Fire Early Warning System in Using Fuzzy Logic Tsukamoto Inference Method Based on Internet of Things

Abstract

Fire incidents frequently occur and result in significant losses, including damage to property, disruption of economic activities, and loss of human life. In Indonesia, the number of fire incidents increased considerably in 2023, highlighting the urgent need for effective fire prevention and early warning systems. Conventional fire detection systems often experience delays in identifying fire hazards, which can lead to severe consequences. Therefore, this research aims to develop an indoor fire early warning system based on Internet of Things (IoT) technology integrated with the Tsukamoto fuzzy logic method to improve the accuracy and reliability of fire detection. The proposed system employs a flame sensor to detect the presence of fire and an MQ-2 gas sensor to measure smoke concentration. An ESP32 microcontroller processes the sensor data and applies fuzzy logic to determine the fire risk level based on predefined membership functions and inference rules. The system provides real-time monitoring through a web-based dashboard and automatically sends warning notifications to users via the Telegram application when potential fire conditions are detected. Experimental results demonstrate that the proposed system effectively detects fire and smoke under various testing conditions while providing fast and accurate early warnings. The integration of IoT technology with fuzzy logic enables timely emergency response, minimizes fire-related losses, and enhances the safety of residential and commercial indoor environments.