为有效提高造价预测的准确性,建立EEMD-SVM模型,将造价的历史数据平稳化处理后作为输入,利用支持向量机(SVM)对各造价分量进行预测,经叠加得到输电线路工程的造价预测值。以某地区110k V输电线路工程造价的历史数据为样本,经EEMD-SVM预测,结果经过平均相对误差(MAPE)、均等系数(EC)以及均方根误差(RMSE)检验,误差较小。因此,该模型在一定程度上提高了输电线路工程造价的预测精度,对于提升造价管理的精益化水平具有一定的参考价值。 In order to effectively improve the accuracy of cost forecasting, the EEMD-SVM model is established, the historical data of construction cost is smoothed and used as input, and each cost component is predicted by using Support Vector Machine (SVM). The cost forecast of transmission line project is obtained by superposition value. Based on the historical data of project cost of 110k V transmission line in a certain area, the EEMD-SVM predicts the result is less error with the MAPE, EC and RMSE tests. Therefore, the model improves the prediction accuracy of transmission line project cost to a certain extent, which is of certain reference value for improving the lean level of cost management.