论文部分内容阅读
针对露天矿边坡稳定性问题的小样本、非线性等特点,利用遗传算法的全局搜索能力优势,提出了基于遗传算法的最小二乘支持向量回归参数寻优方法,并建立基于遗传最小二乘支持向量回归(GA-LSSVR)的露天矿边坡稳定性预测模型。通过遗传算法对LSSVR进行优化,提高了预测精度和速度。实验结果表明,与BP神经网络、LSSVR模型相比,GA-LSSVR的精度更高,基于GA-LSSVR的露天矿边坡稳定性预测模型更有效。
In view of the small sample and nonlinearity of slope stability problem in open pit mine, the optimization method of least squares support vector regression parameters based on genetic algorithm is proposed by using the advantage of global search ability of genetic algorithm, and the genetic algorithm based on genetic least square Support vector regression (GA-LSSVR) for slope stability prediction of open pit mine. The LSSVR is optimized by genetic algorithm to improve the prediction accuracy and speed. Experimental results show that compared with BP neural network and LSSVR model, GA-LSSVR is more accurate and the GA-LSSVR based prediction model of slope stability is more effective.