Pub Date : 2023-03-11DOI: 10.36001/ijphm.2023.v14i1.3283
A. Meghoe, R. Loendersloot, T. Tinga
While the development of prognostic models is nowadays rather feasible, the implementation and validation thereof can still create many challenges. One of the main challenges is the lack of high-quality input data like operational data, environmental data, maintenance data and the limited amount of degradation or failure data. The uncertainty in the output of the prognostic model needs to be quantified before it can be utilised for either model validation or actual maintenance decision support. This study, therefore, proposes a generic framework for prognostic model validation with limited data based on uncertainty propagation. This is realised by using sensitivity indices, correlation coefficients, Monte Carlo simulations and analytical approaches. For demonstration purposes, a rail wear prognostic model is used. The demonstration concludes that by following the generic framework, the prognostic model can be validated, and as a result, realistic maintenance advice can be given to rail infrastructure managers, even when limited data is available.
{"title":"Validation of a Physics-based Prognostic Model with Incomplete Data","authors":"A. Meghoe, R. Loendersloot, T. Tinga","doi":"10.36001/ijphm.2023.v14i1.3283","DOIUrl":"https://doi.org/10.36001/ijphm.2023.v14i1.3283","url":null,"abstract":"While the development of prognostic models is nowadays rather feasible, the implementation and validation thereof can still create many challenges. One of the main challenges is the lack of high-quality input data like operational data, environmental data, maintenance data and the limited amount of degradation or failure data. The uncertainty in the output of the prognostic model needs to be quantified before it can be utilised for either model validation or actual maintenance decision support. This study, therefore, proposes a generic framework for prognostic model validation with limited data based on uncertainty propagation. This is realised by using sensitivity indices, correlation coefficients, Monte Carlo simulations and analytical approaches. For demonstration purposes, a rail wear prognostic model is used. The demonstration concludes that by following the generic framework, the prognostic model can be validated, and as a result, realistic maintenance advice can be given to rail infrastructure managers, even when limited data is available.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43052198","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}
Degradation of the starter can lead to the failure of starting Auxiliary Power Units (APU) and the consequent safety hazards. To improve performance monitoring and malfunction prediction of APUs, in this paper, two indicators are developed based on the physics-based model of the APU starting process. The indicators quantify the health level of the starter and provide diagnostic information with no need for past measurements from the system. The health indicators are proposed to identify the degradation of the starter at both the system level and component level. An enhanced joint indicator is then developed to aggregate the two individual indicators to detect the starter failure within a two-dimensional feature space. Receiver operating characteristic (ROC) curves are adopted to evaluate the diagnostic performance of the three indicators and the optimal thresholds are determined based on the trade-off between the diagnostic reliability and the operating cost reduction. The enhanced joint indicator exhibits superior diagnostic performance and offers a significant improvement in overall maintenance costs.
{"title":"An Enhanced Joint Indicator for Starter Failure Diagnostics in Auxiliary Power Unit","authors":"Yu Zhang, Jie Liu, Houman Hanachi, Chunsheng Yang","doi":"10.22215/jphm.v3i1.4154","DOIUrl":"https://doi.org/10.22215/jphm.v3i1.4154","url":null,"abstract":"Degradation of the starter can lead to the failure of starting Auxiliary Power Units (APU) and the consequent safety hazards. To improve performance monitoring and malfunction prediction of APUs, in this paper, two indicators are developed based on the physics-based model of the APU starting process. The indicators quantify the health level of the starter and provide diagnostic information with no need for past measurements from the system. The health indicators are proposed to identify the degradation of the starter at both the system level and component level. An enhanced joint indicator is then developed to aggregate the two individual indicators to detect the starter failure within a two-dimensional feature space. Receiver operating characteristic (ROC) curves are adopted to evaluate the diagnostic performance of the three indicators and the optimal thresholds are determined based on the trade-off between the diagnostic reliability and the operating cost reduction. The enhanced joint indicator exhibits superior diagnostic performance and offers a significant improvement in overall maintenance costs.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84624502","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 : 2023-02-13DOI: 10.36001/ijphm.2023.v14i3.3128
Xinyu Du, Shengbing Jiang, D. Zhou, Alaeddin Bani Milhim, Hossein Sadjadi
An electronic control unit (ECU) with a floating ground is not able to receive or transmit messages or participate in controller area network (CAN) communication. The absence of any ECU, either temporarily or permanently, negatively impacts vehicle functionalities. The offset ground, which by itself will not affect bus functionalities if the grounding resistance is small, however, may evolve into a floating ground or behave similarly if the resistance is large. In this work, the correlation among ground faults, either offset or floating, and CAN bus voltage or messages are analyzed based on the equivalent circuit models and the bus protocol. A voltage-based solution to detect ground faults is proposed. With the help of bus messages, both faults can be isolated at the ECU level. Considering the inherent system delay between the message fetching and voltage measurement, a normalized voltage-message correlation approach with the bus load estimation is developed as well. All proposed approaches are implemented to an Arduino-based embedded system and validated on a vehicle frame.
