河海大学学报（自然科学版）
河海大學學報（自然科學版）
하해대학학보（자연과학판）
JOURNAL OF HOHAI UNIVERSITY (NATURAL SCIENCES)
2013年
4期
294-299
,共6页
阚光远%李致家%刘志雨%李巧玲%胡友兵
闞光遠%李緻傢%劉誌雨%李巧玲%鬍友兵
감광원%리치가%류지우%리교령%호우병
水文模型%BP神经网络%K-最近邻算法%新安江模型%NSGA-Ⅱ算法%呈村流域%东湾流域%大阁流域
水文模型%BP神經網絡%K-最近鄰算法%新安江模型%NSGA-Ⅱ算法%呈村流域%東灣流域%大閣流域
수문모형%BP신경망락%K-최근린산법%신안강모형%NSGA-Ⅱ산법%정촌류역%동만류역%대각류역
hydrological model%BP neural network%K-nearest neighbor algorithm%Xin’ anjiang model%NSGA-Ⅱalgorithm%Chengcun watershed%Dongwan watershed%Dage watershed
将BP神经网络与K-最近邻（ KNN）算法耦合起来，建立BK（ BP-KNN）模型，该模型以前期模拟流量和相应影响要素作为BP神经网络的输入，出口断面流量作为网络输出，对产汇流过程进行模拟；采用K-最近邻算法，基于历史样本的模拟误差和相应影响要素对网络输出进行修正，实现了非实时校正模式下的连续模拟。根据BK模型的计算流程将其参数分为3个层次，各层次分别使用NSGA-Ⅱ多目标优化算法进行参数优选，提高了模拟精度、优化效率和网络泛化能力。分别将新安江模型的产流、产流分水源计算模块与BK模型相耦合，建立 XBK （ Xinanjiang runoff production-BK）和XSBK （ Xinanjiang runoff production and separation-BK）模型，在呈村等3个不同类型的流域应用新安江模型、BK模型、XBK模型和XSBK模型进行模拟精度比较，结果表明改进的模型模拟精度更高，较好地解决了神经网络模型在水文模拟中存在的问题。
將BP神經網絡與K-最近鄰（ KNN）算法耦閤起來，建立BK（ BP-KNN）模型，該模型以前期模擬流量和相應影響要素作為BP神經網絡的輸入，齣口斷麵流量作為網絡輸齣，對產彙流過程進行模擬；採用K-最近鄰算法，基于歷史樣本的模擬誤差和相應影響要素對網絡輸齣進行脩正，實現瞭非實時校正模式下的連續模擬。根據BK模型的計算流程將其參數分為3箇層次，各層次分彆使用NSGA-Ⅱ多目標優化算法進行參數優選，提高瞭模擬精度、優化效率和網絡汎化能力。分彆將新安江模型的產流、產流分水源計算模塊與BK模型相耦閤，建立 XBK （ Xinanjiang runoff production-BK）和XSBK （ Xinanjiang runoff production and separation-BK）模型，在呈村等3箇不同類型的流域應用新安江模型、BK模型、XBK模型和XSBK模型進行模擬精度比較，結果錶明改進的模型模擬精度更高，較好地解決瞭神經網絡模型在水文模擬中存在的問題。
장BP신경망락여K-최근린（ KNN）산법우합기래，건립BK（ BP-KNN）모형，해모형이전기모의류량화상응영향요소작위BP신경망락적수입，출구단면류량작위망락수출，대산회류과정진행모의；채용K-최근린산법，기우역사양본적모의오차화상응영향요소대망락수출진행수정，실현료비실시교정모식하적련속모의。근거BK모형적계산류정장기삼수분위3개층차，각층차분별사용NSGA-Ⅱ다목표우화산법진행삼수우선，제고료모의정도、우화효솔화망락범화능력。분별장신안강모형적산류、산류분수원계산모괴여BK모형상우합，건립 XBK （ Xinanjiang runoff production-BK）화XSBK （ Xinanjiang runoff production and separation-BK）모형，재정촌등3개불동류형적류역응용신안강모형、BK모형、XBK모형화XSBK모형진행모의정도비교，결과표명개진적모형모의정도경고，교호지해결료신경망락모형재수문모의중존재적문제。
The BK ( BPK-NN) model, which is coupled by the BP neural network model and the K-nearest neighbor ( KNN) model, was established .This model was used to simulate flow concentration and runoff generation with antecedent simulated outlet flow and relevant influencing factors as inputs of the BP neural network , and the outlet flow as the output of the network.The output of the network was corrected by the K-nearest neighbor algorithm based on historical samples ’ simulation error and relevant influencing factors .The KNN algorithm realizes continuous simulation in a non-real time mode .According to the computational procedure , parameters of the BK model were divided into three groups and optimized by the NSGA-II multi-object algorithm in each group .This way of calibration improves the accuracy , efficiency , and generalization ability of the BK model . The XBK ( Xin’ anjiang runoff production-BK ) and the XSBK ( Xin’ anjiang runoff production and separation-BK ) model were coupled by the Xin ’ anjiang runoff production module , the Xin ’ anjiang runoff production and separation module, and the BK flow concentration module .BK, XBK, XSBK, and the Xin’anjiang model were applied to the Chengcun ,Dongwan , and Dage watersheds to compare their simulation accuracies .The results show that the improved model has higher accuracy and can be used to solve problems of neural network models during hydrological simulation .
