Article
Hybrid IOT and Machine Learning System for Predictive for Railway Bridge Flood Risk Detection
Flood-induced structural failures of railway bridges create significant threats to transportation safety, infrastructure stability, and uninterrupted railway operations, especially during heavy rainfall and extreme weather events. Early identification and prediction of flood conditions are essential to reduce accidents, minimize structural damage, and ensure operational reliability. This project proposes a hybrid Internet of Things (IoT) and Machine Learning (ML)-based predictive flood risk detection system specifically designed for railway bridge environments. The proposed system combines water-level sensing, vibration monitoring, and environmental gas detection through an MQ-5 sensor integrated with a Raspberry Pi Zero Wbased edge-processing unit. These sensors continuously monitor environmental and structural parameters that influence flood risk and bridge safety. Real-time data are collected through an IoT-enabled wireless sensor network and processed for analysis. A machine learning model is trained using historical flood records along with live sensor data to identify patterns and trends associated with flood occurrences. Unlike conventional threshold-based systems, the ML model categorizes flood conditions into multiple levels such as normal,warning, and danger, enabling predictive risk assessment and early intervention.
Full Text Attachment
