Pub Date : 2020-06-01DOI: 10.1109/ICPHM49022.2020.9187022
Kamyar Azar, F. Naderkhani
Recent heightened enthusiasm towards Industrial Artificial Intelligence (IAI) and Industrial Internet of Things (IIoT) coupled with developments in smart sensor technologies have resulted in simultaneous incorporation of several advanced Condition Monitoring (CM) technologies within manufacturing and industrial sectors. Efficient utilization of CM data leads to enhanced safety, reliability and availability of manufacturing systems. In this regard, the paper proposes an efficient and novel hybrid Maintenance Decision Support System (MDSS) for fault diagnostic and prognostic considering CM data along with event- triggered data. The proposed MDSS model is a hybrid Machine Learning (ML)-based solution coupled with statistical techniques. In order to find an optimal maintenance policy, we concentrate the attention on a time-dependent Proportional Hazards Model (PHM) augmented with a semi-supervised ML approach. The developed hybrid model is capable of inferring and fusing High-Dimensional and Multi-modal Streaming (HDMS) data sources in an adaptive and autonomous fashion to recommend optimal maintenance decisions without human intervention. To illustrate the complete structure of the proposed MDSS, experimental evaluations are designed based on a dataset provided by NASA containing run-to-failure and CM data associated with aircraft engines. The effectiveness of the proposed model is demonstrated through a comprehensive set of comparisons with different ML algorithms.
{"title":"Semi-Supervised Learning Approach for Optimizing Condition-based-Maintenance (CBM) Decisions","authors":"Kamyar Azar, F. Naderkhani","doi":"10.1109/ICPHM49022.2020.9187022","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187022","url":null,"abstract":"Recent heightened enthusiasm towards Industrial Artificial Intelligence (IAI) and Industrial Internet of Things (IIoT) coupled with developments in smart sensor technologies have resulted in simultaneous incorporation of several advanced Condition Monitoring (CM) technologies within manufacturing and industrial sectors. Efficient utilization of CM data leads to enhanced safety, reliability and availability of manufacturing systems. In this regard, the paper proposes an efficient and novel hybrid Maintenance Decision Support System (MDSS) for fault diagnostic and prognostic considering CM data along with event- triggered data. The proposed MDSS model is a hybrid Machine Learning (ML)-based solution coupled with statistical techniques. In order to find an optimal maintenance policy, we concentrate the attention on a time-dependent Proportional Hazards Model (PHM) augmented with a semi-supervised ML approach. The developed hybrid model is capable of inferring and fusing High-Dimensional and Multi-modal Streaming (HDMS) data sources in an adaptive and autonomous fashion to recommend optimal maintenance decisions without human intervention. To illustrate the complete structure of the proposed MDSS, experimental evaluations are designed based on a dataset provided by NASA containing run-to-failure and CM data associated with aircraft engines. The effectiveness of the proposed model is demonstrated through a comprehensive set of comparisons with different ML algorithms.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"21 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":"115612039","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/ICPHM49022.2020.9187046
Safwan Ahmad, Nastaran Enshaei, F. Naderkhani, Anjali Awasthi
Advancements in online sensing technologies and wireless networking has reshaped the competitive landscape of manufacturing systems, leading to exponential growth of data. Among various data types, high-dimensional data sources such as images and videos play an important role in process monitoring. Efficient utilization of such sources can help systems reach high accuracy in fault diagnosis. On the other hand, while the researches on statistical process control (SPC) tools are tremendous, the application of SPC tools considering high-dimensional data sets has received less attention due to their complexity. In this paper, we try to address this gap by designing and developing a hybrid model based on deep learning (DL) and SPC models to monitor the manufacturing process in presence of high-dimensional data. In particular, we first apply a Fast Region-based Convolutional Network method referred to Fast R-CNN in order to monitor the image sequences over time. Then, some statistical features are derived and plotted on the multivariate exponentially weighted moving average (EWMA) control chart. The effectiveness of proposed hybrid model is illustrated through a numerical example.
