From pixels to mass gangue ratio: a lightweight DEM‐assisted end‐to‐end framework for gangue ratio in top coal caving
- 1 August 2026
- journal article
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (16) , 165223
Abstract
When conducting top coal caving, the timely closure of the coal discharge port is crucial for controlling the recovery rate of top coal. The existing semantic segmentation models have issues such as low degree of lightweighting, and can only provide control decisions based on the pixel gangue ratio in the discharge port. This study proposes a real-time prediction framework for end-to-end inference of the mass gangue ratio from coal flow images. Its core is a lightweight model named LEG-U-Net, which integrates knowledge distillation technology and modules such as depth separable convolution, sub-pixel convolution, global shared coordinate attention, and edge guided attention. Experiments show that compared with the teacher model, LEG-U-Net reduces the number of parameters by 87%, increases the FPS by 55%, and achieves an mIoU of 95.27%, achieving a good balance between efficiency and accuracy. Furthermore, through discrete element simulation and mathematical modeling, a quantitative mapping relationship between pixel gangue ratio, volume gangue ratio, and mass gangue ratio was established, enabling end-to-end inference from images to quality gangue ratio. This method provides a new paradigm for real-time intelligent prediction of coal flow gangue ratio, and can effectively support process control and quality optimization decisions in the coal processing process.Keywords
Funding Information
- National Natural Science Foundation of China (U23A20599)
This publication has 31 references indexed in Scilit:
- Benchmarking real-time semantic segmentation models for traffic scene understanding across structured and unstructured environmentsJournal of Real-Time Image Processing, 2026
- Zonal-adaptive caving control technology and its mechanisms for improving extraction efficiency of variable-thickness seamsComputational Particle Mechanics, 2025
- Ms-unet:coal-rock crack image segmentation based on attention mechanism and multi-scale featuresCluster Computing, 2025
- DBA‐DeepLab: Dual‐Backbone Attention‐Enhanced DeepLab V3+ Model for Plant Disease SegmentationFood Science & Nutrition, 2025
- Using a Hybrid of the U-Net and Multilayer Perceptron Models to Automatically Predict the Geological Strength Index from Tunnel Face Rock Joint ImagesRock Mechanics and Rock Engineering, 2025
- A Cascade Model to Detect and Segment Lung Nodule Using YOLOv8 and Resnet50U‐NetInternational Journal of Imaging Systems and Technology, 2025
- Slim-YOLO-PR_KD: an efficient pose-varied object detection method for underground coal mineJournal of Real-Time Image Processing, 2024
- Introducing artificial intelligence technology to plant disease management for sustainable agricultureCrop Protection, 2024
- Research on lightweight Yolo coal gangue detection algorithm based on resnet18 backbone feature networkInternet of Things, 2023
- Falcon: lightweight and accurate convolution based on depthwise separable convolutionKnowledge and Information Systems, 2023