Warning model of new energy vehicle under improving time-to-rollover with neural network

Abstract

The probability of electric vehicle rollover accident can be effectively reduced by shortening the prediction time interval and improving the prediction accuracy. Based on a multilayer neural network, an improved time-to-rollover method is presented in this paper. Firstly, the force model of vehicle rollover is established and analyzed where the structure and mass of a battery box have an important influence on the occurrence of rollover. Then, the rollover indexes considering hyperparameters are divided into five categories, and the multi-layer neural network is used to simplify the algorithm structure of the time to rollover, and quickly calculate the operating state parameters with a variation step size in real time. Finally, the influence of the hyperparameters on the prediction results of neural network is studied, and higher efficiency is obtained by comparing with traditional methods.

Assessing the dependence of vehicle rollover on many factors based on new 4D graphs

“…to assess the danger of rollover [8]. If the value of this indicator fluctuates around the zero point, the car will be more stable.…”

“…However, if only the parameters on the right side of Eq ( 1 ), such as h , t w , a y , g , and ϕ , are used, the calculation will be inaccurate because the mass and stiffness of the suspension system are ignored. The LTR index is also used for the dynamic model with three DOFs, which is shown in the paper by Chao et al According to Chao et al, the values of LTR ranged from -1 to +1, and they divided these values into five respective steps to assess the danger of rollover [ 8 ]. If the value of this indicator fluctuates around the zero point, the car will be more stable.…”

“…On the other hand, if this value changes too much, it could lead to instability and even a rollover if |RI| = 1 [ 9 ]. The 3 DOFs model described in [ 8 ] is quite simple. The authors have ignored the influence of pitch angle and the deformation of nonlinear tires.…”

Proposing a novel fuzzy control algorithm for automotive active stabilizer bars based on views of roll stability and ride comfort

“…The influence of belt and carcass elasticity and transient conditions should be considered in more complex moving situations. [58][59][60] Substitute equations ( 19) to ( 27) into ( 16), (17), and ( 18), and we get:…”

“…16 Another criterion called time to rollover is developed by Chao et al to help evaluate the phenomenon of vehicle rollover in real time. 17 According to Chao et al, this index can be further improved by using the artificial neural network algorithm. In addition, the risk of rolling over is also reflected in the threshold of lateral acceleration.…”