基于最小二乘支持向量机的大坝应力预测模型

Dam's Stress Prediction Model Based on LS-SVM Method

应力的监测一直是大坝安全监测中极为重要的部分,传统的预测方法精度有时候不高,为了提高预测的精度,提出了一种基于最小二乘支持向量机(LS-SVM)的大坝应力预测模型。通过具体工程实例计算,LS-SVM表现出很好的鲁棒性和预测精度高的优势,应力预测精度比传统的逐步回归方法提高了很多,为大坝应力分析提供了一种可靠的、有效的途径和方法。

The stress monitoring has been an extremely important part in dam monitoring.Sometimes the traditional forecasting methods have no high accuracy.In order to improve the accuracy of prediction,a dam＇s stress prediction model is proposed here based on Least Squares Support Vector Machines（LS-SVM）.Through applying in one dam,LS-SVM shows the advantages of good robustness and high prediction accuracy,and its stress prediction accuracy is improved a lot than that using the traditional stepwise regression method,so as to provide a reliable and effictive way and means in dam stress analysis.