Abnormal State Detection in Process Industries using Deep-Learning Method

カテゴリ: 部門大会

論文No: SS1-8

グループ名: 【C】平成29年電気学会電子・情報・システム部門大会講演論文集

発行日: 2017/09/06

タイトル(英語): Abnormal State Detection in Process Industries using Deep-Learning Method

著者名: Song Wen(早稲田大学),Weng Wei(早稲田大学),藤村 茂(早稲田大学)

著者名(英語): Wen Song|Weo Weng|Shigeru Fujimura

キーワード: data analysis|deep learning

要約(日本語): This research is mainly about the data analysis in factories of process industries. The main target is to mine from the whole data, try to de-noise the signal and detect the potential abnormal value from the signals. Since the data is filled with noise and delays among different kind of the signals, we first use the cross-correlation and wavelet transformation to remove the delay and noise. Then, use deep-learning method to train the model with processed data, and finally use the model to detect potential abnormal value.

PDFファイルサイズ: 804 Kバイト