Pub Date : 2013-06-24DOI: 10.1109/ICPHM.2013.6621414
Petek Yontay, R. Pan, O. A. Vanli
Inexpensive wireless sensors can be embedded in structural materials to detect defects. These sensors provide in-situ diagnosis of the system's health, thus invaluable information to decision makers for system maintenance and repair. For example, lamb wave sensors that are embedded in carbon fiber composites can monitor the material integrity by detecting and quantifying fiber delaminations and breakages. Although they are relatively easy to be deployed, their lifetimes are limited due to power consumption and they cannot be replaced without interrupting the operation of system. In this paper, we discuss a sampling method that is based on the material's degradation model for activating sensors and collecting health information. We are interested in predicting the time of failure with a few numbers of signals and with statistical efficiency. Our method is good for the in-situ health monitoring, where the system's failure time is of concern and the sensor's power conservation is required.
{"title":"Sampling schedule optimization of embedded wireless sensors for degradation monitoring","authors":"Petek Yontay, R. Pan, O. A. Vanli","doi":"10.1109/ICPHM.2013.6621414","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621414","url":null,"abstract":"Inexpensive wireless sensors can be embedded in structural materials to detect defects. These sensors provide in-situ diagnosis of the system's health, thus invaluable information to decision makers for system maintenance and repair. For example, lamb wave sensors that are embedded in carbon fiber composites can monitor the material integrity by detecting and quantifying fiber delaminations and breakages. Although they are relatively easy to be deployed, their lifetimes are limited due to power consumption and they cannot be replaced without interrupting the operation of system. In this paper, we discuss a sampling method that is based on the material's degradation model for activating sensors and collecting health information. We are interested in predicting the time of failure with a few numbers of signals and with statistical efficiency. Our method is good for the in-situ health monitoring, where the system's failure time is of concern and the sensor's power conservation is required.","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":"130178006","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.2013.6621437
Y. Langer, A. Urmanov, Anton A. Bougaev
The necessity of discrimination of marginally distinct measured signals is one of the main problems in the creation of maintenance policies. Applying classical methods of statistical classification of observations to the solution of this problem entails considerable difficulties caused by the need to discriminate signals in a gray area between absolutely healthy and fully degraded system. In the gray area, the difference between population parameters inferred from samples is hardly noticeable. Instead of the classical discrimination criteria, a discriminant function that minimizes the expected sum of losses (for example, losses of time) relevant to system preventive maintenance and recovering of the system after its failure is used. This discriminant function is developed on the basis of the representation of the observed system degradation process as a Discrete Parameter Markov chain. The extremum of this function determines the discrimination boundary and the optimal time for maintenance. The requirements for the possible deviation of the experimentally obtained Markov process parameters that do not invalidate the obtained optimal rule of maintenance are specified. The developed methods are illustrated on synthetic data reminiscent of the operation of a database management system.
{"title":"Predictive maintenance policy optimization by discrimination of marginally distinct signals","authors":"Y. Langer, A. Urmanov, Anton A. Bougaev","doi":"10.1109/ICPHM.2013.6621437","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621437","url":null,"abstract":"The necessity of discrimination of marginally distinct measured signals is one of the main problems in the creation of maintenance policies. Applying classical methods of statistical classification of observations to the solution of this problem entails considerable difficulties caused by the need to discriminate signals in a gray area between absolutely healthy and fully degraded system. In the gray area, the difference between population parameters inferred from samples is hardly noticeable. Instead of the classical discrimination criteria, a discriminant function that minimizes the expected sum of losses (for example, losses of time) relevant to system preventive maintenance and recovering of the system after its failure is used. This discriminant function is developed on the basis of the representation of the observed system degradation process as a Discrete Parameter Markov chain. The extremum of this function determines the discrimination boundary and the optimal time for maintenance. The requirements for the possible deviation of the experimentally obtained Markov process parameters that do not invalidate the obtained optimal rule of maintenance are specified. The developed methods are illustrated on synthetic data reminiscent of the operation of a database management system.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"2 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":"114349433","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.2013.6621454
Chunsheng Yang, S. Létourneau, Yubin Yang, Jie Liu
FMEA (Failure Mode and Effects Analysis), which was developed to enhance the reliability of complex systems, is a standard method to characterize and document product and process problems and a systematic method for fault identification/isolation in maintenance industry. Fault identification for a given failure effect or mode is a reactive process. Usually, a failure has occurred and it needs to identify which component is the root cause or to isolate the fault to a specific contributing component. Traditional method is to conduct TSM (Trouble Shooting Manuals)-based fault isolation, which is complicated, expensive, and time-consuming. To efficiently perform fault isolation, this paper proposed data mining-based framework for fault isolation by using FMEA information to rank data-driven models. In this paper, we present the proposed framework along with a case study for APU fault identification.