{"title":"Integrated Deep Learning and Statistical Process Control for Online Monitoring of Manufacturing Processes","authors":"Safwan Ahmad, Nastaran Enshaei, F. Naderkhani, Anjali Awasthi","doi":"10.1109/ICPHM49022.2020.9187046","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187046","url":null,"abstract":"Advancements in online sensing technologies and wireless networking has reshaped the competitive landscape of manufacturing systems, leading to exponential growth of data. Among various data types, high-dimensional data sources such as images and videos play an important role in process monitoring. Efficient utilization of such sources can help systems reach high accuracy in fault diagnosis. On the other hand, while the researches on statistical process control (SPC) tools are tremendous, the application of SPC tools considering high-dimensional data sets has received less attention due to their complexity. In this paper, we try to address this gap by designing and developing a hybrid model based on deep learning (DL) and SPC models to monitor the manufacturing process in presence of high-dimensional data. In particular, we first apply a Fast Region-based Convolutional Network method referred to Fast R-CNN in order to monitor the image sequences over time. Then, some statistical features are derived and plotted on the multivariate exponentially weighted moving average (EWMA) control chart. The effectiveness of proposed hybrid model is illustrated through a numerical example.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"19 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":"125283713","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/ICPHM49022.2020.9187045
J. Zhu, K. Sundaresan, J. Rupe
Proactive network maintenance (PNM) is the concept of using data from a network to identify and locate network faults, many or all of which could worsen to become service failures. The separation between the network fault and the service failure affords early detection of problems in the network to allow PNM to take place. Consequently, PNM is a form of prognostics and health management (PHM).The problem of localizing and classifying anomalies on 1-dimensional data series has been under research for years. We introduce a new algorithm that leverages Deep Convolutional Neural Networks to efficiently and accurately detect anomalies and events on data series, and it reaches 97.82% mean average precision (mAP) in our evaluation.
{"title":"Proactive Network Maintenance using Fast, Accurate Anomaly Localization and Classification on 1-D Data Series","authors":"J. Zhu, K. Sundaresan, J. Rupe","doi":"10.1109/ICPHM49022.2020.9187045","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187045","url":null,"abstract":"Proactive network maintenance (PNM) is the concept of using data from a network to identify and locate network faults, many or all of which could worsen to become service failures. The separation between the network fault and the service failure affords early detection of problems in the network to allow PNM to take place. Consequently, PNM is a form of prognostics and health management (PHM).The problem of localizing and classifying anomalies on 1-dimensional data series has been under research for years. We introduce a new algorithm that leverages Deep Convolutional Neural Networks to efficiently and accurately detect anomalies and events on data series, and it reaches 97.82% mean average precision (mAP) in our evaluation.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"389 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":"116491001","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/ICPHM49022.2020.9187054
G. G. Lee, Myungkyo Jung, Myoungwoo Song, J. Choo
This paper proposes a combination of convolutional neural network and auto-encoder (CAE) for unsupervised anomaly detection of industrial gas turbines. Autonomous monitoring systems protect the gas turbines, with the settings unchanged in their lifetime. Those systems can not detect any abnormal operation patterns which potentially risk the equipment after long-term exposure. Recently, machine learning and deep learning models are applied for industries to detect those anomalies under the nominal working range. However, for gas turbine protection, not much deep learning (DL) models are introduced. The proposed CAE detects irregular signals in unsupervised learning by combining a convolutional neural network (CNN) and auto-encoder (AE). CNN exponentially reduces the computational cost and decrease the amount of training data, by its extraction capabilities of essential features in spatial input data. A CAE identifies the anomalies by adapting characteristics of an AE, which identifies any errors larger than usual pre-trained, reconstructed errors. Using the Keras library, we developed an AE structure in one-dimensional convolution layer networks. We used actual plant operation data set for performance evaluation with conventional machine learning (ML) models. Compared to the isolation forest (iforest), k-means clustering (k-means), and one-class support vector machine (OCSVM), our model accurately predicts unusual signal patterns identified in the actual operation than conventional ML models.
