智能座舱睡眠舒适度的实证研究

目的 基于生物力学原理，评价自动驾驶情景中座椅靠背和座面的多种组合对睡眠舒适度的影响，从而指导智能座舱的设计研发。方法 基于Tekscan的CONFORmat座椅压力分布测量系统，设计了座面角度(15°，25°，35°)和靠背角度(140°，150°，160°)的实验装置，获取了20位被试的客观多维数据与主观评价数据，随后应用人工神经网络构建了舒适度预测模型。结果 重复测量方差分析表明，随着座面平移角度的增加，可有效地均衡界面接触压力分布，座椅靠背角度为160°与座面角度35°的组合设计，其压力的加权平均值、总接触面积、界面压力分布指数、适应性等级与其他实验条件有显著性差异。结论 最后应用人工神经网络预测模型的精确验证，研究建议将35°的座面角度与160°的椅背应用于智能座舱的睡眠位置。

Empirical Study on Sleep Comfort of Intelligent Cockpit

The work aims to evaluate the effect of different combinations of backrest and seat surface on sleep comfort during autopilot based on the artificial neural network, so as to guide the design and development of intelligent cockpit. Based on CONFORmat seat pressure distribution measurement system of Tekscan, the experimental devices of seat surface angle (15°, 25°, 35°) and backrest angle (140°, 150°, 160°) were designed, and the objective multi-dimensional data and subjective evaluation data of 20 subjects were obtained. Then, the comfort prediction model was constructed by artificial neural network.According to the repeated variance measurement and analysis, with the increase of the translation angle of the seat surface, the contact pressure distribution at the interface could be effectively balanced. The combination design of the backrest angle of 160° and the seat surface angle of 35° had significant differences with other experimental conditions in terms of the WAP, Atotal, IPD and SR.Finally, the accuracy of the prediction model is verified by the artificial neural network. It is suggested that the seat surface angle of 35° and the backrest of 160° can be applied to the sleeping positions of intelligent cockpit.