采用改进果蝇优化算法的最小二乘支持向量机参数优化方法

Least Squares Support Vector Machine Parameters Optimization Based on Improved Fruit Fly Optimization Algorithm with Applications

针对最小二乘支持向量机建模中超参数选择盲目的问题,提出了一种新的改进果蝇优化算法用于超参数寻优。该算法在果蝇优化算法的基础上,通过判断当代寻优所获得的最优值与前代最优值的关系来选择不同的步长计算公式,以实现搜索步长的自适应更新,使其不仅具有果蝇优化算法调整参数少、计算速度快的优越性,而且提高了果蝇优化算法的寻优精度和全局寻优能力。仿真结果和磨机负荷应用表明,与基于网格搜索法、粒子群优化算法以及未改进的果蝇优化算法所建立的预测模型相比,基于改进的果蝇优化算法所建立的预测模型可以显著提高磨机负荷的预测精度,能更准确地描述出磨机负荷的变化规律。

Considering the blind hyper parameters selection in least squares support vector machine（LSSVM）modeling,a new improved fruit fly optimization algorithm（IFOA）for hyper parameter optimization is proposed based on the conventional FOA.This algorithm selects the different step size formula to realize the adaptive update of the search step by judging the relation between the optimal value obtained by contemporary optimization and the previous generation optimal value,which improves the optimization precision and global optimization ability of the IFOA with fewer parameters and quick calculation rate.The simulation and mill load softsensing application show that the prediction model based on IFOA,compared with those based on grid search method,particle swarm optimization algorithm and FOA,significantly improves the mill load forecast precision and more accurately reveals the change rule of mill load.