Using artificial intelligence to detect fires in woodworking factory and designing the robotic arm control of the spray system in a mobile firefighting robot

The purpose of this study is to address the challenges of fire detection and suppression in woodworking factories, where the risk of fire is high due to flammable materials such as wood, wood waste, paint, and wood-based panels, as well as fire sources like burners and drying kilns. Firefighting is particularly difficult in these environments due to confined spaces and numerous obstacles. This study aims to enhance the speed and accuracy of fire detection while improving the efficiency of the fire suppression system, thereby increasing both safety and operational effectiveness. The research method utilizes deep learning techniques, specifically convolutional neural networks (CNNs), to detect fires quickly and accurately. Automated control algorithms guide the robotic system to precisely locate the fire and adjust parameters such as spray pressure, flow rate, and distance, reducing reliance on manual control. The results of the study demonstrate that the CNN-based system significantly improves fire detection accuracy and speed, while the automated spray system optimizes water usage and enhances suppression efficiency. The conclusion highlights that integrating artificial intelligence technology into firefighting systems can improve safety, reduce response times, and lower costs, while also expanding the potential applications of AI in other high-risk industries.