城市地下综合管廊一旦发生火灾,会对城市造成很大的经济损失和社会影响.考虑到火灾的快速发展和综合管廊狭长受限的特殊空间结构,迫切需要一套准确、实时的火灾温度预测系统辅助消防救援人员制定决策和指导消防行动.建立了 5 种不同火源位置的地下综合管廊电缆火灾数值模型,结合支持向量机(SVM),根据火源位置、热释放速率、火灾发生时间以及待测点与火源之间的相对位置关系开发了一种数据驱动的温度实时预测模型,实现了地下管廊火灾场景内的纵向温度预测,提出了在火源附近数据结构的优化方案,提高了火源附近的预测准确度.该方法在预测性能和预测时间方面取得了优异的性能,展示了人工智能在火灾预测应用中的优越表现和发展前景.

Underground utility tunnels with various municipal pipelines inside provide convenience for cities and contribute to their sustainable development, but also bring potential fire risks. Previously, the relevant studies have predominately focused on horizontal section, while ignoring the influence of slope at the intersection of utility tunnels. In the present study, the smoke movement and temperature distribution were investigated in utility tunnel fires with five slopes and six heat release rates by numerical simulation. Four different sizes of pool fire experiments were also conducted in a full-scale utility tunnel. The results indicated that: (1) Smoke movement can be divided into five stages, including free rise, diffusion under inclined ceiling, diffusion under horizontal ceiling, flow back, and steady circulation. (2) Temperature upstream is larger than that downstream of the fire source, which is asymmetrically distributed and shows different characteristics with the change in slope. (3) Downstream ceiling temperature decreases gradually with increasing distance from the fire source. An empirical formula is proposed to predict the downstream maximum ceiling temperature rise considering the slope and dimensionless heat release rate. Good agreement was obtained between predicted and experimental values.

3D flame can directly represent the combustion status of combustible and fire scale, but flame pulsation makes it difficult for existing 3D reconstruction technology to achieve flame reconstruction. In response to this situation, we use computer image processing technology to propose a flame model based on the cylindrical hypothesis to realize the 3D reconstruction of the flame in this paper. On this basis, we measured the volume and height of flames with different fuel flow rates for 6 types of burners. The results show that the average flame height and volume increase with the increase of fuel flow rate, but the average flame height decreases with the increase of the burner size, and there is no obvious correlation between the average volume and burner size.

火灾态势的实时感知对提升消防救援指挥与决策水平有非常重要的意义.为实现火源热释放速率的实时预测,通过丙烷气体燃烧实验获取火焰体积和高度的实时数据,选取MATLAB中精细高斯SVM做分类训练,建立了基于图像处理的热释放速率预测模型.结果表明,训练完成后的模型可以根据3s内的火焰体积/高度数据预测得到实时的燃料流量,获取相应的火源热释放速率.该预测模型在已知数据集和未知数据集上都表现出了较高的准确性,为火灾态势发展预测提供了理论和技术基础,有很好的应用前景.

A full-scale model was established by the Fire Dynamics Simulator (FDS) to study the fire characteristics in the cable cabin of utility tunnel with different longitudinal fire source locations. Five fire sources at different locations were placed in a 200-meter-long fire compartment. Several important parameters were obtained and analyzed, including temperature distribution, smoke concentration, and fire self-extinguishing. The results present that the fire source located at 1/2 of the longitudinal direction has the largest range of high-temperature smoke, which leads to the largest damage range of the concrete structure. The reverse filling of the smoke in the utility tunnel leads to the longitudinal CO peak concentration first decreasing and then increasing from the fire source to the end. When the fire source is located at 1/8 of the longitudinal direction, the fire self-extinguishing time is the longest. These encouraging results could provide significant references for the fire protection design and fire control of the utility tunnel.