Vehicle running attitude prediction model based on Artificial Neural Network-Parallel Connected (ANN-PL) in the single-vehicle collision

Artificial neural networks have drawn growing attention for their outstanding predictive capability combined with traditional research methods. This paper aims to propose a vehicle running attitude prediction model based on Artificial Neural Network-Parallel Connected (ANN-PL), predicting the longitudinal displacement (Svx) and vertical displacement (Svz) of the vehicle body, the vehicle head-up angle (α), and the overriding risk (Cd). The 3D multibody dynamics model (MBD) of the single-vehicle impact on the rigid wall, namely 3D-MBD-SV, was established and validated by the experimental full-scale vehicle collision test. Based on the reliable 3D-MBD-SV, the design of experiment (DOE) approach was carried out to obtain the datasets for training the ANN-PL. The ANN-PL exhibited excellent computational efficiency and satisfactory prediction accuracy compared to the multibody dynamics and finite element simulation calculation methods. However, the different network hyperparameters of the ANN-PL network are essential to prediction accuracy, considering the number of hidden layers and neurons in this paper. In terms of the variables factor analysis, the change of Mean Square Error (MSE) method (COM) in the ANN-PL was used to explore the relationship between the eleven essential input variables and vehicle running attitude. It was found that the maximum relative contribution in ANN-PL (Svx, Svz, α, Cd) is vehicle body mass (Mc) at 70.65%, impact velocity (Vx) at 43.39%, vertical offset of the vehicle body center mass (CMz) at 30.14%, and primary suspension axle box spring vertical travel (Dpz) at 13.63%, respectively. The outcome of this study is expected to provide a research method to solve the complicated engineering issue by building a new artificial neural network algorithmic framework combined with the multibody dynamics and finite element simulation calculation methods.