基于BP神经网络的高速铁路风险评价模型研究

发布时间：2018-12-24 06:43

【摘要】：随着高铁的飞速发展,让人们的出行越来越便捷,为国家的经济发展增添了新的活力。轨道交通作为国家的经济大动脉,其能否安全运营直接关系着人民的财产生命安全。因为铁路具有性能安全、可靠、高效、运输距离长、运输成本低并且运输能力强、环保、在大多恶劣天气下均能进行运输作业等诸多无与伦比优势,都是公路、海运、航空无法比拟的,所以铁路是陆上的主要运力。但是,由于我国的高铁建成时间较短、采用的新技术、新设备较多,再加之我国的高铁覆盖范围广等诸多因素使得高铁在建设和运营上面临着诸多风险问题。因此,为了保障高铁的安全运营,铁路部门将系统的安全理论引入到了高铁的管理中并大力推行针对高铁的风险管理体系,加大对铁路风险的管控力度,从而降低事故发生的可能性,为高铁的安全开行保驾护航。本文主要针对高铁中存在的风险隐患,建立适当的评价指标体系,并采用BP神经网络方法建立模型。从而利用建立的模型对高铁进行风险评价并得出相应的结论和整改建议。本文首先针对高铁上存在的风险隐患,采用故障树的方法识别出影响高铁安全运营的主要因素,并建立相应的评价指标体系。然后采用模糊算法量化出20条样本铁路的数据,再采用加权求和法降低数据的主观性。另外为了简化网络的输入,提高了网络的收敛速率。因此,当输入数据的维数较大时,采用主成分分析法对归一化后的分数进行降维处理,从而简化BP网络结构,提高了训练速率。其次,的指标体系进行降维处理后,将得到的前15条铁路的的分数作为BP神经网络的训练数据,后5条铁路的分数作为BP神经网络的测试数据。测试结果表明该风险评价模型的预测精度达到了95%,因此该高铁风险评价模型是有效的。最后,对京沪高铁同时采用BP神经网络模型评价和模糊评价法进行评价,分别得出京沪高铁的相应的风险状况,并对两种评价法进行了分析、比较。此外,还根据主成分分析法中主成分公式的系数分析了影响高铁安全的主要指标因素。进而,可以将有限的人力物力投入到对这些主要因素的管控和处理上,将好钢用在刀刃上,从而对高铁的安全管理更加的有的放矢。
[Abstract]:With the rapid development of high-speed rail, people travel more and more convenient, adding new vitality to the country's economic development. As the national economic artery, whether rail transit can operate safely or not is directly related to the safety of people's property. Because the railway has many unparalleled advantages, such as safety, reliability, high efficiency, long transportation distance, low transportation cost, strong transportation capacity, environmental protection, and the ability to carry out transportation operations in most bad weather, all of them are roads, sea transportation, etc. Aviation is incomparable, so rail is the main onshore capacity. However, due to the short construction time of high-speed railway in China, the new technology and equipment, and the wide coverage of high-speed rail in China, the construction and operation of high-speed rail are facing a lot of risk problems. Therefore, in order to ensure the safe operation of the high-speed railway, the railway department has introduced the safety theory of the system into the management of the high-speed railway and vigorously promoted the risk management system for the high-speed railway, and increased the control of railway risks. Thus reducing the possibility of accidents, for the safety of high-speed rail escort. In this paper, an appropriate evaluation index system is established for the hidden risks in high-speed rail, and the BP neural network method is used to establish the model. The model is used to evaluate the risk of high-speed rail, and the corresponding conclusions and corrective suggestions are obtained. In this paper, the main factors affecting the safety operation of high-speed railway are identified by fault tree method, and the corresponding evaluation index system is established. Then the fuzzy algorithm is used to quantify the data of 20 sample railways, and the weighted summation method is used to reduce the subjectivity of the data. In addition, in order to simplify the input of the network, the convergence rate of the network is improved. Therefore, when the dimension of the input data is large, the normalized fraction is reduced by principal component analysis, which simplifies the BP network structure and improves the training rate. Secondly, after dimensionality reduction, the scores of the first 15 railways are taken as the training data of the BP neural network, and the scores of the last 5 railways are taken as the test data of the BP neural network. The test results show that the prediction accuracy of the model is 95%, so the model is effective. Finally, the BP neural network model and fuzzy evaluation method are used to evaluate the Beijing-Shanghai high-speed railway, and the corresponding risk status of the Beijing-Shanghai high-speed railway is obtained, and the two evaluation methods are analyzed and compared. In addition, according to the coefficient of principal component formula in principal component analysis, the main index factors affecting the safety of high iron are analyzed. Furthermore, the limited manpower and material resources can be put into the management and treatment of these main factors, and the good steel can be used on the blade, thus the safety management of high-speed railway can be more targeted.
【学位授予单位】：西南交通大学
【学位级别】：硕士
【学位授予年份】：2014
【分类号】：U238;U298

【参考文献】