Research on a Novel Vehicle Rollover Risk Warning Algorithm Based on Support Vector Machine Model

Zhu, Tianjun; Yin, Xiaoxuan; Na, Xiaoxiang; Li, Bin

doi:10.1109/access.2020.3001306

Cited by 12 publications

(7 citation statements)

References 33 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…List the moment balance hydrostatic equations on the axes, establish a simple model, and analyze the main factors affecting the vehicle rollover and rollover stability. 27 It should be noted that, in order to accurately study the stability of vehicle rollover, it is necessary to establish an ideal rollover model that reflects the rollover pattern of the vehicle. For the convenience of calculation, often ignoring some minor elements, the following assumptions need to be made in the establishment of this model.…”

Section: Three-degree-of-freedom Car Modelmentioning

confidence: 99%

“…List the moment balance hydrostatic equations on the axes, establish a simple model, and analyze the main factors affecting the vehicle rollover and rollover stability. 27…”

Section: Establishment Of Model and Character Recognitionmentioning

confidence: 99%

“…The results showed that the presented algorithm can be a good measure of the danger of rollover. A superior vehicle rollover warning algorithm was proposed by Zhu et al 27 considering the nonlinear characteristic of driver-vehicle-road interaction and uncertainty of modeling. The novel algorithm provided an explicit function of vehicle rollover safety limit and its gradient, and defined the rollover safety area and the unsafe area through the hypersurface visualization boundary.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Chao

Zhang

Wang

et al. 2022

Measurement and Control

View full text Add to dashboard Cite

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.

show abstract

Section: Three-degree-of-freedom Car Modelmentioning

confidence: 99%

“…List the moment balance hydrostatic equations on the axes, establish a simple model, and analyze the main factors affecting the vehicle rollover and rollover stability. 27…”

Section: Establishment Of Model and Character Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Chao

Zhang

Wang

et al. 2022

Measurement and Control

View full text Add to dashboard Cite

show abstract

“…Many other values relating to vehicle dynamics behaviour can also be considered to warn of the rollover, such as the estimation of the vehicle roll angle, 22,23 slip angle, 24 or the sprung mass displacement. 25 Besides, a few new solutions used to warn of this phenomenon have also been introduced by many researchers, such as the support vector machine algorithm, 26 empirical modelling, 27 the contour line of LTR algorithm, 28 or several 4D graphs that describe dependencies among many factors. 12 Various control methods are used to improve the vehicle's roll stabilization performance, collectively known as anti-roll control.…”

Section: Introductionmentioning

confidence: 99%

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

Nguyen

2023

Proceedings of the Institution of Mechanical Engineers, Part K:

View full text Add to dashboard Cite

Using stabilizer bars in cars to limit rollover is a necessity applied to many vehicles today. In this article, the author proposes using a new fuzzy method to control the hydraulic stabilizer bars. Previous studies only focused on improving the roll stability of cars, while this article focuses on ensuring both the roll stability and ride comfort of the vehicle, which is considered the new contribution of the article. Vehicle oscillations are described through a complex nonlinear dynamic model. The MATLAB® application performs the simulation with two specific cases, including fish-hook steering and J-turn steering. According to the findings of this research, the roll angle value is significantly reduced when using active stabilizer bars directed by the novel algorithm. In addition, the risk of the rollover was also strongly reduced for both simulations (there are four-speed thresholds used in each case). For the first case, rollover does not occur when the car utilizes active stabilizer bars, even when travelling at v4 = 100 (km/h). In the other case, the rollover occurs only for the Active situation when travelling at a very high speed. In contrast, this phenomenon occurs in the None situation at v1 and the Passive situation at v2. The results found from this work help to evaluate the performance of the fuzzy control algorithm for active stabilizer bars.

show abstract

“…Zhu et al 15 developed a new dynamic driving condition identification method through incorporating Hierarchical Hidden Markov Models into the rollover warning system for heavy duty vehicles. Zhu et al 16 proposed a novel vehicle rollover warning algorithm based on support vector machine empirical model. Although many scholars have studied the prediction of vehicle rollover, they have also achieved a lot of results.…”

Section: Introductionmentioning

confidence: 99%

Sliding mode control for overturning prevention and hardware-in-loop experiment of heavy-duty vehicles based on dynamical load transfer ratio prediction

Han

Huang

et al. 2021

Proceedings of the Institution of Mechanical Engineers, Part K:

View full text Add to dashboard Cite

Aiming at the rollover risk of heavy-duty vehicles, an adaptive rollover prediction and control algorithm based on identification of multiple road adhesion coefficients is proposed, and the control effect has been verified by hardware-in-the-loop experiments. Based on the establishment of a 3 DOFs (Degree of freedom) vehicle dynamic model, the roll angle of the vehicle dynamic model is estimated in real time by using Kalman filter algorithm. In order to ensure the real-time operation of anti-rollover control strategy for multi-body dynamic heavy vehicle model, a sliding mode variable structure controller for anti-rollover of vehicles is designed to determine the optimal yaw moment. Specially, the recognition algorithm of road surface type is integrated into the control rollover algorithm. When the control system with road recognition algorithm recognizes whether the vehicle is in danger of rollover, it can not only adjust the state of the vehicle, but also shorten the time to reach the stable area of the vehicle's lateral load transfer rate by about 2 s. In order to further improve its adaptability and control accuracy, a Hardware-in-loop test platform for three-axis heavy-duty vehicles is built to verify the proposed anti-rollover control strategy. The results prove that the proposed control strategy can accurately predict the rollover risk and control the rollover in time.

show abstract

Research on a Novel Vehicle Rollover Risk Warning Algorithm Based on Support Vector Machine Model

Cited by 12 publications

References 33 publications

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

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

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

Sliding mode control for overturning prevention and hardware-in-loop experiment of heavy-duty vehicles based on dynamical load transfer ratio prediction

Contact Info

Product

Resources

About