Track Condition Monitoring using Machine Learning Technique for Regional Railways

カテゴリ: 研究会(論文単位)

論文No: TER18020

グループ名: 【D】産業応用部門 交通・電気鉄道研究会

発行日: 2018/02/01

タイトル(英語): Track Condition Monitoring using Machine Learning Technique for Regional Railways

著者名: TSUNASHIMA HITOSHI(College of Industrial Technology Nihon University),HAYASHIDA YUICHI(Graduate School of Nihon University),ODASHIMA MAI(Graduate School of Nihon University)

著者名(英語): HITOSHI TSUNASHIMA(College of Industrial Technology Nihon University),YUICHI HAYASHIDA(Graduate School of Nihon University),MAI ODASHIMA(Graduate School of Nihon University)

キーワード: Railway|Condition monitoring|Track|Machine learning|Regional railway|Railway|Condition monitoring|Track|Machine learning|Regional railway

要約(日本語): A track condition monitoring system that uses a compact on-board sensing device has developed and applied for track condition monitoring of regional railway lines in Japan. Monitoring examples show that the system is effective for rural railway operators. A classifier for track faults has been developed to detect track fault automatically. Simulation studies using SIMPACK and field test were carried out to detect and isolate the track faults from car-body vibration. The results show that feature of track faults is extracted from car-body vibration and classified from proposed feature space using machine learning techniques.

要約(英語): A track condition monitoring system that uses a compact on-board sensing device has developed and applied for track condition monitoring of regional railway lines in Japan. Monitoring examples show that the system is effective for rural railway operators. A classifier for track faults has been developed to detect track fault automatically. Simulation studies using SIMPACK and field test were carried out to detect and isolate the track faults from car-body vibration. The results show that feature of track faults is extracted from car-body vibration and classified from proposed feature space using machine learning techniques.

原稿種別: 英語

PDFファイルサイズ: 4,927 Kバイト