{"title":"Unsupervised anomaly detection of the gas turbine operation via convolutional auto-encoder","authors":"G. G. Lee, Myungkyo Jung, Myoungwoo Song, J. Choo","doi":"10.1109/ICPHM49022.2020.9187054","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187054","url":null,"abstract":"This paper proposes a combination of convolutional neural network and auto-encoder (CAE) for unsupervised anomaly detection of industrial gas turbines. Autonomous monitoring systems protect the gas turbines, with the settings unchanged in their lifetime. Those systems can not detect any abnormal operation patterns which potentially risk the equipment after long-term exposure. Recently, machine learning and deep learning models are applied for industries to detect those anomalies under the nominal working range. However, for gas turbine protection, not much deep learning (DL) models are introduced. The proposed CAE detects irregular signals in unsupervised learning by combining a convolutional neural network (CNN) and auto-encoder (AE). CNN exponentially reduces the computational cost and decrease the amount of training data, by its extraction capabilities of essential features in spatial input data. A CAE identifies the anomalies by adapting characteristics of an AE, which identifies any errors larger than usual pre-trained, reconstructed errors. Using the Keras library, we developed an AE structure in one-dimensional convolution layer networks. We used actual plant operation data set for performance evaluation with conventional machine learning (ML) models. Compared to the isolation forest (iforest), k-means clustering (k-means), and one-class support vector machine (OCSVM), our model accurately predicts unusual signal patterns identified in the actual operation than conventional ML models.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"222 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":"131691661","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}
Remaining useful life (RUL) prediction is a key component of reliability evaluation and conditional-basedmaintenance (CBM). In the existing prediction methods, neural networks (NNs) are widely used because of the high accuracy. However, most of the traditional NNs prediction methods only focus on accuracy without the ability in handling the problem of uncertainty, where the generalization of the method is limited and their application to practical application are challenging. In this paper, an efficient prediction method based on the Bayesian Neural Network (BNN) is proposed. Network weights are assumed to follow the Gaussian distribution, based on which they can be updated by Bayes’ theorem and the confidence interval (CI) is consequently derived. The method is verified on the C-MAPSS data set published by NASA and the degradation starting point is determined via change point detection method. The experimental results demonstrate that the method performs well in prediction accuracy with the capability of the uncertainty quantification, which is critical for the condition monitoring of complex systems.
{"title":"Bayesian Neural Network Based Method of Remaining Useful Life Prediction and Uncertainty Quantification for Aircraft Engine","authors":"Dengshan Huang, Rui Bai, Shuai Zhao, Pengfei Wen, Shengyue Wang, Shaowei Chen","doi":"10.1109/ICPHM49022.2020.9187044","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187044","url":null,"abstract":"Remaining useful life (RUL) prediction is a key component of reliability evaluation and conditional-basedmaintenance (CBM). In the existing prediction methods, neural networks (NNs) are widely used because of the high accuracy. However, most of the traditional NNs prediction methods only focus on accuracy without the ability in handling the problem of uncertainty, where the generalization of the method is limited and their application to practical application are challenging. In this paper, an efficient prediction method based on the Bayesian Neural Network (BNN) is proposed. Network weights are assumed to follow the Gaussian distribution, based on which they can be updated by Bayes’ theorem and the confidence interval (CI) is consequently derived. The method is verified on the C-MAPSS data set published by NASA and the degradation starting point is determined via change point detection method. The experimental results demonstrate that the method performs well in prediction accuracy with the capability of the uncertainty quantification, which is critical for the condition monitoring of complex systems.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"191 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":"114985290","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/ICPHM49022.2020.9187064
Nobal B. Niraula, Anne Kao, Daniel Whyatt
Aircraft maintenance records contain vital information about airplane parts and their conditions in free-form text that are crucial health indicators of an aircraft. Extraction of these types of information is essential to improve safety, and lower lifecycle maintenance cost, and to minimize downtime and spare parts inventory. The task, however, is challenging as it is a domain-specific knowledge discovery problem that poses unique challenges in the field of information extraction which have not been studied much. This paper discusses these unique issues and challenges and how we approach them by adapting an advanced deep learning technique that has been widely used for information extraction tasks in other domains. The proposed system has good performance on extracting part names and conditions from noisy texts and is shown to be effective in processing data sets across diverse types of aircraft systems.
