Research and Development of an Early Fire Warning System for Ships Using Artificial Neural Networks

Fire has become a serious threat to both human life and the natural environment. Traditional fire alarm systems often face challenges during deployment, especially in large areas or with complex terrain. Some methods of detecting fire risks apply artificial intelligence integrated into intelligent fire alarm systems on shore. In addition, the application of artificial intelligence on modern ships is increasingly popular for many purposes, such as enhancing maritime safety and minimizing accidents and risks during operations at sea. This paper studies and tests an early fire warning system based on Artificial Neural Network (ANN) to minimize damage related to fires on ships. The system combines temperature, humidity, and Carbon Monoxide (CO) and Carbon Dioxide (CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>) sensors, all collected through a microcontroller. The environmental data collected from these sensors is processed and analyzed using a predictive model built in MATLAB. The research results demonstrate that the model achieves high accuracy and provides rapid response, significantly reducing the time required to detect potential fire hazards and thus minimizing damage.