电子学报
電子學報
전자학보
ACTA ELECTRONICA SINICA
2009年
10期
2130-2133
,共4页
浊度%预测%经验模态分解%支持向量
濁度%預測%經驗模態分解%支持嚮量
탁도%예측%경험모태분해%지지향량
turbidity%prediction%empirical mode decomposition%support vector
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.
針對江水濁度序列寬頻、非線性、非平穩的特點,將經驗模態分解(EMD)和支持嚮量機(SVM)迴歸方法引入濁度預測領域,建立瞭基于EMD-SVM的濁度預測模型.通過EMD分解,將原始非平穩的濁度序列分解為若榦固有模態分量(IMF),根據各IMF序列的特點,選擇不同的參數對各IMF序列進行預測,最後閤成原始序列的預測值.將該方法應用于實際濁度預測,併與徑嚮基神經網絡(RBF)預測及單獨支持嚮量機迴歸預測結果進行比較,倣真結果錶明該方法預測精度有明顯提高.
침대강수탁도서렬관빈、비선성、비평은적특점,장경험모태분해(EMD)화지지향량궤(SVM)회귀방법인입탁도예측영역,건립료기우EMD-SVM적탁도예측모형.통과EMD분해,장원시비평은적탁도서렬분해위약간고유모태분량(IMF),근거각IMF서렬적특점,선택불동적삼수대각IMF서렬진행예측,최후합성원시서렬적예측치.장해방법응용우실제탁도예측,병여경향기신경망락(RBF)예측급단독지지향량궤회귀예측결과진행비교,방진결과표명해방법예측정도유명현제고.
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.