针对单一模型在大坝变形预测中精度不高的问题,提出一种基于LS-SVM—马尔科夫模型的预测方法,即基于LS-SVM模型的预测结果,利用马尔科夫模型对其进行误差修正,从而提高了预测精度。通过对某拱坝变形的预测分析,并与LS-SVM模型预测结果进行对比,发现LS-SVM—马尔科夫模型的预测结果较符合实际情况,该模型具有更高的预测精度和优越性。 Aiming at the problem that single model is not accurate enough in dam deformation prediction, a prediction method based on LS-SVM-Markov model is proposed, which is based on the prediction results of LS-SVM model, Correction, thus improving the prediction accuracy. By predicting the deformation of an arch dam and comparing it with the prediction results of LS-SVM model, it is found that the prediction results of LS-SVM-Markov model are more realistic. The model has higher prediction accuracy and superiority.