This project presents a smart IoT-based monitoring system designed for chemical plants, integrating machine learning and real-time data communication to enhance safety. Gas sensors such as MQ135 and MQ2 are used to detect hazardous gases like smoke and ammonia. These sensors interface with an ESP32 microcontroller, which transmits the data using LoRa technology to a Raspberry Pi for further processing.
The system leverages a Random Forest machine learning algorithm, implemented in Python, to analyze the collected sensor data and predict potential gas leaks or hazardous conditions. The results are displayed locally on an LCD screen, and a buzzer provides on-site alerts to nearby personnel when unsafe gas levels are detected.
An IoT dashboard is developed using HTML and CSS for the frontend, while Python handles the backend processing and communication. This dashboard allows for real-time remote monitoring of gas levels from any location, enabling rapid response and improved safety management.
This integrated solution ensures accurate, efficient, and user-friendly gas monitoring, making it highly effective for industrial safety in chemical plants.