scholarly journals The Uses of Artificial Intelligence for Electric Vehicle Control Applications

10.5772/36653 ◽  
2012 ◽  
Author(s):  
Brahim Gasbaoui ◽  
Abdelfatah Nasri
Keyword(s):  
Artificial Intelligence ◽  
Electric Vehicle ◽  
Vehicle Control ◽  
Control Applications

Effect of Inner and Outer Wheels Driving Force Control on Small Electric Vehicle

2020 ◽  
Vol 17 (4) ◽  
pp. 8246-8254
Author(s):  
K. Shibazaki ◽  
H. Nozaki
Keyword(s):  
Control System ◽  
Angular Velocity ◽  
Electric Vehicle ◽  
Force Constant ◽  
Force Control ◽  
Driving Force ◽  
Vehicle Control ◽  
Steering Angle ◽  
Force Control System ◽  
The Difference

In this study, in order to improve steering stability during turning, we devised an inner and outer wheel driving force control system that is based on the steering angle and steering angular velocity, and verified its effectiveness via running tests. In the driving force control system based on steering angle, the inner wheel driving force is weakened in proportion to the steering angle during a turn, and the difference in driving force is applied to the inner and outer wheels by strengthening the outer wheel driving force. In the driving force control (based on steering angular velocity), the value obtained by multiplying the driving force constant and the steering angular velocity,  that differentiates the driver steering input during turning output as the driving force of the inner and outer wheels. By controlling the driving force of the inner and outer wheels, it reduces the maximum steering angle by 40 deg and it became possible to improve the cornering marginal performance and improve the steering stability at the J-turn. In the pylon slalom it reduces the maximum steering angle by 45 deg and it became possible to improve the responsiveness of the vehicle. Control by steering angle is effective during steady turning, while control by steering angular velocity is effective during sharp turning. The inner and outer wheel driving force control are expected to further improve steering stability.

The Location of Electric Vehicle Charging Stations based on FRLM with Robust Optimization

2019 ◽  
Vol 33 (08) ◽  
pp. 1959027 ◽  
Author(s):  
Jing-min Wang ◽  
Yan Liu ◽  
Yi-fei Yang ◽  
Wei Cai ◽  
Dong-xuan Wang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Robust Optimization ◽  
Electric Vehicle ◽  
Optimization Algorithm ◽  
Site Selection ◽  
Queuing Theory ◽  
Location Model ◽  
Electric Vehicle Charging ◽  
Charging Stations ◽  
Charging Demand

It is very important for the application of artificial intelligence to accurately and quickly help the electric vehicles to find matching charging facilities. The site selection for electric vehicle charging station (EVCS) is a new field of artificial intelligence application, using artificial intelligence to analyze the current complex urban electric vehicle driving path, and then determining the location of charging stations. This paper proposes a novel hybrid model to decide the location of EVCS. First of all, this paper carries out the flow-refueling location model (FRLM) based on path requirement to determine the site selection of EVCS. Secondly, robust optimization algorithm is used to resolve the location model considering the uncertainty of charging demand. Then, queuing theory, which takes the charging load as a constraint in the location model, is integrated into the model. Last, but not the least, a case is conducted to verify the validity of the proposed model when dealing with location problem. As a result of the above analysis, it is effective to apply robust optimization algorithm and to determine the location of EVCSs effectively when charging demand generated on the path is uncertain. At the same time, queuing theory can help to determine the optimal number of EVCSs effectively, and reduce the cost of building EVCSs.

Sign in / Sign up

Export Citation Format

Share Document