Pub Date : 2020-06-01DOI: 10.1109/ICPHM49022.2020.9187043
Alex Falcon, Giovanni D'Agostino, G. Serra, G. Brajnik, C. Tasso
Estimating the Remaining Useful Life of a mechanical device is one of the most important problems in the Prognostics and Health Management field. Being able to reliably estimate such value can lead to an improvement of the maintenance scheduling and a reduction of the costs associated with it. Given the availability of high quality sensors able to measure several aspects of the components, it is possible to gather a huge amount of data which can be used to tune precise data-driven models. Deep learning approaches, especially those based on Long-Short Term Memory networks, achieved great results recently and thus seem to be capable of effectively dealing with the problem. A recent advancement in neural network architectures, which yielded noticeable improvements in several different fields, consists in the usage of an external memory which allows the model to store inferred fragments of knowledge that can be later accessed and manipulated. To further improve the precision obtained thus far, in this paper we propose a novel way to address the Remaining Useful Life estimation problem by giving an LSTM-based model the ability to interact with a content-based memory addressing system. To demonstrate the improvements obtainable by this model, we successfully used it to estimate the remaining useful life of a turbofan engine using a benchmark dataset published by NASA. Finally, we present an exhaustive comparison to several approaches in the literature.
{"title":"A Neural Turing Machine-based approach to Remaining Useful Life Estimation","authors":"Alex Falcon, Giovanni D'Agostino, G. Serra, G. Brajnik, C. Tasso","doi":"10.1109/ICPHM49022.2020.9187043","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187043","url":null,"abstract":"Estimating the Remaining Useful Life of a mechanical device is one of the most important problems in the Prognostics and Health Management field. Being able to reliably estimate such value can lead to an improvement of the maintenance scheduling and a reduction of the costs associated with it. Given the availability of high quality sensors able to measure several aspects of the components, it is possible to gather a huge amount of data which can be used to tune precise data-driven models. Deep learning approaches, especially those based on Long-Short Term Memory networks, achieved great results recently and thus seem to be capable of effectively dealing with the problem. A recent advancement in neural network architectures, which yielded noticeable improvements in several different fields, consists in the usage of an external memory which allows the model to store inferred fragments of knowledge that can be later accessed and manipulated. To further improve the precision obtained thus far, in this paper we propose a novel way to address the Remaining Useful Life estimation problem by giving an LSTM-based model the ability to interact with a content-based memory addressing system. To demonstrate the improvements obtainable by this model, we successfully used it to estimate the remaining useful life of a turbofan engine using a benchmark dataset published by NASA. Finally, we present an exhaustive comparison to several approaches in the literature.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126264894","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 : 2020-06-01DOI: 10.1109/ICPHM49022.2020.9187033
A. Abbasi, F. Nazari, C. Nataraj
Condition-based maintenance (CBM) is a predictive maintenance strategy that monitors the machinery states and provides optimum sets of maintenance decisions. Diagnostics and prognostics are considered to be the main aspects of CBM which are used for assessment of the monitored states. Diagnostics focuses on the detection, isolation and identification of faults while prognostics determines whether the faults or failures are forthcoming or how soon they will occur. The importance of precise prediction on the potential problems of an asset have made prognostics the topic of much recent scholarly research. Crack propagation in mechanical systems is considered as one of the main sources of mechanical failure that can bring about catastrophic consequences. Hence, obtaining a precise model for the crack propagation is crucial from the maintenance point of view. The current paper takes advantage of long short-term memory (LSTM) neural networks’ ability in forecasting the evaluation of the sequential date in predicting crack growth. The presented approach is applied to the Virkler crack growth dataset. The effectiveness of the proposed method is demonstrated by post-processing the outputs of the LSTM neural network.
