Premium
Belt speed control in a sintering plant using neural networks
Author(s) -
Jang Min,
Cho Sungzoon,
Lee Shinjae,
Kwon Yuhwa
Publication year - 1998
Publication title -
steel research
Language(s) - English
Resource type - Journals
eISSN - 1869-344X
pISSN - 0177-4832
DOI - 10.1002/srin.199805571
Subject(s) - sintering , blast furnace , coke , artificial neural network , backpropagation , metallurgy , process (computing) , mechanical engineering , engineering , materials science , computer science , process engineering , artificial intelligence , operating system
Sintering transforms fine‐grained ore into lumped ore so that the latter can be used in a blast furnace. The fine‐grained ore combined with coke and other materials is loaded into a sinter box and moved along by the sintering belt while the ignited coke burns. The speed by which the belt moves determines how much sintering takes place. Since the process is complicated and lacks an accurate mathematical model, human operators manually control the speed by monitoring various factors in the plant. In this paper, a neural network‐based sintering belt speed controller is proposed which copies human operator knowledge. Actual process data were collected from a sintering plant for eight months and preprocessed to remove noisy and inconsistent data. A multilayer perceptron was trained using a backpropagation learning algorithm. In on‐line testing at the sintering plant, the proposed model reliably controlled the sintering belt speed during normal operation without the help of human operators. Moreover, the quality and productivity was as good as with human operators.