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

Abstract

Coal is still a strategic fuel for many developing countries. The environmental impact of emissions resulting from the widespread use of coal worldwide is a matter of serious debate. In this perspective, clean coal burning technologies are in demand. In this study, a measurement system that estimates emission from flame images in a domestic coal burner is proposed. The system consists of a charge-coupled device camera, image processing software (real time image acquisition, noise reduction and extracting features) and artificial intelligence elements (classification of features by neural networks). In feature extraction stage, only five flame region features (Gx, Gy , trace, L 2 and L ∞ norm) is extracted. Gcx and Gcy are the instantaneous change of the horizontal and vertical components of center mass of the flame image. These features are new concepts for emission estimation from the flame image. The proposed system makes a difference with its simpler structure and higher accuracy compared to its counterparts previously presented in the literature.

Augmented flame image soft sensor for combustion oxygen content prediction

“…A third imbalanced dataset is obtained. Then each of the imbalanced datasets is used to train the CNN regression model, DBN-BP, DBN-SVR, PCA-BP, PCA-SVR, ANN-1 [14], and ANN-2 [15]. After the training, their compared results are given in table 2.…”

“…ANN-2 [15]: Five region features (G x , G y , trace, L 2 , L ∞ norm) from the gray flame images are extracted. Subsequently, an ANN model is designed by the obtained matrix weighted center features for oxygen content prediction.…”

“…The onlinemeasured flame images provide valuable information about the current burning status [12]. They have been used to predict the outlet content of the flue gas [13], oxygen content [1], flue gas temperature [14], emission [15], and excess air coefficient [16]. However, the features need to be extracted first from the flame images based on feature extraction methods before training prediction models such as the artificial neural network (ANN) regression model in [14].…”

Bilgisayarlı Görüş Kullanarak Bakteri ve Hücre Sayılarının Hızlı Karakterizasyonu

“…Image processing and target object/feature detection are increasingly becoming more practical with the advancement of computational hardware and software [11,12]. In this work, an open-sourced automated cell and bacteria counting method based on computer vision (CV) is demonstrated.…”

Online Estimation of Combustion Oxygen Content with an Image-Augmented Soft Sensor Using Imbalanced Flame Images

“…Several studies − have shown that valuable information about the current combustion process can be presented from flame images taken online. This provides a new idea for combustion oxygen content measurement, that is, designing soft sensors based on flame images.…”