Comparative analysis on temperature characteristics of hydrogen-powered and traditional fossil-fueled vehicle fires in the tunnel under longitudinal ventilations

Vehicle fires in the tunnel are a great threat to the safe operation of the tunnel. Due to the rapid development of the hydrogen economy, the fire due to the hydrogen leakage could not be avoided and may bring great damage to the passengers and infrastructure. Due to the large difference between pool fires of traditional fossil-fueled and jet fires of hydrogen-powered vehicles, it is in doubt whether the existing longitudinal ventilation design could still be effective for the safety issue of hydrogen powered vehicles. To solve this problem, it is necessary to compare temperature characteristics of hydrogen-powered and traditional vehicle fires with and without longitudinal ventilations. In present work, we conducted a numerical investigation to discuss the different temperature distributions of traditional and hydrogen-fueled vehicle fires. Results indicate that the high temperature zone of the pool fire only exists above the ceiling of the vehicle. For hydrogen-powered vehicle fire, the high-speed hydrogen jet with the strong inertial force could push the hot smoke flows back to the ground. The ceiling temperature of hydrogen-powered vehicle fire is larger since hydrogen-powered vehicle has a larger heat release rate and the fire hazard of jet fires bring more danger compared with the pool fire. Although the temperature stratification is also obvious for the hydrogen-powered vehicle fire, the air temperature in the lower region could be heated and still high enough to bring a great damage to the passengers’ lives. This is quite different with the traditional pool fire. In addition, the critical ventilation velocity is also discussed. The theoretical equation could well predicted the critical ventilation velocity of traditional vehicle fires. For hydrogen-powered vehicle fires, the critical ventilation velocity could reach up to 6 m/s. The theoretical equation could not well predict the critical ventilation velocity of hydrogen-powered vehicle fires due to exist of hydrogen jet fires.     

Fire safe,sustainable loose furnishing

The aim of this exploratory study has been to investigate the fire properties and environmental aspects of different upholstery material combinations, mainly for domestic applications. An analysis of the sustainability and circularity of selected textiles, along with lifecycle assessment, is used to qualitatively evaluate materials from an environmental perspective. The cone calorimeter was the primary tool used to screen 20 different material combinations from a fire performance perspective. It was found that textile covers of conventional fibres such as wool, cotton and polyester, can be improved by blending them with fire resistant speciality fibres. A new three‐dimensional web structure has been examined as an alternative padding material, showing preliminary promising fire properties with regard to ignition time, heat release rates and smoke production.     

Reduced‐scale test to assess the effect of fire barriers on the flaming combustion of cored composites: An upholstery‐material case study

Herein, we describe a reduced‐scale test (“Cube” test), measuring the fire performance of specimens including a fire barrier (FB) and a flammable core material, which acts as the main fuel load. The specimen is intended to reproduce a cross‐section of a composite product where heat/mass transfer occurs primarily in a direction perpendicular to the FB. The Cube test procedure and benefits are discussed in this work by adopting residential upholstery furniture as an exemplary study. One flexible polyurethane foam, one polypropylene cover fabric, and 10 commercially available FBs were selected. They were used to compare the fire performance of FBs, measured in terms of peak of heat release rate, in the ASTM E1474‐14 standard test and the newly developed Cube test. Edge effects severely affected the performance of FBs in the ASTM E1474‐14 standard test but not in the Cube test. Furthermore, appropriate test conditions were determined in the Cube test to measure the so‐called “wetting point,” that is, the time and value of heat release rate measured when flammable liquid products were first observed on the bottom of the specimen. The relevance of the “wetting point” in terms of full‐scale fire performance and failure mechanism of FBs is discussed.     

云冈矿采空区自然发火综合治理技术实践

针对云冈矿12#煤层8820、8822采空区出现CO泄漏事件,采用粉煤灰填充,构筑木板墙充填粉煤灰,配以墙体周边注马丽散堵漏;采用灌浆泵进行地面黄土灌浆,实施采空区灭火。通过对采空区自然发火进行综合治理,取得了良好效果,消除了自然发火隐患。     

四台矿均压硐室的优化与研究

四台矿属于近距离容易自燃煤层开采,综采工作面采用均压通风系统。在进风顺槽中布置的本巷均压硐室,风机吸风口距离均压风门近,吸风风流经过带式输送机,往往会造成均压风门漏风严重,均压硐室周围温度较高、煤尘较大。据此四台矿优化均压硐室布置方式,采用独立均压硐室代替先前的本巷均压硐室。对优化前后的数据进行研究分析,得出独立均压硐室的应用在减少风门漏风量,降低温度,抑制煤尘方面均有很大改善,实践证明了采用独立均压硐室的可行性及优点。     

