Abstract: The research on the harmonic loss of cable lines at home and abroad is mainly calculated through electromagnetic physical analysis. The correction of equivalent parameters mostly relies on empirical formulas, and the accuracy is lacking. In order to accurately evaluate the harmonic loss of the cable line, an intelligent loss evaluation model based on the vertical and horizontal crossover algorithm to optimize the BP neural network is proposed. Cable lines under the influence of harmonics generally have various harmonic orders, variable content of each order, and many influencing factors of training samples. The use of traditional BP algorithm has the disadvantages of slow convergence and easy to fall into local optimum. In order to overcome these shortcomings, the BP neural network is optimized by the cross-over algorithm with stronger search ability, and the intelligent evaluation model of the cable line harmonic loss based on the CSO-BP neural network is obtained. The loss evaluation value of the model, the traditional BP model evaluation value and the calculation value of the physical formula method are compared. The simulation results show that the result of the cable harmonic loss intelligent evaluation model proposed in this paper is closer to the actual value and has a higher value. Accuracy and stability.

Key words: Cable, Loss, Harmonic, BP neural network, CSO algorithm