Petrochemical enterprise safety evaluation method based on PSO-BP neural network

Abstract

The invention discloses a petrochemical enterprise safety evaluation method based on a PSO-BP neural network. The petrochemical enterprise safety evaluation method comprises the steps of 1, determining an index system (influence factors) of a petrochemical enterprise safety state; step 2, constructing a PSO-BP neural network model; 3, collecting a data sample; step 4, inputting the training sample to train the PSO-BP neural network; step 5, obtaining parameters such as corresponding weights of the PSO-BP neural network and a trained neural network security evaluation model; and 6, evaluating the safety state of the petrochemical enterprise. According to the method, the workload of manual evaluation is reduced, the subjective influence of evaluation personnel is greatly reduced, the accuracy and objectivity of the safety evaluation result of the petrochemical enterprise are improved, and technical support is provided for mastering the safety operation of the petrochemical enterprise.

Description

technical field [0001] The invention relates to a safety evaluation method for petrochemical enterprises based on a PSO-BP neural network, belonging to the technical field of safety engineering. Background technique [0002] As a basic industry with wide correlation and strong driving force, the petrochemical industry is closely related to the national economy and people's life, and its development level also represents the economic strength of a country or a region. However, due to the particularity of petrochemical products, the production of petrochemical enterprises has the characteristics of flammability, high temperature and high pressure, poisonous and harmful, etc., and the safety problems are prominent. Once a safety production accident occurs in a petrochemical enterprise, it may cause serious casualties and huge property losses. At present, petrochemical enterprises generally have established a trinity management system of HSE (Health: Health, Safety: Safety, Env...

AI Technical Summary

Problems solved by technology

Although the neural network can make certain predictions and evaluations on the chemical process and safety, from the research on the safety evaluation model constructed by the neural network, the neural network can be used to describe the complex chemical process and the safety status of petrochemical enterprises under the condition of limited data. The expressive ability of the function is limited, the parameter setting is random, and the ability to extract features describing the complex security state is subject to certain constraints. Therefore, the application of artificial neural networks to the security evaluation of petrochemical enterprises has the possibility of further improvement

[0004] In summary, there are some unavoidable defects in the use of BP neural network to evaluate the safety of petrochemical enterprises at home and abroad. The BP algorithm is an optimization method of local search, and the safety evaluation of petrochemical enterprises is a complex nonlinear global extremum problem. , the BP algorithm is likely to fall into a local extremum, so that the network training fails

The particle swarm optimization (PSO, particle swarm optimization) algorithm is a swarm intelligence optimization algorithm in the field of computational intelligence, which can solve the optimal value for the weight and deviation of the BP neural network through the particle swarm optimization algorithm, but it has not yet Research on Safety Evaluation of Petrochemical Enterprises Using PSO-BP Neural Network

Images