Aircraft cargo compartment fire detection and smoke transport modeling

The US Federal Aviation Administration, along with other regulatory agencies, requires that cargo compartments on passenger carrying aircraft be equipped with fire detection and suppression systems. Current regulations require that the detection system alarms within 1 min of the start of a fire and flight tests are required to demonstrate compliance with these regulations. Due to the high costs of flight tests, extensive ground certification tests are typically conducted to ensure that the detection system will meet the time to alarm requirements during the flight tests. For the purpose of improving the detection system design and certification process, a transient computational fluid dynamics computer code for the prediction of smoke, heat, and gas species transport in cargo compartments has been developed. This simulation tool couples heat, mass, and momentum transfer in a body-fitted coordinate system in order to handle a variety of cargo bay shapes and sizes. Ideally, such a physics-based simulation tool can be used during the certification process to identify worst case locations for fires, optimum placement of detector sensors within the cargo compartment, and sensor alarm levels and algorithms needed to achieve detection within the required time. Validation of the model was completed, and comparison of the predicted results with the results obtained from full-scale fire tests in a variety of actual aircraft cargo compartments provides insight into the model capabilities.     

Experimental measurements,integral modeling and smoke detection of early fire in thermally stratified environments

Building fires go through a series of stages. They start with a fire plume period during which buoyant fire smoke rises to the ceiling. A second stage is the following enclosure smoke-filling period. In this paper, the first stage is the subject, especially for the fire plume behavior in thermally stratified environments in large volume spaces. In NFPA 92B, Morton's integral equation was introduced for calculating the maximum plume rise, and beam smoke detectors were recommended for smoke detection design. In this work, experiments and CFD simulations were conducted in a small-scale enclosure and a large space to investigate early fire movements in temperature-stratified ambients. The results show that in a thermally stratified environment, the axial temperature and velocity of a fire plume decrease more quickly along the vertical axis than in uniform environment, and in some cases the fire plume ceases to rise. The previous integral equation was shown to underestimate the actual maximum height of a fire smoke plume, and also was unable to explain the differences of the maximum heights of low-density and high-density smoke plumes with the same stratification and outlet conditions. The integral equation was improved by introducing two correction factors, and extended for non-linear temperature stratified environments. A light section smoke detection method with three space-protected area was suggested and discussed.     

Fire detection based on vision sensor and support vector machines

This paper proposes a new vision sensor-based fire-detection method for an early-warning fire-monitoring system. First, candidate fire regions are detected using modified versions of previous related methods, such as the detection of moving regions and fire-colored pixels. Next, since fire regions generally have a higher luminance contrast than neighboring regions, a luminance map is made and used to remove non-fire pixels. Thereafter, a temporal fire model with wavelet coefficients is created and applied to a two-class support vector machines (SVM) classifier with a radial basis function (RBF) kernel. The SVM classifier is then used for the final fire-pixel verification. Experimental results showed that the proposed approach was more robust to noise, such as smoke, and subtle differences between consecutive frames when compared with the other method.