基于遗传支持向量机的地下工程裂隙岩体注浆量预测

提出了地下工程裂隙岩体注浆量预测的遗传支持向量机方法，通过支持向量机对实际注浆数据样本进行学习，建立注浆量及其影响因素之间的非线性映射关系，基于这种关系实现注浆量的预测。模型建立过程中，考虑到支持向量机惩罚因子和核参数对预测精度的影响，以预测误差为适应度，采用遗传算法对最佳参数进行搜索。结果表明，本文方法计算快速，预测精度高，是一种注浆量预测的好方法。

Forecasting grouting in fractured rock mass of underground engineering based on genetic algorithm-support vector machine

In order to improve the accuracy and overcome the extra learning problem of ANN, a new method coupling genetic algorithm (GA) and support vector machine (SVM) is proposed to forecast the grouting in the fractured rock mass. By learning samples, the SVM model with optimal penalty factor and kernel parameter which are searched out by using the SVM predicting error as the fitness of GA is established which can reflect the nonlinear relation between the grouting and its affecting factors. The practical examples have been computed to testify the efficiency and ability of this method; and the calculational results show that the method has rapid speed and sufficient predicting accuracy.