2019 IEEE International Conference on Prognostics and Health Management (ICPHM)最新文献

{"title":"Data-Informed Lifetime Reliability Prediction for Offshore Wind Farms","authors":"A. K. Papatzimos, P. Thies, J. Lonchampt, A. Joly, T. Dawood","doi":"10.1109/ICPHM.2019.8819378","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819378","url":null,"abstract":"Offshore wind operation and maintenance (O&M) costs can reach up to 1/3 of the overall project costs. In order to accelerate the deployment of these clean energy assets, costs need to come down. This requires, a good understanding of the different operations along with a robust planning, maintenance and monitoring strategy. Asset management tools have been developed, which require reliability inputs, able to estimate the lifetime operational expenditure (OPEX) and optimize the maintenance strategies for the assets. The lack of large datasets with offshore wind failure rate data in the literature increases the uncertainty in the estimations made by those tools. This paper aims to compare whether the publicly available data could provide an accurate information of the lifetime reliability predictions of the assets. It initially uses a generic average failure rate, taken from literature to model the wind farm; as most wind farm developers will not have any detailed understanding of the reliability of the asset prior to construction. It then uses a more detailed, turbine-specific model, taking into account reliability data from an operational wind farm. Results show a small overall difference when the model uses the data-informed parameters, by up to 0.4% in the overall availability. Moreover, it is shown that the use of generic values can create more pessimistic results compared to the data-informed data. The results of the paper are of interest to offshore wind farm developers and operators aiming to improve their lifetime reliability estimations and reduce the O&M costs of the offshore wind farms.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"147 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113972845","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}

{"title":"Degradation Estimation of Turbines in Wind Farm Using Denoising Autoencoder Model","authors":"S. Sato, K. Sanda","doi":"10.1109/ICPHM.2019.8819375","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819375","url":null,"abstract":"We propose a method to estimate the power performance degradation in wind turbines (WTs) that arises from damage in the turbine blade and other components. In general, the single anemometer mounted on the nacelle is unable to measure precise wind speed distributions that the WT receives, thus, degradation of the power output is difficult to evaluate. By focusing on the fact that the power output data of adjacent WTs have some correlation although the wake effect on downstream turbines sometimes exists, our method uses the power output data of every WT in a farm to estimate the amount of degraded power performance of each turbine by the introduction of the virtual variable which corresponds to each turbine’s degraded amount. The feature of the correlation among each WT’s non-degradation data was learned by a denoising autoencoder (DAE). The virtual variables along with the power output are fed into the trained DAE model and these variables were updated by minimizing the reconstruction error. Moreover, the proposed method can perform the estimation even when some WTs are down, i.e., due to the periodical maintenance, and can classify between non-degraded and degraded WTs without enforcing diagnostics to set suitable threshold parameters. We demonstrated the superiority of this novel method over traditional methods by using real and artificial data inputs.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133644314","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}

{"title":"An Improved Particle Filter Method for Accurate Remaining Useful Life Prediction","authors":"Dengshan Huang, M. Wang, Shuai Zhao, Pengfei Wen, Shaowei Chen, Zhi Dou","doi":"10.1109/ICPHM.2019.8819414","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819414","url":null,"abstract":"The prognostics method that updates the parameters of degradation model using particle filter to predict the remaining useful life (RUL) of equipment is widely used in recent years. However, most of the traditional methods that use this strategy for prognostics do not establish the state transition equation and measurement equation of particle filter from the aspect of degradation trend, which makes the predicted curve may not conform to the degradation trend of the known data because of the loss of information. This paper proposes a prognostics method based on degeneration trajectory, which updates model parameters using particle filter and makes the predicted curve which depends on the updated parameters conform to the known degradation trend by establishing the measurement equation of particle filter different from the traditional method. The proposed method is verified by using the turbine engine degradation data published by NASA and the experiment shows that this method is superior to the traditional method in prediction accuracy and precision.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129147245","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}

