基于FTA-SVM的车辆发动机故障识别方法

发动机结构日益复杂,其故障具有多样性和频发性的特点,收集大量故障样本存在很多实施障碍。为了提高车辆发动机的故障识别的效率和准确性,提出了一种新的结合故障树(FTA)和支持向量机(SVM)各自特点,从故障模式分析到故障类型识别的FTA-SVM故障识别方法。首先利用故障树在复杂系统故障模式分析中的优势,找出系统的故障模式,建立故障树模型,通过对故障树模型中各故障事件的分析,采集与故障事件状态相关的数据,建立数据与故障树底事件的映射模型,最后利用支持向量机在小样本数据处理中的优势,进行故障类型的识别。以发动机的失火故障为例建立了发动机失火故障树模型及故障数据与故障模式映射模型,验证了FTA-SVM方法的有效性和适用性。     

基于优化方法的区域疏散路径规划研究

由于各种灾害的频频发生,对于区域整体及局部的疏散规划方案的研究具有迫切性和必要性。基于传统的迪杰斯特拉算法和回溯法的思想,对矩阵化的地图信息进行处理和计算,得到满足最大疏散人数、总体最短疏散路径、最短疏散时间等优化条件的优化方案。最后将这种方法运用到实际中,得出了某大学校区的路径选择方案。     

Implementing SDG 15: Can large‐scale public programs help deliver biodiversity conservation,restoration and management,while assisting human development?

Among the Sustainable Development Goals (SDGs), the proposed SDG 15 promotes activities that, inter alia, “Protect, restore and promote sustainable use of terrestrial ecosystems”. An important potential contribution in achieving SDG 15 is through public programmes designed to jointly promote human development through poverty alleviation and improvement of human livelihoods and biodiversity conservation/management/restoration. An analysis of twenty public programmes with such joint objectives yielded twelve lessons learned. In addition to financial commitments, government and intergovernmental agency input for such public programmes includes ensuring political will and appropriate legal frameworks. Local communities and civil society provide input through traditional and indigenous ecological knowledge and stewardship. Appropriate shared inputs in development and the implementation of such public programmes, with communication between local community, broader civil society, the scientific community and governments will result in: better use and management of biodiversity; alleviation of poverty; security of livelihoods and better governance systems. The Ecosystem Approach of the Convention on Biological Diversity provides an ideal framework when planning and implementing new programmes. Application of the lessons learned to new public programmes will ensure that the answer to the question posed in the title is an emphatic “Yes”, and assist with the achievement of SDG 15.     

The role of situation awareness in accidents of large-scale technological systems

In the last two decades, several serious accidents at large-scale technological systems that have had grave consequences, such as that at Bhopal, have primarily been attributed to human error. However, further investigations have revealed that humans are not the primary cause of these accidents, but have inherited the problems and difficulties of working with complex systems created by engineers. The operators have to comprehend malfunctions in real time, respond quickly, and make rapid decisions to return operational units to normal conditions, but under these circumstances, the mental workload of operators rises sharply, and a mental workload that is too high increases the rate of error. Therefore, cognivitive human features such as situation awareness (SA)—one of the most important prerequisite for decision-making—should be considered and analyzed appropriately. This paper applys the SA Error Taxonomy methodology to analyze the role of SA in three different accidents: (1) A runaway chemical reaction at Institute, West Virginia killing two employees, injuring eight people, and requiring the evacuation of more than 40,000 residents adjacent to the facility, (2) The ignition of a vapor cloud at Bellwood, Illinois that killed one person, injured two employees, and caused significant business interruption, and (3) An explosion at Ontario, California injuring four workers and caused extensive damage to the facility. In addition, the paper presents certain requirements for cognitive operator support system development and operator training under abnormal situations to promote operators’ SA in the process industry.     

