基于BP神经网络的受限空间火灾联合探测方法

针对航空受限空间火灾探测高误报的问题,在现有技术成果基础上对多种火灾探测方式进行研讨,并提出1种基于BP神经网络技术的飞机机身内部受限空间火灾联合探测报警方法。该方法结合现有烟雾感应、气体传感器探测等常用火灾探测技术,以红外热成像探测为辅助手段,采用神经网络实现数据融合,对模拟实验舱火灾烟雾进行联合探测,在单一火灾探测方式基础上提高了探测准确率。     

施工组织正式网络结构特征对组织安全行为的影响关系研究

为提升建筑施工安全管理水平,探讨施工组织正式网络的结构特征对组织安全行为的影响关系。基于社会网络分析方法,引入安全沟通作为中介变量,建立施工组织正式网络结构特征、安全沟通和组织安全行为的假设模型。基于91个施工组织正式网络结构特征分析,使用多层回归分析方法检验假设模型。结果表明:网络密度、出度中心势和聚类系数均显著正向影响组织安全行为;中间中心势和平均路径长度均显著负向影响组织安全行为;入度中心势对组织安全行为影响不显著;安全沟通分别在出度中心势和中间中心势与组织安全行为的关系中起完全中介作用;安全沟通分别在密度、平均路径长度和聚类系数与组织安全行为的关系中起部分中介作用;安全沟通在入度中心势与组织安全行为的关系中未起到中介作用。     

基于人工神经网络的气体泄爆最大超压预测研究

为解决传统经验公式在预测气体泄爆中最大超压出现时的较大偏差或过于保守的问题,提出使用人工神经网络预测气体泄爆最大超压。基于124组实验数据,采用BP与RBF神经网络,通过优化算法计算与迭代循环对泄爆样本中的影响因素进行降维与选择,并确定2类神经网络本身在学习与计算气体泄爆样本时的相关参数。结果表明:PCA（主成分分析法）在当前样本条件下的降维效果较差,而通过迭代对比确认气体泄爆样本中的5类特征全部保留时神经网络的训练模拟效果最好;通过对124组实验数据进行随机挑选训练集与测试集的训练模拟结果发现,神经网络对气体泄爆中最大超压的预测效果较好;通过对比Molkov提出的和经Fakandu等改进的NFPA 68经验公式以及2类神经网络的预测结果表明,神经网络相比于传统气体泄爆经验公式具有明显优势。     

基于贝叶斯网络气化炉供料系统风险分析

为解决当前气化炉供料系统风险分析不完善的状况,提出1种基于贝叶斯网络和HAZOP的风险分析模型。以某单日投煤量3 000 t级气化炉煤化工企业实际运行情况为研究对象,应用HAZOP法对其进行风险分析,并将HAZOP分析结果中各偏差产生原因转化为贝叶斯网络节点;考虑到先验知识的缺乏问题,引入Leaky Noisy OR模型,通过文献资料和相关领域专家经验知识获得先验概率,并利用贝叶斯网络进行风险分析,找出系统运行的薄弱环节。结果表明:未知因素影响会使各节点的后验概率值差异性降低,更加贴合实际;在引入未知因素影响后,系统运行薄弱环节并未发生改变。     

隧道救援站通风网络优化设计及人员疏散研究*

为确定铁路隧道救援站最佳通风结构,对烟道布置提出合理建议,采用计算流体力学（CFD）的方法,对铁路隧道救援站通风网络进行优化设计。同时,采用模拟计算的方法对救援站人员疏散进行模拟分析,确定救援横通道布置及防护门开度设置的合理性。研究结果表明:在同等通风参数工况设置下,采用多节点排烟竖井结构后各救援横通道流量分配更均匀,救援站压力平衡性更好,通风效率可提升15%;通过疏散模拟证实,在长560 m的紧急救援站范围内设置10条疏散横通道,横通道设1.7 m宽的逃生门能够满足疏散要求。     

基于复杂网络的燃气管线破裂灾害链风险分析*

为提高燃气管线突发事件应急处置决策水平和应急响应能力及效率,采用复杂网络理论和灾害链演化机理对燃气管线破裂灾害事件影响进行耦合分析,构建燃气管线破裂灾害链网络和风险评估模型,并计算得出燃气管线破裂灾害链风险度。为更准确地表达无传播路径的灾害事件之间的关系,将灾害网络中所有最短路径长度的最大值作为其最短路径长度,计算表明这种算法更符合灾害传播实际情况。结果表明:通过燃气管线破裂灾害链风险分析,能够为燃气管线灾害风险控制措施和方案制定提供参考,有利于提高燃气管线破裂灾害事件的应急处置能力和决策水平。     

