融合特征降维与人工神经网络的坐姿人体头部振动特性研究

打开文本图片集

关键词：人体振动；座椅到头部传递函数；体征参数；人工神经网络；特征降维 中图分类号：TP393 文献标志码：A DOI：10.16385/j.cnki.issn.1004-4523.202508081

Modeling of the seat-to-head transmissibility based on the artificial neural network and the feature dimensionality reduction method

ZHANG Xiaolu， CHEN Xiangyu，DUAN Yuanfei， SUNHaoyu，LIN Sen （College ofMechanical and Energy Engineering，Beijing Universityof Technology，Beijing 100124，China）

Abstract：Low-freqencyvibrationstransmitdfromteseattotheeadofthseatedindividualscanimpactridingcomfortandeveduce motionsickne.asedoteolebdbatioexperetsartfcalraltwokodelstodictteatadtaii weredevelopdTddrssthiollaritsseusedytropometricpametersdtoableuratepredictiofeatt headransmisibilitteimensioalityofteanthropometricparametersieodelwasotiidymploingothpriipalopot analysisandkeelprincipalcompoentanalysis.eresultsindicatetatunderconditionswithandwitoutabackrest，theprediction acuracyofthatdtrasssbilitfogleaisouliaisciationasiificantlmrodineodeliatig principalcomponentanalysis，comparedtothebackpropagationartficialneuralnetworkmodel.Whenpredictingtheseato-ead transisibilityunderconditions withandwitoutabackrest，themodelfusedwithkeelpricipalcompoentanalysisexhibitsfurther reduced prediction errors by 2.5% and 28.7% ，achieving accuracies of 0.9657and0.9676，respectively，compared to the principal component analysisntegratedmodel.Teeseachsggstedtheeelpricipalcomponentaalysisisoreefiientthantheprincipalopot analysisatminimizingredundantinformation，therebyenhancingthepredictionprecisionoftheseat-to-headtransmisibilty.

Keywords：wolbodybratio;sattadtrasibilitythopometparameters;rtiialraletrk;featreducti

车辆行驶等振动环境下的人体头部振动响应可能会影响乘员的视觉功能和驾乘舒适性，甚至可能导致晕动症等疾病[1-2]。（剩余14159字）