论文部分内容阅读
区域能源安全预警研究对于解决中国现阶段区域能源安全突发事件频现问题,保障区域经济与区域安全协调发展具有重要现实意义。本文以区域能源安全外生警源为研究对象,通过对区域能源安全事件案例收集及整理,构建了能源安全外生警源预警指标和数据集。融合模糊积分(Fuzzy Integral)、遗传算法(Genetic Algorithm)和神经网络(Neural Network)等方法的基本原理,设计了区域能源安全外生警源分级预警的FI-GA-NN模型,该模型首先利用模糊积分方法评估出区域能源安全外生警源样本分级预警的期望值,然后利用训练样本对遗传神经网络进行训练,最后对外生警源测试样本进行分级预警。实验测试结果表明:(1)利用FI-GA-NN模型对外生警源训练样本(1999-2006年)进行拟合训练,模型收敛速度快,训练到第717步时,模型误差平方和小于期望值。经过大约60代的搜索后模型的拟合度趋于稳定,模型训练的实际输出值与期望输出值较接近;(2)利用FI-GA-NN模型对能源安全外生警源测试样本(2007-2015年)进行分级预警,预警准确率较高,能有效提高区域能源安全外生警源预警的正确性,降低预警风险,模型体现出了较强的应用价值。
It is of great practical significance to study the early warning of regional energy security in order to solve the frequent problems of regional energy security emergencies at present and ensure the coordinated development of regional economy and regional security. In this paper, the exogenous source of regional energy security is taken as the research object. By collecting and arranging the cases of regional energy security incidents, the warning indicators and data sets of exogenous source of energy security are constructed. Combining with the basic principles of Fuzzy Integral, Genetic Algorithm and Neural Network, the FI-GA-NN model of exogenous warning classification of regional energy security is designed. This model first utilizes Fuzzy integral method is used to evaluate the expectation of grading warning of exogenous source samples of regional energy security. Then, the training sample is used to train the genetic neural network, and finally the exogenous source samples are classified and pre-warned. Experimental results show that: (1) The FI-GA-NN model is used to fit the training of exogenous source samples (1999-2006), and the convergence speed of the model is fast. When training reaches the 717th step, the square error sum of the model errors is less than the expected value . After approximately 60 generations of searching, the fitting degree of the model tends to be stable, and the actual output value of the model training is close to the expected output value; (2) Using the FI-GA-NN model to test the energy security exogenous source test sample 2015), the accuracy of early warning is high, which can effectively improve the correctness of early warning of exogenous source of energy security and reduce the risk of early warning. The model shows strong application value.