{"title":"Application of Long Short-Term Memory Neural Network to Crack Propagation Prognostics","authors":"A. Abbasi, F. Nazari, C. Nataraj","doi":"10.1109/ICPHM49022.2020.9187033","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187033","url":null,"abstract":"Condition-based maintenance (CBM) is a predictive maintenance strategy that monitors the machinery states and provides optimum sets of maintenance decisions. Diagnostics and prognostics are considered to be the main aspects of CBM which are used for assessment of the monitored states. Diagnostics focuses on the detection, isolation and identification of faults while prognostics determines whether the faults or failures are forthcoming or how soon they will occur. The importance of precise prediction on the potential problems of an asset have made prognostics the topic of much recent scholarly research. Crack propagation in mechanical systems is considered as one of the main sources of mechanical failure that can bring about catastrophic consequences. Hence, obtaining a precise model for the crack propagation is crucial from the maintenance point of view. The current paper takes advantage of long short-term memory (LSTM) neural networks’ ability in forecasting the evaluation of the sequential date in predicting crack growth. The presented approach is applied to the Virkler crack growth dataset. The effectiveness of the proposed method is demonstrated by post-processing the outputs of the LSTM neural network.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126282916","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 : 2020-06-01DOI: 10.1109/ICPHM49022.2020.9187024
Yan Zhang, H. Wei, Qingqing Huang, Jin Guo
The vibration characteristics of rolling bearings under variable speed are time-varying, which brings great difficulties to fault diagnosis. An iterative time-frequency (TF) curve extraction and demodulation based method is proposed for fault diagnosis of bearings under variable speed. The envelope of the vibration signal is firstly extracted by utilizing Hilbert transform, and the instantaneous frequency associated with each envelope component can be iteratively estimated based on curve extraction from the reassigned time-frequency spectrogram derived using synchrosqueezing transform (SST). Secondly, The instantaneous fault characteristic frequency (IFCF) of bearing is extracted, and the phase mapping function for generalized demodulation is further estimated. Thirdly, the envelope signal is generalized demodulation processed with the phase mapping function, which is computed based on the IFCF, then the time-varying component is converted into a component of constant frequency. Finally, spectrum analysis is applied to the demodulated signal to identify the bearing fault characteristics. The effectiveness of this proposed method are verified using simulation data and the bearing vibration data measured under variable speed conditions.
{"title":"Bearing Fault Diagnosis Under Variable Speed Based on Iterative TF Curve Extraction and Demodulation","authors":"Yan Zhang, H. Wei, Qingqing Huang, Jin Guo","doi":"10.1109/ICPHM49022.2020.9187024","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187024","url":null,"abstract":"The vibration characteristics of rolling bearings under variable speed are time-varying, which brings great difficulties to fault diagnosis. An iterative time-frequency (TF) curve extraction and demodulation based method is proposed for fault diagnosis of bearings under variable speed. The envelope of the vibration signal is firstly extracted by utilizing Hilbert transform, and the instantaneous frequency associated with each envelope component can be iteratively estimated based on curve extraction from the reassigned time-frequency spectrogram derived using synchrosqueezing transform (SST). Secondly, The instantaneous fault characteristic frequency (IFCF) of bearing is extracted, and the phase mapping function for generalized demodulation is further estimated. Thirdly, the envelope signal is generalized demodulation processed with the phase mapping function, which is computed based on the IFCF, then the time-varying component is converted into a component of constant frequency. Finally, spectrum analysis is applied to the demodulated signal to identify the bearing fault characteristics. The effectiveness of this proposed method are verified using simulation data and the bearing vibration data measured under variable speed conditions.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130260686","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 : 2020-06-01DOI: 10.1109/ICPHM49022.2020.9187051
Xiaoyu Shi, Yuhua Cheng, Bo Zhang, Haonan Zhang
Bearings are necessary rotating machinery and plays an important role in the modern industrial systems for its safety and reliability. Timely fault diagnosis of bearings can reduce the probability of failure, thereby reducing economic losses and casualties. Many signal processing methods for fault feature extraction and fault recognition have been applied by scholars and engineers. Although numerous current methods identify and diagnose bearing faults correctly, they rely on a lot of existing information and experts experience, so it is not possible to establish a one-to-one correspondence between the original signal and the failure mode. Furthermore, the structure and parameters of the artificial intelligent neural network need to be optimized through experts and current knowledge. Alexnet neural network improves the learning ability and provides inspiration and direction for the above problem. The ensemble empirical mode decomposition (EEMD) solve the problem of mode mixing. The wavelet transform could impose the time and frequency features. Combing the prior of EEMD with continue wavelet transform, an adaptive fault feature model has been constructed that can directly provide the information to corresponding with the fault classified neural network. In this approach, fault signals are enhanced by extracting envelope decomposition and frequency signals. Numerous bearing data which containing different fault signals are used to verify the effectiveness and accuracy of the proposed method. The diagnosis results show that the novel alexnet neural network classifies bearings fault with high accuracy and robustness under complexity environment.