{"title":"High-Accuracy Unsupervised Fault Detection of Industrial Robots Using Current Signal Analysis","authors":"Fangzhou Cheng, A. Raghavan, Deokwoo Jung, Yukinori Sasaki, Y. Tajika","doi":"10.1109/ICPHM.2019.8819374","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819374","url":null,"abstract":"Robots and other similar automation machines have been widely used in various industries, such as automotive and semiconductor industries to improve productivity, quality, and safety in manufacturing processes. However, an unforeseen robot shutdown has the potential to cause an interruption in the entire production line, resulting in significant unplanned downtime, economic, production losses, and even work injuries. Thus, it is of high interest to detect incipient faults in industrial robots before they totally shut down or otherwise fail. A challenge for fault detection in industrial robots is the difficulty to obtain sufficient labeled training data under normal and abnormal health conditions. Thus, unsupervised machine learning algorithms are desired. In this work, a Gaussian mixture model-based unsupervised fault detection framework is proposed to effectively detect the faults in industrial robots using current signals. Signal preprocessing is first performed to clean the measured raw current signals. Then, motion-insensitive fault features chosen based on a system physics model that can reflect the deterioration of the industrial robots are extracted and fed into unsupervised learning algorithms for effective fault detection. The effectiveness and high accuracy of the proposed method are validated by experimental data obtained from industrial robot systems.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123318831","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}

{"title":"A novel unsupervised anomaly detection for gas turbine using Isolation Forest","authors":"S. Zhong, Song Fu, Lin Lin, Xu-yun Fu, Zhiquan Cui, Rui Wang","doi":"10.1109/ICPHM.2019.8819409","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819409","url":null,"abstract":"Monitoring gas turbines’ health, in particular, detecting abnormal behaviors in time, is critical in ensuring gas turbine operating safety and in preventing costly unplanned maintenance. One most popular anomaly detection method is to obtain a classification-prediction model by training a classifier using the real-life data of gas turbine. The excellent detection ability of this method is attributed to enough annotated samples, especially enough annotated abnormal samples. Nevertheless, in gas turbine monitoring data, normal data is far more than abnormal data, even no abnormal data. Advanced technologies that can accurately detect the abnormal behaviors in time using the unlabeled data are in great need. Thus, a novel unsupervised anomaly detection based on Isolation Forest is investigated for gas turbine gas path anomaly detection in this paper. Specifically, the monitoring data is grouped by time series for weakening the affection of inevitable performance degradation when gas turbine operating, and then all detected by an isolation forest model with low contamination. Each detected abnormal group is detected again by an isolation forest model with high contamination for obtaining the specific abnormal flight-cycles. Using the real-life monitoring data from 8 different CFM56-7B aeroengines, the detection results show that the method based on Isolation Forest can achieve high accuracy abnormal detection under unlabeled data and small data set.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"2018 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131462390","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}

{"title":"Vibration feature extraction using local temporal self-similarity for rolling bearing fault diagnosis","authors":"Shichen Zeng, Guoliang Lu, Peng Yan","doi":"10.1109/ICPHM.2019.8819380","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819380","url":null,"abstract":"This paper presents a new method for rolling bearing fault diagnosis. The novel vibration feature extraction is learned with local temporal self-similarities (TSS) continuously from collected vibration signals. The bag-of-words (BoW) scheme is then employed for fault classification taking advantages of these features. We investigated the effectiveness of the framework on the publicly-available Case Western Reserve University (CWRU) data set. We also compare the method with state-of-the-art approaches. The result demonstrates excellent performance of the proposed method, outperforming those compared state-of-the-art approaches.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121332408","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}