{"title":"Ground Fault Diagnostics for Automotive Electronic Control Units","authors":"Xinyu Du, Shengbing Jiang, D. Zhou, Alaeddin Bani Milhim, Hossein Sadjadi","doi":"10.36001/ijphm.2023.v14i3.3128","DOIUrl":"https://doi.org/10.36001/ijphm.2023.v14i3.3128","url":null,"abstract":"An electronic control unit (ECU) with a floating ground is not able to receive or transmit messages or participate in controller area network (CAN) communication. The absence of any ECU, either temporarily or permanently, negatively impacts vehicle functionalities. The offset ground, which by itself will not affect bus functionalities if the grounding resistance is small, however, may evolve into a floating ground or behave similarly if the resistance is large. In this work, the correlation among ground faults, either offset or floating, and CAN bus voltage or messages are analyzed based on the equivalent circuit models and the bus protocol. A voltage-based solution to detect ground faults is proposed. With the help of bus messages, both faults can be isolated at the ECU level. Considering the inherent system delay between the message fetching and voltage measurement, a normalized voltage-message correlation approach with the bus load estimation is developed as well. All proposed approaches are implemented to an Arduino-based embedded system and validated on a vehicle frame.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49663413","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 : 2023-02-13DOI: 10.36001/ijphm.2023.v14i3.3123
Aditya Jain, Piyush Tarey
The automotive industry is witnessing its next phase of transformation. The vehicles are getting defined by software, becoming intelligent, connected and more complex to design, develop and analyze. For these complex vehicles, prognostics and proactive maintenance has become ever more critical than before.OEMs and suppliers analyze probable failures that a vehicle component is likely to encounter, define fault codes to identify those failures, and provide procedure or guided steps to resolve them. For smarter vehicles, it is required that vehicles be capable to catch potential problems as soon as the component’s condition starts to deteriorate and becomes a failure. These failures could be known (defined) or new (undefined). Given the vehicle development timelines and increasing complexity, many problems are not analyzed at design stage and remain undetected before production. Hence, no fault code or test case exist for them. Diagnosing such problems become very difficult, postproduction.The aim of this paper is to propose a Machine Learning (ML) based framework which utilizes minimally labelled or unlabeled sensor data generated from a vehicle system at a given frequency. The framework utilizes an ML model to identify any anomalous behavior or aberration, and flag it for further review. This framework can be adopted on large amount of real time or time series data to identify known as well as undefined failures early. These models could be deployed on cloud or on edge (on vehicles) for analyzing real-time sensor data for a given system/component and flag any anomaly. It could further be utilized to create a part specific Predictive Maintenance (PM) model to provide proactive warnings and prevent downtime.
