Rockburst intensity prediction is one of the basic works of underground engineering disaster prevention and mitigation. Considering the dynamic variability and fuzziness in rockburst intensity prediction, variable fuzzy sets (VFS) are selected for evaluation and prediction. Here, there are two problems in the application of traditional VFS: (i) the relative membership degree (RMD) calculation process is complex and time-consuming, and the RMD matrix of all indexes can be only obtained by using the RMD function repeatedly; (ii) unreasonable weights of indicators have great impact on the synthetic relative membership degree (SRMD), so it is difficult to guarantee the correctness of the final prediction result. In view of the above problem, this paper established three simplified feature relationship expressions of RMD based on VFS principle and used the SRMD function to establish a BP neural network model to optimize SRMD. The improved VFS method is more efficient and the prediction results are more stable and reliable than the traditional VFS method. The main advantages are as follows: (1) the improved VFS method has higher computational efficiency; (2) the improved VFS method can verify the correctness of RMD at all times; (3) the improved VFS method has higher prediction accuracy; and (4) the improved VFS method has higher fault tolerance and practicability. because rockburst is a very complex nonlinear dynamic phenomenon, it needs many methods to combine and complement each other to accurately predict the intensity of rockburst. Therefore, it is still necessary to introduce new theories and methods to study the occurrence of rockburst and intensity classification prediction.Based on fuzzy mathematics, Chen [15] has proposed the variable fuzzy sets (VFS) method with relative membership degree (RMD) and synthetic relative membership degree (SRMD) at the core. This method establishes the corresponding VFS model according to the index classification level; then, the RMD function is established by using the VFS model corresponding to each level, and finally the method uses the SRMD function to combine the RMD values and weights of each index to get the final result. Compared with the fuzzy mathematics method, this method considers the dynamic variability and fuzziness of objective things, which improves the reliability of the prediction results [16]. Thus, the VFS method has been widely used in many multi-attribute decision-making problems, such as flood disaster risk assessment [16], surrounding rock stability assessment [17], water resources carrying capacity assessment [18], runoff prediction [19], and so on. Although the indexes and classification criteria are different in different evaluation types, the principle of the VFS method and the characteristics of RMD and SRMD functions are unchanged.Recently, the research of VFS mainly focuses on the application of the VFS method in different fields and the development of some new methods. For example, Guo et al. [20] applied the VFS model to landslide stability eva...