{"title":"HPart and Condition Extraction from Aircraft Maintenance Records","authors":"Nobal B. Niraula, Anne Kao, Daniel Whyatt","doi":"10.1109/ICPHM49022.2020.9187064","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187064","url":null,"abstract":"Aircraft maintenance records contain vital information about airplane parts and their conditions in free-form text that are crucial health indicators of an aircraft. Extraction of these types of information is essential to improve safety, and lower lifecycle maintenance cost, and to minimize downtime and spare parts inventory. The task, however, is challenging as it is a domain-specific knowledge discovery problem that poses unique challenges in the field of information extraction which have not been studied much. This paper discusses these unique issues and challenges and how we approach them by adapting an advanced deep learning technique that has been widely used for information extraction tasks in other domains. The proposed system has good performance on extracting part names and conditions from noisy texts and is shown to be effective in processing data sets across diverse types of aircraft systems.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"33 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":"130067319","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/ICPHM49022.2020.9187059
M. Takanashi, Yoshinao Ishii, S. Sato, Noriyoshi Sano, K. Sanda
Recently, the maintenance and management of infrastructure, such as paved roads and bridges, at a low cost has become important. Although some measurement methods including the falling weight deflectometer test have been developed to assess the soundness of paved roads, it is difficult to measure the data in a constant manner, for instance, on a daily basis. Therefore, we present an approach as per which we install vibration sensors on paved roads and automatically detect the deterioration of the paved roads via the installed vibration sensor and a machine-learning technique.Deterioration detection techniques that exploit vibration sensors have been studied; however, those were limited to bridge monitoring. No studies for the vibration measurement of paved roads using fixed sensors have been conducted. Herein, we focus on the deterioration of paved roads, specifically, in the form of road cracks, and conduct vibration measurements that highlight the differences in the vibrations of roads with and without cracks.In this paper, we describe the vibration measurements of a paved road with and without cracks and propose a framework for detecting cracks. An anomaly detection technique is necessary for using our detection framework. In this paper, we also evaluate the detection performance using anomaly detection techniques—namely, one-class support vector machine, isolation forest, and local outlier factor—using the measured vibration data.
{"title":"Road-Deterioration Detection using Road Vibration Data with Machine-Learning Approach","authors":"M. Takanashi, Yoshinao Ishii, S. Sato, Noriyoshi Sano, K. Sanda","doi":"10.1109/ICPHM49022.2020.9187059","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187059","url":null,"abstract":"Recently, the maintenance and management of infrastructure, such as paved roads and bridges, at a low cost has become important. Although some measurement methods including the falling weight deflectometer test have been developed to assess the soundness of paved roads, it is difficult to measure the data in a constant manner, for instance, on a daily basis. Therefore, we present an approach as per which we install vibration sensors on paved roads and automatically detect the deterioration of the paved roads via the installed vibration sensor and a machine-learning technique.Deterioration detection techniques that exploit vibration sensors have been studied; however, those were limited to bridge monitoring. No studies for the vibration measurement of paved roads using fixed sensors have been conducted. Herein, we focus on the deterioration of paved roads, specifically, in the form of road cracks, and conduct vibration measurements that highlight the differences in the vibrations of roads with and without cracks.In this paper, we describe the vibration measurements of a paved road with and without cracks and propose a framework for detecting cracks. An anomaly detection technique is necessary for using our detection framework. In this paper, we also evaluate the detection performance using anomaly detection techniques—namely, one-class support vector machine, isolation forest, and local outlier factor—using the measured vibration data.","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":"123029217","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/ICPHM49022.2020.9187048
Binghao Fu, Zhenyu Wu, Juchuan Guo
In the industrial production process, the remaining useful life (RUL) of the machine part is the key factor to determine the product quality, so it is important to predict the RUL of the machine part for industrial manufacturing. With the development of intelligent manufacturing, data-driven RUL prediction has become very popular. When the training dataset and the test dataset are distributed similarly, the traditional machine learning prediction method is very effective. However, in actual production, the operation conditions of the machine part used for training and testing may be different, resulting in different distribution of data sets. In this paper, we propose a domain adaptive SAE-LSTM (DASL) model for RUL prediction of the machine part to solve this problem. The DASL model contains sparse autoencoder (SAE) and Long Short-Term Memory (LSTM) with domain adaptive mechanism. The latent features extracted by SAE from source dataset and target dataset are transformed to reproducing kernel Hilbert space (RKHS) and the distribution discrepancy is reduced by using maximum mean discrepancy (MMD). Then the latent features are input into the LSTM to predict the RUL. What is more, the case where both source data and target data are data containing multiple conditions is also considered. The proposed model is tested on Foxconn tool wear dataset and PHM Challenging 2012 dataset. The results show that the method has a better improvement. In most experiments, this method outperforms other state-of-arts' methods.
