S171013 センサデータの確率分布に基づく機械の状態フィルタリング([S171-01]産業機械の安全(1))

DOI Web Site

書誌事項

タイトル別名
  • S171013 Machine State Filtering based on Probability Distribution of Sensor Data for Anomaly Detection System

抄録

Anomaly detection method is becoming important for condition based maintenance. This paper proposes machine state filtering based on probability distribution of sensor data for anomaly detection system. To achieve high performance of anomaly detection, it is important to extract machine steady state with filter before learn and diagnosis. This method can extract it automatically using observed probability distribution and expected probability distribution of machine sensor data. Experimental results demonstrate that proposed method is efficient to reduce false positive of anomaly detection.

収録刊行物

  • 年次大会

    年次大会 2013 (0), _S171013-1-_S171013-4, 2013

    一般社団法人 日本機械学会

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