A5023980618- Mineral Processing and Grinding
- Minerals Flotation and Separation Techniques
- Metal Extraction and Bioleaching
- Image and Object Detection Techniques
- Geoscience and Mining Technology
- Digital Imaging for Blood Diseases
- Industrial Vision Systems and Defect Detection
- Geochemistry and Geologic Mapping
- Coal Properties and Utilization
- Advanced X-ray and CT Imaging
- Coal Combustion and Slurry Processing
- Water Quality Monitoring Technologies
- Spectroscopy and Chemometric Analyses
- Brain Tumor Detection and Classification
- Spectroscopy Techniques in Biomedical and Chemical Research
- Color Science and Applications
- Domain Adaptation and Few-Shot Learning
- Advanced Image Fusion Techniques
- Elevator Systems and Control
- Geomechanics and Mining Engineering
- Anomaly Detection Techniques and Applications
- Robotics and Sensor-Based Localization
- Infrastructure Maintenance and Monitoring
- Non-Destructive Testing Techniques
- Remote-Sensing Image Classification
China University of Mining and Technology
2018-2025
Beijing General Research Institute of Mining and Metallurgy
2024
China University of Mining and Technology - Beijing
2021-2023
Ultrasonic flotation was an effective method to float fine coal. In this study, the effects of standing waves with different frequencies on ultrasonic were investigated. The dynamic processes bubble and coal-bubble revealed by a high-speed camera. results showed that under action Bjerknes force, aggregates formed within 450 ms coal 20 ms. statistically analyzed image processing method. number small bubbles in field at 100 kHz greater than those 80 120 kHz. Besides, achieved highest yields...
Abstract Condition recognition in coal flotation is a critical component achieving process control and optimization. To develop reliable models for condition recognition, two key challenges must be addressed: first, the effective extraction integration of froth visual feature information from multiple cells; second, fusion features with parameters to create comprehensive representation conditions. tackle these challenges, time series classification model based on multi-source heterogeneous...
Under the strategic objectives of carbon peaking and neutrality, energy transition driven by new quality productive forces has emerged as a central theme in China's development. Among these, intelligent sorting analysis raw coal using deep learning constitute pivotal technical process. However, progress preparation China been constrained absence accurate large-scale data. To address this gap, study introduces DsCGF, large-scale, open-source image dataset. Over past five years, extensive...
This article proposes a method that can be used to improve the differentiation of coal and gangue via image processing use support vector machine (SVM). Images were converted grayscale in this approach, background was segmented, contrast stretched. A basic eigenvalue then determined based on between mean gray-level co-occurrence matrix each image. The biorthogonal wavelet expand images discrete transforms two dimensions (2-D), while supplementary is comprised variance coefficient at...
Coal gangue image recognition is a critical technology for achieving automatic separation in coal processing, characterized by its rapid, environmentally friendly, and energy-saving nature. However, the response characteristics of vary greatly under different illuminance conditions, which poses challenges to stability feature extraction recognition, especially when strict requirements are necessary. This leads fluctuating accuracy industrial environments. To address these issues improve...
Surrounding rock pressure prediction for fully mechanized coal face (FMCF) roof management and control is of great significance. The key challenge to effectively combine various factors evolve the surrounding trend with high temporal-spatial correlation heterogeneity. hydraulic support load an important indicator that reflects change in pressure. Inspired by research on 'support-surrounding rock' massive data collected sensors, this paper proposes a data-driven framework FMCFs. includes...