A5102822513- Railway Engineering and Dynamics
- Piezoelectric Actuators and Control
- Magnetic Properties and Applications
- Civil and Geotechnical Engineering Research
- Neural Networks and Reservoir Computing
- Innovative Energy Harvesting Technologies
- Energy Harvesting in Wireless Networks
- Electromagnetic Simulation and Numerical Methods
- Geotechnical Engineering and Underground Structures
- Advanced Measurement and Metrology Techniques
- Iterative Learning Control Systems
- Traffic Prediction and Management Techniques
- Advanced Memory and Neural Computing
- Anomaly Detection Techniques and Applications
- Drilling and Well Engineering
- Neural Networks and Applications
- Autonomous Vehicle Technology and Safety
- Electromagnetic Scattering and Analysis
- Geophysical and Geoelectrical Methods
- Speech Recognition and Synthesis
- Robotic Mechanisms and Dynamics
- Wireless Power Transfer Systems
- Geophysical Methods and Applications
- Advanced Sensor and Energy Harvesting Materials
- Shape Memory Alloy Transformations
Tsinghua University
2024
Virginia Tech
2018-2024
Beijing Jiaotong University
2022-2024
Southwest Petroleum University
2023
Guizhou University
2023
China Academy of Engineering Physics
2023
Yanshan University
2022
Chinese Academy of Sciences
2022
DeepMind (United Kingdom)
2022
Shenyang Institute of Automation
2022
The world is witnessing an unprecedented growth of cyber-physical systems (CPS), which are foreseen to revolutionize our via creating new services and applications in a variety sectors, such as environmental monitoring, mobile-health systems, intelligent transportation so on. information communication technology sector experiencing significant data traffic, driven by the widespread usage smartphones, tablets, video streaming, along with sensors deployments that anticipated near future. It...
Wireless Sensor Networks represent a new generation of real-time embedded systems with significantly different communication constraints from the traditional networked systems. This paper first discusses about hardware platforms and secondly software platform. Then detailed information networking applications is outlined. Lastly, this provides future application wireless sensor networks for laboratory mice.
Abstract In multiagent worlds, several decision-making individuals interact while adhering to the dynamics constraints imposed by environment. These interactions, combined with potential stochasticity of agents’ dynamic behaviors, make such systems complex and interesting study from a perspective. Significant research has been conducted on learning models for forward-direction estimation agent example, pedestrian predictions used collision-avoidance in self-driving cars. many settings, only...
Reservoir computing (RC) is attracting widespread attention in several signal processing domains owing to its nonlinear stateful computation. It deals particularly well with time-series prediction tasks and reduces training complexity over recurrent neural networks. also suitable for hardware implementation whereby device physics are utilized performing data processing. In this paper, the RC concept applied modeling a Multiple-Input Multiple-Output Orthogonal Frequency Division Multiplexing...
With the development of railway networks, a new infrastructure integrating underground comprehensive transportation hub and building complex (UCTH&BC) is constructed in many metropolitan cities. However, there no relevant research to analyse its railway-induced environmental vibrations propose an appropriate mitigation measure for such large structure. To have assessment satisfying control potential vibration problem during life-cycle UCTH&BC, numerical study newly-built UCTH&BC was carried...
In this paper, we present the first BEM impedance extraction algorithm for multiple dielectrics. The effect of dielectrics is significant and efficient modeling challenging. However, previous algorithms, including Fastlmp EastPep, assume uniform dielectric, thus causing considerable errors. new introduces a circuit formulation which makes it possible to utilizes either multilayer Green's function or equivalent charge method extract in novelty reduction number unknowns application...
In this paper, we present the first BEM impedance extraction algorithm for multiple dielectrics. The effect of dielectrics is significant and efficient modeling challenging. However, previous algorithms, including Fastlmp EastPep, assume uniform dielectric, thus causing considerable errors. new introduces a circuit formulation which makes it possible to utilizes either multilayer Green's function or equivalent charge method extract in novelty reduction number unknowns application...
Multi-sensor technology has been widely applied in the condition monitoring of rail transit. In practice, data some channels high channel counts are often abnormal or lost due to abnormality and damage sensors, thus resulting a large amount waste. A method for recovery by using adjacent is proposed solve this problem. Based on LSTM network algorithm, model established based “sequence-to-sequence” regression analysis data. Taking measured vibration subway as an example, trained with...
For the dual peg-in-hole compliance assembly task of upper and lower double-hole structural micro-devices, a skill-learning method is proposed. This combines offline training in simulation space online realistic space. In this paper, model built according to results force analysis, contact-point searching methods are provided for calculating contact force. Then, framework based on deep reinforcement learning. Both expert action incremental used training, reward system considers both...
Large complex workpieces are the core components in aerospace, shipbuilding, transportation and other fields. Such usually have large size, shape characteristics poor stiffness of workpieces, such as common bottom launch vehicles, rocket panels, aircraft radomes, etc. When machining high-performance parts, it is necessary to copy parts according task requirements. The integration technology surface measurement organic combination digital an effective means ensure high-precision copying...
Low latency and low energy consumption are the indispensable characteristics of Edge Computing applications. With fusion Artificial Intelligence (AI) into Intelligence, this need is more than ever. Of late, Spiking Neural Networks have shown a promise for power AI when deployed on neuromorphic hardware e.g., Intel's Loihi. In paper, we present Reservoir model, based Legendre Memory Units which processes temporal data Loihi hardware. Such model greatly suitable battery-powered enabled edge...
Knapsack problem is applied broadly to practice in resource allocation, investment decision-making, storage loading and so on. The paper adopts Handel-C language program for the simple improved genetic algorithm that solve knapsack problem. procedures of two algorithms are provided detail paper. enhances obviously global search ability converging velocity through contrasting experiment results algorithms. Thus effectiveness demonstrated.
We present electrostatic flapping actuators with selfsustained oscillations powered by on-board capacitors for the untethered flight control of a palm-sized tiny balloon. With length 13 mm and weight only 3 mg, actuator can generate lift force 1mg stroke frequency 50Hz under applied DC voltages. The produces wing rotation angles up to ±45° lateral propelling force, successfully realizes on plastic balloon 23 seconds movements 295 in sky. As such, this work provides new mechanism artificial...