Intelligent forecasting of sintered ore’s chemical components based on SVM

Abstract

Using object mathematical model of traditional control theory can not solve the forecasting problem of the chemical components of sintered ore. In order to control complicated chemical components in the manufacturing process of sintered ore, some key techniques for intelligent forecasting of the chemical components of sintered ore are studied in this paper. A new intelligent forecasting system based on SVM is proposed and realized. The results show that the accuracy of predictive value of every component is more than 90%. The application of our system in related companies is for more than one year and has shown satisfactory results.

Keywords

sintered ore / support vector machine / intelligent forecasting / nonlinear regression / optimized control

References

[1] Wang C., Wu M., She Chunhua. An Intelligent Integrated-prediction Model for Components of Pb-Zn Agglomerate Based on the Process Neural Network(PNN) and the Improved Grey System(IGS)[J]. Control Theory and Application, 2009, 26(3): 316-320.

[2] Xu Z., Wu Min. Intelligent Integrated Optimization Control of Quality and Quantity for Lead-zinc Sintering Process[J]. Control Theory and Application, 2008, 25(4): 688-692.

[3] Bodriguez M. J., Serodes J. B. Application of Back-Propagation Neural Network Modeling for Free Residual Chlorine Total Trihalomethanes and Trihalomethanes Speciationl[J]. Jourmal of Environmental Engineering and Science, 2004, 3(2): 23-30.

[4] Scholkopf B., Platt J. C., Shawe Taylor J. e. a1. Estimating the Support of a High-dimensional Distribution[J]. Neural Computation, 2001, 13(7): 1 443-1 471.

[5] Chang C. C., Lin C. J. Training nu-Support Vector Classifier: Theory and Algorithms[J]. Neural Computation, 2001, 13(9): 2 119-2 147.

[6] Zhong L., Liu L., Zou C., . The Application of Neural Network in Lifetime Prediction of Concrete[J]. Journal of Wuhan University of Technolog, 2002, 17(1): 79-81.

[7] Tian H., Sun Shanxia. Gear Fault Diagnosis Based on Rough Set and Support Vector Machine[J]. Journal of Wuhan University of Technology, 2006, 3: 1 046-1 051.

[8] Zhong L., Li Z., Ding Z., . Multiple Sources Data Fusion Strategies Based on Multi-class Support Vector Machine[C]. Lecture Notes in Computer Science, 2008, 5263: 715-722.