摘要
针对传统卷积神经网络(Convolutional neural network,CNN)应用于焊缝缺陷识别时,池化模型适应差及特征选择能力低、以及易导致过拟合问题,提出了一种基于改进卷积神经网络(Improved pooling model and feature selection of CNN,IPFCNN)的焊缝缺陷识别方法。结合焊缝缺陷图像本身的特点,对传统平均池化模型做出改进,提出一种综合考虑池化域与其所在区域特征图分布的池化模型;为增强模型特征选择能力,提出将随机森林与卷积神经网络相结合的强化特征选择方法。以某汽轮机制造过程中焊缝缺陷识别案例对所提方法进行了验证和说明,结果表明提出的池化模型在处理不同特征分布的池化域时具有动态自适应性,并通过提高特征选择能力,使得所提方法比传统CNN方法具有更高的缺陷识别率。
Aiming at the problems of poor adaptability of pooling model,low feature selection ability and over-fitting when traditional convolutional neural network(CNN)is applied to weld defect recognition,a new method of weld defect recognition based on improved pooling model and feature selection CNN(IPFCNN)is proposed.According to the characteristics of weld defect image,the average pooling model is improved by taking into account the pooling region and its feature distribution.In order to enhance the feature selection ability of the CNN,an enhanced feature selection method combining random forest and CNN is proposed.A case study of weld defect recognition in the manufacturing process of steam turbine is to illustrate the work.The results show that the proposed method IPFCNN has dynamic adaptability in dealing with pooling region with different feature distributions and improving the feature selection ability,and it has higher defect recognition rate than the traditional CNN method.
作者
姜洪权
贺帅
高建民
王荣喜
高智勇
王晓桥
夏锋社
程雷
JIANG Hongquan;HE Shuai;GAO Jianmin;WANG Rongxi;GAO Zhiyong;WANG Xiaoqiao;XIA Fengshe;CHENG Lei(State Key Laboratory for Manufacturing Systems Engineering,Xi’an Jiaotong University,Xi’an 710049;Laboratory for Manufacturing and Productivity,Massachusetts Institute of Technology,Cambridge,02139 USA;Shaanxi Special Equipment Inspection and Testing Institute,Xi’an 710048)
出处
《机械工程学报》
EI
CAS
CSCD
北大核心
2020年第8期235-242,共8页
Journal of Mechanical Engineering
基金
国家重点研发计划(2017YFF0210502)
陕西省自然科学基础研究计划(2019JM-214)
陕西省质量人才计划(3211000781)资助项目。
关键词
焊缝缺陷识别
卷积神经网络
池化模型
特征强化选择
深度学习
weld defect recognition
convolutional neural network
pooling strategy
feature enhancement selection
deep learning