Due to the nonlinear and nonstationary characteristics of river water turbidity, a novel intelligent forecasting method based on empirical mode decomposition (EMD) and support vector machines (SVMs), is proposed. The intrinsic mode functions (IMFs) are adaptively extracted via EMD from a time series of turbidity according to the intrinsic characteristic time scales.Then tendencies of these IMFs are forecasted with SVMs respectively,in which the kernel functions are appropriately chosen with these different fluctuations of IMFs. Finally these forecasting results are combined to output the ultimate forecasting result.The proposed model is applied to a water turbidity tendency forecasting example, and the simulation results show that the forecasting performance of the hybrid model outperforms SVMs and RBF ahead forecasting.%针对江水浊度序列宽频、非线性、非平稳的特点,将经验模态分解(EMD)和支持向量机(SVM)回归方法引入浊度预测领域,建立了基于EMD-SVM的浊度预测模型.通过EMD分解,将原始非平稳的浊度序列分解为若干固有模态分量(IMF),根据各IMF序列的特点,选择不同的参数对各IMF序列进行预测,最后合成原始序列的预测值.将该方法应用于实际浊度预测,并与径向基神经网络(RBF)预测及单独支持向量机回归预测结果进行比较,仿真结果表明该方法预测精度有明显提高.
展开▼