FMEA (Failure Mode and Effects Analysis)是为了提高复杂系统的可靠性而发展起来的，是表征和记录产品和过程问题的标准方法，也是维修行业故障识别/隔离的系统方法。对于给定的故障效果或模式，故障识别是一个反应过程。通常，故障已经发生，它需要确定哪个组件是根本原因，或者将故障隔离到特定的贡献组件。传统的方法是基于TSM (Trouble Shooting manual)进行故障隔离，这种方法复杂、成本高、耗时长。为了有效地进行故障隔离，本文提出了基于数据挖掘的故障隔离框架，利用FMEA信息对数据驱动模型进行排序。在本文中，我们提出了该框架，并对APU故障识别进行了实例研究。
{"title":"Data mining based fault isolation with FMEA rank: A case study of APU fault identification","authors":"Chunsheng Yang, S. Létourneau, Yubin Yang, Jie Liu","doi":"10.1109/ICPHM.2013.6621454","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621454","url":null,"abstract":"FMEA (Failure Mode and Effects Analysis), which was developed to enhance the reliability of complex systems, is a standard method to characterize and document product and process problems and a systematic method for fault identification/isolation in maintenance industry. Fault identification for a given failure effect or mode is a reactive process. Usually, a failure has occurred and it needs to identify which component is the root cause or to isolate the fault to a specific contributing component. Traditional method is to conduct TSM (Trouble Shooting Manuals)-based fault isolation, which is complicated, expensive, and time-consuming. To efficiently perform fault isolation, this paper proposed data mining-based framework for fault isolation by using FMEA information to rank data-driven models. In this paper, we present the proposed framework along with a case study for APU fault identification.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"119 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":"114474241","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.2013.6621422
P. Ghavami, K. Kapur
Prognostic methods promise to improve patient healthcare if predictions of adverse disease and medical complications for each patient can be predicted in advance. Prognostics and prediction of patients' physiological health status are getting attention in medicine because they provide insight that can be used for medical interventions that prevent adverse medical complications. While various predictive analytics have been developed for detection and prediction of certain diseases, efforts to combine the predictive power of multiple algorithms have gone mostly unnoticed. This study proposes a prognostics engine using multiple models to predict patient physiological status. Given the diversity of clinical data and disease conditions, no single model can be the ideal prediction algorithm to cover all medical cases. Certain algorithms are more accurate than others depending on input data available, the type, amount and diversity of possible outcomes. In this study four different neural network algorithms were used for the prognostics engine and their accuracy on a dataset were compared. The study proposes using an ensemble of algorithms and an oracle, an overseer program to select the most accurate combination of the predictive models that is most suited for a particular disease prediction. The feasibility of this approach is tested using a clinical data set of 1,073 patient cases including 255 patients presented with Deep Vein Pulmonary Embolism. The study compared accuracy of five different schemas for constructing ensembles of various neural networks. The multiple schema approach combined with multi-model ensembles showed to improve accuracy of prediction for this case and promises to be a robust approach to other clinical prediction problems.
