Gabor-GLCM-Based Texture Feature Extraction Using Flame Image to Predict the O₂ Content and NO_x

Abstract

Flame image feature extraction is the basis for boiler combustion monitoring and control. The flame video images of recent research are mainly derived from experimental burners in the laboratory, and few pay attention to the flame images in industrial boilers. The actual industrial boiler flame images differ significantly from the laboratory flame images. Additionally, certain flame image features cannot be captured in the laboratory owing to the limitations of the camera installations. Therefore, a flame image texture feature extraction algorithm based on an industrial boiler is proposed in this paper. The texture features were enhanced using a Gabor filter for the RGB channels of the flame images, and then, the statistics of the texture features were scalarized by a gray-level co-occurrence matrix (GLCM). The data were filtered and downscaled by a data compressor consisting of Gaussian-weighted mean and principal component analysis (PCA) to obtain eight key variables. The extracted eight variables were verified to be effective in characterizing the O2 and NO x contents of flue gas using the mutual information method. The combustion process regression model was constructed using a gated recurrent unit (GRU) on the 8 h combustion data of the boiler, and the predicted mean absolute percentage error (MAPE) for O2 and NO x content in the test set reached 7.5 and 10.2%, respectively. Compared to the conventional methods of direct PCA on images and GLCM plus PCA on images, the MAPE for O2 content prediction was reduced by 12.3 and 7.3%, and the MAPE for NO x content prediction was reduced by 10.5 and 6.1%, respectively. The advantage of the new flame feature based on Gabor-GLCM is suitable for the subsequent analysis and control of an industrial combustion system.

Optical Analysis of Blast Furnace Gas Combustion in a Laboratory Premixed Burner

“…14 Furthermore, other Haralick features have been used to characterize O 2 and NO x content in flue gases. 33 In this way, dependences between the combustion characteristics and IMC1 (or other related texture features) have been empirically reported. When Otsu's thresholding segmentation is applied, a small number of flame pixels could be separated from the main contour of the flame and distort the values of the geometrical features.…”

“…Nevertheless, IMC1 has been used together with other color and texture features to characterize primary air flow and secondary air to territory air split . Furthermore, other Haralick features have been used to characterize O 2 and NO x content in flue gases . In this way, dependences between the combustion characteristics and IMC1 (or other related texture features) have been empirically reported.…”

“…Most studies use statistical characteristics of the image pixel values, 13 − 16 , 29 − 32 which are related to the intensity of light emissions. Additionally, other methods can also compute texture 14 , 33 and geometrical characteristics 15 , 31 , 34 − 36 and flame speeds. 37 , 38 Before the characteristics are extracted from the image, several preprocessing techniques are used.…”

“…Most studies use statistical characteristics of the image pixel values, − ,− which are related to the intensity of light emissions. Additionally, other methods can also compute texture , and geometrical characteristics ,,− and flame speeds. , Before the characteristics are extracted from the image, several preprocessing techniques are used. These preprocessing techniques include the averaging of image sequences, ,, flame segmentation with thresholding, ,, noise filters, color space conversions to grayscale, and finally hue, saturation, and intensity (HSI). , …”

Experimental Study on Prediction for Combustion Optimal Control of Oil-Fired Boilers of Ships Using Color Space Image Feature Analysis and Support Vector Machine

“…Xia proposed a learning model that combines principle component analysis (PCA) and Kernel-SVM for flame images from a gas-fired boiler (GFB) [15]. Yang developed an algorithm for predicting exhaust gas emissions by applying Garbor filters to gray-level co-occurrence matrix (GLCM) features in flame images from an industrial circulating fluidized bed (CFB) [16]. Ganpati [17] predicted the oxygen (O 2 ) content by combining GFB images with operational data using a data ensemble model [17].…”