A5033390427- Vibration Control and Rheological Fluids
- Robotic Locomotion and Control
- Soft Robotics and Applications
- Robotic Path Planning Algorithms
- Innovative Energy Harvesting Technologies
- Advanced Sensor and Energy Harvesting Materials
- Structural Engineering and Vibration Analysis
- Modular Robots and Swarm Intelligence
- Structural Health Monitoring Techniques
- Underwater Vehicles and Communication Systems
- Machine Fault Diagnosis Techniques
- Energy Harvesting in Wireless Networks
- Seismic Performance and Analysis
- Robotics and Sensor-Based Localization
- Robotic Mechanisms and Dynamics
- Vibration and Dynamic Analysis
- Control and Dynamics of Mobile Robots
- Adaptive Control of Nonlinear Systems
- Prosthetics and Rehabilitation Robotics
- Dielectric materials and actuators
- Image and Video Quality Assessment
- Geophysics and Sensor Technology
- Magnetic Bearings and Levitation Dynamics
- Advanced Materials and Mechanics
- Advanced Image Fusion Techniques
Chongqing University
2020-2025
State Key Laboratory of Mechanical Transmission
2023-2025
Shanghai University
2015-2024
Medical Architecture (United Kingdom)
2023
China State Shipbuilding (China)
2022
Southwest University
2022
Huazhong University of Science and Technology
2007-2020
Dalhousie University
2015
University of Wuppertal
1999
The University of Queensland
1972
A predictive energy management strategy considering travel route information is proposed to explore the energy-saving potential of plug-in hybrid electric vehicles. The extreme learning machine used as a short-term speed predictor, and battery temperature added an optimization term cost function. By comparing training data sets, it found that using real-world historical for can achieve higher prediction accuracy than typical standard driving cycles. predictor trained based on further improve...
Committed to optimizing the fuel economy of hybrid electric vehicles (HEVs), improving working conditions engine, and promoting research on deep reinforcement learning (DRL) in field energy management strategies (EMSs), this article first proposed a DRL-based EMS combined with rule-based engine start–stop strategy. Moreover, considering that both transmission are controlled components, developed novel double DRL (DDRL)-based EMS, which uses Q-network (DQN) gear-shifting strategy...
This paper presents human-robot cooperation with adaptive behavior of the robot, which helps human operator to perform cooperative task and optimizes its performance. A novel impedance control is proposed for robotic manipulator, whose end-effector's motions are constrained by arm motion limits. In order minimized tracking errors acquire an optimal mode arms, linear quadratic regulation (LQR) formulated; then, integral reinforcement learning (IRL) has been solve given LQR little information...
This paper presents a reliable intelligent path following control method for robotic airship subject to sensor faults. First, an adaptive backstepping sliding mode controller is designed based on the six degrees of freedom model airship, where technique used obtain desired velocities, and adopted deal with unknown uncertainties. The stabilization whole system studied Lyapunov stability theory. Specially, since measured data in are interrelated, data-driven soft neuro-fuzzy inference detect...
This paper studies the compound learning control of disturbed uncertain strict-feedback systems. The design is using dynamic surface equipped with a novel scheme. integrates recently developed online recorded data-based neural nonlinear disturbance observer (DOB) to achieve good "understanding" system uncertainty including unknown dynamics and time-varying disturbance. With proposed method show how networks DOB are cooperating each other, one indicator constructed included into update law....
Abstract Ocean contain abundant clean energies including tidal and wave, but such are known for low frequency large excitation amplitude, posing considerable challenges high‐efficiency energy conversion. As an emerging technology, triboelectric nanogenerators (TENGs) have been widely used in harvesting novel sensor design due to their high sensitivity flexible structure. Meanwhile, they show great advantages the low‐frequency environment (<5 Hz), display potential deployment remote ocean...
Abstract Jumping is an important locomotion function to extend navigation range, overcome obstacles, and adapt unstructured environments. In that sense, continuous jumping direction adjustability can be essential properties for terrestrial robots with multimodal locomotion. However, only few soft achieve rapid controlled turning obstacle crossing. Here, we present electrohydrostatically driven tethered legless robot capable of rapid, continuous, steered based on a electrohydrostatic bending...
Wireless communication technology has promoted the development of connected hybrid electric vehicles (CHEVs). With traffic signal information, fuel economy CHEVs can be improved via optimal speed planning. However, road environment in most existing studies is unreal and riding comfort ignored. Therefore, this paper uses real phase position information lights to establish a model proposes multi-objective hierarchical (MOHO) strategy. First, planning module developed as upper layer. By...
Various domain adaptation (DA) methods have been proposed to address distribution discrepancy and knowledge transfer between the source target domains. However, many DA models focus on matching marginal distributions of two domains cannot satisfy fault-diagnosed-task requirements. To enhance ability DA, a new mechanism, called deep joint alignment (DJDA), is simultaneously reduce in conditional A statistical metric that can align means covariances designed match class distributions, Gaussian...