{"title":"Anomaly Detection for Early Failure Identification on Automotive Field Data","authors":"Aditya Jain, Piyush Tarey","doi":"10.36001/ijphm.2023.v14i3.3123","DOIUrl":"https://doi.org/10.36001/ijphm.2023.v14i3.3123","url":null,"abstract":"The automotive industry is witnessing its next phase of transformation. The vehicles are getting defined by software, becoming intelligent, connected and more complex to design, develop and analyze. For these complex vehicles, prognostics and proactive maintenance has become ever more critical than before.OEMs and suppliers analyze probable failures that a vehicle component is likely to encounter, define fault codes to identify those failures, and provide procedure or guided steps to resolve them. For smarter vehicles, it is required that vehicles be capable to catch potential problems as soon as the component’s condition starts to deteriorate and becomes a failure. These failures could be known (defined) or new (undefined). Given the vehicle development timelines and increasing complexity, many problems are not analyzed at design stage and remain undetected before production. Hence, no fault code or test case exist for them. Diagnosing such problems become very difficult, postproduction.The aim of this paper is to propose a Machine Learning (ML) based framework which utilizes minimally labelled or unlabeled sensor data generated from a vehicle system at a given frequency. The framework utilizes an ML model to identify any anomalous behavior or aberration, and flag it for further review. This framework can be adopted on large amount of real time or time series data to identify known as well as undefined failures early. These models could be deployed on cloud or on edge (on vehicles) for analyzing real-time sensor data for a given system/component and flag any anomaly. It could further be utilized to create a part specific Predictive Maintenance (PM) model to provide proactive warnings and prevent downtime.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"70086164","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 : 2023-02-13DOI: 10.36001/ijphm.2023.v14i3.3130
Yuan-Ming Hsu, Dai-Yan Ji, Marcella Miller, Xiaodong Jia, J. Lee
Electric Vehicles (EVs) have become a trending topic in recent years due to the industry’s race for competitive pricing as well as environmental awareness. These concerns have led to increased research into the development of both affordable and environmentally friendly EV technology. This paper aims to review EV-related issues beginning with the component level, through the system level, based on intelligent maintenance aspects. The paper will also clarify the existing gaps in practical applications and highlight the potential opportunities related to the current issues in EVs for the EV industry moving forward. More specifically, we will briefly start with an overview of the fast-growing EV market, showing the urgent demand for Prognostics and Health Management (PHM) applications in the EV industry. At the component level, the issues of the major components such as the motor, battery, and charging system in EVs are elaborated, and the relevant PHM research of these components is surveyed to show the development in the era of EV expansion. Moreover, the impact of an increasing number of EVs at the system level such as power distribution systems and power grid are explored to uncover possible research in the future. The combination of existing PHM techniques and robust measurement or feature extraction methods can provide better solutions to address the motor, battery, or transformer issues at the component level. A comprehensive optimization and cybersecurity strategy will help to address the issues of the whole network at a system level. Four aspects of vision in the overall charging network – battery innovation, charging optimization, infrastructure evolution, and sustainability – that cover the demands of research in new battery materials, innovative charging techniques, new architectures of the charging network, and reliable waste treatment mechanisms are outlined. A conclusion is reached in this paper by summarizing the opportunities for future EV research and development.
{"title":"Intelligent Maintenance of Electric Vehicle Battery Charging Systems and Networks","authors":"Yuan-Ming Hsu, Dai-Yan Ji, Marcella Miller, Xiaodong Jia, J. Lee","doi":"10.36001/ijphm.2023.v14i3.3130","DOIUrl":"https://doi.org/10.36001/ijphm.2023.v14i3.3130","url":null,"abstract":"Electric Vehicles (EVs) have become a trending topic in recent years due to the industry’s race for competitive pricing as well as environmental awareness. These concerns have led to increased research into the development of both affordable and environmentally friendly EV technology. This paper aims to review EV-related issues beginning with the component level, through the system level, based on intelligent maintenance aspects. The paper will also clarify the existing gaps in practical applications and highlight the potential opportunities related to the current issues in EVs for the EV industry moving forward. More specifically, we will briefly start with an overview of the fast-growing EV market, showing the urgent demand for Prognostics and Health Management (PHM) applications in the EV industry. At the component level, the issues of the major components such as the motor, battery, and charging system in EVs are elaborated, and the relevant PHM research of these components is surveyed to show the development in the era of EV expansion. Moreover, the impact of an increasing number of EVs at the system level such as power distribution systems and power grid are explored to uncover possible research in the future.\u0000The combination of existing PHM techniques and robust measurement or feature extraction methods can provide better solutions to address the motor, battery, or transformer issues at the component level. A comprehensive optimization and cybersecurity strategy will help to address the issues of the whole network at a system level. Four aspects of vision in the overall charging network – battery innovation, charging optimization, infrastructure evolution, and sustainability – that cover the demands of research in new battery materials, innovative charging techniques, new architectures of the charging network, and reliable waste treatment mechanisms are outlined. A conclusion is reached in this paper by summarizing the opportunities for future EV research and development.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41855643","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 : 2023-02-13DOI: 10.36001/ijphm.2023.v14i3.3438
Yilu Zhang, R. Salehi, Shiyu Zhou, Xiaodong Jia, Jason A. Siegel
This special issue on Advanced Diagnostics and Prognostics for Automotive Systems provides an opportunity to discuss recent advances in different topics related to modern automotive systems. The topics include model-based monitoring algorithm for diesel vehicle aftertreatment system, air-path health management strategy for estimation of the mass flows and mitigation of the air-path faults, early detection of anomalies in fuel system evaporative and purge systems leveraging vehicles connectivity, review of intelligent maintenance of EVs at both component level and system level to identify existing gaps in EVs DnP, detection and isolation of ground connection faults in electronic control units, root cause detection of defects in arc stud welding that is used to join automotive structures, machine learning based anomaly detection framework demonstrated on the hydraulic system of electric off-road vehicles, and signal abstraction to assist fast root-cause detection of large scale control systems.
