基于探地雷达与PSO-BP神经网络的煤岩界面预测研究

打开文本图片集

中图分类号：TD67 文献标志码：A

Abstract：To address the problem of insuficient accuracyin the applicationof ground-penetrating radar for coal-rock interface prediction，the Particle Swarm Optimization （PSO）algorithm was used to optimize the BP neural network，andacoal-rock interface prediction model basedon ground-penetrating radarandPSO-BP neural network was established.The single-sided reflection method of ground-penetrating radar was employed to detect the coal-rock interface，and the radar image response characteristics under different conditions were summarized to determine thecoal-rock interfacecharacteristic parameters，includingcoal proportion，amplitude at theresponse position，average amplitude at coal response position，amplitude attenuation value，two-way travel time of reflection wave，electromagnetic wave velocity，andcoaldielectricconstant.Basedontheselectedcharacteristic parameters，dielectric constant testsand simulated coal-rock interface recognition experiments were caried out to obtain measured sample data.The PSO algorithm was used to optimize the weights and thresholds of the BP neuralnetwork toobtain the optimal model.Thecoal-rock interfacecharacteristic parameters were then input into the PSO-BP neural network model to predict the coal-rock interface.The experimental results showed that， compared with GA-BP and BP neural network models，the MSE of the PSO-BP model decreased by 22.14% and 45.54% ，the MAPE decreased by 22.22% and 46.15% ，and the MAE decreased by 31.58% and 55.68% ， respectively.ThePSO-BPmodel has significantadvantages inpredictionaccuracy，errorcontrolability，anddata fiting performance，predicting coal-rock interface positions closer to the actual locations with better stability.

Key words： coal-rock interface recognition; ground-penetrating radar;BP neural network; particle swarm optimization algorithm;PSO-BP neural network; characteristic parameters

0引言

煤岩界面识别是实现煤矿智能化和无人化开采的关键技术之一[1-3]。（剩余10550字）