Component Content Soft-Sensor of SVM Based on Ions Color Characteristics

Lu Rongxiu, Yang Hui, Zhang Kunpeng,

Indonesian Journal of Electrical Engineering and Computer Science, Vol 10, No 6: October 2012 , pp. 1445-1452

Abstract

In consideration of different characteristic colors of Ions in the P507-HCL Pr/Nd extraction separation system, ions color image feature H, S, I that closely related to the element component contents are extracted by using image processing method. Principal Component Analysis algorithm is employed to determine statistics mean of H, S, I which has the stronger correlation with element component content and the auxiliary variables are obtained. With the algorithm of support vector machine, a component contents soft-sensor model in Pr/Nd extraction process is established. Finally, simulations and tests verify the rationality and feasibility of the proposed method. The research results provide theoretical foundation for the online measurement of the component content in Pr/Nd countercurrent extraction separation process. DOI: http://dx.doi.org/10.11591/telkomnika.v10i6.1418