Abstract: An intelligent comprehensive evaluation model of coal seam impact risk based on the BP neural network optimized by the Bat algorithm was established through in-depth analysis of the in-fluence of mining depth, property of top and bottom floors of coal seams, impact tendency, geological structure, mining technology and other factors on coal seam impact risks. The determined factors in-fluencing impact risks are classified by order of magnitude,and the Bat algorithm is employed to optimize the selection of the optimal weight and threshold value of the BP neural network, and the rating evaluation is performed for coal seam impact risks in terms of no-impact risk, weak impact risk, medium impact risk and strong impact risk. The intelligent comprehensive evaluation model of coal seam impact risk based on the BP neural network optimized by the Bat algorithm was used for in-stance validation of coal seams in a mine in Inner Mongolia and a face in Jiangsu Province, and the evaluation results were consistent with the results calculated by the synthetic index method, showing that this model could be used to evaluate coal seam impact risks. When this model is employed to evaluate coal seam impact risks, the random defects in the determination of weight and threshold value of the BP network structure can be overcome and the algorithm stability can be improved, so the evaluation results obtained are more reasonable.