{"title":"Intelligent fault diagnosis of bearings based on feature model and Alexnet neural network","authors":"Xiaoyu Shi, Yuhua Cheng, Bo Zhang, Haonan Zhang","doi":"10.1109/ICPHM49022.2020.9187051","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187051","url":null,"abstract":"Bearings are necessary rotating machinery and plays an important role in the modern industrial systems for its safety and reliability. Timely fault diagnosis of bearings can reduce the probability of failure, thereby reducing economic losses and casualties. Many signal processing methods for fault feature extraction and fault recognition have been applied by scholars and engineers. Although numerous current methods identify and diagnose bearing faults correctly, they rely on a lot of existing information and experts experience, so it is not possible to establish a one-to-one correspondence between the original signal and the failure mode. Furthermore, the structure and parameters of the artificial intelligent neural network need to be optimized through experts and current knowledge. Alexnet neural network improves the learning ability and provides inspiration and direction for the above problem. The ensemble empirical mode decomposition (EEMD) solve the problem of mode mixing. The wavelet transform could impose the time and frequency features. Combing the prior of EEMD with continue wavelet transform, an adaptive fault feature model has been constructed that can directly provide the information to corresponding with the fault classified neural network. In this approach, fault signals are enhanced by extracting envelope decomposition and frequency signals. Numerous bearing data which containing different fault signals are used to verify the effectiveness and accuracy of the proposed method. The diagnosis results show that the novel alexnet neural network classifies bearings fault with high accuracy and robustness under complexity environment.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130850562","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 : 2020-06-01DOI: 10.1109/ICPHM49022.2020.9187041
V. Rathod, Subrata Mukherjee, L. Udpa, Y. Deng
Delamination is the most common type of damage that can occur in a composite structure at a very early stage of its operation. Detection, localization and classification of delamination parameters in composite laminates assist in determining the operating condition of the structure. Such a task, especially involving global localization on the structure and local localization along the thickness of the laminate is difficult using guided waves that are inherently multimodal leading to complicated mixed mode response of transducers. This paper proposes the use of embedded thin film sensors to decouple the response due to each wave mode enabling easy interpretation of the signals for damage detection. Delamination damage has been considered and the strength of reflected guided wave modes has been studied in the purview of delamination localization along with the thickness. The variation of mode conversion strength for fundamental and higher order wave modes further provides additional data to determine the delamination parameters.
{"title":"Extracting Mode Converted Guided Wave Response due to Delamination using Embedded Thin Film Sensors","authors":"V. Rathod, Subrata Mukherjee, L. Udpa, Y. Deng","doi":"10.1109/ICPHM49022.2020.9187041","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187041","url":null,"abstract":"Delamination is the most common type of damage that can occur in a composite structure at a very early stage of its operation. Detection, localization and classification of delamination parameters in composite laminates assist in determining the operating condition of the structure. Such a task, especially involving global localization on the structure and local localization along the thickness of the laminate is difficult using guided waves that are inherently multimodal leading to complicated mixed mode response of transducers. This paper proposes the use of embedded thin film sensors to decouple the response due to each wave mode enabling easy interpretation of the signals for damage detection. Delamination damage has been considered and the strength of reflected guided wave modes has been studied in the purview of delamination localization along with the thickness. The variation of mode conversion strength for fundamental and higher order wave modes further provides additional data to determine the delamination parameters.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132868998","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 : 2020-06-01DOI: 10.1109/ICPHM49022.2020.9187037
Qingqing Huang, Zhen Kang, Yan Zhang, Dong Yan
The real-time prediction of tool remaining useful life is a challenging problem. This paper proposes a Long Short-Term Memory (LSTM) recurrent neural network model, which is combined with an edge data processing method to predict the tool remaining useful life in real-time. Data cleaning and feature extraction are carried out at the edge node to reduce the transmission time, save the transmission cost and improve the real-time performance of life prediction. After further feature selection in the cloud, a simple three-layer LSTM recurrent neural network model is established. Compared with the tree model and the ordinary neural network model, the experimental results show that the LSTM model has better performance of the tool remaining useful life prediction.
