基于BP神经网络的儿童乘员头部损伤预测模型及评估参数研究

doi:10.19562/j.chinasae.qcgc.2024.02.015

摘要/Abstract

摘要：

智能座舱与虚拟测评规程的推广，给乘员损伤评价带来新挑战，损伤机理与损伤风险评估参数更加多样化。本文基于图斯特6岁儿童乘员损伤仿生模型与BP神经网络算法构建正面100%重叠刚性壁障工况中乘员坐姿角度与头部损伤指标相关性预测模型，探究不同坐姿下头部损伤风险以及不同评价指标之间的相关性与差异性。结果表明，构建的相关性损伤预测模型具有良好的可信度（R²> 0.90），可以用于损伤预测与分析。现有头部损伤评价指标在小角度坐姿范围内（95°~108°）对头损伤评估及预测具有良好的一致性，但是对于大角度坐姿乘员，不同损伤评价指标对头部损伤风险的评估存在显著差异。因此，目前实施的头部损伤评价参数具有局限性，未来虚拟测评中应综合运动学和生物力学参数对头部损伤风险进行更加全面的评估。该研究结果可以为儿童约束系统的改善、虚拟测评以及大角度坐姿乘员头部损伤评价参数的选取提供数据与理论支撑。

关键词: 损伤仿生模型, 儿童乘员, BP神经网络, 虚拟测评, 坐姿角度

Abstract:

The promotion of intelligent cockpit and virtual testing protocols bring new challenge to assess the occupant injury， with the injury mechanism and injury risk assessment parameters more diversified. Based on the TUST IBMs 6YO-O and the BP neural network algorithm， a predictive model for the correlation between occupant sitting angle and head injury indicators in frontal 100% overlapping rigid barrier condition is constructed in this paper， and the correlation and difference between evaluation indicators with the different seating postures are explored. The results show that the constructed correlation injury prediction model has high reliabilities （R² > 0.90）， which can be used for injury prediction and analysis. Existing head injury evaluation indicators have good consistency in the small angle range （95°~108°）， but for the occupants with larger seating postures， there are significant differences to assess the head injury risks using different injury evaluation indicators. Therefore， there is certain limitation of the head injury assessment parameters implemented currently. In the future virtual testing， the kinematic and biomechanical parameters should be integrated to assess more comprehensively for the head injury risks. The research results can provide data and theoretical support for the improvement of child restraint systems， virtual testing， and selection of head injury evaluation parameters for occupants with larger seating postures.

Key words: injury bionic model, child occupant, BP neural network, virtual testing, seating posture

王彦鑫,李海岩,崔世海,贺丽娟,吕文乐. 基于BP神经网络的儿童乘员头部损伤预测模型及评估参数研究[J]. 汽车工程, 2024, 46(2): 329-336.

Yanxin Wang,Haiyan Li,Shihai Cui,Lijuan He,Lü Wenle. Research on Prediction Model and Assessment Parameters of Head Injury for Child Occupants Based on BP Neural Network[J]. Automotive Engineering, 2024, 46(2): 329-336.

