http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Hongyan Zhang,Changqing Bai,Yijun Mao 대한기계학회 2015 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.29 No.8
Random properties and random loads are highly important in rotor dynamic analysis because they cause system dynamic responses tobehave randomly. In this paper, a stochastical finite element of rotating shaft based on Timosheko beam theory is proposed for rotor systemmodeling, in which material and geometric random properties are considered one-dimensional stochastic field functions. A randomresponse analytical method is developed to determine the statistics of the dynamic responses of stochastical rotor systems under randomloads. The numerically obtained whirl speed of a turbopump rotor system is compared with the test data to validate the proposed model,and good agreement is observed. Linear and nonlinear turbopump rotor systems are employed to compare the results obtained from theproposed model and the Monte Carlo simulation. The numerically predicted results, which coincide well with Monte Carlo simulationdata, demonstrate the feasibility and efficiency of the proposed stochastic model and method for actual rotor system analysis and design.
Dongfang Zhang,Yunduan Cui,Yao Xiao,Shengxiang Fu,Suk Won Cha,Namwook Kim,Hongyan Mao,Chunhua Zheng 한국정밀공학회 2024 International Journal of Precision Engineering and Vol.11 No.1
With the rapid development of artificial intelligence, deep reinforcement learning (DRL)-based energy management strategies (EMSs) have become an important research direction for hybrid electric vehicles recently, which still face some problems such as fragile convergence characteristics, slower convergence speed, and unsatisfactory optimization effects. In this research, a novel DRL algorithm, i.e. an improved soft actor-critic (ISAC) algorithm is applied to the EMS of a fuel cell hybrid vehicle (FCHV), in which the priority experience replay (PER) and emphasizing recent experience (ERE) methods are adopted to improve the convergence performance of the algorithm and to enhance the FCHV fuel economy. In addition, the fuel cell durability is also considered in the proposed EMS based on a nonlinear fuel cell degradation model while considering the fuel economy. Results indicate that the FCHV fuel consumption of the proposed EMS is decreased by 7.87%, 2.79%, and 2.44% compared to that of the deep deterministic policy gradient (DDPG)-based, the twin delayed deep deterministic policy gradient (TD3)-based, and the SAC-based EMSs respectively while the fuel consumption gap to the dynamic programming-based EMS is narrowed to 2.37% by the proposed EMS. Moreover, the proposed EMS presents the best training performance considering both the convergence speed and stability, and the convergence speed of the proposed EMS is increased by an average of 47.89% compared to that of the other DRL-based EMSs. Furthermore, the fuel cell durability is improved by more than 95% using the proposed EMS compared to that of the EMS without considering the fuel cell degradation.