基于卷积神经网络的玛钢管件表面缺陷检测仿真  

Surface defect detection simulation of malleable iron based on convolutional neural network

作　　者：白杰 江先亮[1] BAI Jie;JIANG Xianliang(Faculty of Electrical Engineering and Computer Science,Ningbo University,Ningbo,Zhejiang 315211,China)

机构地区：[1]宁波大学信息科学与工程学院,浙江宁波315211

出　　处：《江苏大学学报（自然科学版）》2024年第4期449-455,463,共8页Journal of Jiangsu University：Natural Science Edition

基　　金：浙江省基础公益研究计划项目(LTGN24F020003)。

摘　　要：针对现有检测算法HRNetV2p无法很好地平衡各尺度缺陷的检测精度等问题,在HRNetV2p中引入一种结合通道注意力机制的特征融合模块,自适应地调整融合特征中空间-语义信息的比率,解决浅层特征缺乏语义信息的问题.建立一个玛钢管件表面缺陷检测数据集IIDD,进行数据标注及数据统计.在HRNetV2p网络中引入CG密集跳跃传输单元及CG自适应融合模块,通过整合、重新校准和重新整合3个操作自适应地调整浅层特征空间-语义信息比率.给出了试验的设置以及评价指标,完成了改进的玛钢管件表面缺陷检测算法在IIDD测试集上的性能试验.结果表明,改进后的HRNetV2p算法在IIDD上的平均检测精度AP 50为91.3%,相比原始HRNetV2p提高了2.6%,其中对大、中、小尺度缺陷的平均检测精度分别提高了2.7%、2.7%、5.6%.To solve the problems that the existing detection algorithm of HRNetV2p could not balance the detection accuracy of defects at various scales,the feature fusion module combined with channel attention mechanism was introduced into the detection algorithm of HRNetV2p,which could adaptively adjust the ratio of spatial-semantic information in the fusion features and could improve the network ability to preserve semantic information in shallow features.The surface defect detection dataset of IIDD for malleable iron was established for data labelling and data statistics.The CG dense skip transmission unit and the CG adaptive fusion module were introduced into the HRNetV2p network for adaptively adjusting the spatial-semantic information ratio of the front-layer features through three operations of integration,recalibration and reintegration.The experimental setup and evaluation index were given,and the performance experiments of the improved HRNetV2p algorithm on the malleable iron surface defect dataset of IIDD were completed.The results show that the average detection accuracy AP 50 of the improved HRNetV2p algorithm on IIDD is 91.3%,which is 2.6%higher than the average detection accuracy of the original HRNetV2p.The detection accuracies of large,medium and small scale defects are improved by 2.7%,2.7%and 5.6%,respectively.

关 键 词：玛钢管件 表面缺陷检测仿真 卷积神经网络 注意力机制 HRNetV2p 特征融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]