A5030481039- Fault Detection and Control Systems
- Advanced Sensor Technologies Research
- Machine Learning and ELM
- Control Systems and Identification
- Target Tracking and Data Fusion in Sensor Networks
- Advanced Measurement and Detection Methods
- Advanced Sensor and Control Systems
- Advanced Combustion Engine Technologies
- Advanced Control Systems Optimization
- Scientific Measurement and Uncertainty Evaluation
- Advanced Battery Technologies Research
- Adaptive Control of Nonlinear Systems
- Industrial Technology and Control Systems
- Hydraulic and Pneumatic Systems
- Advanced Algorithms and Applications
- Anomaly Detection Techniques and Applications
- Aerospace and Aviation Technology
- Advanced Aircraft Design and Technologies
- Network Security and Intrusion Detection
- Neural Networks and Applications
- Machine Fault Diagnosis Techniques
- Rocket and propulsion systems research
- Real-time simulation and control systems
- Metaheuristic Optimization Algorithms Research
- Adaptive Dynamic Programming Control
Nanjing University of Aeronautics and Astronautics
2016-2025
China Huarong Energy (China)
2024
Dalian University of Technology
2024
Shenyang Aerospace University
2024
China People's Public Security University
2007-2021
Central South University
2021
ORCID
2017-2018
University of Toronto
2016-2018
Aviation Industry Corporation of China (China)
2013-2017
Aero Engine Corporation of China (China)
2015-2017
Aero-engine performance monitoring is a core component of the engine health management system and an important approach to enhancing flight safety reliability. Meanwhile, improve operation efficiency, control systems are evolving from traditional centralized architectures distributed architectures. To alleviate negative impact network uncertainties, this paper proposes Distributed Adaptive Kalman Filter (DAKF), which resolves estimation degradation classical under uncertainty by designing...
Different approaches for gas path performance estimation of dynamic systems are commonly used, the most common being variants Kalman filter. The extended filter (EKF) method is a popular approach nonlinear which combines traditional filtering and linearization techniques to effectively deal with weakly non-Gaussian problems. Its mathematical formulation based on assumption that probability density function (PDF) state vector can be approximated Gaussian. Recent investigations have focused...
The on-board sensor fault detection and isolation (FDI) system is essential to guarantee the reliability safety of an aero engine. In this paper, a novel online sequential extreme learning machine with memory principle (MOS-ELM) proposed for detecting, isolating, reconstructing signal engines. many practical applications, sequentially coming data chunk usually possesses characteristic timeliness, overdue training may mislead subsequent process. MOS-ELM can improve process by introducing...
Aero-engine gas path health monitoring plays a critical role in Engine Health Management (EHM). To achieve unbiased estimation, traditional filtering methods have strict requirements on measurement parameters which sometimes cannot be measured engineering. The most typical one is the High-Pressure Turbine (HPT) exit pressure, vital to distinguishing failure modes between different turbines. For case of an abrupt occurring single turbine component, model-based sensor reconstruction method...
Extreme learning machine (ELM) owns the advantages of less computational efforts and simple topology with single-hidden layer structure. However, performance plain ELM is sensitive to input weights, bias, number hidden neurons; former two are randomly generated. This paper develops a restricted Boltzmann strategy combined Moore-Penrose generalized inverse learn topological parameters in both output layers. A novel extreme model based on ELM, constructs feature mapping recursively tune...