Affiliations: School of Mechanical & Electronic Engineering, Jingdezhen Ceramic Institute, Jingdezhen, Jiangxi, China
Correspondence:
[*]
Corresponding author: Yong-Hong Zhu, School of Mechanical & Electronic Engineering, Jingdezhen Ceramic Institute, Jingdezhen, Jiangxi, China. Tel.: +86 0798 8497977; Fax: +86 0798 8497977; E-mail: [email protected].
Abstract: In view of present single detection method and low detection accuracy of ceramic shuttle kiln temperature, a kind of multi-sensor-based information fusion optimization algorithm of burning zone temperature is proposed according to fundamental characteristics of ceramic shuttle kiln burning zone in this paper. Firstly, the different temperatures corresponding to the flame images’ RGB three primary colors are obtained by an expert system. Secondly, real-time three primary colors values of the kiln flame images taken by CCD camera are got by using K-mean clustering algorithm for segmentation. Thirdly, the corresponding temperature value of the image in the expert system is obtained by least square method. Finally, the temperature values obtained from the multi-sensor are fused, and the burning zone temperature of ceramic shuttle kiln is obtained by using Kalman filter to smooth the fusion temperature. In the end, the simulation results show that this method has achieved good effect.