摘要
为实现多种影响因素下驾驶员关键区域的温度预测,探究驾驶员各区域温度分布规律,将东风商用车作为研究对象,基于大量实车实验数据,探究不同环境因素对驾驶员关键区域温度分布影响,采用以驾驶员头部红外图像为输入,Yolov5目标检测与DNN模型预测相结合的方法预测驾驶员11个区域温度值,对预测模型进行评价验证,并通过十折交叉验证模型稳定性。最后基于不同驾驶室温度及外界光照对驾驶员关键区域温度分布规律进行总结,结论表明:不同驾驶室温度及外界光照环境对驾驶员肩部、背部、脚部及手部等区域温度值影响较为明显,在不同外界环境因素影响下,各区域温度分布存在不同规律。
In order to realize the temperature prediction of key areas of commercial vehicle drivers under various influencing factors,and to explore the temperature distribution of the driver's area,Dongfeng Commercial Vehicle was taken as the research object,based on a large number of real vehicle experimental data,to explore the influence of different environmental factors on the temperature distribution of the driver's key area.Using the infrared image of the driver's head as input,the method of combining yolov5 target detection and DNN model prediction to predict the temperature values of 11 regions of the driver,evaluate and verify the prediction model,and verify the stability of the model through ten-fold cross-validation.Finally,based on different cab temperatures and external light,the temperature distribution of the key areas of the driver is summarized.Obviously,under the influence of different external environmental factors,the temperature distribution in each region has different laws.
作者
程麒鎏
苏楚奇
汪怡平
刘珣
CHENG Qi-liu;SU Chu-qi;WANG Yi-ping;LIU Xun(School of Automotive Engineering,Wuhan University of Technology,Wuhan 430070,China;Hubei Key Laboratory of Advanced Technology for Automotive Components,Wuhan University of Technology,Wuhan 43oo70,China;Hubei Collaborative Innovation Center for Automotive Components Technology,Wuhan University of Technology,Wuhan 430070,China)
出处
《武汉理工大学学报》
CAS
2023年第7期46-53,67,共9页
Journal of Wuhan University of Technology
基金
国家自然科学基金(5207050100)。
关键词
关键区域
目标检测
DNN模型
温度预测
交叉验证
keyareas
target detection
DNN model
temperature prediction
cross validation
