An Intelligent Vision System for Monitoring and Control of Combustion Flames

Abstract

System developmentFigure 1: Schematic diagram ofthe flame monitoring and control system. Experimental set-upIn order to examine the suitability of the proposed system for advanced monitoring and control of combustion flames, experimental work has been undertaken on a model combustor. A schematic diagram of the experimental set-up is shown in Figure 1. Butane-gas flames were generated on a burner with an exit diameter of 15 mm. Variations in the air and fuel flow rates were achieved by adjusting the positions of air and fuel valves driven by two stepper motors. A 1/ 2 inch monochromatic CCD camera fitted with a short-wave-pass filter (450±5 om) was used to transmit the image signal of the flameto a frame-grabber at a frame rate of 25 frames/s (50 fields/s). The frame-grabber is capable of performing 8-bit digitisation at 45 MHz and transferring the image signal to the host computer memory at 132 Mbytes/s. A software system was developed to establish the computing imaging from a particular intermediate radical (OH) in the flame zone. And all information derived from each pixel over a specific region of the image was used to construct the neural network. A prototype fuzzy system developed by Tao and Burkhardt 8 was used for the control of gas-fired flames on a miniature combustion model, whereby a flame image was divided into two separate luminous regions. However, the system could only be applied to the control of a single predetermined setpoint.Present work reported in this paper is concerned with the development and experimental evaluation of an intelligent vision system for the monitoring and control of combustion flames by combining image processing and neural network techniques. Both geometrical and luminous parameters of an entire flame are determined over a specific luminous region of the image on a dynamic basis. A neural network is constructed from these param-.

On the use of stereovision to develop a novel instrumentation system to extract geometric fire fronts characteristics

“…For more than two decades, visual and infrared cameras have been used as complementary metrological instruments in fire and flame experiments [1][2][3][4][5]. Vision systems are now capable of reconstructing a 3D turbulent flame and its front structure when the flame is the only density field in images [6,7].…”

Efficient Low-Driving-Voltage Blue Phosphorescent Homojunction Organic Light-Emitting Devices

“…Therefore, burner slagging is strongly dependent upon the quarl temperature and material, the burner aerodynamics and the composition of the lowest melting species in the coal. Flame monitoring methods, incorporating measurements of flame infra-red (IR) or ultraviolet (UV) radiation signals and combustion noise, together with neural network techniques, have been used to optimize the combustion process both with pilot and full-scale burners [9][10][11][12]. As mentioned earlier, the presence of eyebrows can alter the burner aerodynamics and hence the combustion characteristics of the flame.…”

Rotary Kiln Product Quality Forecasting Based on Flame Imaging

“…Flame imaging has already been investigated in the past, but most of these contributions were performed on laboratory scale combustion systems and premixed flames, and their approach was to compute geometrical and luminous properties of the flame extracted from gray scale images and use them to either classify the flame into arbitrarily defined states (Bertucco et al, 2000;Victor et al, 1991) or to predict various quantities such as flicker rate (Huang et al, 1999), unburnt carbon, CO 2 and NO x emissions (Shimoda et al, 1990;Lu et al, 1999;Yan et al, 2002) or fuel and air flow rates (Tao and Burkhardt, 1995). Only a few past investigations were extracting the flame features from RGB color images (Wang et al, 2002;Keyvan, 2003) and were taking advantage of the three wavelengths to estimate the flame temperature distribution using the bicolor method.…”