{"title":"Tool Remaining Useful Life Prediction based on Edge Data Processing and LSTM Recurrent Neural Network","authors":"Qingqing Huang, Zhen Kang, Yan Zhang, Dong Yan","doi":"10.1109/ICPHM49022.2020.9187037","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187037","url":null,"abstract":"The real-time prediction of tool remaining useful life is a challenging problem. This paper proposes a Long Short-Term Memory (LSTM) recurrent neural network model, which is combined with an edge data processing method to predict the tool remaining useful life in real-time. Data cleaning and feature extraction are carried out at the edge node to reduce the transmission time, save the transmission cost and improve the real-time performance of life prediction. After further feature selection in the cloud, a simple three-layer LSTM recurrent neural network model is established. Compared with the tree model and the ordinary neural network model, the experimental results show that the LSTM model has better performance of the tool remaining useful life prediction.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133413339","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 : 2020-06-01DOI: 10.1109/ICPHM49022.2020.9187040
Ali Al-Dulaimi, A. Asif, Arash Mohammadi
The paper introduces a multi-path parallel hybrid deep neural design for remaining useful life (RUL) estimation of critical infrastructure, referred to as the MPHD. The proposed framework integrates three noisy deep learning structures in parallel: (a) A noisy path uses Long Short-Term Memory (LSTM), (b) A noisy path uses Gated Recurrent Unit (GRU), and; (c) A noisy path uses Convolutional Neural Network (CNN), The proposed framework aims to collect different types of features from the most popular deep neural networks architectures and then utilizing a fusion center consists of noisy fully connected multilayer neural network, to combine the collected features of the three parallel paths and predict the RLU. The MPHD framework utilizes noisy training to improve accuracy, enhance robustness, and mitigate the overfitting problem associated with neural networks. The proposed model is evaluated by utilizing (CMAPSS) dataset, which is provided by NASA.
{"title":"Multipath Parallel Hybrid Deep Neural Networks Framework for Remaining Useful Life Estimation","authors":"Ali Al-Dulaimi, A. Asif, Arash Mohammadi","doi":"10.1109/ICPHM49022.2020.9187040","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187040","url":null,"abstract":"The paper introduces a multi-path parallel hybrid deep neural design for remaining useful life (RUL) estimation of critical infrastructure, referred to as the MPHD. The proposed framework integrates three noisy deep learning structures in parallel: (a) A noisy path uses Long Short-Term Memory (LSTM), (b) A noisy path uses Gated Recurrent Unit (GRU), and; (c) A noisy path uses Convolutional Neural Network (CNN), The proposed framework aims to collect different types of features from the most popular deep neural networks architectures and then utilizing a fusion center consists of noisy fully connected multilayer neural network, to combine the collected features of the three parallel paths and predict the RLU. The MPHD framework utilizes noisy training to improve accuracy, enhance robustness, and mitigate the overfitting problem associated with neural networks. The proposed model is evaluated by utilizing (CMAPSS) dataset, which is provided by NASA.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121324578","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 : 2020-06-01DOI: 10.1109/ICPHM49022.2020.9187061
Jinhyuck Choi, Jinwoo Lee, Wonjeong Cho
To enhance the reliability and availability of an asset in its life, predicting the remaining useful life of an asset is strongly encouraged by assessing the extent of deviation or degradation of the asset's monitored parameters from its expected normal operating conditions. Although intelligent fault prognostic techniques such as machine learning and artificial neural networks have been applied in modern industries, application in actual industrial conditions requires that the forecasting process is revealed and more descriptive. To investigate the issue and increase the accuracy, this paper proposes an additional technique that can be further applied to any recent intelligent prognostic methods. The proposed method consists of two steps. First, the entire training set is divided into several degradation stages before regression using a heuristic approach and then the regression results are synthesized for each stage. The proposed method will increase the monotonicity of the predictive parameters, thus helping improve the predictive model's accuracy. To demonstrate the hypothesis, real condition monitoring data of high-pressure LNG pump and acceleration experimental data of a rotating machine is used for an experiment. Moreover, a system in which the proposed method can be appropriately executed is introduced with Lambda architecture. Finally, by demonstrating that the proposed method is capable of parallel computing, it is proven suitable for use in the proposed large-scale distributed processing system.