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%。     

战场环境下装备保障信息系统安全风险与防护

目的研究战场环境下装备保障信息系统的安全问题。方法从装备保障及装备保障信息系统的概念、分类和复杂战场环境下装备保障信息系统所面临的安全威胁入手,依照五分法把装备保障信息系统安全风险划分为5个等级,推导出风险评估模型,提出实施装备保障信息系统安全防护的技战术策略。结果战场环境下,为确保整个作战进程中装备保障活动安全、有效、稳定地进行,装备保障信息系统防护必须遵循统一协调、综合利用的积极防护原则,采用有效的风险控制措施加以应对。结论通过积极探索和发展装备保障信息安全与防护理论,找准战场环境信息防护中存在的薄弱环节,制定了装备保障信息安全防护策略,加强装备保障信息系统的安全管理工作,最终提高我军装备保障信息系统的防护能力。     

有机化学品不同温度下(过冷)液体蒸气压预测模型的建立与评价

(过冷)液体蒸气压(PL)是评价化学品在环境中分配、迁移和归趋行为的重要参数。PL具有较强的温度依附性。发展一种能够精确预测不同环境温度下化学品PL的方法,有助于填补化学品生态风险评估的大量数据缺失。本研究收集整理了661种有机化合物在不同温度下(200~830 K)共计10 478个log PL值。在此基础上,采用偏最小二乘(PLS)回归和支持向量机(SVM)方法,构建了PL的线性和非线性预测模型。结果表明:2种模型均具有良好的拟合度、稳健性及预测能力,SVM模型的预测性能略高于PLS模型(PLS:R2adj.tra=0.912,RMSEtra=0.477,Q2ext=0.910;SVM:R2adj.tra=0.997,RMSEtra=0.092,Q2ext=0.967)。机理分析表明,温度是影响PL的主要因素,温度越高,蒸气压越大;其次,X1sol也影响PL大小,X1sol用来描述分子间的色散作用,分子间色散力越小,蒸气压越大;此外,化合物的氢键个数、极性和分子构型等因素也影响PL大小。采用Wiliams plot方法表征了PLS模型应用域。所建立的模型可用来预测烷烃、烯烃、醇、酮、羧酸、苯、酚、联苯、卤代芳香烃、含N化合物及含S化合物在不同温度下的PL数据。     

Simulation of scenario characteristics of LPG tank explosion accident and its contribution to emergency planning: A case study

Leakage and explosion of hazardous chemicals during road transportation can cause serious building damage and casualties, and adoption of highly-efficient emergency rescue measures plays a critical role in reducing accidental hazards. Considering a liquefied petroleum gas (LPG) transport tanker explosion accident that occurred in Wenling, Zhejiang Province, China on June 13, 2020 as example, this study proposes a risk assessment framework. This framework recreates the leakage and explosion of the accident process using FLACS v10.9, suggests plans for evacuation, describes the rescue areas of different levels, and explores the influence of environmental factors on the evacuation and rescue areas. The results show that simulated and predicted distributions of fuel vapour cloud concentration and explosion overpressure can provide a reference basis for rapid rescue activities; the characterization of the dynamic effects of wind speed, wind direction, and temperature with respect to the evacuation and rescue areas can be used as theoretical support for on-site adjustment of rescue forces. The role of obstacles can prevent the expansion of the evacuation areas under low wind-speed conditions, and the presence of highly congested obstacles determines the level of the rescue area. The results obtained are important for the risk analysis and the development of emergency rescue measures in case of explosion accidents associated with transportation of hazardous chemicals on high-hazard and high-sensitive road sections.     

A mixed method study of hurricane evacuation: demographic predictors for stated compliance to voluntary and mandatory orders

The present paper examines the role of several demographic indicators on stated hurricane evacuation thresholds, or the lowest category storm for which participants indicated they would evacuate, for mandatory and voluntary orders. Quantitative analyses reveal that race was significantly associated with a lower stated evacuation threshold in both the bivariate and multivariate models and that previous refusal to comply with evacuation orders was associated with higher stated evacuation thresholds. Qualitative analyses reveal two key findings: (1) wind is perceived as more dangerous than water (rain and storm surge) associated with hurricanes; (2) traffic concerns were the most frequently cited reason listed for possible refusal to comply with evacuation orders. Implications of the findings include the value of future evaluations of race and trust, storm characteristics and threat perception, and other practical considerations for improving evacuation compliance such as the amelioration of traffic concerns. Findings also lead to the discussion of the social complexities of race and hurricane vulnerability as a key finding.