Abstract:

To ensure the structural safety in smart grid construction, the accurate information on the diameter of steel bars in concrete structure can be obtained by effective detection methods. According, an improved random forest eddy current detection method for predicting the steel diameter is proposed. The principal component analysis(PCA) is used to reduce the dimensionality of features, eliminate the redundant information and highlight the key features. At the same time, the K-nearest neighbors(KNN) algorithm is introduced to optimize the leaf node prediction of the random forest model, thereby improving its generalization ability and robustness. The sample data is collected by constructing a finite element model with the help of Ansys Maxwell electromagnetic simulation software, and mean square error(MSE), mean absolute error(MAE) and mean absolute percentage error(MAPE) are adopted as evaluation indexes. The results demonstrate that the proposed method achieves significantly higher prediction accuracy than the traditional random forest model on the test set. The proposed method has been shown to effectively enhance the performance of the random forest model, demonstrating the advantages of high efficiency and accuracy in the non-destructive testing of steel bar diameter in smart grid construction, with the wide application potential in practical engineering.

Key words: improve random forest, steel bar diameter detection, eddy current testing, principal component analysis, K-nearest neighbor(KNN)