechanical failures of the transformer. Vibration-based health diagnostics results are generally sensitive to the number of sensors and their locations. This study aims at developing robust health diagnostics for two dominant mechanical failure mechanisms of the transformer. Based upon the characteristics of transformer vibration, robust health indices were developed using sensitivity analysis. This study employed 33 transformers and each with 36~48 accelerometers for demonstration purpose. It is concluded that the proposed health index are suitable for robust health diagnostics and fault identification of power transformers.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124085591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Test points are observation points extracting system information, so the selection of test points is a key step for electronic systems on PHM. Test points should be able to characterize the fault precursors of the system for diagnosis and prognosis with accuracy. Current methods of selection of test points generally rely on functional simulation analysis or testability modeling analysis. This paper makes an attempt to combine the method of circuit functional simulation analysis with FMMEA method to select test points for an electronic system, and presents a case study of a board level system to illustrate it.
{"title":"Test point selection based on functional simulation and FMMEA for an electronic system on PHM","authors":"Xufei Wang, Zhongqun Li, Shunong Zhang, Jiaming Liu, Cong Shao","doi":"10.1109/ICPHM.2013.6621444","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621444","url":null,"abstract":"Test points are observation points extracting system information, so the selection of test points is a key step for electronic systems on PHM. Test points should be able to characterize the fault precursors of the system for diagnosis and prognosis with accuracy. Current methods of selection of test points generally rely on functional simulation analysis or testability modeling analysis. This paper makes an attempt to combine the method of circuit functional simulation analysis with FMMEA method to select test points for an electronic system, and presents a case study of a board level system to illustrate it.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"10 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129104512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-24DOI: 10.1109/ICPHM.2013.6621440
Jing Tian, C. Morillo, M. Pecht
To diagnose the bearing fault using vibration signal, methods like envelope analysis have been used. These methods need to locate the optimum frequency band to perform the analysis. Researchers have developed spectral kurtosis through kurtogram to detect the optimum frequency band. However, kurtogram uses a rigid structure of frequency filter bank and when the optimum frequency band does not match any of the frequency bands in the structure the fault may not be detected. In this paper a method based on simulated annealing is developed to locate the optimum frequency band. The method models spectral kurtosis as a function of the variables of a band-pass filter. Firstly the analysis result from the kurtogram is obtained as a start point, and then the central frequency and the bandwidth are optimized by maximizing spectral kurtosis through simulated annealing. Finally, the test signal is band-pass filtered by the optimized filter, and the envelope analysis is applied to complete the diagnosis. Experimental study shows that the method can diagnose the fault for different fault types. Being able to detect the real optimum frequency band, this method can strengthen the detection of the fault feature frequency component.
{"title":"Rolling element bearing fault diagnosis using simulated annealing optimized spectral kurtosis","authors":"Jing Tian, C. Morillo, M. Pecht","doi":"10.1109/ICPHM.2013.6621440","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621440","url":null,"abstract":"To diagnose the bearing fault using vibration signal, methods like envelope analysis have been used. These methods need to locate the optimum frequency band to perform the analysis. Researchers have developed spectral kurtosis through kurtogram to detect the optimum frequency band. However, kurtogram uses a rigid structure of frequency filter bank and when the optimum frequency band does not match any of the frequency bands in the structure the fault may not be detected. In this paper a method based on simulated annealing is developed to locate the optimum frequency band. The method models spectral kurtosis as a function of the variables of a band-pass filter. Firstly the analysis result from the kurtogram is obtained as a start point, and then the central frequency and the bandwidth are optimized by maximizing spectral kurtosis through simulated annealing. Finally, the test signal is band-pass filtered by the optimized filter, and the envelope analysis is applied to complete the diagnosis. Experimental study shows that the method can diagnose the fault for different fault types. Being able to detect the real optimum frequency band, this method can strengthen the detection of the fault feature frequency component.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125679154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-24DOI: 10.1109/ICPHM.2013.6621433
Chao-Shiou Chen, S. Kunche, M. Pecht
Prognostics is the key function in prognostics and health management (PHM), which can provide remaining useful life of systems in real-time so that timely maintenance plans can be scheduled to avoid system downtime and even catastrophic events. In system prognostics, fault degradation models are necessarily established to describe the fault evolution dynamics and used to extrapolate the future health conditions. However, it is very challenging to build an accurate fault degradation model considering the complex fault growth dynamics and numerous modeling uncertainties, such as unit to unit variation. Particularly, in data driven modeling methods, the variations of loading conditions, environments and usage patterns will influence greatly the fault modeling accuracy. Some research has been conducted to tackle this problem by utilizing real-time monitoring data to update the fault model in terms of model parameters and even model structures to accommodate these varying factors. But whenever new data are available, it becomes difficult to determine how to retain the prior learned model while also learning new fault degradation dynamics. That is, how to learn new knowledge without forgetting what was learned previously. In this paper, we develop a new model update and fusion method for prognostics by using incremental learning. A case study is given to validate the developed approach via the battery degradation data.
{"title":"Incremental learning approach for improved prediction","authors":"Chao-Shiou Chen, S. Kunche, M. Pecht","doi":"10.1109/ICPHM.2013.6621433","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621433","url":null,"abstract":"Prognostics is the key function in prognostics and health management (PHM), which can provide remaining useful life of systems in real-time so that timely maintenance plans can be scheduled to avoid system downtime and even catastrophic events. In system prognostics, fault degradation models are necessarily established to describe the fault evolution dynamics and used to extrapolate the future health conditions. However, it is very challenging to build an accurate fault degradation model considering the complex fault growth dynamics and numerous modeling uncertainties, such as unit to unit variation. Particularly, in data driven modeling methods, the variations of loading conditions, environments and usage patterns will influence greatly the fault modeling accuracy. Some research has been conducted to tackle this problem by utilizing real-time monitoring data to update the fault model in terms of model parameters and even model structures to accommodate these varying factors. But whenever new data are available, it becomes difficult to determine how to retain the prior learned model while also learning new fault degradation dynamics. That is, how to learn new knowledge without forgetting what was learned previously. In this paper, we develop a new model update and fusion method for prognostics by using incremental learning. A case study is given to validate the developed approach via the battery degradation data.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117148331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：