Risk assessment of power supply enterprises based on improved BP neural network

With the development and reformation of china's power market, the environment of production and management is changing fundamentally. Considering the risk characters of power supply enterprises, this paper builds a risk evaluation index system including quantitative and qualitative indices and then creates an improved BP neural network to evaluate risks of power supply enterprises. In order to make the output of the neural network more objective, Principal Component Analysis(PCA) is uesd to estimate the output before training the network. At last, a test is made to demonstrate the effectiveness of the neural network and the result shows that this method can be adopted in the risk assessment of power supply enterprises since it could give an accurate judgment of risk management.