http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Deep Reinforcement Learning-Based Energy Management Strategy for Fuel Cell Hybrid Buses
Chunhua Zheng,Wei Li,Wei-Min Liu,Kun Xu,Lei Peng,차석원 한국정밀공학회 2022 International Journal of Precision Engineering and Vol.9 No.3
An energy management strategy (EMS) plays an important role for hybrid vehicles, as it is directly related to the power distribution between power sources and further the energy saving of the vehicles. Currently, rule-based EMSs and optimizationbased EMSs are faced with the challenge when considering the optimality and the real-time performance of the control at the same time. Along with the rapid development of the artificial intelligence, learning-based EMSs have gained more and more attention recently, which are able to overcome the above challenge. A deep reinforcement learning (DRL)-based EMS is proposed for fuel cell hybrid buses (FCHBs) in this research, in which the fuel cell durability is considered and evaluated based on a fuel cell degradation model. The action space of the DRL algorithm is limited according to the efficiency characteristic of the fuel cell in order to improve the fuel economy and the Prioritized Experience Replay (PER) is adopted for improving the convergence performance of the DRL algorithm. Simulation results of the proposed DRL-based EMS for an FCHB are compared to those of a dynamic programming (DP)-based EMS and a reinforcement learning (RL)-based EMS. Comparison results show that the fuel economy of the proposed DRL-based EMS is improved by an average of 3.63% compared to the RL-based EMS, while the difference to the DP-based EMS is within an average of 5.69%. In addition, the fuel cell degradation rate is decreased by an average of 63.49% using the proposed DRL-based EMS compared to the one without considering the fuel cell durability. Furthermore, the convergence rate of the proposed DRL-based EMS is improved by an average of 30.54% compared to the one without using the PER. Finally, the adaptability of the proposed DRL-based EMS is validated on a new driving cycle, whereas the training of the DRL algorithm is completed on the other three driving cycles.
A Predictive Driving Control Strategy of Electric Vehicles for Energy Saving
Zheng, Chunhua,Xu, Guoqing,Cha, Suk Won,Liang, Quan Korean Society for Precision Engineering 2015 International Journal of Precision Engineering and Vol.16 No.1
The driving route of a vehicle depends on the traffic condition and road condition in which the vehicle is operating and the driver's behavior. Different driving route will result in different energy consumption. It is very helpful for the vehicle energy saving if the most energy-efficient driving route is obtained based on the traffic preview information and provided to the drivers. This paper presents a predictive driving control strategy for pure electric vehicles for electrical energy saving. The strategy is established based on the optimal control theory and the traffic preview information in which the maximum and minimum vehicle velocity profiles for a traffic preview period and the route length over the period are included. The information is assumed to be acquired from Global Positioning System and Intelligent Transportation System. The proposed driving control strategy is implemented in a computer simulation environment for an electric vehicle and the simulation results of the strategy are compared to those of three benchmark cases. It is concluded that the battery energy of the electric vehicle is saved around 12.1%, 12.8%, and 13.8% by the proposed strategy compared to each benchmark case.
PMP-based Power Management Strategy for Two-State Variable FCHV Systems and its Optimality
Chunhua Zheng,차석원,Guoqing Xu,박영일,임원식 한국정밀공학회 2014 International Journal of Precision Engineering and Vol.15 No.4
The battery temperature affects the total fuel consumption in a hybrid vehicle, as it influences the battery efficiency and furtherinfluences the powertrain efficiency. In this research, a Pontryagin’s Minimum Principle (PMP)-based optimal control problem fora fuel cell hybrid vehicle (FCHV) is formulated in which the battery temperature is designated as a second-state variable other thanthe battery state of charge (SOC). Moreover, optimality of the two-state variable PMP-based power management strategy is discussedbased on a conclusion derived from previous research. Simulation results of the PMP-based strategy are compared to those ofDynamic Programming (DP) approach. It is concluded from this research that the two-state variable PMP-based power managementstrategy guarantees global optimality under certain battery assumptions. Meanwhile, the proposed strategy saves much timecompared to DP approach.
Power Source Sizing of Fuel Cell Hybrid Vehicles Considering Vehicle Performance and Cost
Chunhua Zheng,차석원,Guoqing Xu,정종렬,박영일,임원식 한국정밀공학회 2014 International Journal of Precision Engineering and Vol.15 No.3
Power source sizing is an important step when designing hybrid vehicles, which directly influences the fuel economy and total cost of hybrid vehicles. This research presents a power source sizing methodology for fuel cell hybrid vehicles (FCHVs) considering the vehicle performance and cost. Acceleration time and maximum speed of the vehicle are introduced as the constraints on choosing effective power source size combinations. The powertrain mass difference resulted from different power source sizes is taken into account when dealing with the constraints, and consequently different constraint line is applied to different power source size combination. Different sizes of batteries and fuel cell systems (FCSs) in the effective region are modeled in order to select the best power source size combination according to sizing objectives (criterion). The sizing objective in this research is to minimize the fuel consumption or to minimize the total cost (FCS cost plus battery cost plus consumed hydrogen cost). A Pontryagin’s Minimum Principle (PMP)-based power management strategy is adopted when comparing the fuel consumption, and some reference values are introduced to the cost comparison. Power source sizing results reveal that the best power source size combination is different for the two sizing objectives.
