基于决策树模型的电动自行车与SUV碰撞中骑车人头部响应

Cyclist head responses in electric-bicycle-to-SUV accidents based on decision tree model

为提高对电动自行车(E-bike)骑车人头部的防护,利用运动型多功能车(SUV)与电动自行车碰撞的多刚体模型,调整相关参数开展仿真分析,获得不同工况下骑车人头部运动学响应。利用C4.5决策树算法挖掘仿真结果,建立骑车人头部运动学响应决策树模型。分析显示:影响骑车人头部响应的关键因素SUV碰撞初始速度越高,骑车人头部碰撞相对速度、碰撞点包绕距离(WAD)及损伤风险(HIC15)均增大;骑车人体型则对头部碰撞点WAD影响最为显著,体型越大,头部碰撞点WAD越高。因而,本决策树模型还具有预测和决策功能,可用于制定头部安全评估法规性实验及头部防护研究。

A multi-rigid body model for electric-bicycle(E-bike)-to-SUV(sports utility vehicle)impact was used to adjust the parameters to obtain the cyclist’s head kinematic responses in different accident conditions to improve the protections on the head of cyclists.Through the C4.5 decision tree algorithm,the decision tree models of cyclist’s head kinematic responses were then created from this dataset and verified accordingly.The results show that initial impact velocity of SUV is a key factor affected the cyclist head responses.Increasing the initial impact velocity of SUV increases the cyclist’s head relative impact velocity,WAD(wrap around distance)of head impact location,and head injury criterrion(HIC15).And the WAD of cyclist’s head impact location is also significantly affected by the body size of cyclist.The WAD of head impact location becomes higher with increasing body size of cyclist.Therefore,the decision tree model will be used to predict and decision for guiding develop tests for cyclist’s head safety assessment regulatory and for investigating head protection.