摘要： 在锌净化除钴过程中，生产数据存在噪声且变量间具有多重相关性，从而难以准确预测钴离子浓度。为此，采用偏最小二乘方法去除数据中的噪声，降低各参数间的多重相关性。通过为不同时期的样本数据赋予不同的权值，提高了最小二乘支持向量机(LSSVM)模型预测的准确性。利用改进的粒子群优化算法优化选择LSSVM模型的惩罚因子和核函数参数，以避免人为选择参数的盲目性。仿真结果表明，PLS- LSSVM模型的预测精度高于偏最小二乘回归和LSSVM。

关键词: 偏最小二乘法, 最小二乘支持向量机, 净化, 粒子群优化算法, 钴离子

Abstract: There are some problems in the zinc purification such as slow variation in parameters, noise in field data, and multiple correlation between variables, which lead to the difficulty of cobalt ion prediction. Partial Least Squares(PLS) is used to eliminate the noisy of data, lower the multiple correlation and reduce the dimensions of the input samples. And to demonstrate the contribution of the parameters for the system, a weighting method is introduced in the Least Squares Support Vector Machine(LSSVM). The parameters of LSSVM model are optimized by improved Particle Swarm Optimization(PSO) algorithm to escape from the blindness of man-made choice. The experimental verification analysis is performed using the industrial production data from purification process. Simulation result shows that the proposed algorithm satisfies the requirements of cobalt ion concentration prediction in industrial field, and it has higher accuracy compared with Partial Least Squares Regression (PLSR) and LSSVM.

Key words: Partial Least Squares(PLS), Least Squares Support Vector Machine(LSSVM), purification, Particle Swarm Optimization(PSO) algorithm, cobalt ion

中图分类号: 

• TP391