A5000706566- Industrial Vision Systems and Defect Detection
- Metaheuristic Optimization Algorithms Research
- Imbalanced Data Classification Techniques
- Advanced Multi-Objective Optimization Algorithms
- Machine Fault Diagnosis Techniques
- Advanced Neural Network Applications
- Robotic Path Planning Algorithms
- Welding Techniques and Residual Stresses
- Robotics and Sensor-Based Localization
- Advanced Measurement and Metrology Techniques
- Robot Manipulation and Learning
- Advanced machining processes and optimization
- Anomaly Detection Techniques and Applications
- Manufacturing Process and Optimization
- Optical measurement and interference techniques
- Evolutionary Algorithms and Applications
- Color perception and design
- Electricity Theft Detection Techniques
- Magnesium Alloys: Properties and Applications
- Advanced Algorithms and Applications
- Advanced Surface Polishing Techniques
- High Entropy Alloys Studies
- Advanced Numerical Analysis Techniques
- Advanced Machining and Optimization Techniques
- Control and Stability of Dynamical Systems
Guizhou University
2011-2025
Chongqing Vocational and Technical University of Mechatronics
2022-2024
Ministry of Education of the People's Republic of China
2024
Guizhou Education University
2018
Xi'an Technological University
2018
Wenzhou University
2018
Huazhong University of Science and Technology
2018
Northwestern Polytechnical University
2018
Ministry of Education
2016
This paper aims to achieve real-time and accurate detection of surface defects by using a deep learning method. For this purpose, the Single Shot MultiBox Detector (SSD) network was adopted as meta structure combined with base convolution neural (CNN) MobileNet into MobileNet-SSD. Then, method for proposed based on Specifically, SSD optimized without sacrificing its accuracy, parameters were adjusted streamline model. The applied typical like breaches, dents, burrs abrasions sealing...
UAV multitarget detection plays a pivotal role in civil and military fields. Although deep learning methods provide more effective solution to this task, changes target size, shape change, occlusion, lighting conditions from the perspective of drones still bring great challenges research field. Based on above problems, paper proposes an aerial image model with excellent performance strong robustness. First, view common problem that small targets images are prone misdetection missed...
Abstract Numerical optimization, Unmanned Aerial Vehicle (UAV) path planning, and engineering design problems are fundamental to the development of artificial intelligence. Traditional methods show limitations in dealing with these complex nonlinear models. To address challenges, swarm intelligence algorithm is introduced as a metaheuristic method effectively implemented. However, existing technology exhibits drawbacks such slow convergence speed, low precision, poor robustness. In this...
Abstract Numerical optimization and point cloud registration are critical research topics in the field of artificial intelligence. The differential evolution algorithm is an effective approach to address these problems, LSHADE-SPACMA, winning CEC2017, a competitive variant. However, LSHADE-SPACMA’s local exploitation capability can sometimes be insufficient when handling challenges. Therefore, this work, we propose modified version LSHADE-SPACMA (mLSHADE-SPACMA) for numerical registration....
To monitor the tool wear state of computerized numerical control (CNC) machining equipment in real time a manufacturing workshop, this paper proposes real-time monitoring method based on fusion convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) with an attention mechanism (CABLSTM). In method, CNN is used to extract deep features from time-series signal as input, then BiLSTM symmetric structure constructed learn information between feature vectors. The...
Object detection for remote sensing images (RSIs) is an important research topic in data analysis. Many efforts have been devoted to object (RSOD) tasks, most of which try use attention mechanisms improve the performance detectors. However, difference information between global features and local feature maps ignored. In this paper, we design a novel enhanced mechanism (GLE-AM) capture information. Then, propose network (GLE-Net) fully utilize extracted by GLE-AM. Furthermore, order make...
Existing surface defect detection methods for micro-motor commutators suffer from low accuracy, poor real-time performance, and high false missed rates small targets. To address these issues, this paper proposes a high-performance robust commutator model (CLS-YOLO), using YOLOv11-n as the baseline model. First, lightweight Cross-Scale Feature Fusion Module (CCFM) is introduced to integrate features different scales, enhancing model’s adaptability scale variations ability detect objects. This...