图/表 6

图1

图2

图3

图4

表1

图5

参考文献 23

1	WHO. Global status report on road safety 2018［R］. Geneva： World Health Organization， 2018.
2	CHANG L Y， WANG H W. Analysis of traffic injury severity： an application of non-parametric classification tree techniques［J］. Accident Analysis & Prevention， 2006， 38（5）： 1019-1027.
3	武和全，旷世杰，胡林.老年乘员在自动驾驶车辆中的碰撞响应研究［J］.机械工程学报，2020，56（12）：144-154.
	WU H Q， KUANG S J， HU L. Research on collision response of elderly occupant in autonomous vehicles［J］. Journal of Mechanical Engineering， 2020，56（12）：144-154.
4	SEYEDMIRSAJAD M， JASON C A， ATOROD A， et al. Factors affecting injury severity in vehicle-pedestrian crashes： a day-of-week analysis using random parameter ordered response models and Artificial Neural Networks - ScienceDirect［J］. International Journal of Transportation Science and Technology， 2020， 9（2）：100-115.
5	LIN C， WU D， LIU H， et al. Factor identification and prediction for teen driver crash severity using machine learning： a case study［J］. Applied Sciences， 2020， 10（5）：1675.
6	GAN X， WENG J. Predicting crash injury severity for the highways involving traffic hazards and those involving no traffic hazards［C］. COTA International Conference of Transportation Professionals，2020.
7	HOSSEINZADEH A， MOEINADDIN A， GHASEMZADEH A. Investigating factors affecting severity of large truck-involved crashes： comparison of the SVM and random parameter logit model［J］. Journal of Safety Research， 2021（4）.
8	OSPINA-MATEUS H， LEONARDO A Q J， FRANCISCO J L V， et al. Extraction of decision rules using genetic algorithms and simulated annealing for prediction of severity of traffic accidents by motorcyclists［J］. Journal of Ambient Intelligence and Humanized Computing， 2021：1-22.
9	李海岩，王彦鑫，贺丽娟，等.不同坐姿的6岁儿童乘员在MPDB碰撞测试中头颈部损伤评价［J］.汽车工程，2021，43（12）：1793-1799，1824.
	LI H Y， WANG Y X， HE L J， et al. Evaluation of head and neck injuries of a six-year-old child occupant with different sitting postures during a MPDB crash test［J］. Automotive Engineering， 2021，43（12）：1793-1799，1824.
10	CUI S H， CHEN Y， LI H Y， et al. Development and validation for the finite element model of child head［J］. Journal of Medical Biomechanics， 2015.
11	LV W L， RUAN S J， LI H Y， et al. Development and validation of finite element model for 6-year-old pediatric neck［J］. Journal of Medical Biomechanics， 2016.
12	LV W L， RUAN S J， LI H Y， et al. Development and validation of a 6-year-old pedestrian thorax and abdomen finite element model and impact injury analysis［J］. International Journal of Vehicle Safety， 2015， 8（4）：339.
13	LV W L， RUAN S J， LI H Y， et al. Injury analysis of a six-year-old child pedestrian thorax in lateral/oblique impact［C］. The 12th International Forum of Automotive Traffic Safety.0［2023-07-11］.
14	LV W L， RUAN S J， LI H Y， et al. Abdominal injury analysis of a 6-year-old pedestrian finite element model in lateral impact［J］. International Journal of Vehicle Safety， 2016， 9（1）：85.
15	李蓓. 6岁儿童行人下肢有限元建模及碰撞响应分析［D］.天津：天津科技大学，2014.
	LI B. Development of a 6-year-old child lower limb finite element model and analysis of pedestrian impact responses［D］. Tianjin： Tianjin University of Science & Technology， 2014.
16	LI H Y， WANG Y X， HE L J， et al. Development of biomechanical computational models of six-year-old child occupant with different sitting postures and application in the study of whiplash injuries［J］.SAE International Journal of Advances and Current Practices in Mobility，2022，4（4）： 1296-1308.
17	ZHANG N， SHEN S L， ZHOU A N， et al. Investigationon performance of neural networks using quadratic relative error cost function［J］. IEEE Access， 2019， 7： 106642-106652.
18	BAS E， USLU V R， EGRIOGLU E. Robust learning algorithm for multiplicative neuron model artificial neural networks［J］.Expert Systems with Applications， 2016， 56（Sep.）：80-88.
19	MULLER K R， SMOLA A J， BF G R， et al. Predicting time series with support vector machines［C］. ICANN '97： Proceedings of the 7th International Conference on Artificial Neural Networks， 1997.
20	TAKHOUNTS E G， CRAIG M J， MOORHOUSE K， et al. Development of brain injury criteria （BrIC）［J］. Stapp Car Crash J.， 2013， 57：243-266.
21	BAUMGARTNER D， WILLINGER R， SHEWCHENKO N， et al. Tolerance limits for mild traumatic brain injury derived from numerical head impact replication［C］. International Ircobi Conference on the Biomechanics of Impact， 2001.
22	ZHANG L， YANG K H， KING A I. A proposed injury threshold for mild traumatic brain injury［J］. Journal of Biomechanical Engineering， 2004， 126（2）：226-236.
23	BANDAK F A， EPPINGER R H. A three-dimensional finite element analysis of the human brain under combined rotational and translational accelerations［C］. Stapp Car Crash Conference，1994.

指标	RMSE	MAE	R²
头部3 ms合成加速度	0.028	0.024	0.98
HIC₁₅	0.064	0.059	0.91
BrIC	0.032	0.028	0.97
von Mises	0.030	0.027	0.99
Maxshear	0.029	0.025	0.99
MPS	0.020	0.020	0.98

[1]	陈国强,申正义,孙利,支梦帆,李彤. 基于BP神经网络优化遗传算法的智能座舱感性意象预测[J]. 汽车工程, 2023, 45(8): 1479-1488.
[2]	李海岩,胡静,贺丽娟,冉令华,吕文乐,崔世海,阮世捷. 中国体征第五百分位女性汽车乘员损伤仿生模型开发及验证[J]. 汽车工程, 2023, 45(10): 1965-1974.
[3]	梁旺,秦兆博,陈亮,边有钢,胡满江. 基于改进BP神经网络的智能车纵向控制方法[J]. 汽车工程, 2022, 44(8): 1162-1172.
[4]	阮世捷,苏航杰,李海岩,崔世海,贺丽娟,吕文乐. 正面100%重叠刚性壁障碰撞试验仿真中三岁儿童乘员的损伤评价[J]. 汽车工程, 2022, 44(3): 403-411.
[5]	李海岩,苏航杰,祝贺,刘冲,王彦鑫,崔世海,贺丽娟,王一达,吕文乐. 中国体征3岁儿童乘员损伤仿生模型在C-NCAP正面碰撞测试仿真中的应用[J]. 汽车工程, 2022, 44(12): 1944-1953.
[6]	刘刚,洪亮,葛如海. 面向“离位”儿童乘员的常开式安全气囊优化设计[J]. 汽车工程, 2022, 44(1): 94-104.
[7]	郭祥靖,孙攀,邓杰,刘勇,刘壮,刘双平. 基于BP神经网络算法预测的重型半挂汽车列车AEB控制策略研究[J]. 汽车工程, 2021, 43(9): 1350-1359.
[8]	李海岩,王彦鑫,贺丽娟,吕文乐,崔世海. 不同坐姿的6岁儿童乘员在MPDB碰撞测试中头颈部损伤评价[J]. 汽车工程, 2021, 43(12): 1793-1799.
[9]	郭柏苍,谢宪毅,金立生,戎辉,贺阳,纪丙东. 考虑多维驾驶特性的制动反应时间预测模型[J]. 汽车工程, 2021, 43(11): 1683-1692.
[10]	葛如海, 崔义忠, 洪亮, 肖轩. 针对12岁儿童的主动式安全气囊的优化^*[J]. 汽车工程, 2020, 42(6): 771-777.