Abstract: The factors of coal mine safety risk pre control management are complex. In the actual evaluation process, the chaotic hierarchy results in a small MAPE value output from safety risk assessment, which leads to a lack of accuracy in the results of coal mine safety risk assessment. This paper proposes a safety risk assessment method based on Grey Relational Analysis （GRA） and Radial Basis Function （RBF） neural network models for coal mine safety risk pre control management. Firstly, integrating a large amount of coal mine environmental data, constructing a multi-level safety risk assessment system, comprehensively considering the impact of each level and element on safety risks. Then, using the GRA algorithm, key pre control management indicators are determined based on the urgency of safety risks, ensuring the accuracy and pertinence of the evaluation. Finally, utilizing the powerful nonlinear mapping ability of RBF neural network, especially its radial basis function for fine processing of high weight safety risk indicators, and defining the topological structure processing process of each layer of the neural network, the evaluation results are ultimately output. To verify the effectiveness of this method, this study prepared a diverse set of safety risk datasets and performed dimensionality reduction to generate different numbers of safety indicators and match them with different clustering parameters. In the comparative experiment, the new method is tested in parallel with two mature safety risk assessment methods, with MAPE as the core evaluation indicator. The research results show that the MAPE values output by the safety risk assessment method based on the GRA-RBF neural network model designed are significantly improved, indicating that it can more accurately predict high-risk safety evaluation indicators, provide corresponding risk evaluation standards for coal mine safety risk pre control management, and to a certain extent ensure the smooth progress of coal mine safety work. It can provide strong technical support and decision-making basis for coal mine safety risk pre control management.