简介:为了给工业界提供一种快速预测二元混合液体自燃温度的有效途径,将试验所测不同组分及配比的168个二元混合液体的自燃温度作为期望输出,将基于电性拓扑状态指数(ETSI)理论、引入混合ETSI概念而计算出的9种原子类型所对应的混合ETSI作为输入,采用三层BP神经网络技术建立了根据原子类型混合ETSI来预测混合液体自燃温度的BP神经网络模型,并应用改进的Garson算法进行多参数敏感性分析。经模型评价验证及稳定性分析,得到训练集的决定系数R2为0.965,平均绝对误差MAE为11.892K,测试集的交叉验证系数Q2ext为0.923,平均绝对误差MAE为15.530K,发现该模型的预测性能优于已有的多元非线性回归(MNR)模型,表明BP神经网络模型具有较好的拟合能力和预测能力,对烷、醇类混合体系自燃温度的预测精度最佳。
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.
简介:PriorityorderedBPneuralnetworkandtheapplicationforspeakeridentification;ProbingmodificationofBPneuralnetworklearning-rate;Real-timeoptimalexcitationcontrollerusingneuralnetwork;ResearchonthemodelingoftheaxialloaddistributioncoefficientofcylindricalgearsingearCADbasedonANN;Short-termsystemmarginalpriceforecastingwithhybridmodule;StudyonautomaticcreatingmethodofpublictransportationdispatchingformbasedonBPneuralnetwork。
简介:HarmonicMinimizingNeuralNetworkSVCControllerforCompensatingUnbalancedFluctuatingLoads;ImplementationofanAdaptivePredictor-CorrectorNeuralControllerwithintheNASAIFCSF-15WVUSimulator;NeuralNetworkAdaptiveControlofaSpacePlatform-BasedDeployableManipulator;Neuralnetworkcontroldesignforarigid-linkelectricallydrivenrobot;Neuralnetworkcontrolfordynamicvoltagerestorer;NeuralNetworkControlofAir-to-FuelRatioinaBi-FuelEngine;Neuralnetworkcontrolofcoldflowcirculatingfluidizedbed;Neuralnetworkcontrolofmultlvariableprocesseswithafastoptimisationalgorithm。