Search

In order to actively control combustion reaction, this study proposes an adaptive neuro-fuzzy (ANFIS) control scheme of interaction between premixed combustion reaction and acoustic flame perturbation where the flame pressure movement will be considered as model perturbation. Using the Cantera database, it is possible to investigate the mechanisms by which the combustion process interacts with acoustic, vorticity, and entropy waves. A well-stirred reactor (WSR) has been extensively used to model combustion processes in three different reaction zone regimes. We designed the control architecture to achieve an intelligent representation of the system for various operating scenarios, which was motivated by the complexity of the mathematical model that was being used. This goal is accomplished by an artificial bee colony (ABC), which uses simulated data from a mathematical model to optimize a neuro-fuzzy with less computational expense. The optimized neuro-fuzzy identifier is converted to an adaptive neural-based (ANFIS) controller optimized to control the outputs of the system. In keeping with the combustion temperature set point, the results demonstrate a remarkable attenuation of flame perturbation and acceptable combustion reaction quality (NOx emission).

Abstract: Traditional methods for quantifying and modelling compartment fires for structural engineering analysis assume spatially homogeneous temperature conditions. The accuracy and range of validity of this assumption is examined here using the previously conducted fire tests of Cardington (1999) and Dalmarnock (2006). Statistical analyses of the test measurements provide insights into the temperature field in the compartments. The temperature distributions are statistically examined in terms of dispersion from the spatial compartment average. The results clearly show that uniform temperature conditions are not present and variation from the compartment average exists. Peak local temperatures range from 23% to 75% higher than the compartment average, with a mean peak increase of 38%. Local minimum temperatures range from 29% to 99% below the spatial average, with a mean local minimum temperature of 49%. The experimental data are then applied to typical structural elements as a case study to examine the potential impact of the gas temperature dispersion above the compartment average on the element heating. Compared to calculations using the compartment average, this analysis results in increased element temperature rises of up to 25% and reductions of the time to attain a pre-defined critical temperature of up to 31% for the 80th percentile temperature increase. The results show that the homogeneous temperature assumption does not hold well in post-flashover compartment fires. Instead, a rational statistical approach to fire behaviour could be used in fire safety and structural engineering applications. [Copyright &y& Elsevier]