Power transmission line audible noise evaluation method and system based on optimized BP neural network

Abstract

The present application belongs to the technical field of audible noise evaluation, and provides a power transmission line audible noise evaluation method and system based on an optimized BP neural network. In view of the problem that the influence degree of audible noise generated by a power transmission line on residents is difficult to evaluate, the scheme is as follows: firstly, the threshold value and weight value of the traditional BP neural network are globally optimized by using the mayfly algorithm improved by offset evolution and a Tent chaotic sequence. Then, the octave band sound pressure level features of the audible noise signal of the power transmission line are extracted, and then a neural network model with the features as input and the subjective evaluation value as output is constructed. Finally, training and testing are performed. The METCMA-BP neural network is used to evaluate the size of the audible noise of the power transmission line, so that the evaluation result fully considers the subjective ideas of the nearby residents and the objective environmental conditions of the area where the power transmission line is located, and the evaluation result is more accurate.

Images