{"title":"Remaining Useful Life Prediction under Multiple Operation Conditions Based on Domain Adaptive Sparse Auto-Encoder","authors":"Binghao Fu, Zhenyu Wu, Juchuan Guo","doi":"10.1109/ICPHM49022.2020.9187048","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187048","url":null,"abstract":"In the industrial production process, the remaining useful life (RUL) of the machine part is the key factor to determine the product quality, so it is important to predict the RUL of the machine part for industrial manufacturing. With the development of intelligent manufacturing, data-driven RUL prediction has become very popular. When the training dataset and the test dataset are distributed similarly, the traditional machine learning prediction method is very effective. However, in actual production, the operation conditions of the machine part used for training and testing may be different, resulting in different distribution of data sets. In this paper, we propose a domain adaptive SAE-LSTM (DASL) model for RUL prediction of the machine part to solve this problem. The DASL model contains sparse autoencoder (SAE) and Long Short-Term Memory (LSTM) with domain adaptive mechanism. The latent features extracted by SAE from source dataset and target dataset are transformed to reproducing kernel Hilbert space (RKHS) and the distribution discrepancy is reduced by using maximum mean discrepancy (MMD). Then the latent features are input into the LSTM to predict the RUL. What is more, the case where both source data and target data are data containing multiple conditions is also considered. The proposed model is tested on Foxconn tool wear dataset and PHM Challenging 2012 dataset. The results show that the method has a better improvement. In most experiments, this method outperforms other state-of-arts' methods.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"25 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":"132574455","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/ICPHM49022.2020.9187025
Masanao Natsumeda, Haifeng Chen
Remaining Useful Life (RUL) estimation is a key element in Predictive maintenance. System agnostic approaches which just utilize sensor and operational time series have gained popularity due to its ease of implementation. Due to the nature of measurement or degradation mechanisms, its accurate estimation is not always feasible. Existing methods suppose the range of RUL with feasible estimation is given from results at upstream tasks or prior knowledge. In this work, we propose the novel framework of end-to-end learning for RUL estimation, which is called RULENet. RULENet simultaneously optimizes its Dual-estimator for RUL estimation and its feasible range estimation. Experimental results on NASA C-MAPSS benchmark data show the superiority of the end-to-end framework.
{"title":"RULENet: End-to-end Learning with the Dual-estimator for Remaining Useful Life Estimation","authors":"Masanao Natsumeda, Haifeng Chen","doi":"10.1109/ICPHM49022.2020.9187025","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187025","url":null,"abstract":"Remaining Useful Life (RUL) estimation is a key element in Predictive maintenance. System agnostic approaches which just utilize sensor and operational time series have gained popularity due to its ease of implementation. Due to the nature of measurement or degradation mechanisms, its accurate estimation is not always feasible. Existing methods suppose the range of RUL with feasible estimation is given from results at upstream tasks or prior knowledge. In this work, we propose the novel framework of end-to-end learning for RUL estimation, which is called RULENet. RULENet simultaneously optimizes its Dual-estimator for RUL estimation and its feasible range estimation. Experimental results on NASA C-MAPSS benchmark data show the superiority of the end-to-end framework.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"52 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":"117162424","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/ICPHM49022.2020.9187030
Y. Bian, Ning Li
In this paper, we propose a novel method based on kalman filter banks to estimate remaining useful life for industrial components. Instead of the common linear state space equation, we adopt jump Markov linear model for the proposed method. Thus, the problem that kalman filter and particle filter are not able to deal with non-Gaussian noises can be solved. Besides, proposed kalman filter banks method has no need for resampling, which is a commonly used in particle filter. We conduct a case study on Lithium-ion batteries, and find that the proposed method outperforms many existing model-based remaining useful life prediction methods, especially kalman filter and particle filter.
{"title":"Estimating remaining useful life for lithium-ion batteries using kalman filter banks","authors":"Y. Bian, Ning Li","doi":"10.1109/ICPHM49022.2020.9187030","DOIUrl":"https://doi.org/10.1109/ICPHM49022.2020.9187030","url":null,"abstract":"In this paper, we propose a novel method based on kalman filter banks to estimate remaining useful life for industrial components. Instead of the common linear state space equation, we adopt jump Markov linear model for the proposed method. Thus, the problem that kalman filter and particle filter are not able to deal with non-Gaussian noises can be solved. Besides, proposed kalman filter banks method has no need for resampling, which is a commonly used in particle filter. We conduct a case study on Lithium-ion batteries, and find that the proposed method outperforms many existing model-based remaining useful life prediction methods, especially kalman filter and particle filter.","PeriodicalId":148899,"journal":{"name":"2020 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"26 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":"123710111","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：