{"title":"Prognostics by classifying degradation stage on Lambda architecture","authors":"Jinhyuck Choi, Jinwoo Lee, Wonjeong Cho","doi":"10.1109/ICPHM49022.2020.9187061","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187061","url":null,"abstract":"To enhance the reliability and availability of an asset in its life, predicting the remaining useful life of an asset is strongly encouraged by assessing the extent of deviation or degradation of the asset's monitored parameters from its expected normal operating conditions. Although intelligent fault prognostic techniques such as machine learning and artificial neural networks have been applied in modern industries, application in actual industrial conditions requires that the forecasting process is revealed and more descriptive. To investigate the issue and increase the accuracy, this paper proposes an additional technique that can be further applied to any recent intelligent prognostic methods. The proposed method consists of two steps. First, the entire training set is divided into several degradation stages before regression using a heuristic approach and then the regression results are synthesized for each stage. The proposed method will increase the monotonicity of the predictive parameters, thus helping improve the predictive model's accuracy. To demonstrate the hypothesis, real condition monitoring data of high-pressure LNG pump and acceleration experimental data of a rotating machine is used for an experiment. Moreover, a system in which the proposed method can be appropriately executed is introduced with Lambda architecture. Finally, by demonstrating that the proposed method is capable of parallel computing, it is proven suitable for use in the proposed large-scale distributed processing system.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120938346","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 : 2020-06-01DOI: 10.1109/ICPHM49022.2020.9187031
R. Palanisamy, P. Banerjee, Subrata Mukherjee, M. Haq, Y. Deng
Adhesive bonding have been increasingly employed in composite structures owing to several advantages over mechanically fastened or riveted joints. Adhesively bonded composite lap joints not only yield light-weighted structures but also provide a more uniform stress distribution than riveted joints resulting in higher fatigue life. However, modeling the physics behind crack initiation and propagation inside bonded regions is challenging especially under fatigue loading. As a result, NDE techniques such as guided wave sensing is required to monitor composite lap-joints. In addition to monitoring the damage state, prediction of disbond area inside the joints or the remaining useful life of the structure is imperative. This paper discusses a guided wave sensing technique to monitor damage area in Glass Fiber Reinforced Plastic (GFRP) lap-joints. Further, a damage propagation model based on Paris law is developed to estimate remaining useful life in terms of the GW signal features. Finally, the remaining useful life of the lap-joint is predicted for lap-joints subjected to fatigue cycles.
{"title":"Fatigue damage prognosis in adhesive bonded composite lap-joints using guided waves","authors":"R. Palanisamy, P. Banerjee, Subrata Mukherjee, M. Haq, Y. Deng","doi":"10.1109/ICPHM49022.2020.9187031","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187031","url":null,"abstract":"Adhesive bonding have been increasingly employed in composite structures owing to several advantages over mechanically fastened or riveted joints. Adhesively bonded composite lap joints not only yield light-weighted structures but also provide a more uniform stress distribution than riveted joints resulting in higher fatigue life. However, modeling the physics behind crack initiation and propagation inside bonded regions is challenging especially under fatigue loading. As a result, NDE techniques such as guided wave sensing is required to monitor composite lap-joints. In addition to monitoring the damage state, prediction of disbond area inside the joints or the remaining useful life of the structure is imperative. This paper discusses a guided wave sensing technique to monitor damage area in Glass Fiber Reinforced Plastic (GFRP) lap-joints. Further, a damage propagation model based on Paris law is developed to estimate remaining useful life in terms of the GW signal features. Finally, the remaining useful life of the lap-joint is predicted for lap-joints subjected to fatigue cycles.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133825013","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 : 2020-06-01DOI: 10.1109/ICPHM49022.2020.9187035
H. Rasay, F. Naderkhani
From quality and reliability perspectives, acceptance sampling plans play a significant role in manufacturing and industries in order to minimize the defect in the process. It is essential that the final product received by the customers, either external or internal, to be defect-free. In this regard, this paper presents the special case of acceptance sampling plan referred to as quick switching sampling (QSS) plan in the context of failure censoring reliability tests by considering the information from lifetime performance index (LPI). Unlike the common process capability indexes, LPI is usually appropriate for processes with non-negative quality characteristics. It is assumed that the lifetime of items follows Weibull distribution. Derivations of the operating characteristic curves are developed and a mathematical model is presented which determines the optimal parameters of the QSS plan. In order to see the effectiveness of proposed QSS, a real example is presented. In addition, different sensitivity analyses are conducted which the results indicate that proposed QSS plan can significantly decrease the costs of the life testing and sampling in comparison with a single sampling plan.
{"title":"Designing a Reliability Quick Switching Sampling Plan based on the Lifetime Performance Index","authors":"H. Rasay, F. Naderkhani","doi":"10.1109/ICPHM49022.2020.9187035","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187035","url":null,"abstract":"From quality and reliability perspectives, acceptance sampling plans play a significant role in manufacturing and industries in order to minimize the defect in the process. It is essential that the final product received by the customers, either external or internal, to be defect-free. In this regard, this paper presents the special case of acceptance sampling plan referred to as quick switching sampling (QSS) plan in the context of failure censoring reliability tests by considering the information from lifetime performance index (LPI). Unlike the common process capability indexes, LPI is usually appropriate for processes with non-negative quality characteristics. It is assumed that the lifetime of items follows Weibull distribution. Derivations of the operating characteristic curves are developed and a mathematical model is presented which determines the optimal parameters of the QSS plan. In order to see the effectiveness of proposed QSS, a real example is presented. In addition, different sensitivity analyses are conducted which the results indicate that proposed QSS plan can significantly decrease the costs of the life testing and sampling in comparison with a single sampling plan.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115629076","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：