基于BP神经网络的液化石油气铁路运输安全评价研究

发布时间：2018-05-19 10:50

本文选题：液化石油气 + 指标体系　；参考：《兰州交通大学》2013年硕士论文

【摘要】：随着我国经济的快速发展，对危险品特别是液化石油气的需求在逐年增长，，而液化石油气的生产地和使用地一般不在同一区域，这就需要公路、铁路等运输方式来运输。在通过铁路运输液化石油气的过程中所涉及到的运输环节较多，难度较大，且对专用线的办理条件要求较高，因此铁路运输液化石油气的危险性也较高。所以，对办理液化石油气的铁路专用线进行运输安全现状综合分析，直观地了解铁路专用线办理液化石油气的风险性就有非常重要的意义。本文首先介绍了国内外液化石油气运输安全研究现状和铁路危险货物运输状况，分析了危险货物运输事故的成因机理；然后对液化石油气的理化性质及运输过程中存在的危害性进行了分析，并对液化石油气运输安全技术条件以及专用线（专用铁路）相关技术设备、管理制度等方面进行研究，综合考虑铁路运输液化石油气的风险因素，对影响液化石油气铁路运输安全的风险因素进行逐层分析，再结合现行的铁路危险货物运输安全综合分析中的相关评价体系，建立具有针对性和较为全面的液化石油气铁路运输安全现状评价指标体系。根据所建立的液化石油气铁路运输安全现状评价指标体系，并采用通过L-M算法优化过的BP神经网络，建立较为优化的神经网络模型。通过查阅相关专用线资料以及专家打分法构建了训练样本，使用MATLAB软件中的神经网络工具箱对该样本进行训练，通过分析训练结果来验证神经网络的可行性。最后应用训练好的BP神经网络对实例进行安全评价，验证该模型的实用性。
[Abstract]:With the rapid development of economy in our country, the demand for dangerous goods, especially liquefied petroleum gas (LPG), is increasing year by year, but the place of production and use of LPG is generally not in the same area, which requires road, railway and other transportation modes to transport. In the process of transportation of liquefied petroleum gas (LPG) by railway, the transportation links are more difficult, and the handling conditions of special railway line are higher, so the risk of railway transportation of LPG is also higher. Therefore, it is of great significance to analyze the present situation of transportation safety of the special railway line for handling liquefied petroleum gas (LPG), and to understand directly the risk of handling LPG on the special railway line. Firstly, this paper introduces the present situation of transportation safety of liquefied petroleum gas (LPG) at home and abroad and the transportation status of railway dangerous goods, and analyzes the cause of formation of the accidents of transportation of dangerous goods. Then the physical and chemical properties of liquefied petroleum gas (LPG) and the harmfulness existing in the transportation process are analyzed, and the technical conditions of transportation safety of LPG, the related technical equipment and management system of the special railway line are studied. Considering comprehensively the risk factors of railway transportation of liquefied petroleum gas (LPG), the risk factors affecting the safety of LPG railway transportation are analyzed layer by layer, and then combined with the existing relevant evaluation system in the comprehensive analysis of railway dangerous goods transportation safety, The evaluation index system of LPG railway transportation safety is established. According to the established evaluation index system of LPG railway transportation safety and the BP neural network optimized by L-M algorithm, an optimized neural network model is established. The training sample is constructed by consulting the relevant data of the special line and the expert scoring method. The training sample is trained by the neural network toolbox in MATLAB software. The feasibility of the neural network is verified by analyzing the training results. Finally, the trained BP neural network is used to evaluate the safety of the model and verify the practicability of the model.
【学位授予单位】：兰州交通大学
【学位级别】：硕士
【学位授予年份】：2013
【分类号】：TP183;U294.82;U298

【参考文献】