Research on a coal-rock burst risk evaluation model based on particle swarm optimized BP neural network

Coal-rock dynamic disasters, especially rock bursts, pose serious threats to mining safety and production efficiency in deep mining operations. To improve the accuracy and intelligence of coal-rock burst risk assessment, this paper proposes a BP neural network model optimized by Particle Swarm Optimization (PSO). The model integrates coal seam mechanical parameters, mining conditions, and surrounding rock properties as input indicators to construct a comprehensive evaluation system. PSO is applied to optimize the initial weights and thresholds of the BP neural network to avoid local minima and improve convergence speed and prediction accuracy. The optimized model is trained using field monitoring and testing data. Comparative experiments demonstrate that the PSO-BP model exhibits higher prediction accuracy and better generalization ability compared to the traditional BP network. The results indicate that this method can effectively evaluate the risk of coal-rock burst and provides technical support for early warning and disaster prevention in coal mines.