Predictive and Real-Time Railway Safety Solutions using IOT & Ml
Predictive and Real-Time Railway Safety Solutions using IOT & Ml
Dr N Pushpalatha1, D Rajyalakshmi2, M Rekha3 , K Venkata Subhash4 , R Shirisha5
1 Professor, Department of Electronics and Communication Engineering, Annamacharya Institute of Technology and
Sciences- Tirupati, India, pushpalatha825@gmail.com
2U.G. Student, Department of Electronics and Communication Engineering, Annamacharya
Institute of Technology and Sciences- Tirupati, India, devaralarajyalakshmi265@gmail.
3 U.G. Student, Department of Electronics and Communication Engineering, Annamacharya Institute of Technology and
Sciences- Tirupati, India, maremrekha@gmail.com
4 U.G. Student, Department of Electronics and Communication Engineering, Annamacharya
Institute of Technology and Sciences- Tirupati, India, subhashkoduru68@gmail.com
5 U.G. Student, Department of Electronics and Communication Engineering, Annamacharya Institute of Technology and
Sciences- Tirupati, India, ramanadhamshirisha2@gmail.com
ABSTRACT: Railway transportation plays an important role in economic growth and public mobility. However, railway accidents caused by track cracks, fire risks, signal failures, and delayed fault detection still threaten passenger safety. Traditional manual inspection systems take too much time and are inefficient. This paper presents a railway safety system that combines Internet of Things (IoT) technology and Machine Learning (ML) methods for real-time monitoring and smart fault detection. The proposed system uses Arduino Uno as the main controller, connected to fire sensors, track detection modules, a NodeMCU Wi- Fi module, an LCD display, a buzzer, a relay, and a water pump. Sensor data is sent to a cloudplatform for remote monitoring and predictive analysis. Machine learning algorithms are used to find track problems and predict possible failures. The system improves railway safety by ensuring early detection, automated alerts, and quick responses. Experimental results show better accuracy, faster response times, and improved reliability compared to traditional methods.