{"title":"The application of multi-model ensemble approach as a prognostic method to predict patient health status","authors":"P. Ghavami, K. Kapur","doi":"10.1109/ICPHM.2013.6621422","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621422","url":null,"abstract":"Prognostic methods promise to improve patient healthcare if predictions of adverse disease and medical complications for each patient can be predicted in advance. Prognostics and prediction of patients' physiological health status are getting attention in medicine because they provide insight that can be used for medical interventions that prevent adverse medical complications. While various predictive analytics have been developed for detection and prediction of certain diseases, efforts to combine the predictive power of multiple algorithms have gone mostly unnoticed. This study proposes a prognostics engine using multiple models to predict patient physiological status. Given the diversity of clinical data and disease conditions, no single model can be the ideal prediction algorithm to cover all medical cases. Certain algorithms are more accurate than others depending on input data available, the type, amount and diversity of possible outcomes. In this study four different neural network algorithms were used for the prognostics engine and their accuracy on a dataset were compared. The study proposes using an ensemble of algorithms and an oracle, an overseer program to select the most accurate combination of the predictive models that is most suited for a particular disease prediction. The feasibility of this approach is tested using a clinical data set of 1,073 patient cases including 255 patients presented with Deep Vein Pulmonary Embolism. The study compared accuracy of five different schemas for constructing ensembles of various neural networks. The multiple schema approach combined with multi-model ensembles showed to improve accuracy of prediction for this case and promises to be a robust approach to other clinical prediction problems.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"79 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":"125393016","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.2013.6621413
Kamran Javed, R. Gouriveau, N. Zerhouni, P. Nectoux
Performances of data-driven approaches are closely related to the form and trend of extracted features (that can be seen as time series health indicators). (1) Even if much of data-driven approaches are suitable to catch non-linearity in signals, features with monotonic trends (which is not always the case!) are likely to lead to better estimates. (2) Also, some classical extracted features do not show variation until a few time before failure occurs, which prevents performing RUL predictions in a timely manner to plan maintenance task. The aim of this paper is to present a novel feature extraction procedure to face with these two problems. Two aspects are considered. Firstly, the paper focuses on feature extraction in a new manner by utilizing trigonometric functions to extract features (health indicators) rather than typical statistic measures like RMS, etc. The proposed approach is applied on time-frequency analysis with Discrete Wavelet Transform (DWT). Secondly, a simple way of building new features based on cumulative functions is also proposed in order to transform time series into descriptors that depict accumulated wear. This approach can be extended to other types of features. The main idea of both developments is to map raw data with monotonic features with early trends, i.e., with descriptors that can be easily predicted. This methodology can enhance prognostics modeling and RUL prediction. The whole proposition is illustrated and discussed thanks to tests performed on vibration datasets from PRONOSTIA, an experimental platform that enables accelerated degradation of bearings.
{"title":"A feature extraction procedure based on trigonometric functions and cumulative descriptors to enhance prognostics modeling","authors":"Kamran Javed, R. Gouriveau, N. Zerhouni, P. Nectoux","doi":"10.1109/ICPHM.2013.6621413","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621413","url":null,"abstract":"Performances of data-driven approaches are closely related to the form and trend of extracted features (that can be seen as time series health indicators). (1) Even if much of data-driven approaches are suitable to catch non-linearity in signals, features with monotonic trends (which is not always the case!) are likely to lead to better estimates. (2) Also, some classical extracted features do not show variation until a few time before failure occurs, which prevents performing RUL predictions in a timely manner to plan maintenance task. The aim of this paper is to present a novel feature extraction procedure to face with these two problems. Two aspects are considered. Firstly, the paper focuses on feature extraction in a new manner by utilizing trigonometric functions to extract features (health indicators) rather than typical statistic measures like RMS, etc. The proposed approach is applied on time-frequency analysis with Discrete Wavelet Transform (DWT). Secondly, a simple way of building new features based on cumulative functions is also proposed in order to transform time series into descriptors that depict accumulated wear. This approach can be extended to other types of features. The main idea of both developments is to map raw data with monotonic features with early trends, i.e., with descriptors that can be easily predicted. This methodology can enhance prognostics modeling and RUL prediction. The whole proposition is illustrated and discussed thanks to tests performed on vibration datasets from PRONOSTIA, an experimental platform that enables accelerated degradation of bearings.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"98 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":"115732208","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.2013.6621446
P. Johnson
Cost effective smart industrial data recorders promise to automate the collection of condition indicating sensor data. Automatic and pervasive data recording creates a wealth of condition assessment data that couples with operational history to yield a data store rich in opportunity for data driven prognostics as well as model development. Storing, managing, scoring, and otherwise utilizing this new found wealth of machinery condition indicators challenges the prognostics designer. Implementation of new and existing prognostic algorithms and techniques in an automated and useful way are the challenge of the day. While the application is not yet complete, this paper describes the motivation, the tools, the vision, and the current state of the power generation prognostics application with over 300 “balance of plant” machines under automatic surveillance.
