In order to study the damage in coal rock under high pressure water jet, which is closely related to the efficiency of coalbed gas drainage, a three-dimensional damage numerical model is est
ablished. Based on the simulation results and PSO-BNPP (particle swarm optimization, PSO and back-propagation neural network, BPNN) method, a damage prediction model of high pressure water jet impacting coal rock was established. The results show that the mean absolute error, the mean absolute percentage error of the model are 1.23 and 7.45% respectively, and the actual and the predicted values show significant positive correlation. In this sense, the model can describe the relationship between the coal roc k damage and the water jet parameters well.