冲击地压危险等级预测的PSO-SVM模型

为了对冲击地压进行有效的预测,分析了冲击地压的主要影响因素,建立了基于粒子群优化支持向量机方法(PSO-SVM)的冲击地压危险程度预测模型,并通过实例,对PSO-SVM模型的预测效果进行了检验,同时还分别采用了BP神经网络(BP-NN)和支持向量机方法(SVM)对实例进行了预测,最后对三种方法的预测精度进行了比较分析,结果显示:PSO-SVM方法的预测精度要高于BP-NN和SVM方法的预测精度,可见,PSO-SVM预测方法对煤矿冲击地压危险程度预测具有一定的参考价值和指导意义.

Prediction of Rock Burst Intensity Based on PSO-SVM Model

In order to effectively predict rock burst, the main factors influencing rock burst were analyzed, and the PSO-SVM model for predicing the degree of rock burst risk was established and tested. Furthermore, the BP neural network （BP-NN） prediction model and the Support Vector Machine （SVM） prediction＇model were established and applied ＇to predict the same instance. And the prediction results show that the prediction accuracy of the PSO-SVM model is higher than that of BP network and SVM. So the PSO-SVM method is effective for rock burst prediction.