PENGEMBANGAN SISTEM DETEKSI KEBAKARAN BERBASIS ESP32 DENGAN PENDEKATAN LOGIKA FUZZY MAMDANI

Fire is one of the most significant types of disasters, posing serious threats to human safety and causing substantial material losses. This study aims to design and implement a fire detection system based on the ESP32 microcontroller, integrated with the Mamdani fuzzy logic method and Internet of Things (IoT) technology. The system is designed to detect environmental parameters such as temperature, humidity, gas concentration, and the presence of flame using DHT22, MQ2, and a five-direction flame sensor. The detection data are processed in real time using a fuzzy logic approach to classify the risk levels into three categories: Safe, Alert, and Danger. The system includes an automatic notification feature via the Telegram application, which is only triggered when the Danger condition is detected, along with the transmission of the incident location. In addition, a buzzer serves as a local warning device, producing a short beep for the Alert condition and a long beep for Danger. All monitoring data are displayed in real time through a web-based interface to support rapid response and continuous supervision. The test results show that the system has an average response time of 1 second and a high level of accuracy, with an average fuzzy logic error rate of 0.16% and an overall accuracy of 99.83%. With its reliable and efficient performance, this system is considered an effective, adaptive, and applicable solution for early fire detection in high-rise buildings.
Keywords: Fire Detection, ESP32, IoT, Mamdani Fuzzy Logic, Telegram