Pub Date : 2018-08-24DOI: 10.1002/9781119515326.CH22
M. Pecht, Myeongsu Kang
This chapter provides a comprehensive overview of prognostics and health management (PHM) patents from three aspects: PHM for electrical systems, PHM for mechanical systems, and general PHM methodologies. It deals with the PHM implementation methods, algorithms, and apparatus for specific electrical systems, electronic devices, or pieces of equipment. PHM patents for semiconductor components, computers, and their accessories, such as hard disk drives, memories, and mainboards, account for more than 60% of all PHM patents for electrical systems. Additionally, PHM patents for batteries represent less than a 10% share of patents for electrical systems up to 2015. Nearly all PHM patents for electric motors are based on the measurement of current, since it is closely related to the operating condition of electric motors. PHM patents for electrical devices in automobiles and aircraft are constantly being proposed. Although PHM technologies have matured, PHM patents for networks and communications facilities are currently insufficient.
{"title":"Analysis of PHM Patents for Electronics","authors":"M. Pecht, Myeongsu Kang","doi":"10.1002/9781119515326.CH22","DOIUrl":"https://doi.org/10.1002/9781119515326.CH22","url":null,"abstract":"This chapter provides a comprehensive overview of prognostics and health management (PHM) patents from three aspects: PHM for electrical systems, PHM for mechanical systems, and general PHM methodologies. It deals with the PHM implementation methods, algorithms, and apparatus for specific electrical systems, electronic devices, or pieces of equipment. PHM patents for semiconductor components, computers, and their accessories, such as hard disk drives, memories, and mainboards, account for more than 60% of all PHM patents for electrical systems. Additionally, PHM patents for batteries represent less than a 10% share of patents for electrical systems up to 2015. Nearly all PHM patents for electric motors are based on the measurement of current, since it is closely related to the operating condition of electric motors. PHM patents for electrical devices in automobiles and aircraft are constantly being proposed. Although PHM technologies have matured, PHM patents for networks and communications facilities are currently insufficient.","PeriodicalId":163377,"journal":{"name":"Prognostics and Health Management of Electronics","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132583506","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 : 2018-08-24DOI: 10.1002/9781119515326.app1
{"title":"Commercially Available Sensor Systems for PHM","authors":"","doi":"10.1002/9781119515326.app1","DOIUrl":"https://doi.org/10.1002/9781119515326.app1","url":null,"abstract":"","PeriodicalId":163377,"journal":{"name":"Prognostics and Health Management of Electronics","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128801344","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 : 2018-08-24DOI: 10.1002/9781119515326.ch20
R. Karim, Phillip Tretten, U. Kumar
{"title":"eMaintenance","authors":"R. Karim, Phillip Tretten, U. Kumar","doi":"10.1002/9781119515326.ch20","DOIUrl":"https://doi.org/10.1002/9781119515326.ch20","url":null,"abstract":"","PeriodicalId":163377,"journal":{"name":"Prognostics and Health Management of Electronics","volume":"05 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131359626","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 : 2018-08-24DOI: 10.1002/9781119515326.CH5
Michael G. Pecht, Myeongsu Kang
In prognostics and health management (PHM), data pre‐processing generally involves the following tasks: data cleansing, normalization, feature discovery, and imbalanced data management. Data cleansing is the process of detecting and correcting corrupt or inaccurate data. Feature engineering is the process of using domain knowledge of the data to create features that make machine learning algorithms work. Feature extraction, also known as dimensionality reduction, is the transformation of high‐dimensional data into a meaningful representation of reduced dimensionality, which should have a dimensionality that corresponds to the intrinsic dimensionality of the data. Linear discriminant analysis (LDA) is commonly used as a dimensionality reduction technique in the data pre‐processing step for classification and machine learning applications. Feature selection, also called variable selection/attribute selection, is the process of selecting a subset of relevant features for use in model construction. The synthetic minority oversampling technique (SMOTE) algorithm produces artificial data based on the feature space similarities between minority data points.
