Title: Temperature intelligent prediction model of coke oven flue based on CBR and RBFNN

Authors: Yang He; Gongfa Li; Ying Sun; Guozhang Jiang; Jianyi Kong; Du Jiang; Honghai Liu

Addresses: Key Laboratory of Metallurgical Equipment and Control Technology, Wuhan University of Science and Technology, Ministry of Education, 430081, Hubei, Wuhan, China; Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, 430081, China ' Key Laboratory of Metallurgical Equipment and Control Technology, Wuhan University of Science and Technology, Ministry of Education, 430081, Hubei, Wuhan, China; Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, 430081, China ' Key Laboratory of Metallurgical Equipment and Control Technology, Wuhan University of Science and Technology, Ministry of Education, 430081, Hubei, Wuhan, China; Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, 430081, China ' Key Laboratory of Metallurgical Equipment and Control Technology, Wuhan University of Science and Technology, Ministry of Education, 430081, Hubei, Wuhan, China; Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, 430081, China ' Key Laboratory of Metallurgical Equipment and Control Technology, Wuhan University of Science and Technology, Ministry of Education, 430081, Hubei, Wuhan, China; Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, 430081, China ' Key Laboratory of Metallurgical Equipment and Control Technology, Wuhan University of Science and Technology, Ministry of Education, 430081, Hubei, Wuhan, China; Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, 430081, China ' State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China; Intelligent Systems and Biomedical Robotics Group, School of Computing, University of Portsmouth, Portsmouth, PO1 3HE, UK

Abstract: The temperature of coke oven is an important process parameter, but it is difficult to obtain the temperature of the vertical flue in real-time. The establishment based on the case-based reasoning (CBR) and radial basis function neural network (RBFNN) of coke oven flue temperature intelligent prediction model, realise the real-time prediction of the temperature, and help to realise the coke oven production process of intelligent optimisation control. The real-time forecast under different conditions is realised by the selective intelligent forecasting model of the coke oven, and the forecasting performance of system model is simulated. The results show that the forecasting model is faster and more reliable than the traditional artificial forecast. Finally, combining with the actual data of a steel enterprise to verify, the results show that the model meet the actual working condition, it can provide relevant processing methods for the soft measurement of complex industrial production control process, and it has some practical significance for intelligent optimisation control.

Keywords: coke oven; temperature measurement; intelligent forecast; neural network; case-based reasoning; CBR.

DOI: 10.1504/IJCSM.2018.10015908

International Journal of Computing Science and Mathematics, 2018 Vol.9 No.4, pp.327 - 339

Received: 27 Jul 2017
Accepted: 11 Sep 2017

Published online: 05 Sep 2018 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article