小样本下基于改进ACGAN数据增强的X射线矿石图像分类方法  

X-ray Ore Image Classification Method Based on Improved ACGAN Data Augmentation in Small Samples

作　　者：王文 何剑锋[1,2,3] 朱文松 李卫东[1,3] 聂逢君[1,3] 夏菲[1,3] 汪雪元[1,2,3] 钟国韵 瞿金辉[1,3] WANG Wen;HE Jianfeng;ZHU Wensong;LI Weidong;NIE Fengjun;XIA Fei;WANG Xueyuan;ZHONG Guoyun;QU Jinhui(Jiangxi Engineering Technology Research Center of Nuclear Geoscience Data Science and System,East China University of Technology,Nanchang 330013,China;Information Engineering College,East China University of Technology,Nanchang 330013,China;Jiangxi Engineering Laboratory on Radioactive Geoscience and Big Data Technology,East China University of Technology,Nanchang 330013,China)

机构地区：[1]东华理工大学江西省核地学数据科学与系统工程技术研究中心,南昌330013 [2]东华理工大学信息工程学院,南昌330013 [3]东华理工大学江西省放射性地学大数据技术工程实验室,南昌330013

出　　处：《有色金属工程》2024年第3期122-132,共11页Nonferrous Metals Engineering

基　　金：国家自然科学基金资助项目(11865002,U2067202);江西省主要学科学术和技术带头人培养计划(20225BCJ22004);江西省重点研发计划(20203BBG73069)。

摘　　要：针对工业领域利用深度学习模型对矿石进行在线分类时,矿石样本稀少导致的模型过拟合、分类准确率低的问题,提出一种结合X射线透射成像技术的矿石数据增强分类方法。该方法基于改进辅助生成对抗网络(Enhance-based Classification ACGAN-gp, EC-ACGAN-gp),采用卷积和连续残差块构建判别器和生成器,引入注意力机制捕捉矿石细节特征,生成高质量样本扩充原始数据集,同时使用带梯度惩罚的Wasserstein距离重构判别器的损失函数提高对抗训练的稳定性,避免模式崩溃。通过增加辅助分类器重建样本标签信息,最终实现矿石样本的类别预测。结果表明,该方法能实现矿石品位分类的精准预测,准确率可达89.62%,比现有传统方法提高3.98%。该模型生成的矿石样本泛化性良好,能够显著提高小样本数据集的泛化性,在SVM、LeNet5、VGGNet、ResNet上测试,精度分别提升了2.83%、2.36%、1.89%和3.74%,可进一步用于提升其他分类模型在矿石品位预测方面的性能。Aiming at the problems of overfitting and low classification accuracy due to the scarcity of ore samples in industrial applications of deep learning models for online ore classification,a method combining X-ray transmission imaging technology for ore data augmentation and classification is proposed.The method is based on an improved auxiliary classifier generative adversarial network(Enhance-based Classification ACGAN-gp,EC-ACGAN-gp),which uses convolutional and continuous residual blocks to construct the network structures of the discriminator and generator.An attention mechanism is introduced to capture detailed ore features and generate high-quality samples to expand the original dataset.Simultaneously,the Wasserstein distance function with gradient penalty is used to reconstruct the classification loss function,achieving improved stability of adversarial training and avoiding mode collapse.Finally,an auxiliary classifier is utilized to reconstruct label information for ore sample category prediction.The research results show that the proposed method can accurately predict the ore grade classification,with an accuracy of up to 89.62%,which is 3.98%higher than traditional methods.The model-generated ore samples demonstrate good generalization performance,significantly improving the generalization of small sample datasets.When tested on SVM,LeNet5,VGGNet,and ResNet,the accuracy is increased by 2.83%,2.36%,1.89%,and 3.74%,respectively.This method can further be used to enhance the performance of other classification models in ore grade prediction.

关 键 词：矿石分类 小样本 数据增强 辅助生成对抗网络 X射线成像 自注意力机制 

分 类 号：TD921[矿业工程—选矿] TP183[自动化与计算机技术—控制理论与控制工程]