A Basic ANN System for Prediction of Excess Air Coefficient on Coal Burners Equipped with a CCD Camera

Abstract

Excess air coefficient (λ) is the most important parameter characterizing the combustion efficiency. Conventional measurement of λ is practiced by way of the flue analyze device with high market priced. Estimating of the λ from flame images is crucial in perspective of the combustion control because of decreasing structural dead time of the combustion process. Beside, estimation systems can be used continuously in a closed loop control system, unlike conventional analyzers. This paper represents a basic λ prediction system with a neural network for small scale nut coal burner equipped with a CCD camera. The proposed estimation system has two inputs. First input is stack gas temperature simply measuring from the flue. To choose the second input, eleven different matrix parameters have been evaluated together with flue gas temperature values and performed by matrix-based multiple linear regression analysis. As a result of these analyses, it has been seen that the trace of image matrix obtained from the flame image provides higher accuracy than the other matrix parameters. This instantaneous trace value of image source matrix is then filtered from high frequency dynamics by means of a low pass filter. Experimental data of the inputs and λ are synchronously matched by a neural network. Trained algorithm has reached R=0.984 in terms of accuracy. It is seen from the result that proposed estimating system using flame image with assistance of the stack gas temperature can be preferred in combustion control systems.

Influence of Operating Parameters on Chlorine Release and Pollutant Emission Characteristics of a 130 t/h BCFB Combustion System

“…Excess Air Coefficient Variation Test. The excess air coefficient is the most important parameter that affects the boiler combustion efficiency 43 and has a great influence on the variations of combustion temperature and flue gas composition. It was assumed that the biomass feed amount was maintained at 9.8 kg/s in the simulation test, and the ratio of primary to secondary air was 1:1.…”

Prediction of combustion states from flame image in a domestic coal burner

“…On the other hand, the flame images immediately reflect the instantaneous combustion conditions [8]. Considering the advantages of low market prices and low operating costs, the estimation of emissions [9][10][11][12][13][14], flue gas temperature [15] and instantaneous combustion efficiency from flame images obtained by charge-coupled device (CCD) cameras by means of artificial neural networks (ANNs) [16][17][18][19] and control applications [20][21][22][23][24][25][26][27] are current issues. At this point, it should be noted that finding the appropriate analytical formula for predicting emission values or efficiencies of coal burners is another option [28][29][30].…”

“…While the image is processed in the emission estimation studies performed with the CCD camera, it is available in the studies with the hue saturation intensity (HSI) [10] color space as well as in the red green blue (RGB) [9] color space. The use of only one channel of the CCD camera [16] or only gray images [17] is also reported to minimize the computational load. In studies performed with colored flame image, the image is generally converted to gray level in order to reduce the size and features are obtained from the gray level image [20,21,24,25].…”