Regression analysis is often formulated as an optimization problem with squared loss functions. Facing the challenge of the selection of the proper function class with polynomial smooth techniques applied to support v...Regression analysis is often formulated as an optimization problem with squared loss functions. Facing the challenge of the selection of the proper function class with polynomial smooth techniques applied to support vector regression models, this study takes cubic spline interpolation to generate a new polynomial smooth function ｜×｜ε^ 2, in g-insensitive support vector regression. Theoretical analysis shows that Sε^2 -function is better than pε^2 -function in properties, and the approximation accuracy of the proposed smoothing function is two order higher than that of classical pε^2 -function. The experimental data shows the efficiency of the new approach.展开更多
When a four in-wheel motors drive electric vehicle with a specific wheels mass is running on an uneven road and transient steering occurs in the meantime, the joint action of the large unsprung dynamic load and the ce...When a four in-wheel motors drive electric vehicle with a specific wheels mass is running on an uneven road and transient steering occurs in the meantime, the joint action of the large unsprung dynamic load and the centrifugal force may cause the vehicle to rollover. To avoid the above accident, a rollover prevention control method based on active distribution of the in-wheel motors driving torques is investigated. First, tile rollover evolution process of the four in-wheel motors drive electric vehicle under the described operating condition is analyzed. Next, a multiple degrees of freedom vehicle dynamics model including an uneven road tyre model is established, and the rollover warning threshold is determined according to the load transfer ratio. Then, the hypothesis of the effects of unsprung mass on the vehicle roll stability on a plat road and on an uneven road is verified respectively. Finally, a rollover prevention controller is designed based on the distribution of the four wheels driving torques with sliding mode control, and the control effect is verified by simulations. The conclusion shows that, once the wheels mass does not match road conditions, the large unsprung mass may play a detrimental role on the vehicle roll stability on an uneven road, which is different from the beneficial role of large unsprung mass on the vehicle roll stability on a plat road. With the aforementioned rollover prevention controller, the vehicle rollover, which is caused by the coupling effect between large unsprung dynamic load and suspension potential energy on an uneven road, can be avoided effectively.展开更多
基金Supported by Guangdong Natural Science Foundation Project(No.S2011010002144)Province and Ministry Production and Research Projects(No.2012B091100497,2012B091100191,2012B091100383)+1 种基金Guangdong Province Enterprise Laboratory Project(No.2011A091000046)Guangdong Province Science and Technology Major Project(No.2012A080103010)
文摘Regression analysis is often formulated as an optimization problem with squared loss functions. Facing the challenge of the selection of the proper function class with polynomial smooth techniques applied to support vector regression models, this study takes cubic spline interpolation to generate a new polynomial smooth function ｜×｜ε^ 2, in g-insensitive support vector regression. Theoretical analysis shows that Sε^2 -function is better than pε^2 -function in properties, and the approximation accuracy of the proposed smoothing function is two order higher than that of classical pε^2 -function. The experimental data shows the efficiency of the new approach.
基金supported by the National Natural Science Foundation of China(Grant Nos.51405259&51775478)
文摘When a four in-wheel motors drive electric vehicle with a specific wheels mass is running on an uneven road and transient steering occurs in the meantime, the joint action of the large unsprung dynamic load and the centrifugal force may cause the vehicle to rollover. To avoid the above accident, a rollover prevention control method based on active distribution of the in-wheel motors driving torques is investigated. First, tile rollover evolution process of the four in-wheel motors drive electric vehicle under the described operating condition is analyzed. Next, a multiple degrees of freedom vehicle dynamics model including an uneven road tyre model is established, and the rollover warning threshold is determined according to the load transfer ratio. Then, the hypothesis of the effects of unsprung mass on the vehicle roll stability on a plat road and on an uneven road is verified respectively. Finally, a rollover prevention controller is designed based on the distribution of the four wheels driving torques with sliding mode control, and the control effect is verified by simulations. The conclusion shows that, once the wheels mass does not match road conditions, the large unsprung mass may play a detrimental role on the vehicle roll stability on an uneven road, which is different from the beneficial role of large unsprung mass on the vehicle roll stability on a plat road. With the aforementioned rollover prevention controller, the vehicle rollover, which is caused by the coupling effect between large unsprung dynamic load and suspension potential energy on an uneven road, can be avoided effectively.
