Dynamic Stacking ensemble monitoring model of dam displacement based on the feature selection with PCA-RF

The factors that affect the prediction accuracy of monitoring models are the selection of environmental features, the optimization of model hyper-parameters, and the robustness of the model itself. For dam systems affected by multiple factors, there is usually a multi-collinear relationship between features. Eliminating the collinearity problem and selecting the optimal feature subset are the essential methods to affect the performance of the monitoring model. The super-parameters of the model do not depend on data-driven but need to be set artificially before training. Choosing an appropriate hyper-parameter optimization algorithm can optimize the training effect of the model. In this paper, a feature selection method with PCA-RF is proposed, which employs principal component analysis (PCA) to reconstruct the feature with equal dimensional mapping to eliminate the collinearity of the feature set. Then, based on the feature importance evaluation method of random forest (RF) to eliminate the interference factors in the new feature set to improve the model's prediction accuracy. The Bayesian optimization algorithm is introduced to optimize the model hyper-parameters. Secondly, based on the idea of Stacking ensemble, the dam displacement monitoring models of support vector regression (SVR), MLP neural network (MLP), and Gaussian process regression (GPR) are integrated, and static and dynamic monitoring Stacking heterogeneous ensemble models are proposed, respectively. Based on the dynamic monitoring model, the dynamic monitoring index of the dam service status is realized by the confidence interval estimation method. Finally, an engineering example is given to verify the prediction ability of the method. The results show that the feature selection method with PCA-RF has good adaptability to deal with collinear feature selection, the Bayesian optimization algorithm can optimize parameters efficiently. The prediction performance of the dynamic Stacking ensemble monitoring model has higher accuracy and robustness. The monitoring indexes have the advantage of dynamic updating, which provides a more reliable basis for the dynamic safety warning of dam deformation.

Automated summary

This paper proposes a method to improve the prediction accuracy of monitoring models, including feature selection, hyper-parameter optimization, and model ensemble. By eliminating the collinearity problem between features and optimizing model hyperparameters, the prediction accuracy of the monitoring model is improved, and dynamic monitoring indexes are realized using the confidence interval estimation method.