Determining vehicle pre-crash speed in frontal barrier crashes using artificial neural network for intermediate car class

Adam Mrowicki; Mateusz Krukowski; Filip Turoboś; Przemysław Kubiak

doi:10.1016/j.forsciint.2020.110179

Determining vehicle pre-crash speed in frontal barrier crashes using artificial neural network for intermediate car class

Forensic Sci Int. 2020 Mar:308:110179. doi: 10.1016/j.forsciint.2020.110179. Epub 2020 Feb 4.

Authors

Adam Mrowicki¹, Mateusz Krukowski², Filip Turoboś³, Przemysław Kubiak⁴

Affiliations

¹ Department of Vehicles and Fundamentals of Machine Design, Lodz University of Technology, Poland. Electronic address: mrowicki.adam@gmail.com.
² Institute of Mathematics, Lodz University of Technology, Poland. Electronic address: mateusz.krukowski@p.lodz.pl.
³ Institute of Mathematics, Lodz University of Technology, Poland. Electronic address: filip.turobos@p.lodz.pl.
⁴ Department of Vehicles and Fundamentals of Machine Design, Lodz University of Technology, Poland; Institute of Vehicles, Warsaw University of Technology, Warsaw, Poland. Electronic address: przemyslaw.kubiak@pw.edu.pl.

PMID: 32058270
DOI: 10.1016/j.forsciint.2020.110179

Abstract

This paper introduces a new, innovative approach to pre-crash velocity determination, namely the artificial neural networks. A perceptron based on a database obtained from NHTSA (National Highway Traffic Safety Administration) with numerous data concerning frontal vehicle crash tests: i.e. vehicle mass, deformation zone and deformation coefficients C₁-C₆. Part of the database entries were used to train the network to develop consistent accuracy and the remainder was used as validation and training sets.

Keywords: Car accidents; Car crash reconstruction; Neural networks.