Engineering Item Risk Evaluating based on Evolutionary Algorithm and BP Neural Network

The purpose of this paper is to improve the risk evaluating quality of engineering item. The topology structure of evolutionary algorithm based BP (EABP) neural network is described, the principle of EABP neural network is introduced, and the implement step of EABP neural network is given. The combination algorithm is applied to risk evaluating for the engineering item, and its result is compared with that of conventional BP neural network. The comparing result shows that EABP neural network fits to complex system such as risk evaluating for engineering item, it improves in a certain extent on training speed and precision, it can improve the quality of engineering item risk evaluating, and it fits to solve some problems in which evaluating indexes weights are difficult to be determined or there exists complex non-linear relation among them.