基于Faster R-CNN的颜色导向火焰检测

基于深度特征的目标检测方法Faster R-CNN在火焰检测任务上存在检测效率低的问题,因此提出了基于颜色引导的抛锚策略。该策略设计火焰颜色模型来限制锚的生成,即利用火焰颜色约束锚的生成区域,从而减少了初始锚的数量,提升了计算效率。为了进一步提高网络的计算效率,将区域生成网络中的卷积层替换成掩膜卷积。为了验证所提方法的检测效果,采用BoWFire和Corsician数据集进行验证。实验结果表明,该方法实际检测速度相较于原Faster R-CNN提高了10.1%,BoWFire上该方法的火焰检测F值为0.87,Corsician上该方法的准确度可达99.33%。所提方法可以提高火焰检测的效率,并能够准确检测图像中的火焰。     

两池火耦合作用下柴油拱顶罐热响应的数值模拟

化工园区多池火事故是典型的高后果低概率事件。鉴于目前两池火辐射模型存在一定局限性，本文采用数值模拟方法，以3个直线排布的5000m³柴油拱顶罐为研究场景，从热释放速率、火焰形态、热辐射强度三方面分析两池火燃烧特性，并与单池火场景对比，考虑储罐间距这一影响因素，进一步研究目标储罐热响应。结果表明：采用GB 50160—2008（2018年版）规定的防火间距，两燃烧罐产生的池火会发生耦合作用，并得出目标储罐受到的热辐射强度分布，最高热辐射达17.04kW/m²；两池火作用下目标储罐的温度、Mises应力与失效时间分别为644℃、356MPa、936s，单池火为488℃、280MPa、2880s，目标储罐在两池火作用下的变形也比单池火更为严重；随着储罐间距增加，目标储罐的温度与Mises应力逐渐减小，失效时间逐渐增加，当储罐间距为标准防火间距的2.5倍（20m）时，失效时间为2800s，与单池火作用产生的失效时间2880s较为接近。本研究可为优化储罐防火间距及区域韧性提升提供理论指导。     

基于循环一致性对抗网络的室内火焰图像场景迁移

基于深度学习的视频火灾探测模型的训练依赖于大量的正负样本数据,即火灾视频和带有干扰的场景视频。由于很多室内场合禁止点火,导致该场景下的火灾视频样本不足。本文基于生成对抗网络,将其他相似场景下录制的火焰迁移到指定场景,以此增广限制性场合下的火灾视频数据。文中提出将火焰内核预先植入场景使之具备完整的内容信息,再通过添加烟雾和地面反射等风格信息,完成场景与火焰的融合。该方法克服了现有多模态图像转换方法在图像转换过程中因丢失信息而造成的背景失真问题。同时为减少数据采集工作量,采用循环一致性生成对抗网络以解除训练图像必须严格匹配的限制。实验表明,与现有多模态图像转换相比,本文方法可以保证场景中火焰形态的多样性,迁移后的场景具有较高的视觉真实性,所得结果的FID与LPIPS值最小,分别为119.6和0.134 2。     

Cable tray FIRE tests simulations in open atmosphere and in confined and mechanically ventilated compartments with the CALIF3S/ISIS CFD software

Fire hazard in nuclear power plants (NPPs) is particularly often investigated as potential cause of safety equipment failure and confinement loss. Many fire events recorded in NPPs involve electric cables, widely used throughout facilities. IRSN is developing the CALIF3S/ISIS computational fluid dynamics software devoted to fire simulation in large‐scale confined and mechanically ventilated compartments. This paper presents two aspects of the CALIF3S/ISIS code ability to simulate fires. The first one concerns vertical and horizontal spreading of a cable tray fire in open atmosphere using an approach based on the FLASH‐CAT cable fire spread model. Resorting to the suitable parameters of the FLASH‐CAT model based on video fire analyses of tests enables to properly compute the heat release rate of the fire. The second aspect concerns the ability to simulate the evolution and consequences of fires in confined and mechanically ventilated compartments. For these cases, the heat release rate measured during the corresponding experiment is used as input data for the calculations. The predicted evolutions of pressure or gas temperatures are in relatively good accordance with the experiments. The major discrepancy concerns gas concentrations in the fire room which is attributed to a lack of information about the properties of the fuel material.     

基于优势学习的深度Q网络

强化学习问题中，同一状态下不同动作所对应的状态-动作值存在差距过小的现象，Q-Learning算法采用MAX进行动作选择时会出现过估计问题，且结合了Q-Learning的深度Q网络（Deep Q Net）同样存在过估计问题。为了缓解深度Q网络中存在的过估计问题，提出一种基于优势学习的深度Q网络，通过优势学习的方法构造一个更正项，利用目标值网络对更正项进行建模，同时与深度Q网络的评估函数进行求和作为新的评估函数。当选择的动作是最优动作时，更正项为零，不对评估函数的值进行改动，当选择的动作不是最优动作时，更正项的值为负，降低了非最优动作的评估值。和传统的深度Q网络相比，基于优势学习的深度Q网络在Playing Atari 2600的控制问题breakout、seaquest、phoenix、amidar中取得了更高的平均奖赏值，在krull、seaquest中取得了更加稳定的策略。