Metal fracture recognition based on lightweight convolutional neural network
[基于轻量化卷积神经网络的金属断口图像识别]作者机构：College of Control Science and Engineering Dalian University of Technology Dalian 116024 China
出 版 物：《Kongzhi yu Juece/Control and Decision》 (Control and Decision)
年 卷 期：2024年第39卷第9期
页 面：2858-2866页
核心收录：
学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0835[工学-软件工程] 0503[文学-新闻传播学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
基 金：国家自然科学基金项目(62073056,61876029) 辽宁省应用基础研究计划项目(2023JH2/101300207) 大连市重点领域创新团队项目(2021RT14) 新疆维吾尔自治区科技重大专项项目(2022A01001)
主 题：Convolutional neural networks
摘 要：The recognition of metal fracture images in an industrial environment plays a pivotal role in the analysis of metal failures and carries substantial research significance. While convolutional neural networks have been proven effective in image recognition tasks, the recognition of metal fracture images in an industrial environment still encounters the following challenges. 1) Metal fracture images exhibit strong intra-class complexity and inter-class similarity. 2) Existing CNN structures are complex, with a large number of parameters, which makes deployment on embedded devices challenging. To address the aforementioned problems, this paper proposes a metal fracture image recognition method based on the lightweight CNN. First, a CNN model structure with multi-feature fusion is designed to enhance the network’s feature extraction capability. Second, a hybrid pruning algorithm is proposed to slim the network and reduce the complexity of the algorithm. Simultaneously, the search process for important hyperparameters is treated as an optimization problem, and the Bayesian optimization (BO) algorithm is utilized to solve it, thereby automating the model design and pruning process. The experimental results show that the proposed method requires only 3.82 million parameters to achieve 97.56 % recognition accuracy. The deployment on the Jetson Nano embedded platform verifies the practical feasibility of the proposed method. © 2024 Northeast University. All rights reserved.
维普期刊数据库