Supervised Learning Application for Refrigeration Showcase Fault discrimination

カテゴリ: 部門大会

論文No: GS9-5

グループ名: 【C】平成28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: 2016/08/31

タイトル(英語): Supervised Learning Application for Refrigeration Showcase Fault discrimination

著者名: Santana Adamo(Federal University of Para),福山 良和(明治大学),村上 賢哉(富士電機),松井 哲郎(富士電機)

著者名(英語): Adamo Santana|Yoshikazu Fukuyama|Kenya Murakami|Tetsuro Matsui

キーワード: 機械学習|ショーケース|教師学習教師学習|Machine learning|Showcase|Supervised learning

要約(日本語): Open refrigeration showcases are common utilized equipment in super markets and convenience stores to maintain the temperature and quality of products; it is, however, still a system that is susceptible to fault events, such as coolant leakage and frost formation, causing losses. Therefore, faults and early abnormal behaviors that can lead to future problems should be identified. To classify events as in-control or faulty, samples or patterns for both types of events are needed, however, it is often the case in practical industrial applications where only the in-control type of data is available. This?paper assesses?the applicability of two supervised approaches in identifying unusual?behavior in real showcase data when no output data labels are given a priori.

PDFファイルサイズ: 1,013 Kバイト