A Bayesian network-based approach for the assessment and management of ageing in major hazard establishments

Currently, there is an increasing attention towards ageing of industrial equipment, as the phenomenon has been recognised as a cause of severe accidents, recorded in the last years in many process establishments. Recent studies described ageing through a number of key-factors affecting the phenomenon by accelerating or slowing it down. The Italian Competent Authority for the prevention of chemical accidents (Seveso III Directive) adopted a short-cut method, accounting for the assessment of these factors, to evaluate the adequateness of ageing management during inspections at Seveso sites. In this paper, a Bayesian Network was developed, by using the data gathered during the first application of the short-cut method, with the aim to verify the robustness of the approach for ageing assessment and the validity of the a priori assumptions used in assessing the key-factors. The structure of the Bayesian network was established by using experts’ knowledge, whereas the Counting Learning algorithm was adopted to execute the parameter learning by means of the software Netica. The results showed that this network could effectively explore the complex logical and uncertain relationships amongst factors affecting equipment ageing. Results of the present study were exploited to improve the short-cut method.     

Numerical study on premixing characteristics and explosion process of starch in a vertical pipe under turbulent flow

Fire and explosion accidents are frequently caused by combustible dust, which has led to increased interest in this area of research. Although scholars have performed some research in this field, they often ignored interesting phenomena in their experiments. In this paper, we established a 2D numerical method to thoroughly investigate the particle motion and distribution before ignition. The optimal time for the corn starch dust cloud to ignite was determined in a semi-closed tube, and the characteristics of the flame propagation and temperature field were investigated after ignition inside and outside the tube. From the simulation, certain unexpected phenomena that occurred in the experiment were explained, and some suggestions were proposed for future experiments. The results from the simulation showed that 60–70 ms was the best time for the dust cloud to ignite. The local high-temperature flame clusters were caused by the agglomeration of high-temperature particles, and there were no flames near the wall of the tube due to particles gathering and attaching to the wall. Vortices formed around the nozzle, where the particle concentration was low and the flame spread slowly. During the explosion venting, particles flew out of the tube before the flame. The venting flame exhibited a “mushroom cloud” shape due to interactions with the vortex, and the flame maintained this shape as it was driven upward by the vortex.     

How can process safety and a risk management approach guide pandemic risk management?

The coronavirus disease (COVID-19) brought the world to a halt in March 2020. Various prediction and risk management approaches are being explored worldwide for decision making. This work adopts an advanced mechanistic model and utilizes tools for process safety to propose a framework for risk management for the current pandemic. A parameter tweaking and an artificial neural network-based parameter learning model have been developed for effective forecasting of the dynamic risk. Monte Carlo simulation was used to capture the randomness of the model parameters. A comparative analysis of the proposed methodologies has been carried out by using the susceptible, exposed, infected, quarantined, recovered, deceased (SEIQRD) model. A SEIQRD model was developed for four distinct locations: Italy, Germany, Ontario, and British Columbia. The learning-based approach resulted in better outcomes among the models tested in the present study. The layer of protection analysis is a useful framework to analyze the effect of different safety measures. This framework is used in this work to study the effect of non-pharmaceutical interventions on pandemic risk. The risk profiles suggest that a stage-wise releasing scenario is the most suitable approach with negligible resurgence. The case study provides valuable insights to practitioners in both the health sector and the process industries to implement advanced strategies for risk assessment and management. Both sectors can benefit from each other by using the mathematical models and the management tools used in each, and, more importantly, the lessons learned from crises.     

Application of dynamic risk analysis in offshore drilling processes

Process safety is the common global language used to communicate the strategies of hazard identification, risk assessment and safety management. Process safety is identified as an integral part of process development and focuses on preventing and mitigating major process accidents such as fires, explosions, and toxic releases in process industries. Accident probability estimation is the most vital step to all quantitative risk assessment methods. Drilling process for oil is a hazardous operation and hence safety is one of the major concerns and is often measured in terms of risk. Dynamic risk assessment method is meant to reassess risk in terms of updating initial failure probabilities of events and safety barriers, as new information are made available during a specific operation. In this study, a Bayesian network model is developed to represent a well kick scenario. The concept of dynamic environment is incorporated by feeding the real-time failure probability values (observed at different time intervals) of safety barriers to the Bayesian network in order to obtain the corresponding time-dependent variations in kick consequences. This study reveals the importance of real-time monitoring of safety barrier performances and quantitatively shows the effect of deterioration of barrier performance on kick consequence probabilities. The Macondo blowout incident is used to demonstrate how early warnings in barrier probability variations could have been observed and adequately managed to prevent escalation to severe consequences.