基于LSSVM的六价铬含量预测模型

Hexavalent chromium content prediction model based on LSSVM

设计一种六价铬自动测量系统,为提高测量的准确度,使用最小二乘支持向量机(LSSVM)算法建立预测模型,并使用混合蛙跳算法优化LSSVM算法的参数,可避免算法收敛于局部最优,增强算法的泛化能力,减少算法对异常样本的预测偏差,提高精度。通过对神经网络模型及LSSVM模型进行仿真对比,结果显示LSSVM模型的六价铬含量预测误差更小。

A hexavalent chromium automatic measuring system was designed to improve the measurement accuracy. The least square support vector machine(LSSVM)algorithm is used to establish the prediction model,and the shuffled frog leaping algorithm is used to optimize the parameters of LSSVM algorithm to prevent the algorithm converging to the local optimum,en?hance the generalization ability of the algorithm,reduce the algorithm′s prediction deviation for the abnormal samples,and im?prove the accuracy. The neural network model and LSSVM model are simulated respectively. The results show that the prediction error of the hexavalent chromium content predicted with LSSVM model is much smaller.