{"title":"Building asset monitoring and prognostics systems using cost effective technologies for power generation applications","authors":"P. Johnson","doi":"10.1109/ICPHM.2013.6621446","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621446","url":null,"abstract":"Cost effective smart industrial data recorders promise to automate the collection of condition indicating sensor data. Automatic and pervasive data recording creates a wealth of condition assessment data that couples with operational history to yield a data store rich in opportunity for data driven prognostics as well as model development. Storing, managing, scoring, and otherwise utilizing this new found wealth of machinery condition indicators challenges the prognostics designer. Implementation of new and existing prognostic algorithms and techniques in an automated and useful way are the challenge of the day. While the application is not yet complete, this paper describes the motivation, the tools, the vision, and the current state of the power generation prognostics application with over 300 “balance of plant” machines under automatic surveillance.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"5 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":"129804233","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.2013.6621428
Jamie L. Godwin, Peter C. Matthews
In this paper we present a new methodology for the prognosis of a wind turbine gearbox. The statistically robust Mahalanobis distance was used to determine multivariate outliers within low frequency SCADA data without the need for manual labelling. Domain knowledge (meta-knowledge) was used to determine the multivariate vectors which encapsulate the condition of the wind turbine gearbox, providing a means to model anomalous gearbox behaviour whilst quantifying the severity of a monitored fault. A prognostic horizon of over 146 days was achieved using a new 3 degrees of freedom model, with a strong trend observed within the presented prognostic. This allowed for the quantification of fault severity, an estimation of the rate of fault development and also a means to quantify the quality and effectiveness of maintenance. In order to reduce noise inherent within SCADA data, an expert system was developed to transform the prognostic capability into actionable intelligence. This reduced the potential cognitive load placed upon the maintenance operator, whilst providing the knowledge required to optimise available maintenance resources. Due to the statistically robust nature of the approach, no gearbox fault data was required for training, enabling prognostic capability without the capital expense incurred through destructive testing. Furthermore, no additional capital expenditure is required due to data being collected from the pre-existing SCADA system available on all of the latest generation of wind turbines.
{"title":"Prognosis of wind turbine gearbox failures by utilising robust multivariate statistical techniques","authors":"Jamie L. Godwin, Peter C. Matthews","doi":"10.1109/ICPHM.2013.6621428","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621428","url":null,"abstract":"In this paper we present a new methodology for the prognosis of a wind turbine gearbox. The statistically robust Mahalanobis distance was used to determine multivariate outliers within low frequency SCADA data without the need for manual labelling. Domain knowledge (meta-knowledge) was used to determine the multivariate vectors which encapsulate the condition of the wind turbine gearbox, providing a means to model anomalous gearbox behaviour whilst quantifying the severity of a monitored fault. A prognostic horizon of over 146 days was achieved using a new 3 degrees of freedom model, with a strong trend observed within the presented prognostic. This allowed for the quantification of fault severity, an estimation of the rate of fault development and also a means to quantify the quality and effectiveness of maintenance. In order to reduce noise inherent within SCADA data, an expert system was developed to transform the prognostic capability into actionable intelligence. This reduced the potential cognitive load placed upon the maintenance operator, whilst providing the knowledge required to optimise available maintenance resources. Due to the statistically robust nature of the approach, no gearbox fault data was required for training, enabling prognostic capability without the capital expense incurred through destructive testing. Furthermore, no additional capital expenditure is required due to data being collected from the pre-existing SCADA system available on all of the latest generation of wind turbines.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"15 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":"127706490","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.2013.6621431
Ranjith-Kumar Sreenilayam-Raveendran, M. Azarian, M. Pecht, E. Rhem
