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

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.

Non-linear method of determining vehicle pre-crash speed based on tensor B-spline products with probabilistic weights - Intermediate Car Class.

In the following study we consider the Intermediate Car Class. We apply a novel non-linear method, where the work W of car deformation is defined as an algebraic function of deformation ratio Cs. We use the data from the NHTSA (National Highway Traffic Safety Administration) database comprising numerous frontal crash tests. On the basis of this database, we determine the mathematical model parameters. In the so-called energetic approach, collisions are treated as non-elastic. The velocity threshold that defines the elastic collision was set to be 11km/h. Such an approach, which greatly simplifies our considerations, determines the linear dependence of energy lost during deformation on deformation coefficient Cs. The coefficient Cs is calculated as a weighted mean value of deformation points C1-C6. In this paper, the authors suggest a more precise non-linear method in order to determine the work of deformation.