Research on the farthest scattering distance of blasting flying stones based on improved WOA-BP neural network

The flying rocks in mining blasting operations pose a great threat to safety production, and the reasonable division of safety blasting scope is of great significance for production operations. In response to the problem of the farthest scattering distance of flying rocks in mining blasting operations, based on the excellent nonlinear mapping ability of BP neural network and mature research on its theory and application, WOA (whale optimization algorithm) is used to optimize the BP neural network, improving its weak global search ability and poor anti-interference ability. And adaptive weight adjustment is introduced, and an improved WOA-BP neural network model is applied to predict the farthest scattering distance of flying rocks in mining blasting. The minimum burden of blasting, unit consumption of blasting explosives, and maxi-mum charge weight of a single hole, which have a greater impact on the distance of flying rocks during blasting operation, are selected as input variables. The experimental results show that the average absolute error MAE, mean square error MSE, root mean square error RMSE, and average absolute percentage error MAPE of the improved WOA-BP model are 0.52283, 0.60303, 0.77655, and 2.8102%, respectively, which are better than the comparison model, indicating that the prediction accuracy of the model is high, it can provide guidance for actual mine blasting production.