Study Of Combined Evaluation About Emergency Plans In Railway

In recent years, due to emergencies in some industries are becoming more frequent, so emergency management is more and more attention, and emergency plans as the core content of emergency management is natural can’t be ignored. Establish comprehensive and rational emergency plan system is the premise and requirement to improve the capability of emergency response, and the railway transport safety requires that. In this paper, the object of study is emergency plan in railway, and this paper uses qualitative and quantitative methods to evaluate the emergency plans in railway.First, this paper studies the literature of the emergency plans and the characteristics of the emergency plan in railway, and analysis the basic content of the emergency plan in railway, including general principles, identification of sources of danger, and emergency response etc.. The system of the emergency plan in railway includes comprehensive emergency plans, special emergency plans, and station emergency plans. The management of emergency plan in railway involves the preparation of plans, plan approval, the using of plans, and plan amendments. Using the Analytic Hierarchy Process to select evaluation indexes, it gets the system of evaluation indexes of the emergency plan in railway.Secondly, due to the used evaluation method of the emergency plan in railway is single, this paper proposes three kinds of combined evaluation method:combined evaluation based on fuzzy theory and AHP about emergency plans in railway, combined evaluation based on AHP and neural network about emergency plans in railway, and combined evaluation based on genetic algorithm and fuzzy neural network about emergency plans in railway.Combined evaluation based on fuzzy theory and AHP about emergency plans in railway, which uses the AHP to determine the weight of each index by the different affects of each index. The evaluation indexes are qualitative and fuzzy, so use the fuzzy function to determine the degree of membership to the fuzzy comprehensive evaluation. The combined evaluation model focused on the advantages of the Analytic Hierarchy Process and fuzzy theory, and the combined evaluation method is effective to evaluate the emergency plans.Combined evaluation based on AHP and neural network about emergency plans in railway, at the first, using of the AHP to determine the weight of the indexes, then can get the comprehensive value of each evaluation index. Build BP neural network evaluation model and define the index value and the comprehensive evaluation value as the input and output in the network. According to the learning and training of the network can get good results and accumulate of knowledge and experience of experts. If need to evaluate the emergency plans in the future, we can input the index value to the trained BP network, it will get the results of the evaluation results. It can avoid evaluation errors caused by human factors in the process to improve the accuracy of the evaluation.Combined evaluation based on genetic algorithm and fuzzy neural network about emergency plans in railway, first build fuzzy neural network using genetic algorithm to optimize the network. By entering the sample data and training repeatedly, get the minimum error of the center of the Gaussian membership function, the connection between the width and the normalized layer and output layer weights. Finally input the value of the evaluation index to the trained fuzzy neural network, can get the evaluation results of the emergency plans. This method can avoid the influence of subjective factors, so that the evaluation more objective, accurate and reasonable.Finally, these three methods apply to emergency plans in railway. The evaluation results show that these three models can do a good evaluation. Through the analysis of the results of the evaluation get specific recommendations to modify plans.