{"title":"Special Issue on Advanced Diagnostics and Prognostics for Automotive Systems","authors":"Yilu Zhang, R. Salehi, Shiyu Zhou, Xiaodong Jia, Jason A. Siegel","doi":"10.36001/ijphm.2023.v14i3.3438","DOIUrl":"https://doi.org/10.36001/ijphm.2023.v14i3.3438","url":null,"abstract":"This special issue on Advanced Diagnostics and Prognostics for Automotive Systems provides an opportunity to discuss recent advances in different topics related to modern automotive systems. The topics include model-based monitoring algorithm for diesel vehicle aftertreatment system, air-path health management strategy for estimation of the mass flows and mitigation of the air-path faults, early detection of anomalies in fuel system evaporative and purge systems leveraging vehicles connectivity, review of intelligent maintenance of EVs at both component level and system level to identify existing gaps in EVs DnP, detection and isolation of ground connection faults in electronic control units, root cause detection of defects in arc stud welding that is used to join automotive structures, machine learning based anomaly detection framework demonstrated on the hydraulic system of electric off-road vehicles, and signal abstraction to assist fast root-cause detection of large scale control systems.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42230313","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 : 2023-02-13DOI: 10.36001/ijphm.2023.v14i3.3122
Ala E. Omrani, Pankaj Kumar, A. Dudar, Michael Casedy, Steven Szwabowski, Brandon M. Dawson
From automobile manufacturers’ perspective, reduction of warranty cost leads to less expenditures, which then yields higher profits. Hence, it is crucial to leverage the different methods and available tools to achieve such outcome. Connected vehicle data is one critical resource that can be a gamechanger, reducing the associated costs and improving the business profitability. This project uses Mode06 (On-Board diagnostics reported tests results) connected vehicle data along with contextual data to early detect EVAP and purge monitors’ anomalies. Early detection allows fixing the issue through software (SW) and/or hardware (HW) upgrades before it turns into a failure (preventive maintenance), yielding then system quality improvement. Root cause analysis, which can be developed based on the anomaly detection outcomes and which is not within the scope of this paper, allows diagnostics of HW and/or SW related issues in a timely manner and eventually be prepared ahead of time for system failures. In this paper, statistics-based early anomaly detection models, based on vehicle data and fleet data, are developed. The proposed solution is a generic tool that does not make assumptions on data distribution and can be adapted to other systems by tweaking mainly the data cleaning process. It also incorporates specific system definitions of abnormal behavior, which makes it more accurate compared to conventional anomaly detection tools, which are mainly affected by the imbalanced data and the EVAP and purge definition of an anomaly. When deployed with field data, the algorithm showed higher performance, compared to popular anomaly detection techniques, and proved that failures can be prevented through detection of the anomalies several weeks/miles before the actual fail.
