Augmented flame image soft sensor for combustion oxygen content prediction. (1st January 2023)

• Record Type: Journal Article
• Authors: Gao, Shuang; Dai, Yun; Li, Yingjie; Jiang, Yuxin; Liu, Yi
• Is Part Of: Measurement science & technology. Volume 34:Number 1(2023)
• Publication Date: 2023-01-01
• Subjects: oxygen content prediction -- regression generative adversarial network -- imbalanced learning -- convolutional neural network -- deep learning; Physical measurements -- Periodicals; Scientific apparatus and instruments -- Periodicals; Equipment and Supplies -- Periodicals; Science -- instrumentation -- Periodicals; Technology -- instrumentation -- Periodicals; Mesures physiques -- Périodiques; Physical measurements; Scientific apparatus and instruments; Periodicals; 502.87
• DOI: 10.1088/1361-6501/ac95b5
• Languages: English
• ISSNs: 0957-0233

Abstract

Abstract: Oxygen content is one of the most critical factors for high-efficiency combustion. Online measurement of oxygen content from flame images is important but still challenging. For construction of an oxygen content prediction model, most current feature extraction methods are not straightforward. Additionally, there are always sufficient data for common operating conditions in practice, while only limited data for other operating conditions. The data collection process for model training is costly and time-consuming. To tackle the problem, this work presents an augmented flame image soft sensor for automated combustion oxygen content prediction. A convolutional neural network (CNN) regression model is designed to predict the oxygen content directly from flame images, without a single feature extraction process. Moreover, a regression generative adversarial network with gradient penalty is proposed to generate flame images with oxygen content labels. It overcomes the imbalanced and insufficient data problem arising in the CNN regression model training. The proposed soft sensor is compared with several common regression methods for oxygen content prediction. Experimental results show that the proposed method can predict the combustion oxygen content with high accuracy from flame images although the original datasets are imbalanced.