刘畅,张剑,林建平.基于神经网络的磁瓦表面缺陷检测识别[J].表面技术,2019,48(8):330-339.
LIU Chang,ZHANG Jian,LIN Jian-ping.Detection and Identification of Surface Defects of Magnetic Tile Based on Neural Network[J].Surface Technology,2019,48(8):330-339
基于神经网络的磁瓦表面缺陷检测识别
Detection and Identification of Surface Defects of Magnetic Tile Based on Neural Network
投稿时间:2018-12-25  修订日期:2019-08-20
DOI:10.16490/j.cnki.issn.1001-3660.2019.08.044
中文关键词:  磁瓦  表面缺陷  缺陷提取  缺陷分类识别  图像分割  UNet
英文关键词:magnetic tile  surface defect  defect extraction  defect classification and recognition  image segmentation  UNet
基金项目:工信部2017年智能制造新模式项目
作者单位
刘畅 同济大学 机械与能源工程学院,上海 201804 
张剑 同济大学 机械与能源工程学院,上海 201804 
林建平 同济大学 机械与能源工程学院,上海 201804 
AuthorInstitution
LIU Chang School of Mechanical and Energy Engineering, Tongji University, Shanghai 201804, China 
ZHANG Jian School of Mechanical and Energy Engineering, Tongji University, Shanghai 201804, China 
LIN Jian-ping School of Mechanical and Energy Engineering, Tongji University, Shanghai 201804, China 
摘要点击次数:
全文下载次数:
中文摘要:
      目的 针对传统算法提取磁瓦表面缺陷的局限性,以及通过人为选择缺陷特征进而判断缺陷种类的方法精度不足等问题,结合改进的UNet模型和一个分类神经网络提出一种磁瓦缺陷检测识别算法。方法 改进的UNet模型用于提取缺陷,而分类神经网络则用于对所提取的缺陷区域进行分类识别。为了提高模型的分类精度,使用空洞卷积对UNet模型部分卷积层和池化层进行替代,以减少多次池化带来的细节丢失的问题,同时,增加多次跳跃连接,使UNet模型能够融合更多的卷积特征。结果 经实验验证表明,改进UNet模型对缺陷区域的预测精度可达到93%。根据预测结果使用分类神经网络对缺陷进行分类,经实验验证,分类的精度可达94%,满足工业要求。结论 改进的UNet模型对磁瓦缺陷提取精度有所提高,分类神经网络的缺陷分类精度较高。结合改进的UNet模型和分类神经网络能同时并有效地实现缺陷提取和分类识别,为磁瓦质量检测和性能评估打下基础。
英文摘要:
      The work aims to propose a magnetic tile defect detection and recognition algorithm based on the improved UNet model and a classification neural network for the limitation of extracting the surface defects of the magnetic tile by the traditional algorithm, and the lack of accuracy in the method for judging the defect type by artificially selecting the defect feature. The improved UNet model was used to extract defects, and the classification neural network was used to classify and identify the extracted defect regions. In order to improve the classification accuracy of the model, the cavity convolution was adopted to replace the partial convolution layer and the pooling layer of the UNet model to reduce the loss of detail caused by multiple pooling. At the same time, adding multiple jump connections enabled the UNet model to combine more convolution features. The experimental results showed that the improved UNet model could predict the defect area by 93%. According to the prediction results, classification neural network was used to classify defects. After verified by experiment, the accuracy of the classification could reach 94% and meet the industrial requirements. The improved UNet model improves the accuracy of magnetic tile defect extraction; the classified neural network has higher defect classification accuracy; and the combination of improved UNet model and classification neural network can realize the defect extraction and classification identification simultaneously and effectively, which lays a foundation for the quality detection and performance evaluation of the magnetic tile.
查看全文  查看/发表评论  下载PDF阅读器
关闭

关于我们 | 联系我们 | 投诉建议 | 隐私保护 | 用户协议

您是第19513304位访问者    渝ICP备15012534号-3

版权所有:《表面技术》编辑部 2014 surface-techj.com, All Rights Reserved

邮编:400039 电话:023-68792193传真:023-68792396 Email: bmjs@surface-techj.com

渝公网安备 50010702501715号