A method for detecting the grade of graphite ore based on an improved YOLO11 model

By improving the YOLO11 model for graphite ore grade detection, the problems of low efficiency and poor real-time performance of traditional detection methods have been solved. This enables rapid and accurate detection of graphite ore grade, which is applicable to industrial sites and improves mine production efficiency and resource utilization efficiency.

CN120783075BActive Publication Date: 2026-06-16JIANGXI UNIV OF SCI & TECH
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
JIANGXI UNIV OF SCI & TECH
Filing Date
2025-06-11
Publication Date
2026-06-16

AI Technical Summary

⚠Technical Problem

Traditional graphite ore grade testing relies on manual sampling and laboratory analysis, which is inefficient and lacks real-time performance, making it difficult to meet the needs of rapid ore quality assessment in dynamic mining scenarios.

⚗Method used

An improved YOLO11 model was adopted to construct a graphite ore grade detection system through image acquisition, data augmentation, model training and deployment. This system includes pre-classification, image acquisition, data augmentation, network model construction and validation, and optimization of the YOLO11 network structure to improve detection accuracy and efficiency.

🎯Benefits of technology

It enables rapid and accurate detection of graphite ore grade, is suitable for real-time application in industrial sites, improves mine production efficiency, reduces resource misallocation and environmental pollution risks, and supports the high-value utilization of graphite resources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120783075B_ABST
    Figure CN120783075B_ABST
Patent Text Reader

Abstract

The application belongs to the technical field of image processing, and particularly relates to a graphite ore grade detection method based on an improved YOLO11 model, C3k2-CAS and Detect-SEAM modules are introduced, the feature extraction capability is enhanced, the expression of different scale ore textures is optimized, the perception capability of the model to grade difference is improved, so that the detection precision is significantly improved; the attention mechanism of the CAS module is used to replace the traditional multiplication operation, while the detection performance is maintained, the calculation complexity and the model parameter quantity are greatly reduced, so that the improved model is more efficient than the baseline model, and is more suitable for edge device deployment; combined with various data enhancement strategies, the model can maintain high robustness and stable detection capability in complex industrial environments; the trained optimized model can be efficiently deployed to graphite ore grade detection intelligent equipment, real-time and accurate industrial site detection is realized, the mineral separation efficiency is greatly improved, and an efficient and reliable computer vision solution is provided for intelligent mining.
Need to check novelty before this filing date? Find Prior Art