基于因子分析和数理统计的管道占压风险评价

Risk assessment of pipeline occupancy based on factor analysis and mathematical statistics

为提高信息缺失情况下管道占压风险评价结果的准确性,在文献调研和资料收集的前提下,通过数据缺失处理、数据变量编码等操作完成数据整合,利用因子分析反向获得管道占压风险评价指标体系,并通过因子分析和G1法计算不同层级的指标权重,结合完全析因设计和数理统计绘制风险评估图,分别以老龄管道和新建管道为例进行验证分析。结果表明,轴线偏移距离、堆载强度和管道缺陷密度的权重较大,对管道占压风险的影响较大;通过Anderson-Darling非参数检验得到风险指数服从均值0.2351、标准差0.02930的正态分布;该评价结果与模糊综合评价法和属性识别理论的结果相比,不需要构造隶属度函数和判断矩阵,也不需要根据置信度准则确定风险等级,在不同类型管道上的应用效果良好。研究结果可为埋地油气管道的占压隐患治理提供实际参考。

To improve the accuracy of risk assessment results of pipeline occupancy under missing information,this paper completes data integration by data missing processing,data variable coding,and other operations based on literature research and data collection.Meanwhile,factor analysis is adopted to obtain a system of risk assessment indicators,and factor analysis and the G1 method are leveraged to calculate the weights of indicators at different levels.Risk assessment charts are drawn by combining full factorial design and mathematical statistics,with the old pipeline and new pipeline taken as examples for analysis verification respectively.The results show that the weights of axis deviation distance,load strength,and pipeline defect density are large,greatly influencing pipeline occupancy risks.The risk index is found to follow the normal distribution with a mean value of 0.2351 and a standard deviation of 0.02930 by the Anderson-Darling nonparametric test.Compared with the results of the fuzzy comprehensive evaluation method and attribute recognition theory,the evaluation results of the proposed system do not need to construct membership functions and judgment matrices and to determine the risk level according to the confidence criterion.Thus,it can yield sound effects when applied to different types of pipelines.The research results can provide practical references for the treatment of hidden occupancy hazards in buried oil and gas pipelines.