Intelligent Warning of Oil Depot Fire Based on Optimized Quantum Particle Swarm Optimization Algorithm in the Oil Depot Fire Information System

Abstract

There are issues with increased energy consumption of terminal equipment in the oil depot information system, as well as issues that are not conducive to the intelligent fire warning of this system. In this regard, edge computing is introduced, multi platform task uninstallation algorithm is designed, and a mathematical model is built. Quantum particle swarm optimization algorithm is used for optimization solution to determine the intelligent uninstallation strategy for multi platform tasks. An intelligent fire warning algorithm based on quantum particle swarm optimization and back propagation neural network is constructed to judge the fire situation. In the simulation results, quantum particle swarm optimization algorithm has significant advantages in multi platform task uninstallation. Compared with particle swarm optimization, quantum particle swarm optimization can reduce energy consumption by up to 17.1%. Compared with completely local algorithms, this research algorithm has saved 13.5%, 24.3%, and 38.3% of energy consumption, indicating the effectiveness of this research method algorithm. The mean squared error of the back propagation neural network optimized by quantum particle swarm optimization algorithm and the back propagation reached the expected error value in 106 iterations and 180 iterations respectively. The former has better convergence and global search ability than those of the latter. The back propagation neural network model optimized by quantum particle swarm optimization algorithm can effectively identify open fire, smoldering fire, and non-fire situations, and there is no false or missed reporting. This indicates that the research method can be beneficial for the intelligent fire warning of oil depot fire information system and promote the operational safety of oil depot.