*Result*: 深度学习在矿物识别中的应用现状与展望.
*Further Information*
*With the promotion of smart mining construction in China, mineral resource development is gradually moving towards mechanization, automation informatization, and intelligence. In recent years, the application of deep learning technology in mineral recognition has received widespread attention, especially image recognition technology based on deep learning, which provides new approach for mineral detection and classification. This article briefly described the main technologies and methods of deep learning in mineral recognition, introduced the current application status of deep learning technology in mineral classification, segmentation, particle size analysis, and summarized its application progress in mineral processing, and pointed out the problems of deep learning in mineral recognition, At present, the optimization direction of deep learning models applied to mineral image recognition mainly focuses on feature extraction optimization, model architecture optimization, training strategy optimization, loss function optimization, interpretability, and visualization tools. Model optimization can improve the recognition ability of the model for the morphology, texture, and boundaries of mineral particles, accelerate the convergence speed of the model, enhance the generalization ability of the model, and improve the transparency and credibility of the model. [ABSTRACT FROM AUTHOR]*
*随着我国智慧化矿山建设的推进, 矿产资源开发逐步朝机械化、自动化、信息化和智能化方向发展。近年 来, 深度学习技术在矿物识别中的应用受到了广泛关注, 特别是基于深度学习的图像识别技术为矿物检测与分类提供 了新的途径。本文简述了深度学习在矿物识别中的主要技术和方法, 介绍了深度学习技术在矿物分类、矿物分割、矿 物粒度分析等方面的应用现状, 并总结了其在选矿过程中的应用进展, 指出了深度学习在矿物识别中存在的问题。目 前应用于矿物图像识别的深度学习模型优化方向主要集中在特征提取优化、模型架构优化、训练策略优化、损失函数 优化以及可解释性和可视化工具等方面。通过优化能够提高模型对矿物颗粒的形态、纹理和边界的识别能力, 加快模 型收敛速度, 提升模型的泛化能力以及增强模型的透明性和可信度。 [ABSTRACT FROM AUTHOR]
Copyright of Industrial Minerals & Processing / Huagong Kuangwu yu Jiagong is the property of Industrial Minerals & Processing Editorial Office and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)*