{"title":"Machine Learning: Data Pre-processing","authors":"Michael G. Pecht, Myeongsu Kang","doi":"10.1002/9781119515326.CH5","DOIUrl":"https://doi.org/10.1002/9781119515326.CH5","url":null,"abstract":"In prognostics and health management (PHM), data pre‐processing generally involves the following tasks: data cleansing, normalization, feature discovery, and imbalanced data management. Data cleansing is the process of detecting and correcting corrupt or inaccurate data. Feature engineering is the process of using domain knowledge of the data to create features that make machine learning algorithms work. Feature extraction, also known as dimensionality reduction, is the transformation of high‐dimensional data into a meaningful representation of reduced dimensionality, which should have a dimensionality that corresponds to the intrinsic dimensionality of the data. Linear discriminant analysis (LDA) is commonly used as a dimensionality reduction technique in the data pre‐processing step for classification and machine learning applications. Feature selection, also called variable selection/attribute selection, is the process of selecting a subset of relevant features for use in model construction. The synthetic minority oversampling technique (SMOTE) algorithm produces artificial data based on the feature space similarities between minority data points.","PeriodicalId":163377,"journal":{"name":"Prognostics and Health Management of Electronics","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131423535","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 : 2018-08-24DOI: 10.1002/9781119515326.CH1
M. Pecht, Myeongsu Kang
Prognostics and systems health management (PHM) is a multifaceted discipline for the assessment of product degradation and reliability. This chapter provides a basic understanding of prognostics and health monitoring of products and the techniques being developed to enable prognostics for electronic products. PHM consists of sensing, anomaly detection, diagnostics, prognostics, and decision support. To enable PHM, the physics‐of‐failure (PoF)‐, canary‐, data‐driven‐, and fusion‐based approaches have been studied. The chapter explains each of these approaches. It then presents various applications using these approaches and discusses how to implement PHM in a system of systems. The chapter further introduces the opportunities of Internet of Things (IoT)‐based PHM for industrial applications. The key conclusion is that IoT‐based PHM is expected to have considerable influence on the implementation of reliability assessment, prediction and risk mitigation, and create new business opportunities.
{"title":"Introduction to PHM","authors":"M. Pecht, Myeongsu Kang","doi":"10.1002/9781119515326.CH1","DOIUrl":"https://doi.org/10.1002/9781119515326.CH1","url":null,"abstract":"Prognostics and systems health management (PHM) is a multifaceted discipline for the assessment of product degradation and reliability. This chapter provides a basic understanding of prognostics and health monitoring of products and the techniques being developed to enable prognostics for electronic products. PHM consists of sensing, anomaly detection, diagnostics, prognostics, and decision support. To enable PHM, the physics‐of‐failure (PoF)‐, canary‐, data‐driven‐, and fusion‐based approaches have been studied. The chapter explains each of these approaches. It then presents various applications using these approaches and discusses how to implement PHM in a system of systems. The chapter further introduces the opportunities of Internet of Things (IoT)‐based PHM for industrial applications. The key conclusion is that IoT‐based PHM is expected to have considerable influence on the implementation of reliability assessment, prediction and risk mitigation, and create new business opportunities.","PeriodicalId":163377,"journal":{"name":"Prognostics and Health Management of Electronics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114269992","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 : 2018-08-24DOI: 10.1002/9781119515326.app2
{"title":"Journals and Conference Proceedings Related to PHM","authors":"","doi":"10.1002/9781119515326.app2","DOIUrl":"https://doi.org/10.1002/9781119515326.app2","url":null,"abstract":"","PeriodicalId":163377,"journal":{"name":"Prognostics and Health Management of Electronics","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129013749","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 : 2018-08-24DOI: 10.1002/9781119515326.CH9
P. Sandborn, C. Wilkinson, Kiri Lee Sharon, T. Jazouli, Roozbeh Bakhshi
{"title":"PHM Cost and Return on Investment","authors":"P. Sandborn, C. Wilkinson, Kiri Lee Sharon, T. Jazouli, Roozbeh Bakhshi","doi":"10.1002/9781119515326.CH9","DOIUrl":"https://doi.org/10.1002/9781119515326.CH9","url":null,"abstract":"","PeriodicalId":163377,"journal":{"name":"Prognostics and Health Management of Electronics","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125450104","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 : 2018-08-24DOI: 10.1002/9781119515326.CH4
Myeongsu Kang, N. J. Jameson
Prognostics and health management (PHM) facilitates maintenance decision‐making and provides usage feedback for the product design and validation process. Electronic component and product manufacturers need new ways to gain insights from the massive volume of data recently streaming in from their systems and sensors, and this can be accomplished by using machine learning (ML). This chapter provides the fundamentals of ML. ML algorithms can be divided into the following four categories depending on the amount and type of supervision they need while training: supervised, unsupervised, semi‐supervised, and reinforcement learning. ML algorithms can be classified into two different learning methods based on whether or not the algorithms can learn incrementally from a stream of incoming data: batch and online learning. Probability theory plays a significant role in ML, specifically as the design of learning algorithms often depends on probabilistic assumption of the data.