{"title":"Machine Learning Based Approach for EVAP System Early Anomaly Detection Using Connected Vehicle Data","authors":"Ala E. Omrani, Pankaj Kumar, A. Dudar, Michael Casedy, Steven Szwabowski, Brandon M. Dawson","doi":"10.36001/ijphm.2023.v14i3.3122","DOIUrl":"https://doi.org/10.36001/ijphm.2023.v14i3.3122","url":null,"abstract":"From automobile manufacturers’ perspective, reduction of warranty cost leads to less expenditures, which then yields higher profits. Hence, it is crucial to leverage the different methods and available tools to achieve such outcome. Connected vehicle data is one critical resource that can be a gamechanger, reducing the associated costs and improving the business profitability. This project uses Mode06 (On-Board diagnostics reported tests results) connected vehicle data along with contextual data to early detect EVAP and purge monitors’ anomalies. Early detection allows fixing the issue through software (SW) and/or hardware (HW) upgrades before it turns into a failure (preventive maintenance), yielding then system quality improvement. Root cause analysis, which can be developed based on the anomaly detection outcomes and which is not within the scope of this paper, allows diagnostics of HW and/or SW related issues in a timely manner and eventually be prepared ahead of time for system failures. In this paper, statistics-based early anomaly detection models, based on vehicle data and fleet data, are developed. The proposed solution is a generic tool that does not make assumptions on data distribution and can be adapted to other systems by tweaking mainly the data cleaning process. It also incorporates specific system definitions of abnormal behavior, which makes it more accurate compared to conventional anomaly detection tools, which are mainly affected by the imbalanced data and the EVAP and purge definition of an anomaly. When deployed with field data, the algorithm showed higher performance, compared to popular anomaly detection techniques, and proved that failures can be prevented through detection of the anomalies several weeks/miles before the actual fail.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41576911","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 : 2023-02-13DOI: 10.36001/ijphm.2023.v14i3.3118
Tomas Poloni, P. Dickinson, Jianrui Zhang, Peng Zhou
This paper presents the air-path health management strategy with the ability to estimate the mass-flows and mitigate (adapt to) the air-path faults in the exhaust system of a heavy-duty diesel combustion engine equipped with a twin-scroll turbine. Based on the engine component models applied in the quasi-steady-state mass-balancing approach, two main engine mass-flow quantities are estimated: the Air mass-flow (AMF) and the Exhaust gas recirculation (EGR) mass-flow. The health management system is monitoring for three kinds of air-path faults that can occur through the combustion engine operation, related either to the after-treatment system, EGR valve, or to the turbine balance valve hardware. For each fault, a fault-mitigation strategy based on in-observer-reconfigurable mass-balance equations with excluded faulty component model and utilized exhaust pressure sensor is proposed. The applied observer is using the iterated Kalman filter (IKF) as the core fault mitigating solver for the quasi-steady-state mass-balancing problem. It is further demonstrated how the individual faults are robustly isolated using the Sequential Probability Ratio Test (SPRT). The strategy and results are validated using the test cycle driving data.
{"title":"Self-Adaptive Air-path Health Management for a Heavy Duty-Diesel Engine","authors":"Tomas Poloni, P. Dickinson, Jianrui Zhang, Peng Zhou","doi":"10.36001/ijphm.2023.v14i3.3118","DOIUrl":"https://doi.org/10.36001/ijphm.2023.v14i3.3118","url":null,"abstract":"This paper presents the air-path health management strategy with the ability to estimate the mass-flows and mitigate (adapt to) the air-path faults in the exhaust system of a heavy-duty diesel combustion engine equipped with a twin-scroll turbine. Based on the engine component models applied in the quasi-steady-state mass-balancing approach, two main engine mass-flow quantities are estimated: the Air mass-flow (AMF) and the Exhaust gas recirculation (EGR) mass-flow. The health management system is monitoring for three kinds of air-path faults that can occur through the combustion engine operation, related either to the after-treatment system, EGR valve, or to the turbine balance valve hardware. For each fault, a fault-mitigation strategy based on in-observer-reconfigurable mass-balance equations with excluded faulty component model and utilized exhaust pressure sensor is proposed. The applied observer is using the iterated Kalman filter (IKF) as the core fault mitigating solver for the quasi-steady-state mass-balancing problem. It is further demonstrated how the individual faults are robustly isolated using the Sequential Probability Ratio Test (SPRT). The strategy and results are validated using the test cycle driving data.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49314425","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 : 2023-02-13DOI: 10.36001/ijphm.2023.v14i3.3125
Sadra Naddaf-sh, M.-Mahdi Naddaf-Sh, Maxim Dalton, Soodabeh Ramezani, Amir R. Kashani, H. Zargarzadeh
Arc Stud Welding (ASW) is widely used in many industries such as automotive and shipbuilding and is employed in building and jointing large-scale structures. While defective or imperfect welds rarely occur in production, even a single low-quality stud weld is the reason for scrapping the entire structure, financial loss and wasting time. Preventive machine learning-based solutions can be leveraged to minimize the loss. However, these approaches only provide predictions rather than demonstrating insights for characterizing defects and root cause analysis. In this work, an investigation on defect detection and classification to diagnose the possible leading causes of low-quality defects is proposed. Moreover, an explainable model to describe network predictions is explored. Initially, a dataset of multi-variate time-series of ASW utilizing measurement sensors in an experimental environment is generated. Next, a set of pre-possessing techniques are assessed. Finally, classification models are optimized by Bayesian black-box optimization methods to maximize their performance. Our best approach reaches an F1-score of 0.84 on the test set. Furthermore, an explainable model is employed to provide interpretations on per class feature attention of the model to extract sensor measurement contribution in detecting defects as well as its time attention.
