The Research On The Chemical Industry Risk Analysis Based On The BP Neural Network

Due to the production particularity of chemical industry, chemical accidents often caused much property loss,casualties and environment pollution, the consequence was very serious. Carrying on accurate, quick and comprehensive risk analysis is pivotal to the performance of emergency logistics risk management. Therefore, it is necessary for the indeed study on the ERA of chemical industry.This paper carried out a new appraising method which is based on the BP neural network. The method was carried on the base of the research on the appraising index system and appraising method of ERA which already exist. The paper built an appraising index system first. Then according to the index system, designed the BP nerve network model, and gave out the feasible valuation procedure. On reckoning, the paper used the MATLAB2009a neural networks case (NNT) to design the net and calculate. Training and testing by studying a sample book, made the model error reach the predetermined range inner. The conclusion showed that using BP neural network model for ERA of chemical industries had relatively high accuracy, which can reach the order of 10-5, meanwhile the output precision can reach the order of 10-4.Finally, the paper used an example to verify that this method is effective and operational,With the DSM Vitamins (Shanghai) polyester resin expansion project as an example, the results showed its risk is 0.3860, lower risk. Meanwhile, by analyzing the change of the overall risk value caused by the change of indicators'value, can easily know that the most effective measures to reduce the risk is to reduce the material storage volume.The ERA model based on the BP artificial neural network provides a simple, objective and practical method for ERA.