隠れマルコフモデルを用いた電気機器稼働状態の診断

カテゴリ: 全国大会

論文No: 4-171

グループ名: 【全国大会】平成18年電気学会全国大会論文集

発行日: 2006/03/15

タイトル(英語): Diagnosis of Electric Appliance Based on Hidden Markov Model

著者名: 江上 司(名古屋大学),稲垣 伸吉(名古屋大学),鈴木 達也(名古屋大学),中村 久栄(トーエネック),伊藤公一 (トーエネック)

著者名(英語): Egami Tsukasa(Nagoya University),Inagaki Shinkichi(Nagoya University),Suzuki Tatsuya(Nagoya University),Nakamura Hisahide(TOENEC CORPORATION),Ito Koichi(TOENEC CORPORATION)

キーワード: 隠れマルコフモデル|電気機器|診断

要約(日本語): This paper proposes a new diagnosis method of operating condition of electric appliances based on Hidden Markov Model. Diagnosis of operating condition is expected to lead to understanding needs of power consumers and forecasting power demands in future. Running a certain electric appliance raises the current waveform with specific characteristics. Therefore, it is quite reasonable to pay attention to the pattern of current waveforms for recognition of used electric appliances. In this paper, Hidden Markov Model, which is widely used for the analysis of time series data, is introduced as the recognizer for the current waveforms. The usefulness of the proposed method is verified through some experiments with embedded computer.

原稿種別: 日本語

PDFファイルサイズ: 1,621 Kバイト