Aerodynamic Characteristics Analysis of Iced Conductor Based on BP Neural Network

Major disasters and losses would be caused by the galloping of transmission lines. The basis for studying the galloping mechanism of transmission lines is to analyze the aerodynamic characteristics of iced conductors. The wind tunnel test is a traditional way to obtain the aerodynamic coefficients of an iced transmission line under wind load. Due to the high cost and long duration of wind tunnel tests, an experimental method based on machine learning to predict aerodynamic coefficients is proposed. Here, the steady and unsteady aerodynamic coefficients of an iced conductor under different parameters were obtained by wind tunnel test, and then the aerodynamic coefficients of the iced conductor under different parameters were predicted by machine learning. The aerodynamic coefficients of each iced conductor varied with the angle of wind attack by the wind tunnel test. The Den Hartog and Nigol coefficients determined based on the aerodynamic coefficients obtained by machine learning and wind tunnel test are in agreement. The results show the feasibility of the machine learning prediction method.

Dieses Werk wurde unter der Creative-Commons-Lizenz Namensnennung 4.0 International (CC-BY 4.0) veröffentlicht und darf unter den Lizenzbedinungen vervielfältigt, verbreitet, öffentlich zugänglich gemacht, sowie abgewandelt und bearbeitet werden. Dabei muss der Urheber bzw. Rechteinhaber genannt und die Lizenzbedingungen eingehalten werden.