Research and Calculation on Emergency Rescue Reliability Model through Entropy Weight-BP Neural Network

In order to evaluate the reliability of the emergency rescue capability of the coal mine in a safe and accident-free time, this article combines the research results of emergency rescue evaluation at home and abroad to construct an emergency rescue reliability index composed of three first-level indicators and 11 second-level indicators. system. The entropy method is used to obtain the objective weight of each indicator in the indicator system, and combine it with the original data to obtain a comprehensive score. In order to train the optimal BP neural network model, the original data is used as the input data of the BP neural network, and the comprehensive score is used as the output data. Proved by examples, the BP neural network optimized by the entropy method has certain accuracy and reliability for evaluating the emergency rescue capability of coal mines.