To resolve the response delay and overshoot problems of intelligent vehicles facing emergency lane-changing due to proportional-integral-differential(PID)parameter variation,an active steering control method based on ...To resolve the response delay and overshoot problems of intelligent vehicles facing emergency lane-changing due to proportional-integral-differential(PID)parameter variation,an active steering control method based on Convolutional Neural Network and PID(CNNPID)algorithm is constructed.First,a steering control model based on normal distribution probability function,steady constant radius steering,and instantaneous lane-change-based active for straight and curved roads is established.Second,based on the active steering control model,a three-dimensional constraint-based fifth-order polynomial equation lane-change path is designed to address the stability problem with supersaturation and sideslip due to emergency lane changing.In addition,a hierarchical CNNPID Controller is constructed which includes two layers to avoid collisions facing emergency lane changing,namely,the lane change path tracking PID control layer and the CNN control performance optimization layer.The scaled conjugate gradient backpropagation-based forward propagation control law is designed to optimize the PID control performance based on input parameters,and the elastic backpropagation-based module is adopted for weight correction.Finally,comparison studies and simulation/real vehicle test results are presented to demonstrate the effectiveness,significance,and advantages of the proposed controller.展开更多
The short life of electric vehicle(EV)batteries is an important factor limiting the popularization of EVs.A hybrid energy storage system(HESS)for EVs combines Li-ion batteries with supercapacitors,so that the supercap...The short life of electric vehicle(EV)batteries is an important factor limiting the popularization of EVs.A hybrid energy storage system(HESS)for EVs combines Li-ion batteries with supercapacitors,so that the supercapacitor shares the peak power during the starting and braking,effectively solving the problem of irreversible capacity degradation of Li-ion batteries.Herein,an energy management strategy for HESS was designed based on battery degradation to extend the service life of the EV battery.First,to obtain accurate battery degradation characteristics,a cycling charge-discharge test was designed.Using this test,the effects of discharge rate and state of charge on battery degradation rate were determined,and the battery degradation model was constructed.Based on the working map of the motor obtained through the bench test,a data-based model of the power system was constructed to accurately characterize the energy consumption of the EV under different operating conditions.Second,rule-based and optimization-based energy management strategies that consider battery degradation were designed using the fuzzy algorithm and dynamic programming(DP)algorithm.The effectiveness of the devised control strategies was assessed using the model-in-the-loop and hardware-in-the-loop test platforms.The fuzzy control strategy had a simple structure and could be rapidly calculated but showed worse performance than the DP-based strategy in terms of battery degradation.The DP-based energy management strategy resulted in 16.68% lower capacity degradation than the fuzzy strategy.展开更多
In order to reduce the dependence of the vehicle acceleration sensor in the regenerative braking control for an electrical vehicle and explore the direct response of energy recovery and regenerative braking decelerati...In order to reduce the dependence of the vehicle acceleration sensor in the regenerative braking control for an electrical vehicle and explore the direct response of energy recovery and regenerative braking deceleration,this paper explores a dynamic control method in the electric motor based on energy constraint control(ECC)which relates to the conservation of energy during the breaking process.The research focuses on the regenerative braking system(RBS)of the series hybrid energy storage system(SHESS)with battery and ultracapacitor(UC),which targets deceleration.For the sake of eliciting the energy constraint equation,the detailed energy flow path is analyzed in the regenerative braking process.Considering the impact of error and sample time,the algorithm of ECC is designed with a quadratic Lagrange interpolation.In addition,the ECC algorithm is verified by software-in-the-loop(SIL)and hardware-in-the-loop(HIL).Moreover,it is determined that the proposed control method works effectivity without an acceleration sensor and RBS with ECC can achieve a 21.69%braking recovery.展开更多
基金Supported by National Key R&D Program of China(Grant No.2018YFB1600500)Jiangsu Provincial Postgraduate Research&Practice Innovation Program of(Grant No.KYCX22_3673).
文摘To resolve the response delay and overshoot problems of intelligent vehicles facing emergency lane-changing due to proportional-integral-differential(PID)parameter variation,an active steering control method based on Convolutional Neural Network and PID(CNNPID)algorithm is constructed.First,a steering control model based on normal distribution probability function,steady constant radius steering,and instantaneous lane-change-based active for straight and curved roads is established.Second,based on the active steering control model,a three-dimensional constraint-based fifth-order polynomial equation lane-change path is designed to address the stability problem with supersaturation and sideslip due to emergency lane changing.In addition,a hierarchical CNNPID Controller is constructed which includes two layers to avoid collisions facing emergency lane changing,namely,the lane change path tracking PID control layer and the CNN control performance optimization layer.The scaled conjugate gradient backpropagation-based forward propagation control law is designed to optimize the PID control performance based on input parameters,and the elastic backpropagation-based module is adopted for weight correction.Finally,comparison studies and simulation/real vehicle test results are presented to demonstrate the effectiveness,significance,and advantages of the proposed controller.
基金supported by the National Natural Science Foundation of China(Grant No.52272367).
文摘The short life of electric vehicle(EV)batteries is an important factor limiting the popularization of EVs.A hybrid energy storage system(HESS)for EVs combines Li-ion batteries with supercapacitors,so that the supercapacitor shares the peak power during the starting and braking,effectively solving the problem of irreversible capacity degradation of Li-ion batteries.Herein,an energy management strategy for HESS was designed based on battery degradation to extend the service life of the EV battery.First,to obtain accurate battery degradation characteristics,a cycling charge-discharge test was designed.Using this test,the effects of discharge rate and state of charge on battery degradation rate were determined,and the battery degradation model was constructed.Based on the working map of the motor obtained through the bench test,a data-based model of the power system was constructed to accurately characterize the energy consumption of the EV under different operating conditions.Second,rule-based and optimization-based energy management strategies that consider battery degradation were designed using the fuzzy algorithm and dynamic programming(DP)algorithm.The effectiveness of the devised control strategies was assessed using the model-in-the-loop and hardware-in-the-loop test platforms.The fuzzy control strategy had a simple structure and could be rapidly calculated but showed worse performance than the DP-based strategy in terms of battery degradation.The DP-based energy management strategy resulted in 16.68% lower capacity degradation than the fuzzy strategy.
基金funded by the National Natural Science Foundation of China,grant number(51105178)funded by the Natural Science Foundation of Jiangsu Province(BK20171300).
文摘In order to reduce the dependence of the vehicle acceleration sensor in the regenerative braking control for an electrical vehicle and explore the direct response of energy recovery and regenerative braking deceleration,this paper explores a dynamic control method in the electric motor based on energy constraint control(ECC)which relates to the conservation of energy during the breaking process.The research focuses on the regenerative braking system(RBS)of the series hybrid energy storage system(SHESS)with battery and ultracapacitor(UC),which targets deceleration.For the sake of eliciting the energy constraint equation,the detailed energy flow path is analyzed in the regenerative braking process.Considering the impact of error and sample time,the algorithm of ECC is designed with a quadratic Lagrange interpolation.In addition,the ECC algorithm is verified by software-in-the-loop(SIL)and hardware-in-the-loop(HIL).Moreover,it is determined that the proposed control method works effectivity without an acceleration sensor and RBS with ECC can achieve a 21.69%braking recovery.