Reduction in the lubricant level of a bearing will reduce the operating life of the bearing. This condition is a concern in lightly loaded bearings, such as cooling fans in electronics applications, whose life is dependent on the service life of the lubricant. If these bearings are manufactured with a sub-optimal amount of lubricant, the degradation of lubricant as well as the wear processes in the bearing can be accelerated, thereby leading to early failures of the fans. Measurements were carried out on bearings containing varying amounts of grease, ranging from none to the nominal amount specified by the manufacturer. Features were extracted from vibration signals that were obtained using an accelerometer mounted on the cooling fan. Measurements were performed on fans operated at various temperatures and speeds. The changes observed in the vibration signals as a function of the operating speed and temperature were utilized to develop features which enable the classification of the bearings according to the amount of grease in the bearing. Finally, a classification method for the detection of under-lubricated bearings was developed using the dependence between the features, temperature, and operating speed. This method can be used as a rapid method for acceptance testing of bearings.
{"title":"Detection of under-lubricated ball bearings using vibration signals","authors":"Ranjith-Kumar Sreenilayam-Raveendran, M. Azarian, M. Pecht, E. Rhem","doi":"10.1109/ICPHM.2013.6621431","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621431","url":null,"abstract":"Reduction in the lubricant level of a bearing will reduce the operating life of the bearing. This condition is a concern in lightly loaded bearings, such as cooling fans in electronics applications, whose life is dependent on the service life of the lubricant. If these bearings are manufactured with a sub-optimal amount of lubricant, the degradation of lubricant as well as the wear processes in the bearing can be accelerated, thereby leading to early failures of the fans. Measurements were carried out on bearings containing varying amounts of grease, ranging from none to the nominal amount specified by the manufacturer. Features were extracted from vibration signals that were obtained using an accelerometer mounted on the cooling fan. Measurements were performed on fans operated at various temperatures and speeds. The changes observed in the vibration signals as a function of the operating speed and temperature were utilized to develop features which enable the classification of the bearings according to the amount of grease in the bearing. Finally, a classification method for the detection of under-lubricated bearings was developed using the dependence between the features, temperature, and operating speed. This method can be used as a rapid method for acceptance testing of bearings.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"61 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":"127908203","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.2013.6621418
Yongzhi Qu, Junda Zhu, D. He, Bin Qiu, Eric Bechhoefer
Acoustic emission (AE) has been studied as a potential information source for machine fault diagnosis for a long time. However, AE sensors have not yet been applied widely in real applications. Firstly, in comparison with other sensors such as vibration, AE sensors require much higher sampling rate. The characteristic frequency of AE signals generally falls into the range of 100 kHz to several MHz, which requires a sampling system with at least 5MHz sampling rate. Secondly, the storage and computational burden for large volume of AE data is tremendous. Thirdly, AE signal generally contains certain nonstationary behaviors which make traditional frequency analysis ineffective. In this paper, a frequency reduction technique and a modified time synchronous average (TSA) based signal processing method are proposed to identify gear fault using AE signals. Heterodyne technique commonly used in communication is employed to preprocess the AE signals before sampling. By heterodyning, the AE signal frequency is down shifted from several hundred kHz to below 50 kHz. Then a low sampling rate comparable to that of vibration sensors could be applied to sample the AE signals. After that, a modified tachometer less TSA method is adopted to further analyze the AE signal feature. Instead of performing TSA on the raw signals, the time synchronous averaging of the first order harmonic signal is obtained and analyzed. With the presented method, no tachometer or real time phase reference signal is required. The TSA reference signal is directly obtained from AE signals. By examining the smoothness of obtained wave form, a noticeable discontinuity or irregularity could be easily observed for gear fault diagnosis. AE data collected from seeded fault tests on a gearbox are used to validate the proposed method. The analysis results of the tests have shown that the proposed method could reliably and accurately detect the tooth fault.
