Advanced correlation-based anomaly detection method for predictive maintenance. Zhao, P., Kurihara, M., Tanaka, J., Noda, T., Chikuma, S., & Suzuki, T. In 2017 IEEE International Conference on Prognostics and Health Management (ICPHM), pages 78–83, June, 2017. doi abstract bibtex Variations in sensor data collected from equipment have been widely analyzed by using anomaly detection methods for predictive maintenance. Our experience shows that correlations between sensors effectively predict failures because the correlations usually reflect the status of equipment with higher sensitivity. In this paper, we present a method that exploits correlations between sensors for pre-processing and enables anomalies to be detected using both sensor data and correlations. The method was evaluated by applying it to compact electric generators, and the results showed it detected anomalies more accurately than when only sensor data were used. This method is expected to predict failures earlier and reduce the cost of downtime and maintenance.
@inproceedings{zhao_advanced_2017,
title = {Advanced correlation-based anomaly detection method for predictive maintenance},
doi = {10.1109/ICPHM.2017.7998309},
abstract = {Variations in sensor data collected from equipment have been widely analyzed by using anomaly detection methods for predictive maintenance. Our experience shows that correlations between sensors effectively predict failures because the correlations usually reflect the status of equipment with higher sensitivity. In this paper, we present a method that exploits correlations between sensors for pre-processing and enables anomalies to be detected using both sensor data and correlations. The method was evaluated by applying it to compact electric generators, and the results showed it detected anomalies more accurately than when only sensor data were used. This method is expected to predict failures earlier and reduce the cost of downtime and maintenance.},
booktitle = {2017 {IEEE} {International} {Conference} on {Prognostics} and {Health} {Management} ({ICPHM})},
author = {Zhao, Pushe and Kurihara, Masaru and Tanaka, Junichi and Noda, Tojiro and Chikuma, Shigeyoshi and Suzuki, Tadashi},
month = jun,
year = {2017},
keywords = {Correlation, Correlation coefficient, Data models, Electric generators, Maintenance engineering, Time series analysis, advanced correlation, anomaly detection, anomaly detection methods, compact electric generators, correlation coefficient, correlation methods, electric generator, electric generators, failure analysis, failure prediction, maintenance engineering, multivairate time series, predictive maintenance},
pages = {78--83},
}
Downloads: 0
{"_id":"ppmwoa5SupKrWrTRQ","bibbaseid":"zhao-kurihara-tanaka-noda-chikuma-suzuki-advancedcorrelationbasedanomalydetectionmethodforpredictivemaintenance-2017","author_short":["Zhao, P.","Kurihara, M.","Tanaka, J.","Noda, T.","Chikuma, S.","Suzuki, T."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Advanced correlation-based anomaly detection method for predictive maintenance","doi":"10.1109/ICPHM.2017.7998309","abstract":"Variations in sensor data collected from equipment have been widely analyzed by using anomaly detection methods for predictive maintenance. Our experience shows that correlations between sensors effectively predict failures because the correlations usually reflect the status of equipment with higher sensitivity. In this paper, we present a method that exploits correlations between sensors for pre-processing and enables anomalies to be detected using both sensor data and correlations. The method was evaluated by applying it to compact electric generators, and the results showed it detected anomalies more accurately than when only sensor data were used. This method is expected to predict failures earlier and reduce the cost of downtime and maintenance.","booktitle":"2017 IEEE International Conference on Prognostics and Health Management (ICPHM)","author":[{"propositions":[],"lastnames":["Zhao"],"firstnames":["Pushe"],"suffixes":[]},{"propositions":[],"lastnames":["Kurihara"],"firstnames":["Masaru"],"suffixes":[]},{"propositions":[],"lastnames":["Tanaka"],"firstnames":["Junichi"],"suffixes":[]},{"propositions":[],"lastnames":["Noda"],"firstnames":["Tojiro"],"suffixes":[]},{"propositions":[],"lastnames":["Chikuma"],"firstnames":["Shigeyoshi"],"suffixes":[]},{"propositions":[],"lastnames":["Suzuki"],"firstnames":["Tadashi"],"suffixes":[]}],"month":"June","year":"2017","keywords":"Correlation, Correlation coefficient, Data models, Electric generators, Maintenance engineering, Time series analysis, advanced correlation, anomaly detection, anomaly detection methods, compact electric generators, correlation coefficient, correlation methods, electric generator, electric generators, failure analysis, failure prediction, maintenance engineering, multivairate time series, predictive maintenance","pages":"78–83","bibtex":"@inproceedings{zhao_advanced_2017,\n\ttitle = {Advanced correlation-based anomaly detection method for predictive maintenance},\n\tdoi = {10.1109/ICPHM.2017.7998309},\n\tabstract = {Variations in sensor data collected from equipment have been widely analyzed by using anomaly detection methods for predictive maintenance. Our experience shows that correlations between sensors effectively predict failures because the correlations usually reflect the status of equipment with higher sensitivity. In this paper, we present a method that exploits correlations between sensors for pre-processing and enables anomalies to be detected using both sensor data and correlations. The method was evaluated by applying it to compact electric generators, and the results showed it detected anomalies more accurately than when only sensor data were used. This method is expected to predict failures earlier and reduce the cost of downtime and maintenance.},\n\tbooktitle = {2017 {IEEE} {International} {Conference} on {Prognostics} and {Health} {Management} ({ICPHM})},\n\tauthor = {Zhao, Pushe and Kurihara, Masaru and Tanaka, Junichi and Noda, Tojiro and Chikuma, Shigeyoshi and Suzuki, Tadashi},\n\tmonth = jun,\n\tyear = {2017},\n\tkeywords = {Correlation, Correlation coefficient, Data models, Electric generators, Maintenance engineering, Time series analysis, advanced correlation, anomaly detection, anomaly detection methods, compact electric generators, correlation coefficient, correlation methods, electric generator, electric generators, failure analysis, failure prediction, maintenance engineering, multivairate time series, predictive maintenance},\n\tpages = {78--83},\n}\n\n\n\n","author_short":["Zhao, P.","Kurihara, M.","Tanaka, J.","Noda, T.","Chikuma, S.","Suzuki, T."],"key":"zhao_advanced_2017","id":"zhao_advanced_2017","bibbaseid":"zhao-kurihara-tanaka-noda-chikuma-suzuki-advancedcorrelationbasedanomalydetectionmethodforpredictivemaintenance-2017","role":"author","urls":{},"keyword":["Correlation","Correlation coefficient","Data models","Electric generators","Maintenance engineering","Time series analysis","advanced correlation","anomaly detection","anomaly detection methods","compact electric generators","correlation coefficient","correlation methods","electric generator","electric generators","failure analysis","failure prediction","maintenance engineering","multivairate time series","predictive maintenance"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["correlation","correlation coefficient","data models","electric generators","maintenance engineering","time series analysis","advanced correlation","anomaly detection","anomaly detection methods","compact electric generators","correlation coefficient","correlation methods","electric generator","electric generators","failure analysis","failure prediction","maintenance engineering","multivairate time series","predictive maintenance"],"search_terms":["advanced","correlation","based","anomaly","detection","method","predictive","maintenance","zhao","kurihara","tanaka","noda","chikuma","suzuki"],"title":"Advanced correlation-based anomaly detection method for predictive maintenance","year":2017}