DocumentCode :
2678582
Title :
A soft sensor based on kernel PCA and composite kernel support vector regression for a flotation circuit
Author :
Yang, Huizhi ; Huang, Min
Author_Institution :
Zhongshan Inst., Univ. of Electron. Sci. & Technol. of China, Zhongshan, China
Volume :
5
fYear :
2010
fDate :
27-29 March 2010
Firstpage :
375
Lastpage :
378
Abstract :
A soft sensor was developed to estimate the concentrate grade and recovery rate of a flotation circuit. The algorithm uses kernel principal component analysis (KPCA) and composite kernel support vector regression (CK-SVR) to perform the estimation. Firstly, the flotation prior knowledge and KPCA are employed to reduce the dimension of input vector of CK-SVR. Then, considering that the characteristics of kernels have great impacts on learning and predictive results of SVR, a composite kernel SVR modeling method based on polynomial kernel and RBF kernel is adopted which hyperparameters are adaptively evolved by the particle swarm optimization (PSO) algorithm. Simulations using real operating data show that the soft sensor provides the necessary accuracy for a flotation circuit.
Keywords :
particle swarm optimisation; principal component analysis; sensors; support vector machines; composite kernel support vector regression; flotation circuit; kernel principal component analysis; particle swarm optimization; soft sensor; Artificial neural networks; Circuit simulation; Kernel; Minerals; Particle swarm optimization; Polynomials; Predictive models; Principal component analysis; Sensor phenomena and characterization; Support vector machines; CK-SVR; KPCA; PSO; flotation circuit; soft sensor;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advanced Computer Control (ICACC), 2010 2nd International Conference on
Conference_Location :
Shenyang
Print_ISBN :
978-1-4244-5845-5
Type :
conf
DOI :
10.1109/ICACC.2010.5487084
Filename :
5487084
Link To Document :
بازگشت