简介:精确的短期电力负荷预测对电力系统的生产调度和安全稳定运行起到十分重要的作用。为提高短期电力负荷预测模型的精度。提出了一种基于Elman神经网络的改进模型。通过在输出层和隐含层之间扩展一个新的承接层。增强了Elman神经网络的动态信息处理能力。仿真结果表明,改进型Elman神经网络预测模型的预测精度要高于反向传播、支持向量机和常规Elman,同时也说明了建立改进型Elman模型用于短期电力负荷预测是可行的。
简介:摘要:针对PM2.5具有非线性、不确定性、难以预测的特点,提出了一种GM-AFSA-ELMAN神经网络的混合特征选择算法,首先是通过灰色关联的分析方法选出与PM2.5相关性较强的特征变量,过滤掉一些相关性小的特征变量。然后利用人工鱼群算法(AFSA)强大的寻优能力对ELMAN神经网络进行初始化、权值优化。接着利用ELMAN神经网络建立相关变量与 PM 2.5 浓度之间的软测量模型,并利用所监测到的数据对模型进行训练,最后将该模型应用于实际环境中,结果表明该方法具有较高的精度和收敛速度
简介:Dynamicnodecreationandfastlearningalgorithmforahybridfeedforwardneuralnetwork.Flight-pathanglecontrolvianeuro-adaptiveBackstepping.Locallearningframeworkforhandwrittencharacterrecognition.Maximizingmarginsofmultilayerneuralnetworks.ModularnetworkSOMself-orgmlizingmapofasystemsgroupinfunctionspace.
简介:ApplicationoftheRTNNmodelforasystemidentification,predictionandcontrol;AssociativeMemoryUsingRatioRuleforMulti-valuedPatternAssociation;Batch-to-BatchModel-basedIterativeOptimisationControlforaBatchPolymerisationReactor;BehaviouralPlasticityinAutonomousAgents:AComparisonbetweenTwoTypesofController;ChannelEqualizationUsingComplex-ValuedRecurrentNeuralNetworks;Classificationofnaturallanguagesentencesusingneuralnetworks;Combiningarecurrentneuralnetworkandtheoutputregulationtheoryfornon-linearadaptivecontrol。
简介:ConfigurablemultilayerCNN-UMemulatoronFPGA;Cortically-inspiredVisualProcessingwithaFourLayerCellularNeuralNetwork;Effectofcouplingresistorsonsteadypatternsincoupledoscillatornetworks;Exponentialconvergenceestimatesforneuralnetworkswithmultipledelays;FEATUREEXTRACTIONINEPILEPSYUSINGACELLULARNEURALNETWORKBASEDDEVICEFIRSTRESULTS;FurtherResultsontheStabilityofDelayedCellularNeuralNetworks;Globalstabilityanalysisindelayedcellularneuralnetworks;ImageedgedetectionusingadaptivemorphologyMeyerWavelet-CNN。
简介:PredictionoftheDimensionalChangesduringSinteringusingBackpropagationAlgorithm,Predictionofthenextstockpriceusingneuralnetwork-extractionthefeaturetopredictnextstockpricebyfiltering,Pulsemodeneuronwithpiecewiselinearactivationfunction,Remarksonmultilayerneuralnetworksinvolvingchaosneurons……
简介:AnewapproachtogenerateAself-organizingfuzzyneuralnetworkmodel.Anonlinearcombiningforecastmethodbasedonfuzzyneuralnetwork.Anovelclustermethodinfrizzyneuralnetworks.AnovelrobustPIDcontrollerdesignbyfuzzyneuralnetwork.Arecurrentfuzzyneuralnetwork:learningandapplication.Astudyofchatterpredictioninendmillingprocess(fuzzyneuralnetworkmodelwithinputsofcuttingconditionsandsound.Aweightedfuzzyreasoninganditscorrespondingneuralnetwork.