{"title":"Explainable Models for Multivariate Time-series Defect Classification of Arc Stud Welding","authors":"Sadra Naddaf-sh, M.-Mahdi Naddaf-Sh, Maxim Dalton, Soodabeh Ramezani, Amir R. Kashani, H. Zargarzadeh","doi":"10.36001/ijphm.2023.v14i3.3125","DOIUrl":"https://doi.org/10.36001/ijphm.2023.v14i3.3125","url":null,"abstract":"Arc Stud Welding (ASW) is widely used in many industries such as automotive and shipbuilding and is employed in building and jointing large-scale structures. While defective or imperfect welds rarely occur in production, even a single low-quality stud weld is the reason for scrapping the entire structure, financial loss and wasting time. Preventive machine learning-based solutions can be leveraged to minimize the loss. However, these approaches only provide predictions rather than demonstrating insights for characterizing defects and root cause analysis. In this work, an investigation on defect detection and classification to diagnose the possible leading causes of low-quality defects is proposed. Moreover, an explainable model to describe network predictions is explored. Initially, a dataset of multi-variate time-series of ASW utilizing measurement sensors in an experimental environment is generated. Next, a set of pre-possessing techniques are assessed. Finally, classification models are optimized by Bayesian black-box optimization methods to maximize their performance. Our best approach reaches an F1-score of 0.84 on the test set. Furthermore, an explainable model is employed to provide interpretations on per class feature attention of the model to extract sensor measurement contribution in detecting defects as well as its time attention.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43319839","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 : 2023-02-13DOI: 10.36001/ijphm.2023.v14i3.3423
R. Salehi, Shiming Duan
Today’s automotive control systems have gained huge advantage from using integrated software and hardware to reliably manage the performance of vehicles. The integration of largescale software with many hardware components, however, have increased the complexity of diagnosis and root cause analysis for a detected malfunction. High level of expertise and detailed knowledge of the underlying software and hardware are typically required to analyze a large list of variables and precisely identify the root cause of the malfunction. In this paper, an abstraction method is presented to identify the most important signals for a root cause analysis by leveraging data collected from a connected fleet of field vehicles. A novel label propagation methodology is proposed to select the most relevant signals for the root cause analysis by detecting linear and nonlinear correlations between an observed malfunction and candidate test signals of the control system. The proposed label propagation method eliminates the requirement for a priori known correlation kernel that is needed for a regression analysis. The signal abstraction method is applied and successfully tested for abstracting signals in the fuel control system, with high degree of interconnection between software and hardware, using data from more than 5000 connected vehicles.
{"title":"Signal Abstraction for Root Cause Identification of Control Systems Malfunctions in Connected Vehicles","authors":"R. Salehi, Shiming Duan","doi":"10.36001/ijphm.2023.v14i3.3423","DOIUrl":"https://doi.org/10.36001/ijphm.2023.v14i3.3423","url":null,"abstract":"Today’s automotive control systems have gained huge advantage from using integrated software and hardware to reliably manage the performance of vehicles. The integration of largescale software with many hardware components, however, have increased the complexity of diagnosis and root cause analysis for a detected malfunction. High level of expertise and detailed knowledge of the underlying software and hardware are typically required to analyze a large list of variables and precisely identify the root cause of the malfunction. In this paper, an abstraction method is presented to identify the most important signals for a root cause analysis by leveraging data collected from a connected fleet of field vehicles. A novel label propagation methodology is proposed to select the most relevant signals for the root cause analysis by detecting linear and nonlinear correlations between an observed malfunction and candidate test signals of the control system. The proposed label propagation method eliminates the requirement for a priori known correlation kernel that is needed for a regression analysis. The signal abstraction method is applied and successfully tested for abstracting signals in the fuel control system, with high degree of interconnection between software and hardware, using data from more than 5000 connected vehicles.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49517657","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：