汽车座椅舒适度人工智能评价方法研究  

An Automobile Seat Comfort Evaluating Method Based on Artificial Intelligence

作　　者：马佳 柯艺杰[2] 苏强[2] 杨海霞[3] 

机构地区：[1]李尔中国工程技术中心,上海201201 [2]同济大学经济与管理学院,上海200092 [3]常州纺织服装职业技术学院,常州213100

出　　处：《机械科学与技术》2011年第3期419-422,共4页Mechanical Science and Technology for Aerospace Engineering

基　　金：国家自然科学基金项目(70672077)资助

摘　　要：随着汽车的普及应用,座椅舒适性成为关注焦点。然而,目前有关汽车座椅舒适度评价主观性较大,缺乏客观可行的评价方法。笔者通过有针对性的客户问卷调查,应用人工神经网络技术,以座椅的各部分特征性能为输入变量,建立了汽车座椅舒适度的人工智能评价系统。此外,为了进一步提高该系统的预测精度,笔者还应用了聚类分析方法。通过样本类数的调整,能将系统预测误差从原来的41.09%最大降至27.845%。With the wide application of automobiles, automobile seat comfort has attracted the attention of researchers. However, there is not an objective and feasible evaluation method. In this paper, based on a survey of automo- bile customers, an effective automobile seat comfort evaluation system is constructed by using artificial neural network; its input variables are characteristics of different seat parts. In addition, in order to improve the prediction accuracy of the system, cluster analysis method is applied. By modif）;ing sample cluster number, the prediction error can be reduced from 41.09% to 27. 845%.

关 键 词：汽车座椅舒适度 神经网络 聚类分析 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]