Interactive Abnormal Condition Sign Discovery for Hydroelectric Power Plants

Autor:	Norihiko Ito, Hironobu Yamasaki, Takashi Onoda
Rok vydání:	2009
Předmět:	Computer science business.industry Data detection Bearing vibration computer.software_genre Power (physics) Reliability engineering Support vector machine Hydroelectricity Data mining Electric power business computer Risk management Sign (mathematics)
Zdroj:	New Frontiers in Applied Data Mining ISBN: 9783642003981 PAKDD Workshops
DOI:	10.1007/978-3-642-00399-8_16
Popis:	Kyushu Electric Power Co.,Inc. collects various sensor data and weather information to maintain hydroelectric power plants while the plants are running. However, it is very rare to occur abnormal and trouble condition data in power equipments. And in order to collect the abnormal and trouble condition data, it is hard to construct an experimental hydroelectric power plant. Because its cost is very high. In this situation, we have to find abnormal condition data as a risk management. In this paper, we consider that the abnormal condition sign may be unusual condition data. This paper shows results of unusual condition data of bearing vibration detected from the collected various sensor data and weather information by using one class support vector machine. The result shows that our approach may be useful for unusual condition data detection and maintaining hydroelectric power plants. Therefore, the proposed method is one of risk management for hydroelectric power plants.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::4faaeedf522802dbd4ec7569ea4cbdd5 https://doi.org/10.1007/978-3-642-00399-8_16 Zobrazit plný text záznamu