{"title":"Development of a new acoustic emission based fault diagnosis tool for gearbox","authors":"Yongzhi Qu, Junda Zhu, D. He, Bin Qiu, Eric Bechhoefer","doi":"10.1109/ICPHM.2013.6621418","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621418","url":null,"abstract":"Acoustic emission (AE) has been studied as a potential information source for machine fault diagnosis for a long time. However, AE sensors have not yet been applied widely in real applications. Firstly, in comparison with other sensors such as vibration, AE sensors require much higher sampling rate. The characteristic frequency of AE signals generally falls into the range of 100 kHz to several MHz, which requires a sampling system with at least 5MHz sampling rate. Secondly, the storage and computational burden for large volume of AE data is tremendous. Thirdly, AE signal generally contains certain nonstationary behaviors which make traditional frequency analysis ineffective. In this paper, a frequency reduction technique and a modified time synchronous average (TSA) based signal processing method are proposed to identify gear fault using AE signals. Heterodyne technique commonly used in communication is employed to preprocess the AE signals before sampling. By heterodyning, the AE signal frequency is down shifted from several hundred kHz to below 50 kHz. Then a low sampling rate comparable to that of vibration sensors could be applied to sample the AE signals. After that, a modified tachometer less TSA method is adopted to further analyze the AE signal feature. Instead of performing TSA on the raw signals, the time synchronous averaging of the first order harmonic signal is obtained and analyzed. With the presented method, no tachometer or real time phase reference signal is required. The TSA reference signal is directly obtained from AE signals. By examining the smoothness of obtained wave form, a noticeable discontinuity or irregularity could be easily observed for gear fault diagnosis. AE data collected from seeded fault tests on a gearbox are used to validate the proposed method. The analysis results of the tests have shown that the proposed method could reliably and accurately detect the tooth fault.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"47 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":"133459709","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.2013.6621419
Rogério Ishibashi, Cairo Lúcio Nascimento Júnior
This paper presents an approach to predict the Remaining Useful Life (RUL) of a generic system when a higher level of interpretability of the prediction model is desired. A set of well known computational intelligence techniques such as Decision Trees, Fuzzy Logic, and Genetic Algorithms is used to generate a hybrid model which is called Genetic Fuzzy Rule-Based System (GFRBS) supported by a Decision Tree. The proposed method automatically generates fuzzy rules and tunes the associated membership functions. Accuracy and improved interpretability are achieved during training since they are coded in the fitness function used by the genetic algorithm. The proposed approach is applied to a case study of degradation of aeronautical engines. The task is to estimate the remaining useful life of a commercial aircraft engine using only historical data gathered by the sensors embedded in the engine.
{"title":"GFRBS-PHM: A Genetic Fuzzy Rule-Based System for PHM with improved interpretability","authors":"Rogério Ishibashi, Cairo Lúcio Nascimento Júnior","doi":"10.1109/ICPHM.2013.6621419","DOIUrl":"https://doi.org/10.1109/ICPHM.2013.6621419","url":null,"abstract":"This paper presents an approach to predict the Remaining Useful Life (RUL) of a generic system when a higher level of interpretability of the prediction model is desired. A set of well known computational intelligence techniques such as Decision Trees, Fuzzy Logic, and Genetic Algorithms is used to generate a hybrid model which is called Genetic Fuzzy Rule-Based System (GFRBS) supported by a Decision Tree. The proposed method automatically generates fuzzy rules and tunes the associated membership functions. Accuracy and improved interpretability are achieved during training since they are coded in the fitness function used by the genetic algorithm. The proposed approach is applied to a case study of degradation of aeronautical engines. The task is to estimate the remaining useful life of a commercial aircraft engine using only historical data gathered by the sensors embedded in the engine.","PeriodicalId":178906,"journal":{"name":"2013 IEEE Conference on Prognostics and Health Management (PHM)","volume":"208 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":"115748699","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：