A Systematic Review on Fault Detection in IoT-Enabled Systems

Fault detection is important for improving the reliability and safety of IoT-enabled monitoring systems used in environmental and industrial applications. This project presents a fault detection system using IoT sensors and machine learning techniques for monitoring environmental conditions and identifying abnormal situations. The proposed system uses an Arduino microcontroller integrated with DHT11, MQ135, and atmospheric sensors to monitor parameters such as temperature, humidity, air quality, pressure, and gas concentration levels. An LCD display is used to show sensor values, while a buzzer and LED indicators provide alerts when abnormal conditions or faults are detected. The collected sensor data is processed using machine learning techniques and the Random Forest algorithm developed in Python for intelligent fault prediction and detection. The system also uses a power supply adapter and USB communication for proper operation and data transfer. The proposed system improves fault detection accuracy, supports environmental monitoring, and helps identify abnormal conditions in IoT-based applications. The integration of IoT and machine learning technologies reduces manual monitoring efforts and enhances system reliability for smart monitoring applications.