Research on Radio Interference of AC/DC Parallel Transmission Line

The radio interference generation mechanism of AC-DC parallel transmission lines is different from that of conventional lines, so that the prediction model is either too rough and leads to large errors, or too complicated to be mastered by engineers. In order to take into account the accuracy of radio interference solution and engineering practicability, an error back-propagation feedforward neural network model combined with gray correlation theory is proposed. First, the gray theory screening of multiple impact indicators of radio interference, and then the indicators that have a real impact on radio interference as input variables, the BP neural network fitting algorithm is used to predict the radio interference. Validation combined with the actual measured radio interference samples of the AC-DC parallel transmission lines that have been put into operation, the results show that compared with the traditional algorithm, the prediction accuracy of the BP neural network prediction model is improved by 14.6%.