DOI QR코드

DOI QR Code

Prediction of Chest Deflection Using Frontal Impact Test Results and Deep Learning Model

정면충돌 시험결과와 딥러닝 모델을 이용한 흉부변형량의 예측

  • 이권희 (동아대학교 기계공학과) ;
  • 임재문 (대덕대학교 정밀기계공학과)
  • Received : 2023.01.27
  • Accepted : 2023.03.23
  • Published : 2023.03.31

Abstract

In this study, a chest deflection is predicted by introducing a deep learning technique with the results of the frontal impact of the USNCAP conducted for 110 car models from MY2018 to MY2020. The 120 data are divided into training data and test data, and the training data is divided into training data and validation data to determine the hyperparameters. In this process, the deceleration data of each vehicle is averaged in units of 10 ms from crash pulses measured up to 100 ms. The performance of the deep learning model is measured by the indices of the mean squared error and the mean absolute error on the test data. A DNN (Deep Neural Network) model can give different predictions for the same hyperparameter values at every run. Considering this, the mean and standard deviation of the MSE (Mean Squared Error) and the MAE (Mean Absolute Error) are calculated. In addition, the deep learning model performance according to the inclusion of CVW (Curb Vehicle Weight) is also reviewed.

Keywords

Acknowledgement

이 논문은 동아대학교 교내연구비 지원에 의하여 연구되었음.

References

  1. Park, C. K. and Kan, C. D., 2015, "Objective Evaluation Method of Vehicle Crash Pulse Severity in Frontal New Car Assessment Program (NCAP) Tests", Paper No. 15-0055, 24th Enhanced Safety of Vehicles Conference, Gothenburg, Sweden, June 8-11.
  2. 임재문, 2020, "USNCAP 정면충돌시험 결과를 이용한 HIC15 예측모델 개발", 자동차안전학회지, 제12권, 제4호, pp. 31~38. https://doi.org/10.22680/KASA2020.12.4.031
  3. Lim, J. M., 2021, "A Method for Predicting HIC15, Chest g's and Chest Deflection Based on Results of USNCAP Frontal Impact Tests," Int. J. Automotive Technology, Vol. 22, No. 3, pp. 657~663. https://doi.org/10.1007/s12239-021-0061-z
  4. 하태웅, 임재문, 2022, "정면충돌 가속도곡선을 이용한 HIC15 예측모델에 관한 고찰", 자동차안전학회지, 제14권, 제1호, pp. 62~67. https://doi.org/10.22680/KASA2022.14.1.062
  5. 박형욱, 송수성, 신장호, 한광철, 최세경, 하헌석, 윤성로, 2022, "머신러닝/ADAS 정보 활용 충돌안전제어로직 개발", 자동차안전학회지, 제14권, 제3호, pp. 60~64. https://doi.org/10.22680/KASA2022.14.3.060
  6. 백서하, 김종호, 이경수, 2022, "딥러닝 데이터 활용한 신호등 색 인식 알고리즘 개발", 자동차안전학회지, 제14권, 제2호, pp. 45~50. https://doi.org/10.22680/KASA2022.14.2.045
  7. 장철원, 2021, "선형대수와 통계학으로 배우는 머신 러닝 with 파이썬", 비제이퍼블릭.
  8. 세바스찬 라시카, 바히드 미자리리, 2021, "머신 러닝 교과서 with 파이썬, 사이킬런, 텐서플로", (주)도서출판 길벗.
  9. National Highway Traffic Safety Administration (NHTSA), 2023, Vehicle Crash Test Database, http://www.nhtsa.gov/research-data/researchtesting-databases#/vehicle.
  10. Abadi, M. et al., 2016, "Tensorflow: A System for Large-Scale Machine Learning", 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI '16), Nov. 2-4, 2016, Savannah, GA, USA, pp. 265-283.
  11. Pedregosa, V., Varoquaux F., Gramfort, G., Michel, A., Thirion, P., Grisel, B., Blondel, O., Prettenhofer, M., Weiss, A., Dubourg, R., Vanderplas, V., Passos, J., Cournapeau, E., Brucher, D., Perrot, M. and Duchesnay E., 2011, "Scikit-learn: Machine Learning in Python", Journal of Machine Learning Research, Vol. 12, pp. 2825-2830.
  12. Kendall, A., and Gal, Y., 2017, "What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?", NIPS 2017, arXiv:1703.04977.