ZHU Yonghong, FU Yao, LI Xuanliang, WANG Junxiang

(School of Mechanical and Electronic Engineering, Jingdezhen Ceramic University, Jingdezhen 333403, Jiangxi, China)

Abstract: Ceramic shuttle kiln is a batch kiln used for ceramic production. Temperature detection mode of the sintering zone in the kiln directly affects the production quality of the final ceramic products. At present, the thermal detection of ceramic shuttle kiln is still inaccurate. As a result, flame image recognition method has been developed to replace the traditional thermocouple to detect the sintering zone temperature. In this paper, to address the problem of flame image recognition in the sintering zone of ceramic shuttle kiln, flame image classification method based on improved convolution neural network was proposed. In this method, the SE module was embedded in optimized convolution neural network (Inception-ResNet-V2) module, so as to improve the attention of the network to the key features, to adaptively refine the features and to improve the classification effect. Experimental results showed that the improved SE-Inception-ResNet-V2 can increase the flame image classification accuracy and accelerate the convergence rate. Compared with other flame image classification methods, our approach achieved an increase in recognition accuracy by 1.60‒5.57%.

Key words: ceramic shuttle kiln; convolution neural network; flame image; image classification