岩溶塌陷倾向性等级的KPCA-SVM预测模型

为了快速、有效地预测岩溶塌陷倾向性等级,在统计分析大量观测实例的基础上,选取岩性系数、岩体结构系数、地下水系数、覆盖层系数、地形地貌系数和环境条件系数作为特征指标。利用核主成分分析(KPCA)方法在高维空间提取岩溶塌陷影响因子的主成分,将获取的主成分作为支持向量机(SVM)的特征向量,建立基于KPCA的岩溶塌陷倾向性等级的SVM预测模型。将12组观测数据作为学习样本对模型进行训练。采用回代估计法进行回检,误判率为0。利用训练好的模型对2组待判样本进行预测。结果表明:经KPCA后指标个数减少,相关性降低,SVM运算的复杂度降低。用该模型所得预测结果的准确率为100%。     

基于模糊信息概率区间数的突发地质灾害降水因子评价研究

根据2010、2012两年云南省的820个地质灾害监测记录,基于模糊信息概率区间数的大小来开展降水量因子的评价研究。结果表明:突发地质灾害发生前10 d的单日降水量与灾害的关系很小,基本不能用于预警模型的建立和风险评价分析;累积降水量与突发地质灾害关系明显,特别是5~10 d的累积降水量预测概括率已达60%以上,可以用于突发地质灾害预警模型的建立和实际的监测预警;加衰减系数的有效累积降水量因子对突发地质灾害预测效果并无提升,与普通累积降水量因子相比并无优势。     

A new pre-assessment model for failure-probability-based-planning by neural network

At present, the prediction of failure probability is based on the operation period for laid pipelines, and the method is complicated and time-consuming. If the failure probability can be predicted in the planning stage, the risk assessment system of gas pipeline will be greatly improved. In this paper, the pre-laying assessment model is established to minimize risk of leakage due to piping layout. Firstly, Fault Tree Analysis (FTA) modeling is carried out for urban natural gas pipeline network. According to expert evaluation, 84 failure factors, which can be determined in the planning stage, are selected as the input variables of the training network. Then the FTA model is used to calculate the theoretical failure probability value, and the failure probability prediction model is determined through repeated trial calculation based on BP (Back Propagation Neural Network) and RBF (Radial Basis Function), for obtaining the optimal network parameter combination. Finally, two prediction models are used to calculate the same example. By comparing our pre-assessment model with the theoretical prediction consequences of the fault tree, the results show that the error of RBF prediction model can be close to 3%, which proves the validity and correctness of the method.     

基于任务成功率的装备综合保障工作体系及协同设计环境研究

本文介绍了基于任务成功率的装备综合保障工作体系框架,提出了可靠性、维修性、测试性、保障性、安全性协同设计环境要求,从而为进行可靠性、维修性、测试性、保障性、安全性综合优化设计奠定基础。     

介绍两种震害损失估算方法

本文介绍了两种震害损失估算方法:全概率法和单位面积法。并据此法对宁夏、青海等地震害作了估算。     

基于偏序集的采空区塌陷危险性评价研究

针对采空区塌陷危险性评价方法中的赋权争议问题,基于偏序集理论提出偏序集评价模型。首先阐明评价指标并确定其分级标准;然后应用偏序集评价模型得到Hasse图,并通过图展现的层集信息判别采空区塌陷危险程度;最后应用该模型对大宝山矿11个采空区的塌陷程度进行判别,评价结果准确合理。研究结果表明:该模型避免了以往研究中的赋权争议问题,克服了样本量不足致使模型无法应用的问题,而且能够应用更多的赋权方法识别排序的稳定程度,体现出样本间的分层信息。     

Corrosion failure probability analysis of buried gas pipelines based on subset simulation

Corrosion is the main reason for the failure of buried gas pipelines. For effective corrosion failure probability analysis, the structural reliability theory was adopted in this study to establish two calculation models for pipeline corrosion failure: the pressure failure model and von Mises stress failure model. Then, two calculation models for the corrosion failure probability were established based on a corrosion depth growth model obtained from actual survey data of soil corrosion characteristics. In an example, Monte Carlo simulation (MCS) and subset simulation (SS) were used to analyze the corrosion failure probability of pipelines, and the results were compared. SS can compensate for the shortcomings of MCS as it has higher computational efficiency and accuracy. Therefore, SS was adopted to simulate variations in the corrosion failure probability of buried pipelines with the service time for the two failure probability calculation models, which were applied to a natural gas pipeline located in a chemical industry park in Zhuhai, China. A sensitivity analysis was carried out on the relevant parameters that affect the failure probability. The results showed that multiple loads caused by the covering soil, residual stress, temperature differential, and bending stress have a non-negligible effect on the pipeline reliability. The corrosion coefficients gradually become the most important factors that affect the failure probability with increased service time. The proposed methodology considers the actual operating conditions of pipelines to provide a reliable theoretical basis for integrity management.     

天然气管道失效个人生命风险评价技术研究

为研究天然气长输管道失效个人生命风险,提出一种以人员伤亡概率为指标的天然气管道失效后果风险评价方法。基于天然气管道的失效概率和失效致死长度参数,建立天然气长输管道生命风险评价模型。用该模型,对国内某城市住宅小区内带腐蚀缺陷的天然气管线进行定量风险分析。借鉴英国天然气输送公司数据,确定天然气管线个人生命风险值。案例证明,用所建立的天然气管道失效个人生命风险评价模型能够有效地分析带缺陷天然气管道失效后果,实现天然气管道的个人安全生命风险全定量评价。     

基于Tripod-Beta模型的船舶火灾事故风险分析

为深入分析船舶火灾事故风险因素及其后果产生的影响,通过分析1991-2017年全球船舶火灾事故调查报告,从人员、管理、船舶设备、货物、环境5个方面对船舶火灾影响因素进行识别研究;采用三脚架事故致因模型(Tripod-Beta model),构建考虑安全栅的船舶火灾事故情景演化模型,识别船舶火灾关键影响因素;并在样本量较少的情况下,采用信息扩散理论计算船舶火灾发生率;最后,利用布尔函数和风险矩阵,对船舶火灾事故风险进行评价研究。结果表明:船员不安全行为和船舶设备表面过热、设备短路是船舶火灾事故的关键风险因素;事故后果链中安全栅遭到破坏时,船舶火灾风险处于不希望发生范围内。该方法能有效评估船舶火灾风险的等级,满足海事管理部门的监管工作需求。