In this work, we design an energy management strategy (EMS) for hybrid electric vehicles (HEVs) using a deep reinforcement learning (DRL) algorithm. Specifically, this paper introduces a soft actor-critic (SAC)-based EMS, tailored for devising optimal energy distribution for HEVs. The proposed SAC-based approach is useful for addressing inherent drawbacks that exist in many DRL methods such as slower convergence rate, discretization error, as well as suboptimal solutions. The designed SAC algorithm presents a self-adaptive efficiency in executing continuous decision-making policies through the balance of exploration and exploitation using an entropy-based action selection method and an entropy-added reward function. Extensive experiments are carried out to demonstrate the merits of the adaptive SAC algorithm over the widely adopted Q-learning (QL), deep-Q-network (DQN), and deep deterministic policy gradient (DDPG) approaches on fuel economy and battery charge sustainability. An unknown driving cycle is also employed to show the adaptability feature of the proposed scheme, revealing fuel savings of 6.26%, 3.01%, and 2.03% over the QL-based, DQN-based, and DDPG-based methods, respectively.

Horizontal vibration in high-speed elevator car systems has been a serious problem affecting the riding feeling, and it may threaten the safety and stability of the elevator system. This review aims to provide a comprehensive overview of the causes of horizontal vibration, focusing on factors such as the car and guide system, aerodynamic characteristics, and the performance during starting and stopping processes. Subsequently, various models of high-speed elevator car systems were discussed in detail, taking into account structural excitations and aerodynamic effects. Finally, a thorough analysis of vibration suppression methods, addressing both passive and active controls, was presented. Compared to passive control, active damping control technology has been shown to offer a more flexible and efficient approach to vibration suppression by leveraging real-time feedback and dynamic adjustments of control forces. To enhance the suppression of horizontal vibration, further research into intelligent control strategies with self-learning capabilities, as well as the integration of intelligent materials, appears promising.

Hand movement disorders caused by neurological diseases like brachial plexus injuries significantly impact daily activities of patients. Compared with the upper-limb rehabilitation that is focused on the large movements of joints, the rehabilitation of the hand movements that are dexterous remains challenging due to its exceptional flexibility. This article aims to reviewing the latest research on the system and related strategies for hand movement rehabilitation. Firstly, the development on the cutting-edge sensing technologies, actuator-driven rehabilitation equipment and hand movement pattern recognition algorithms, all contributing to the design of the hand movement rehabilitation system, are introduced. Secondly, the various rehabilitation strategies, including the active rehabilitation, passive rehabilitation, and guided rehabilitation that are tailored for patients with different disability levels at varying rehabilitation stages, are reviewed. Furthermore, the limitations of current methods and techniques are discussed and future research directions are put forward.

In this paper, by employing a recurrent neural network and a critic neural network (CNN), we design an improved dynamic event-triggered controller for a class of non-affine continuous-time nonlinear systems. To address the transformation of the robust-optimal control problem, an additional utility function reflecting the disturbance is introduced. Besides, a system identifier is utilized for reconstructing the non-affine dynamics to generate an affine model. For reducing the waste of communication resources, a dynamic event-triggered control strategy is developed to replace the traditional time-based structure and improve static event-triggered control design. In addition, we develop an enhanced CNN weight updating law, which allows for greater flexibility in the process of weight selection compared to the conventional approach. The dynamic event-triggered controller is designed by using the CNN framework. Finally, a simulation of a modified torsional pendulum system is performed to demonstrate the effectiveness of the constructed method.