摘要
钢铁材料微观组织决定了钢的力学性能,因此对钢材微观组织的识别十分重要。钢铁材料显微组织图片放大倍数差异大,同种微观组织在不同放大倍数下的形貌也有很大差别,对持续扩充的多尺度钢材微观组织数据集进行分类的难度很大。因此,结合VGG16网络和自组织增量神经网络(Self Organizing Incremental Neural Network,SOINN),构建基于增量学习的多尺度钢材微观组织图像分类模型;同时,提出基于中心距离的交叉熵损失(Cross Entropy Loss based on Center Distance,CELCD)和交叉训练策略,并融合交叉训练、CELCD和Anchor loss克服“灾难性遗忘”问题,实现对钢材微观组织图片数据的持续学习和高效分类。实验比较了不同增量学习方法在旧数据上的分类精度和“遗忘程度”,结果表明,在增量学习后所提方法的预测精度较增量学习前仅下降14.02%的前提下,在旧数据上的分类精度最高可达80.49%,与上限精度仅相差5.49%,优于其他增量学习方法。
The mechanical properties of steels are closely related to their microstructures,so it is important to identify the microstructures of steels.The magnification of steel micrograph varies greatly,and the morphology of the same microstructure at different magnifications is also different,so the classification of the continuously expanded multi-scale steel microstructure dataset is difficult.In this paper,VGG16 and self-organizing incremental neural network(SOINN)are combined to build a classification model for multiscale steel microstructure dataset based on incremental learning.In addition,the cross entropy loss based on center distance(CELCD)and cross train strategy are proposed.Combining with cross train,CELCD and anchor loss are utilized to solve the problem of“cata-strophic forgetting”and realize the incremental learning and efficient classification for steel micrographs.The classification accuracy and“forgotten degree”of the model are compared.Experimental results show that after incremental learning,the classification accuracy of the proposed method is only 14.02%lower than that before incremental learning,which reaches 80.49%on the old data and only 5.49%lower than the upper bound,which is superior to other incremental learning methods.
作者
曾培益
ZENG Peiyi(School of Computer Science and Engineering,University of Electronic Science and Technology of China,Chengdu 611731,China)
出处
《计算机科学》
CSCD
北大核心
2024年第S01期290-297,共8页
Computer Science
基金
国家自然科学基金(51774219)。
关键词
钢材微观组织
增量学习
灾难性遗忘
多尺度
自组织
Steel microstructures
Incremental learning
Catastrophic forgetting
Multi-scale
Self-organizing