Radiator threat assessment based on MEA-BP neural network

Abstract

In order to promote the effectiveness of radiation threat assessment, this article builds the mind evolutionary algorithm (MEA) to optimize the BP neural network model of radiation threat assessment. The mind evolutionary algorithm was used to optimize the BP neural network model, through global population convergence and local populations of alienation, the network’s initial weights and threshold and then training the BP neural network, overcoming the random initial value when the disadvantages of neural network fall into the local optimum. The experimental results show that the evaluation results of the BP neural network optimized by the thinking evolution algorithm are significantly smaller than the mean square error of the BP neural network, this algorithm can quickly and effectively implement radiation threat assessment.