A5100449002- Fault Detection and Control Systems
- Control Systems and Identification
- Industrial Technology and Control Systems
- Advanced Algorithms and Applications
- Neural Networks and Applications
- Microgrid Control and Optimization
- Machine Fault Diagnosis Techniques
- Smart Grid Security and Resilience
- Simulation and Modeling Applications
- Advanced Sensor and Control Systems
- Iterative Learning Control Systems
- Structural Health Monitoring Techniques
- Engineering and Test Systems
- Gear and Bearing Dynamics Analysis
- Advanced Computational Techniques and Applications
- Network Security and Intrusion Detection
- Advanced Control Systems Optimization
- HVDC Systems and Fault Protection
- Pulsed Power Technology Applications
- Advanced Decision-Making Techniques
- Power Line Inspection Robots
- Traffic control and management
- Power Systems Fault Detection
- Adaptive Control of Nonlinear Systems
- Islanding Detection in Power Systems
Anhui University of Technology
2024
Jiangsu University of Technology
2019-2024
Taiyuan University of Technology
2017-2024
Xinjiang New Energy Research Institute (China)
2022-2024
China Southern Power Grid (China)
2020-2024
Guangdong Polytechnic Normal University
2021-2023
Southwest Jiaotong University
2023
State Grid Corporation of China (China)
2022
Beijing Aerospace Flight Control Center
2022
China Aerospace Science and Technology Corporation
2022
To solve the problem of trajectory tracking control for quadrotor UAV with input saturation, a novel prescribed performance backstepping dynamic surface scheme is proposed in presence model uncertainties and unknown external disturbances. In this work, hyperbolic tangent function introduced to construct an auxiliary equation reduce saturation effect. Furthermore, method introduces function, converts original constrained system into equivalent unconstrained through error transformation....
Abstract With the aim of identifying possible mechanical faults in unmanned aerial vehicle (UAV) rotors during operation, this paper proposes a method based on interval sampling reconstruction vibration signals and one-dimensional convolutional neural network (1D-CNN) deep learning. Firstly, experiments were designed to collect acceleration UAV working at high speed under three states (normal, rotor damage by varying degrees, crack different degrees). Then, considering powerful feature...
Dear editor, This letter presents a practical industrial process identification scheme. More specifically, to improve the accuracy of process, decoupled scheme is developed based on neural fuzzy network and autoregressive exogenous (ARX) model, which multi-signal sources. The multiple signal sources include binary signals random signals. Experimental results pH neutralization show that identifi-cation can provide accurate accuracy.
Summary In this article, the parameter learning scheme for multi‐input multi‐output (MIMO) Hammerstein nonlinear systems under measurement noises is studied, which derived by exploiting correlation analysis and data filtering technique. The coupled MIMO system presented involves a static subsystem modeled neural fuzzy model (NFM), dynamic linear established autoregressive moving average with extra input (ARMAX) model. To learn unknown of system, combined signals are designed to realize that...
This article considers the monotone smoothing spline regression problem. We add, as smoothness penalty term, integral of squared second derivative function. The objective function is minimized over space natural cubic splines with knots at design points. give a necessary and sufficient condition for to be nondecreasing an interval. Estimation unknown parameters formulated into second-order cone programming resulting estimated in whole domain also has enough smoothness. Simulation results...
Abstract The application of artificial intelligence methods in fault diagnosis is becoming more and extensive, exploring researching intelligent for automobile engines also a hot spot the field automotive engineering. Different machine learning have their own advantages disadvantages. By extracting different characteristic parameters optimizing combination multiple algorithms, faster stable results can be achieved, so that faults discovered repaired time. Aiming at potential fluctuation...
The safety of the industrial control system directly affects operation critical infrastructure, and requirement interconnection with external network puts at greater risk. However, due to particularity system, traditional intrusion detection algorithm can't be used directly. In this paper, we propose a novel called OPSO-BPNN which is suitable for system. Our optimizes particle swarm nonlinear reduction inertia factor, then uses it optimize weight BP neural network. Simulation results show...
With the development of power systems, flow problem transmission line is becoming more and prominent. This paper presents a regulation method based on phase shifting transformer (PST). Firstly, working principle performance PST are analyzed. Then, simulation model BPA multi node system established. access reduces imbalance to less than 8%. On this basis, considering influence saturation effect leakage reactance, suitable for 220 kV grid designed. Three different conditions simulated by PSCAD...
This paper presents the analysis and mitigation of sub-synchronous resonance (SSR) for doubly fed induction generators (DFIG) under virtual synchronous generator (VSG) control, based on impedance methods. VSGs are considered to have grid-supporting ability good stability in inductance-based weak grids, implemented renewable power generations, including DFIG systems. However, analyses connecting with series capacitor compensation absent. Therefore, this focuses SSR VSG control. Impedance...
Abstract In order to meet the requirements of high reliability and low power consumption during operation aircraft, this paper adopts high-level synthesis method map language into RTL level code that can run directly on FPGA, proposes an intelligent integration system for aircraft based synthesis. The input is image radar sensor data, visible data infrared output. output target identification. Including convolutional IP core, pooled core fully connected core. whole uses 7-layer deep learning...
Cyber search engines, such as Shodan and Censys, have gained popularity due to their strong capability of indexing the Internet Things (IoT). They actively scan fingerprint IoT devices for unearthing IP-device mapping. Because large address space mapping's mutative nature, efficiently tracking evolution mapping with a limited budget scans is essential building timely cyber engines. An intuitive solution use reinforcement learning schedule more networks high churn rates However, an has never...