{"title":"An effective age-based preventive replacement model","authors":"F. Szidarovszky, D. Goodman, Criag Wentzel","doi":"10.1109/ICPHM.2017.7998310","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998310","url":null,"abstract":"The paper introduces a new model to find the optimal timing of preventive replacement of an equipment. The traditional models do not take the down times into account when inspections and repairs are being performed. The distribution of time to failure really depends on the effective age of equipment, which can be computed by solving a monotonic equation including the repair and inspection down times. A mathematical model is then developed based on the modified probabilistic features where the chronological age is replaced by the effective age. The expected cost per unit time is first minimized, and then a mulitobjective approach is introduced. The models and their solutions are illustrated with numerical examples.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123398562","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 sound simulations from normal sounds for data-driven prognosis based on human expert and vibration knowledge","authors":"Takuya Nishino, Shun Takeuchi, Takahiro Saito, Isamu Watanabe","doi":"10.1109/ICPHM.2017.7998339","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998339","url":null,"abstract":"This paper discusses how to simulate plausible machine fault sound data from normal machine sounds using a combination of human empirical knowledge and past case studies of vibration monitoring. We focus on the fact that human experts in many maintenance areas generally listen to sounds when monitoring machine conditions. They can determine machine conditions by listening. Therefore, it is possible to assess machine fault sound simulators based on whether humans find the sound plausible. We successfully generated abnormal sounds that were synthesized from normal machine sounds using several parameters. The simulated sounds were assessed in two steps. One used theoretically synthesized sounds at various loudness levels and a vibration knowledge database. The other involved assessment by human experts by ear. We successfully generated plausible sounds for three rotor rotation machine failures and four roller bearing faults. The sounds were assessed by three human experts who had more than 10 years of experience in machine maintenance in two different areas. Their assessment results were consistent for our parameters.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116843953","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 kind of approach for aero engine gas path fault diagnosis","authors":"Qiang Huang, Guigang Zhang, Ting Zhang, Jian Wang","doi":"10.1109/ICPHM.2017.7998305","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998305","url":null,"abstract":"Support vector machine (SVM) has good generalization performance and is suitable for solving small sample classification problems, so it is often used in the fault diagnosis for aero engine gas path. In this paper, the traditional genetic algorithm and the idea of simulated annealing are combined to optimize the parameters of SVM, and a fault diagnosis method of aero engine gas path based on parameter optimized support vector machine is presented. This method is used to diagnose the aero engine gas path fault to verify the feasibility and effectiveness. The experimental results show that the algorithm can effectively select the parameters of SVM, and ensure the accuracy of fault diagnosis.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124783496","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":"The research on characteristics of DC arc fault based on HHT","authors":"Yaojia Zhang, Li Wang","doi":"10.1109/ICPHM.2017.7998317","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998317","url":null,"abstract":"Due to the randomness in time and space and unobvious characteristics, it is difficult to detect the DC arc fault. To solve the problem, this paper studies the Hilbert-Huang transform to extract the frequency domain characteristics of AC components of the current. The sum of harmonic power in the range from 20kHz to 100kHz is calculated by the IMF4 method, which can be used as the characteristic parameters. Compared with traditional FFT method, the ratio of arc fault characteristics to normal characteristics increases. And results suggest that the arc fault state and normal state are differed clearly.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133333362","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":"Uncertainty quantification in prognostics: A data driven polynomial chaos approach","authors":"P. Duong, N. Raghavan","doi":"10.1109/ICPHM.2017.7998318","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998318","url":null,"abstract":"Prognostic deals with predicting the possible future failure of different types of engineering systems. For the purpose of prognostics, the failure of the system is defined to be the instant when the degradation (performance) level rises above (drops below) a defined threshold. It is impossible to make a precise prediction of the remaining useful life (RUL) of a system due to many sources of uncertainties. Therefore, one has to develop a structured approach to account for the different sources of uncertainties. While some methods such as Monte Carlo/Quasi Monte Carlo can be implemented easily, its accuracy is limited and the computational cost involved is large. Recently, it was shown that UQ in prognostics with the non-intrusive polynomial chaos approach is a good choice, thanks to its accuracy and low computational cost. Unfortunately though, it requires the prior knowledge of parametric distributions. This work tackles the challenge of uncertainty quantification (UQ) in model based prognostics using the moment-based arbitrary polynomial chaos approach. The moment-based polynomial chaos is suitable for this purpose and its advantages can be summarized as: 1) UQ can be done with small computational effort in comparison to the standard Monte Carlo method. 2) It avoids the necessity to assign parametric probability distributions. 