{"title":"Fault Detection and Classification of Time Series Using Localized Matrix Profiles","authors":"Jing Zhang, D. Nikovski, Teng-Yok Lee, Tomoya Fujino","doi":"10.1109/ICPHM.2019.8819389","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819389","url":null,"abstract":"We introduce a new primitive, called the Localized Matrix Profile (LMP), for time series data mining. We devise fast algorithms for LMP computation, and propose a fault detector and a fault classifier based on the LMP. A case study using synthetic sensor data generated from a physical model of an electrical motor is provided to demonstrate the effectiveness and efficiency of our approach.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121986466","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}

{"title":"Dynamic Programming Model for Multi-Stage Reliability Growth Planning","authors":"Dong Xu, Z. Li","doi":"10.1109/ICPHM.2019.8819439","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819439","url":null,"abstract":"The development of modern sophisticated system is increasingly concerned with system overall reliability, which makes Reliability Growth Planning (RGP) particularly important. Reliability Growth Planning provides decision makers with accurate and reliable information during the multi-stage product development decision making process. Dynamic programming (DP) is an effective method to multi-stage decision making such as multiple stage reliability growth planning. This paper adopts the advantages of dynamic programming to establish reliability growth planning model and investigates the computational complexity of the algorithms. Insights during reliability growth planning, such as the relationship between the final achievable reliability and the initial parameter settings, the number of stages, and time allocation granularity is studied through an example. It is found that when the number of stages is fixed, the higher level of the time allocation granularity, the larger the final reliability level of reliability growth planning. In the case of a fixed time allocation granularity, there exists an optimal number of stages to maximize the final reliability level.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130673309","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}

{"title":"Research on General Aircraft Cluster Health Assessment Method","authors":"Guigang Zhang, Sujie Li, Nan Yang, Haixia Su, Jian Wang, Lan Huang, Huiyun Wang","doi":"10.1109/ICPHM.2019.8819419","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819419","url":null,"abstract":"This paper studies the general aircraft platform health characterization technology based on the state parameters. We combines different parameters according to the needs of general aircraft health management. We determines the health status ranking and health status assessment index system for general aircrafts and fleets. Using AHP and grey clustering method, qualitative and quantitative evaluation of the health status of the aircraft and fleet.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127621292","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}

{"title":"Essentials to Develop Data-Driven Predictive Models of Prognostics and Health Management for Distributed Electrical Systems","authors":"Farhad Balali, Hamid Seifoddini, A. Nasiri","doi":"10.1109/ICPHM.2019.8819437","DOIUrl":"https://doi.org/10.1109/ICPHM.2019.8819437","url":null,"abstract":"The reliability of the electrical networks significantly impacts customer as well as energy providers’ bottom line. Connectivity between the various sectors of the electrical network has been expressively increased due to the high penetration of the new smart hardware and software tools. Therefore, Prognostics and Health Management (PHM) becoming a critical factor in the efficiency of capital-intensive corporations especially for the energy sector including the electrical power generation. Degradation based analysis is one of the valuable approaches of condition-based algorithms in order to obtain the reliability information especially for the highly reliable systems, critical assets, and recently developed products. The main purpose of the degradation-based models is to predict the future condition of the asset and perform the maintenance in an optimized time window before the actual failure of the system. Failure is said to have occurred as a soft failure event in these types of models. The main purpose of this study is to study the essentials in developing the first hitting time degradation-based models to predict the critical time for initiating the maintenance actions in order to optimize the effectiveness of the PHM leading to enhancing the value of the assets for the distributed electrical systems. The analyses are mostly focused on the critical components of the distributed electrical systems. The latest generations of the degradation models are exploring the potential improvements based on the more available information provided by smart devices to predict the critical failure time. Robust predictive models are beneficial to both energy providers and customers to enhance the overall reliability and risk of the system by initiating the maintenance before the physical failure occurs. In this paper, General Path (GP) and Autoregressive (AR) models as general methodologies for degradation models would be discussed in detail based on the depth of the analyses and available information.","PeriodicalId":113460,"journal":{"name":"2019 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121195875","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}