A Hybrid Energy Storage System for an Electric Vehicle and Its Effectiveness Validation
Chunhua Zheng,Yafei Wang,Zhongxu Liu,Tianfu Sun,Namwook Kim,Jongryeol Jeong,차석원 한국정밀공학회 2021 International Journal of Precision Engineering and Vol.8 No.6
A hybrid energy storage system (HESS), which consists of a battery and a supercapacitor, presents good performances on both the power density and the energy density when applying to electric vehicles. In this research, an HESS is designed targeting at a commercialized EV model and a driving condition-adaptive rule-based energy management strategy (EMS) is proposed for the HESS, which takes into account the superiority achievement of each ESS and also the protection to each ESS. The effectiveness of the HESS plus the EMS compared to the single battery case is validated by both the computer simulation and the semi-physical rapid control prototype (RCP) test bench. An electric loading equipment is adopted in the RCP experiment validation for simulating the vehicle driving cycle instead of the traditional combination of a motor and a dynamometer. Both validation results show that compared to the single battery case, the working status of the battery is stabilized by the addition of the supercapacitor in the HESS case during both the propelling and regeneration modes and the battery energy is also saved. A dynamic degradation model for the battery is adopted in order to evaluate the life cycle cost of the HESS. Results show that the HESS plus the EMS has the effect of prolonging the battery lifetime and the HESS is economically effective compared to the single battery case.
Chunhua Zheng,차석원,박영일,임원식,Guoqing Xu 한국정밀공학회 2013 International Journal of Precision Engineering and Vol.14 No.5
In order to develop more practical vehicle controllers for hybrid vehicles, performance limitations of hybrid powertrain components need to be considered when constructing power management strategies. This paper introduces a Pontryagin’s Minimum Principle (PMP)-based power management strategy for fuel cell hybrid vehicles which considers not only the fuel consumption minimization but also the requirement on limiting battery state of charge (SOC) usage or on prolonging fuel cell system lifetime. The battery SOC constraint problem is solved by introducing a new cost function to the PMP-based optimal control problem. The limitation requirements on the battery SOC are satisfied by this solution. In order to take into account the lifetime of a fuel cell system,another cost function is defined and added to the PMP-based optimal control problem. Simulation results show that the lifetime of the fuel cell system can be prolonged by this method. Global optimality is discussed for the two extended cases. The proposed PMPbased power management strategy saves much time compared to dynamic programming (DP) approach while it guarantees global optimality under reasonable battery assumptions.
Chunhua Zheng,차석원 한국정밀공학회 2017 International Journal of Precision Engineering and Vol.4 No.2
The Pontryagin’s Minimum Principle (PMP)-based energy management strategy is regarded as one of the most promising strategies for hybrid vehicles, given that it instantaneously provides optimal power distribution solutions between power sources. The real-time application of the PMP, however, is still difficult due to the heavy computational burden and the uncertainty of the future vehicle driving cycle. The driving characteristics of city buses, including the bus dwell time at bus stops and comparatively specified driving routes, are very helpful when realizing the PMP to hybrid powertrains. An energy management approach of fuel cell hybrid buses for real-time applications is proposed in this research based on the driving characteristics of buses, in which a reference driving cycle (RDC) is defined for a bus driving route and the bus dwell time is sufficiently used to calculate the PMP-based power distribution solutions. In order to reflect the deviation of the real bus driving route from the RDC, the control parameter of the PMP is updated at every bus stop before calculating the solutions. Simulation results show that the power distribution result of the proposed energy management approach reaches that of the offline PMP application and the discrepancy is within 2.65% for the driving cycles studied.
정춘화(Chunhua Zheng),김모성(Moseong Kim),김형균(Hyungkyoon Kim),박영일(Yoeng-il Park),차석원(Suk Won Cha) 한국자동차공학회 2011 한국자동차공학회 부문종합 학술대회 Vol.2011 No.5
In a fuel cell hybrid vehicle (FCHV), the operating points of the fuel cell system (FCS) can be shifted to its high-efficiency region by using a battery and the total hydrogen consumption depends on power management strategies. Two types of power management strategies are presented in this paper and the concept of equivalent hydrogen consumption is applied to this study due to the difference between the initial and final SOC of the battery. The equivalent hydrogen consumption of each strategy is evaluated and compared to each other.