A5100756974- Fault Detection and Control Systems
- Spectroscopy and Chemometric Analyses
- Embedded Systems and FPGA Design
- Risk and Safety Analysis
- Mineral Processing and Grinding
- Research studies in Vietnam
- Advanced Computational Techniques and Applications
- Smart Grid and Power Systems
- Vehicle License Plate Recognition
- Image and Object Detection Techniques
- Metallurgical Processes and Thermodynamics
- High-Voltage Power Transmission Systems
- Robotic Path Planning Algorithms
- Manufacturing Process and Optimization
- Metallurgy and Material Forming
- Advanced Neural Network Applications
- Advanced Sensor and Control Systems
- Optimization and Search Problems
- Multi-Criteria Decision Making
- Advanced Algorithms and Applications
- Robotics and Sensor-Based Localization
- Technology Assessment and Management
- Machine Fault Diagnosis Techniques
- Digital Transformation in Industry
- Energy Load and Power Forecasting
Beijing University of Technology
2006-2022
Tongji University
2020
China Jiliang University
2020
Nanjing Audit University
2020
Northeastern University
2019
Changsha University of Science and Technology
2019
Hubei University of Arts and Science
2019
Guizhou University of Finance and Economics
2019
Shanghai Architectural Design & Research Institute
2011
Hangzhou Dianzi University
2011
When mechanical products work in complex environments, it is imperative to build an optimal maintenance strategy, based on accurate positioning of fault locations and prediction conditions. Based digital twinning technology, this paper proposes a “super-network-warning features” method. According the twin five-dimensional structure, three-layer super-network model constructed, providing quantitative research for data among heterogeneous subjects twinning. Early-warning-features physical...
Fault diagnosis and forecasting contribute significantly to the reduction of operating maintenance associated costs, as well improve resilience wind turbine systems. Different from existing fault approaches using monitored vibration acoustic data auxiliary equipment, this research presents a novel approach underpinned by support vector regression model obtained supervisory control acquisition system (SCADA) turbines (WT). To operate, extraction features is conducted measuring SCADA...
Automatic license plate recognition (ALPR) has made great progress, yet is still challenged by various factors in the real world, such as blurred or occluded plates, skewed camera angles, bad weather, and so on. Therefore, we propose a method that uses cascade of object detection algorithms to accurately speedily recognize plates’ contents. In our method, YOLOv3-Tiny, an end-to-end network, used locate areas, YOLOv3 characters. According type position recognized characters, logical judgment...
Alarm trippoints are crucial parameters of alarm systems in industrial processes. Poorly designed will probably bring about overloading which is detrimental to the performance systems. In particular, design recent mostly static and isolated from other related variables, resulting occurrence nuisance alarms, including false alarms missed alarms. A remedy multivariate by taking intricate correlation into account. This work proposes a novel framework based on causal model. First, basis our...
Purpose An important issue in online auditing is how to improve the reliability of order reduce overall audit risk. In this paper, a assessment and early-warning method based on RC (rank centroid), AHP (analytic hierarchy process) GM (1,1) proposed from perspective information technology (IT) risk control. Design/methodology/approach The paper begins by structuring used China. Then, rank importance criteria. Pairwise comparisons criteria are made results RC, leads matrix comparisons. Next,...
More and more robot tasks extend to unknown environments. Extraction of the topological map from exploration results an environment is great importance for completion path-planning tasks. In this research, a explores builds grid in simulation experiments; building based on features studied. A new method proposed that be classified 8 basic types concave protruding corners defined by mathematical equations. According definition strategy designed divide into s built
In industrial process control, data-driven fault detection and isolation methods have developed rapidly due to the easy availability of large amount data. isolation, principal component analysis(PCA) based contribution plot is a standard tool. The problem PCA that they are affected by so called smearing effect. fact, variables can be classified into groups according their correlation or structure, hence it straightforward consider group-wise problem. This paper introduces sparse group Lasso...
At present, the prediction of reduction ratio for pore closure in heavy forgings stock is limited to finite element numerical simulation and complex mathematical formula. To make it fit application, proposed that a new forecasting method by using SVM model predict critical closure. Firstly, selected several major factors which affecting as input features SVM. Then, optimized SVM's nuclear parameters with Particle Swarm Optimization order enhance its accuracy. Finally, trained combining...