Condition Based Monitoring and Maintenance System for Underground Metro Stations
Senthilkumar Meyyappan, K Susmitha, K Vaishnavi, M Sai, Rao Nalla, Malla Reddy, X Zhou, L Yang, M, Senthil Kumar, M Gopinath, Senthilkumar Meyyappan, N Selvamuthukumaran, A Senthilkumar Meyyappan, A Bharath Naik, Uma, Ch Sai, Keerthi, M Kumar, R Karthik, I Raja, Z Cheng, Y Zhang, M, Senthil Kumar, L Praveen, M Kavitha, T Maheshwaran, M Kumar, J Lee, H Kao, M Kumar, C Vimalarani, M Kumar, M Subashinidevi, S Castro, M Kumar, R Srinivasan, S Venkataraman, M, Senthil Kumar, C Sridhathan, M, Senthil Kumar, Ashish Chaturvedi, G Senthilkumar Meyyappan, G Kumar, G Niharika, Chakradhar, R Sivaraman, V Sharma, M, Senthil Kumar, Ashish Chaturvedi, M Kavitha, T Maheshwaran, M Kumar, H Alemzadeh, M Gholami
Abstract
Tunnel booster fans (TBFs) in underground metro stations, which vary in capacity, are essential for ventilation but pose significant maintenance challenges due to their infrequent operation and complex schedules. Traditional preventive maintenance requires extensive manpower and involves risks associated with working at heights. To address these issues, this project introduces a ConditionBased Monitoring and Maintenance (CBM) system designed to optimize maintenance activities and reduce associated costs. The CBM system will utilize an AI-based platform that integrates historical failure data, operational symptoms, parameter limits, and maintenance records. By analysing realtime data collected during mock drills, the AI system will compare it with historical data top redact maintenance needs and identify deviations from normal operation. This approach will enable targeted maintenance actions, thereby reducing unnecessary inspections and associated risks. The expected outcome is a more efficient maintenance process that leverages machine learning and behavioural analytics to proactively manage TB