Research of the Matte Grade Model of Copper Flash Smelting Process Based on ANFIS
- 151 Downloads
The matte grade model of copper flash smelting process, which has the net-structure of 8 put-in, 1 put-out nodes and the membership functions are 5, 3, 5, was developed based on Adaptive Network-Fuzzy Inference System and by using the practical data from one copper smelter. The results indicated that the average absolute error of training samples is 0.087%, the relative error percentage is 0.15%, and the average absolute error of checking samples is 0.0079%, and the relative error percentage is 0.014%. It means that the simulative results accord to the practical data, and the model has good reference value on process optimized control of copper flash smelting. It also can be used to the industrial online control replacing the static burden model.
KeywordsFlash Smelting Fuzzy Control Neural Network Simulation
Unable to display preview. Download preview PDF.
- 1.Wang, J.L., Zhang, C.F., Zeng, Q.Y., Tong, C.R., Zhang, W.H.: Modeling and Optimization of copper Flash Smelting Process Based on Neural Network. The Chinese Journal of Process Engineering 8, 105–109 (2008)Google Scholar
- 2.Wu, X.L., Lin, Z.H.: MATLAB in Assistant Fuzzy Model Design. XDUPH, Xi’an (2002)Google Scholar
- 5.Wang, J.L., Lu, H., Wang, R.L., Zeng, Q.Y.: Analysis of the Effect Factors of Copper Flash Smelting Based on Neural Network. Nonferrous Metals (Extractive Metallurgy) 2, 2–5 (2008)Google Scholar
- 6.Zeng, Q.Y., Wang, J.L.: Developing of the Copper Flash Smelting Model Based on Neural Networks. Journal of Southern Institute of Metallurgy 24, 15–18 (2003)Google Scholar