Fire behaviors along timber linings affixed to tunnel walls in mines

Timber linings are applied as primary supports in the tunnel fault and fracture zones of mines. These linings are essential to prevent broken rock from falling during the occurrence of exogenous fires. In this study, experiments and numerical simulations were carried out using a fire dynamics simulator to investigate the flame-spread rate, flame characteristics, smoke movement, and spread process of timber-lining fires under different wind speeds of 0, 0.25, 0.5, and 0.75 m/s. It was found that cross-section flame spreading follows the three-stage sidewall-ceiling-sidewall pattern. Moreover, the average flame-spread rate increases along the vertical flame-spreading direction and decreases when the flame reaches the timber-lining corners. Moreover, the flame lengths underneath the timber-lining ceiling in the x-direction are longer than those in the y-direction. As the wind speed increases, the normalized flame lengths R(f) in the two directions decrease, and the maximum temperature underneath the ceiling decreases. In addition, the maximum temperature in the three tunnel sections of interest is first recorded in the tunnel cross-section in the initial fire stage. Higher wind speeds correspond to farther distances of the maximum-temperature points of the three timber-lining sections from the fire source.

FDS simulation of smoke backlayering in emergency lay-by of a road tunnel with longitudinal ventilation

This paper investigates smoke movement and its stratification in a lay-by of a 900 m long road tunnel by computer simulation using Fire Dynamics Simulator. The lay-by is located upstream of the fire in its vicinity. The influence of lay-by geometry on smoke spread is evaluated by comparison with a fictional tunnel without lay-by. Several fire scenarios with various tunnel slopes and heat release rates of fire in the tunnels without and with the lay-by are considered. The most significant breaking of smoke stratification and decrease of visibility in the area of the lay-by can be observed in the case of zero slope tunnel for more intensive fires with significant length of backlayering. Several other features of smoke spread in the lay-by are analysed as well. The parallel calculations were performed on a high-performance computer cluster.

Experimental study on the effect of canyon cross wind on temperature distribution of buoyancy-induced smoke layer in tunnel fires

Experiments were conducted in a 1:20 arced tunnel model to investigate the effect of canyon cross wind on buoyancy-induced smoke flow characteristics of pool fires, involving smoke movement behaviour and longitudinal temperature distribution of smoke layer. The canyon wind speed, longitudinal fire location and fire size were varied. Results show that there are two special smoke behaviours with the fire source positioned at different flow field zones. When the fire source is positioned at the negative pressure zone, with increasing canyon wind speed, the smoke always exists upstream mainly due to the vortex, and the smoke temperature near the fire source increases first and then decreases. However, when the fire source is located in the transition zone and the unidirectional flow zone, there is no smoke appearing upstream with a certain canyon wind speed. Meanwhile, the smoke temperature near the fire sources are decreases with increasing canyon wind speed. The dimensionless temperature rise of the smoke layer ΔTs* along the longitudinal direction of the tunnel follows a good exponential decay. As the canyon wind speed increases, the longitudinal decay rate of ΔTs* decreases. The longitudinal decay rate of ΔTs* downstream of the fire is related to the fire location and canyon wind speed, and independent of the fire size. The empirical correlations for predicting the longitudinal decay of ΔTs* downstream of the fire are established. For a relatively large-scale fire, the longitudinal decay rate of ΔTs* upstream of the fire increases as the distance between the fire source and the upstream portal increases, especially for larger canyon wind speeds.

Applications of Artificial Intelligence in Fire Safety of Agricultural Structures

Artificial intelligence applications in fire safety of agricultural structures have practical economic and technological benefits on commercial agriculture. The FAO estimates that wildfires result in at least USD 1 billion in agriculture-related losses due to the destruction of livestock pasture, destruction of agricultural buildings, premature death of farm animals, and general disruption of agricultural activities. Even though artificial neural networks (ANNs), genetic algorithms (GAs), probabilistic neural networks (PNNs), and adaptive neurofuzzy inference systems (ANFISs), among others, have proven useful in fire prevention, their application is limited in real farm environments. Most farms rely on traditional/non-technology-based methods of fire prevention. The case for AI in agricultural fire prevention is grounded on the accuracy and reliability of computer simulations in smoke movement analysis, risk assessment, and postfire analysis. In addition, such technologies can be coupled with next-generation fire-retardant materials such as intumescent coatings with a polymer binder, blowing agent, carbon donor, and acid donor. Future prospects for AI in agriculture transcend basic fire safety to encompass Society 5.0, energy systems in smart cities, UAV monitoring, Agriculture 4.0, and decentralized energy. However, critical challenges must be overcome, including the health and safety aspects, cost, and reliability. In brief, AI offers unlimited potential in the prevention of fire hazards in farms, but the existing body of knowledge is inadequate.

Extraction and Classification of Image Features for Fire Recognition Based on Convolutional Neural Network

Fire image monitoring systems are being applied to more and more fields, owing to their large monitoring area. However, the existing image processing-based fire detection technology cannot effectively make real-time fire warning in actual scenes, and the relevant fire recognition algorithms are not robust enough. To solve the problems, this paper tries to extract and classify image features for fire recognition based on convolutional neural network (CNN). Specifically, the authors set up the framework of a fire recognition system based on fire video images (FVIFRS), and extracted both static and dynamic features of flame. To improve the efficiency of image analysis, a Gaussian mixture model was established to extract the features from the fire smoke movement areas. Finally, the CNN was improved to process and classify the fire feature maps of the CNN. The proposed algorithm and model were proved to be feasible and effective through experiments.

Relationship between Designed Fire and Performance of Smoke-Control System in a Living Room

The effects of the size of a designed fire on the ventilation system of an adjacent zone is estimated in this study based on a visibility requirement of 5 m in a non-fire zone at 600 s after ignition. To verify the adequacy of the fire dynamics simulator (FDS) input file, smoke movement and ceiling temperature under the hot smoke test conditions of AS4391-1999 were compared with those from the FDS results. The average temperatures measured at 12 locations were within the range of ± 2σ, with the exception of one point, and predicted smoke movement adequately. The size of the designed fire was analyzed in terms of the air volume conditions of the NFSC 501 for a heat release rate (HRR) of 1650 kW (air supply and exhaust at 45,000 cubic meters per hour (CMH)) as well as air volume conditions for a HRR of 1100 kW (air supply at 35,606 CMH and exhaust at 32,506 CMH). It was determined that one of the major factors influencing the required safety egress time was the mixture of downdraft airflow from the diffusers and smoke layer crossing the ventilation boundary.