3) It can be used with arbitrary distributions with arbitrary measures, which can be specified numerically by means of a histogram or a raw data set. 4) Global sensitivity indices are available directly and can be used to identify which parameter is relatively more important than the others over the entire parameter space of the models. The method is illustrated for an example of battery resistance degradation.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121167344","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 of K-MEANS analysis model on high-speed railway CIR device maintenance","authors":"Jiaming Fan, Jianping Fan, Feng Liu","doi":"10.1109/ICPHM.2017.7998328","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998328","url":null,"abstract":"When High-speed train runs, the strength of data field signal determines whether the CIR device on the High-speed train can work normally. While proper functioning of the CIR device affects the normal operation of the train deeply. The K-MEANS-analysis-model proposed in this paper, applies the K-MEANS method of machine learning to train numerous data duplicate which generated by different locomotives that run in the same interval. In this way, we obtain the duplicate of normal field strength values in this interval. We employ it and combine with the mean-algorithm and the difference-algorithm to analysis the malfunction reason accurately. In this way we have reduced the run-times of the field inspection vehicle successfully, so as to cut down the operating costs effectively.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"61 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131471790","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 optimal multi-degree open-circuit faults diagnostic algorithm for photovoltaic system","authors":"J. Qin, Li Wang, Shanshui Yang, Ling Mao","doi":"10.1109/ICPHM.2017.7998329","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998329","url":null,"abstract":"In this paper, an optimal multi-degree open-circuit faults diagnostic algorithm, for improving condition monitoring ability of photovoltaics, has been proposed. This algorithm combines output parameters and characteristic impedance of PV-system under low frequency domain in simplified manner. The feasibility and accuracy of the method has been proven through simulation using Siemens-SM100-12.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116815073","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":"Short-term electricity load forecasting with Time Series Analysis","authors":"Hung T. Nguyen, C. K. Hansen","doi":"10.1109/ICPHM.2017.7998331","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998331","url":null,"abstract":"Load forecasting plays a fundamental role throughout all segments of system health management for utility companies, including, but not limited to, financial planning, rate design, power system operation, and electrical grid maintenance. Recently, due to the deployment of Smart Grid technologies, utility companies' ability to create accurate forecasts is of even greater importance, especially in consideration of demand response programs, charging of plug-in electric vehicles, and use of distributed energy resources. In this paper, several time series Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) models will be introduced for the purpose of generating forecasts of short-term load demand, at an hourly interval, based on data made available by the Electric Reliability Council of Texas (ERCOT). The case study which expands on the short-term data analyzed in [1] includes over 100,000 data points representing electricity load in Texas recorded over the past 14 years.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"358 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122743152","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":"Particle filtering based estimation of remaining useful life of lithium-ion batteries employing power fading data","authors":"Arijit Guha, A. Patra","doi":"10.1109/ICPHM.2017.7998327","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998327","url":null,"abstract":"This paper presents a method for remaining useful life (RUL) estimation of lithium-ion batteries based on its power fading model. Firstly, an empirical model of power fading is developed based on battery test data. Then, the obtained model has been used in a particle filtering (PF) framework for making end of life (EOL) predictions at various stages of its cycle life. Finally, the predictions were validated with battery power fade data. From the results it can be observed that as more volume of data becomes available, the accuracy of prediction gradually improves. The prognostics framework proposed in this work provides a systematic way for monitoring the state of health (SoH) of a battery.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117124124","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":"Running state detection and performance evaluation method for feed mechanism of numerical control machine","authors":"Xun Zhang, Qing Zhang, L. Tan, Guanghua Xu","doi":"10.1109/ICPHM.2017.7998332","DOIUrl":"https://doi.org/10.1109/ICPHM.2017.7998332","url":null,"abstract":"Due to the enclosed construction and real-time servo control, it is difficult to detect and evaluate the running state of numerical control (NC) machine feed mechanism. In this paper, the motor torque, which is provided by open NCs, is used to analyze the operating performance of feed mechanism. The torque data is divided into segments in different feed condition and piecewise resolved into long-term trend and short-term fluctuation by the least square method. Features of trend and fluctuation are used to indicate the operating condition and mechanical performance. The proposed method is evaluated by three typical feed mechanisms, i.e. rack & pinion, ball-screw and ball-screw with balance hydraulic cylinder, in a large scale milling and boring machine. Results show that the running state of feed mechanisms can be effectively evaluated and some installed and structural defects are well identified.","PeriodicalId":124147,"journal":{"name":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130985731","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}