Blasting Fragmentation Prediction Based On BFO-LSSVM Algorithm

Accurate and reasonable prediction of the distribution of blasting fragmentation is of great significance for improving the efficiency and economic benefits of water conservancy and hydropower blasting.However,there are many factors affecting the blasting block,and it is difficult to consider all the factors at the current block prediction.In order to solve this problem,this paper constructs a blasting block prediction model based on intelligent algorithm,and writes a convenient and fast blasting block prediction software through MATLAB's App Designer module.The main research contents of this paper are:1.The BFO-LSSVM model is constructed,and the parameters C and g of the least squares support vector machine model are optimized by the bacterial foraging algorithm with good robustness and strong global search ability.In this way,the purpose of optimizing model performance and improving the accuracy of block prediction can be achieved.2.Using the MATLAB App Designer module to design a visual blasting block prediction software.The software can be used to train block samples and make predictions.The operation interface is user-friendly and easy to promote.3.By the data of the blasting block collected at the blasting site of the Aertashi hydraulic project,the blasting block data available for analysis is obtained.4.The gradation curve of the blasting fragmentation data is predicted by the software written in this paper,and the predicted gradation curve is analyzed.The results show that the predicted accuracy of the BFO-LSSVM model is accurate.Combined with the written visualization software,it is easy to accurately predict the gradation curve of the explosion excavation of the dam under the determined blasting parameters.