A5087491823- Building Energy and Comfort Optimization
- Fractional Differential Equations Solutions
- Industrial Vision Systems and Defect Detection
- Neural Networks Stability and Synchronization
- Fault Detection and Control Systems
- Face and Expression Recognition
- Advanced Control Systems Design
- Wind and Air Flow Studies
- Advanced Battery Technologies Research
- Machine Fault Diagnosis Techniques
- Text and Document Classification Technologies
- Imbalanced Data Classification Techniques
- Advanced Algorithms and Applications
- Gene Regulatory Network Analysis
- stochastic dynamics and bifurcation
- Energy Load and Power Forecasting
- Anomaly Detection Techniques and Applications
- Advanced Differential Equations and Dynamical Systems
- Vehicle License Plate Recognition
- Video Surveillance and Tracking Methods
- Industrial Technology and Control Systems
- Advanced Neural Network Applications
- Fire Detection and Safety Systems
- Mineral Processing and Grinding
- Chaos control and synchronization
Anhui Polytechnic University
2018-2024
Nanyang Technological University
2019-2021
Minjiang University
2011-2020
Hunan University
2016-2018
The stable operation of air handling units (AHU) is critical to ensure high efficiency and extend the lifetime heating, ventilation, conditioning (HVAC) systems buildings. In this paper, an online data-driven diagnosis method for AHU in HVAC system proposed elaborated. rule-based can roughly detect sensor condition by setting threshold values according prior experience. Then, efficient feature selection using 1D convolutional neural networks (CNNs) fault system’s historical data obtained...
Fault detection of the electric vehicle battery system is vital for safe driving, energy economy, and lifetime extension. This paper proposes a data-driven method to achieve early accurate fault realize rapid warning. The first adopts support vector data description model mapping feature unlabeled voltage temperature into minimum volume hypersphere in high-dimensional space. When located outside hypersphere, it judged be faulty. Then, overcome problem hyperparameters selection, Bayesian...
Estimation of the sintering state has importance for clinker quality improvements and safe operation rotary kiln. Class imbalanced thermal signals usually pose challenges in feature extraction abnormal recognition. In this article, a novel framework that integrates prior knowledge hidden information is developed recognition class imbalance condition. For discriminative data, cascaded stack autoencoder (SAE) model proposed to fuse our information. The includes SAE deep fusion SAE: former...
Abstract At present, Routh–Herwitz criterion is the mostly applied characteristic equation of time‐lag fractional‐order gene regulatory network systems (FGRNs) for stability analysis. However, it limited by linearization, which makes result have a certain error. In addition, due to processes obtaining roots are too complicated, there many constraints on criterion. To solve these problems, vector Lyapunov function method combined with M‐matrix used in present study. Based this method,...
With the development of underwater vehicle technology, application target detection ranges from ocean search, rescue and to fishing for marine products. At this stage, main problem seafood is slow processing time caused by a large number parameter calculations in deep learning networks. This paper proposes lightweight network based on YOLOv5s. First, GhostBottleneck used reduce parameters. Second, convolution block attention mechanism added last layer backbone increase weight valuable...
Abstract In this paper, we study the dynamic characteristics of fractional‐order nonlinear financial systems, including bifurcation and local asymptotic stability. Among them, select elasticity demand commercial (EDC) as point to discuss state system. By calculating, lowest order is obtained. Furthermore, impulse control gains that follow a law are applied make system stable. addition, some numerical simulation examples provided verify effectiveness benefit proposed form near states when used or not.