{"title":"Machine Learning: Fundamentals","authors":"Myeongsu Kang, N. J. Jameson","doi":"10.1002/9781119515326.CH4","DOIUrl":"https://doi.org/10.1002/9781119515326.CH4","url":null,"abstract":"Prognostics and health management (PHM) facilitates maintenance decision‐making and provides usage feedback for the product design and validation process. Electronic component and product manufacturers need new ways to gain insights from the massive volume of data recently streaming in from their systems and sensors, and this can be accomplished by using machine learning (ML). This chapter provides the fundamentals of ML. ML algorithms can be divided into the following four categories depending on the amount and type of supervision they need while training: supervised, unsupervised, semi‐supervised, and reinforcement learning. ML algorithms can be classified into two different learning methods based on whether or not the algorithms can learn incrementally from a stream of incoming data: batch and online learning. Probability theory plays a significant role in ML, specifically as the design of learning algorithms often depends on probabilistic assumption of the data.","PeriodicalId":163377,"journal":{"name":"Prognostics and Health Management of Electronics","volume":"422 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122798524","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 : 2018-08-24DOI: 10.1002/9781119515326.CH8
S. Sankararaman
{"title":"Uncertainty Representation, Quantification, and Management in Prognostics","authors":"S. Sankararaman","doi":"10.1002/9781119515326.CH8","DOIUrl":"https://doi.org/10.1002/9781119515326.CH8","url":null,"abstract":"","PeriodicalId":163377,"journal":{"name":"Prognostics and Health Management of Electronics","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132326983","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 : 2018-08-24DOI: 10.1002/9781119515326.CH23
M. Pecht, Myeongsu Kang
Prognostics and health management (PHM) is an enabling technology with the potential to solve complex reliability problems that have manifested due to complexity in design, manufacturing, test, and maintenance. This chapter provides an assessment of the state of practice and state of the art in PHM, focused mostly on electronics, and identify the key research and development (R&D) opportunities and challenges that exist, so that resources can be efficiently allocated. In assessing the state of the art and trends for the development of a roadmap for PHM, differences between PHM for electronics and PHM for mechanical structures must be recognized. The foundations of electronic systems are the integrated circuits (ICs) that comprise the computing, processing, memory, and communications. Photo‐electronic components that could greatly benefit from PHM include light‐emitting diodes (LEDs), lasers, radar, infra‐red devices, and tactical sensors. Health monitoring and identifying a baseline usage condition to evaluate system health are fundamental for prognostics.
{"title":"A PHM Roadmap for Electronics-Rich Systems","authors":"M. Pecht, Myeongsu Kang","doi":"10.1002/9781119515326.CH23","DOIUrl":"https://doi.org/10.1002/9781119515326.CH23","url":null,"abstract":"Prognostics and health management (PHM) is an enabling technology with the potential to solve complex reliability problems that have manifested due to complexity in design, manufacturing, test, and maintenance. This chapter provides an assessment of the state of practice and state of the art in PHM, focused mostly on electronics, and identify the key research and development (R&D) opportunities and challenges that exist, so that resources can be efficiently allocated. In assessing the state of the art and trends for the development of a roadmap for PHM, differences between PHM for electronics and PHM for mechanical structures must be recognized. The foundations of electronic systems are the integrated circuits (ICs) that comprise the computing, processing, memory, and communications. Photo‐electronic components that could greatly benefit from PHM include light‐emitting diodes (LEDs), lasers, radar, infra‐red devices, and tactical sensors. Health monitoring and identifying a baseline usage condition to evaluate system health are fundamental for prognostics.","PeriodicalId":163377,"journal":{"name":"Prognostics and Health Management of Electronics","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133446527","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：