一种基于支持向量回归的驾驶座椅舒适度评价方法

An Evolution Method of Driving Seat Comfort Based on Support Vector Regression

提出一种基于支持向量回归的预测驾驶座椅主观舒适度的方法。预测的输入变量为14个体压分布变量以及3个人体变量,输出变量为整体舒适度指数。通过12名被试对5辆不同汽车进行实际驾驶来获取座椅压力数据。在利用支持向量回归建立的舒适度预测方法进行预测时,均方误差为0.0018,相关系数为0.869,这一结果优于人工神经网络预测模型的预测结果。研究结果有助于汽车制造企业在提高汽车座椅舒适性的过程中降低成本并缩短制造时间。

An evaluation method based on support vector regression（SVR） was put forward for the purpose of predicting subjective perceptions of automobile seat comfort. The inputs included fourteen seat interface pressure measures, three anthropometric. The output was an overall comfort index derived from occupant responses to a survey. The SVR developed and validated using data collected from 12 subjects,and the subjects evaluated five different driving seats. The prediction results reach 0. 0018 in mean square error and 0. 869 in linear correlation coefficient; it gives better results than that with artificial neural network. The resulting knowledge should reduce the cost and time associated with the current automobile seat comfort development process.