Deep learning based monitoring of furnace combustion state and measurement of heat release rate. (15th July 2017)

• Record Type: Journal Article
• Authors: Wang, Zhenyu; Song, Chunfeng; Chen, Tao
• Is Part Of: Energy. Volume 131(2017)
• Page Start: 106
• Page End: 112
• Publication Date: 2017-07-15
• Subjects: Deep learning -- Combustion state -- Heat release rate -- Flame image -- Convolutional neural network -- Smooth and adjustment techniques; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2017.05.012
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Effective and efficient monitoring of furnace combustion state and measurement of heat release rate are important and pressing problems in the power industry. However, traditional methods including image segmentation based methods, feature based methods and shallow classifier based methods cannot meet the requirements of highly accurate. These methods are composed with several separating steps, i.e. feature selection and recognition. This paper proposes a novel deep learning based method to identify furnace combustion state and measure heat release rate. With an end-to-end network, feature extraction and classification are integrated into one framework. The deep learning model takes flame images into a multi-layer DNN (Deep Neural Network) or CNN (Convolutional Neural Network) to predict combustion state and heat release rate simultaneously. We also implement smooth and adjustment techniques which can get a trade-off between stability and sensitivity, ensuring both accurate prediction of burner state and fast detection of unstable combustion. The proposed system achieved state-of-the-art 99.9% accuracy in predicting combustion state with a speed of 1 ms per image. Experimental results show that this method has great potential for practical applications on power plants. Highlights: A novel deep learning based framework to identify furnace combustion state. An end-to-end framework to integrate feature extraction and classification. Adopt a smooth and adjustment technique. Achieved state-of-the-art 99.9% accuracy with high processing speed.