Classification of flame extinction based on acoustic oscillations using artificial intelligence methods

Fire, one of the most serious disasters threatening human life, is a chemical event that can destroy forests, buildings, and machinery within minutes. For this reason, there have been numerous methods developed to extinguish the fire. Within the scope of this study, a sound wave flame extinction system was developed in order to extinguish the flames at an early stage of the fire. The data used in the study were obtained as a result of experiments conducted with the developed system. The created dataset consists of data obtained from 17,442 experiments. It is aimed to classify the fuel type, flame size, decibel, frequency, airflow and distance features, and the extinction-non-extinction status of the flame through rule-based machine learning methods. In the study, rule-based machine learning methods, ANFIS (Adaptive-Network Based Fuzzy Inference Systems), CN2 Rule and DT (Decision Tree) were used. The methods of Box Plot, Scatter Plot and Correlation Analysis were utilized for statistical analysis of the data. As a result of the classifications, respectively, 94.5%, 99.91%, and 97.28% success were achieved with the ANFIS, CN2 Rule, and DT methods. As a result of the evaluations made by using Box Plot, Scatter Plot and Correlation Analysis.