DocumentCode :
2665039
Title :
An useful system based data mining of the ore mixing in sintering process
Author :
Ruiyin, Tang ; Hongkun, He
Author_Institution :
Coll. of Electr. Eng., Hebei United Univ., Tangshan, China
fYear :
2012
fDate :
23-25 May 2012
Firstpage :
174
Lastpage :
177
Abstract :
The article introduced the system of ore mixing of sintering based on data mining and neuron network. Appling the method of cluster to the saved history data of the sintering process to classify the history data into three categories. And then, established neuron network model of each cluster. Every new sample should be put into the Corresponding cluster first by the distance of Eucliden, and then we can predict the quality index of the new sample by the neuron network model. The method is more effective and accurate, and it can extend to other production of the enterprise.
Keywords :
data mining; mineral processing; mixing; neural nets; pattern classification; pattern clustering; production engineering computing; quality management; sintering; data mining; enterprise production; history data classification; neuron network model; ore mixing; quality index prediction; sintering process; Data mining; Indexes; Mathematical model; Neurons; Ores; Software; Steel; Data mining; cluster; neuron network; ore-mixing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control and Decision Conference (CCDC), 2012 24th Chinese
Conference_Location :
Taiyuan
Print_ISBN :
978-1-4577-2073-4
Type :
conf
DOI :
10.1109/CCDC.2012.6244025
Filename :
6244025
Link To Document :
بازگشت