Corrosion Rate Prediction of Substation Grounding Network Based on Dung Beetle Algorithm Optimised Support Vector Machine

In order to improve the accuracy of corrosion rate prediction of substation grounding network, this paper proposes a Support Vector Machine (SVM) prediction method based on Dung Beetle Optimizer (DBO). Firstly, moisture content, soil resistivity, porosity, ${\text{S}}{{\text{O}}_4}^{2 - }$ and Cl<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-</sup> concentrations, and the corrosion rate of the grounding grid were selected as input variables for the prediction model. Then, the parameters of SVM were optimised using the DBO algorithm, so as to construct a prediction model for the corrosion rate of substation grounding network. Finally, a case study was carried out through the corrosion test data and compared with the effects of other prediction methods. The results show that the mean square error of the proposed model is 0.0118g•dm<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2-</sup>•a<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-1</sup>, the average absolute percentage error is 1.90%, the relative error standard deviation is 0.1214, and the error fluctuation is significantly lower than that of the other methods, showing higher prediction accuracy. This verifies the effectiveness and superiority of the proposed method for predicting the corrosion rate of substation grounding network.