基于BP神经网络的儿童卧室内灰尘PAEs浓度预测

在实测数据的基础上,以邻苯二甲酸酯(PAEs)的各类影响因素为自变量,PAEs浓度为因变量,采用Back-propagation(BP)神经网络建立儿童卧室内PAEs浓度预测模型.结果表明,该模型的预测效果较理想,其中,STD比值均＞0.5,NMB均接近0,EMR均＜19％.以室内环境与儿童健康(CCHH)课题组天津地...     

基于虚拟碰撞试验分析燃料电池轿车车身结构的安全性

在燃料电池轿车的车身结构配合动力驱动系统的改进而不断改进的过程中,需要从碰撞安全性角度去分析结构方案的优劣.本文采用虚拟正面碰撞试验方法,研究经过改进后的燃料电池轿车的半承载式车身是否满足国家被动安全法规,并通过与第1代燃料电池轿车的整车碰撞模拟结果的对比,分析车身结构改进对正面碰撞安全性的影响,从而为进一步的结构改进提供有价值的建议.     

公路网规划环境影响评价中的困难和不确定性分析

首先分析了公路网规划环境影响评价中的困难,即评价方法的不成熟和获取资料的困难;然后重点分析了评价中的公路网规划方案的不确定、环境信息的不确定、空间信息的不确定和环境影响程度的不确定;最后提出了 4种解决困难和降低不确定的方法,即制定公路网规划环境影响评价技术导则,使用基于情景分析的预测方法,广泛开展公众参与以及通过多方协作的方式开展环境影响评价工作.     

Scenario derivation and consequence evaluation of dust explosion accident based on dynamic Bayesian network

In order to clarify the correlation between the evolution path of dust explosion accidents and emergency decision-making, and to accurately predict the disaster damage levels of various disaster bearing bodies. This paper extracts 56 key scenario elements from four aspects, namely state, answer, goal and environment, based on the analysis of typical dust explosion accident cases. At the same time, a general scenario evolution path of dust explosion accident is constructed. Using fuzzy number set theory and dynamic Bayes joint probability model, the accurate solution of scenario state probability was realized. With the help of accident cases and dynamic Bayes approach, the dust explosion consequence prediction index system and evaluation criteria were constructed, covering factors such as dust explosion intensity, casualties, direct economic losses, equipment damage, building damage, environmental damage and other factors. A polyethylene wax dust explosion accident in a city of China was used to verify the dust explosion accident scenario evolution model and consequences prediction model. The predicted results were in good agreement with the actual damage of various carriers of the accident, which indicated that the model could be used for dust explosion accident prediction and disaster loss prediction. The research results provided reference and technical support for the prediction of dust explosion accident evolution direction, emergency aid measures decision and deployment, disaster damage prediction and evaluation.     

Pipeline leakage detection and isolation: An integrated approach of statistical and wavelet feature extraction with multi-layer perceptron neural network (MLPNN)

Leakage diagnosis of hydrocarbon pipelines can prevent environmental and financial losses. This work proposes a novel method that not only detects the occurrence of a leakage fault, but also suggests its location and severity. The OLGA software is employed to provide the pipeline inlet pressure and outlet flow rates as the training data for the Fault Detection and Isolation (FDI) system. The FDI system is comprised of a Multi-Layer Perceptron Neural Network (MLPNN) classifier with various feature extraction methods including the statistical techniques, wavelet transform, and a fusion of both methods. Once different leakage scenarios are considered and the preprocessing methods are done, the proposed FDI system is applied to a 20-km pipeline in southern Iran (Goldkari-Binak pipeline) and a promising severity and location detectability (a correct classification rate of 92%) and a low False Alarm Rate (FAR) were achieved.     

仓库计算机网络系统的防雷管理

通过雷电危害及侵入途径的分析,根据仓库建设网络建设实际,探讨了仓库计算机网络雷电防护措施。     

基于BP神经网络不同输入变量的爆破振速预测

以某隧道爆破开挖为实例,利用BP神经网络解决复杂非线性函数逼近问题的能力,以最大段药量、爆心距、爆破分段数、泊松比、岩石基本质量指标作为影响爆破振动速度的主要因素,选取不同维数的输入变量建立BP神经网络模型来预测爆破振动速度。对比分析各组预测值与实测值之间的相对误差,选取合理维数的输入变量建立了爆破振动危害预测的BP神经网络模型。     

基于证据理论的煤矿瓦斯涌出组合预测

为提高煤矿瓦斯涌出量预测的准确度,引入证据理论组合预测方法。根据瓦斯涌出量及其主要影响因素间的实验数据,采用3个不同的粒子群神经网络模型对涌出量进行初步预测。并由BP、RBF网络对预测误差及预测点的影响因素进行分析建模,以获取每个模型的可信度。再利用证据理论对其进行合成,确定组合模型的权值,最终实现对瓦斯涌出量的组合预测。实例结果表明,该组合预测方法的平均绝对误差、均方误差分别为18.5%、5.8%,均小于神经网络组合法及等权平均法的相应预测误差,适用于煤矿瓦斯涌出量预测。     

地震灾害紧急救援可支配交通链路选择研究

如何通过科学的算法提前获取决定路网通达性的关键链路,即可支配链路,从而可通过各方面养护措施提高可支配链路的抗震能力,保证震后救援运输的顺利进行。提出可支配链路的相关概念,基于矩阵结构的计算方法与原理,并应用算例进行验证。通过选取云南省保山市隆阳区的部分目标区域来进行震后救援路网的支配性链路计算,同时针对地震发生后的特点,综合考虑医疗救援、火灾救援及紧急物资救援3方面的综合救援需求,获得该区域路网的可支配链路。研究结果表明:结合震后实际救援需求,将需求点扩展为多个需求点,能够进一步获得在多个需求点基础上的可支配链路。因此,利用矩阵结构获得可支配链路的方法,能够综合需求点数量和概率临界值的进一步调整,进一步优化计算结果。     

基于主成分分析法的危险货物运输企业安全评价

为更准确地评估危险货物运输企业安全等级以降低其运输风险,提出基于主成分分析法(PCA)的危险货物运输企业BP神经网络安全评价模型;在从人-机-物-环境-管理角度构建危险货物运输企业安全评价指标的基础上,分别利用该模型和其他3种模型对3家实例企业进行仿真评价和对比分析。结果表明,该模型的评价结果与期望值间的相对误差约为0.5%～1.2%,计算精度优于其他模型,且具有计算量小等特点。