An Improved Convolutional Neural Network for Weld Defect Recognition

doi:10.3901/JME.2020.08.235

Abstract

Abstract: 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.

Key words: weld defect recognition, convolutional neural network, pooling strategy, feature enhancement selection, deep learning

CLC Number:

TP391

JIANG Hongquan, HE Shuai, GAO Jianmin, WANG Rongxi, GAO Zhiyong, WANG Xiaoqiao, XIA Fengshe, CHENG Lei. An Improved Convolutional Neural Network for Weld Defect Recognition[J]. Journal of Mechanical Engineering, 2020, 56(8): 235-242.

References

[1] 余永维,殷国富,殷鹰,等. 基于深度学习网络的射线图像缺陷识别方法[J]. 仪器仪表学报,2014,35(9):2012-2019. YU Yongwei,YIN Guofu,YIN Ying,et al. Defect recognition for radiographic image based on deep learning network[J]. Chinese Journal of Scientific Instrument,2014,35(9):2012-2019.
[2] HAN Liu,GUO Runyuan. Detection and identification of SAWH pipe weld defects based on X-ray image and CNN[J]. Chinese Journal of Scientific Instrument,2018,39(4):247-256.
[3] MALARVEL M. An improved version of Otsu's method for segmentation of weld defects on X-radiography images[J]. Optik-International Journal for Light and Electron Optics,2017,109:109-118.
[4] NAFAA N,DJEMEL Z,LATIFA H. Fusion-based shape descriptor for weld defect radiographic image:retrieval[J]. International Journal of Advanced Manufacturing Technology,2013,68(9):2815-2832.
[5] JIANG Hongquan,ZHAO Yalin,GAO Jianmin,et al. Weld defect classification based on texture features and principal component analysis[J]. Insight,2016,58(4):194-200.
[6] JIANG Hongquan,WANG Rongxi,GAO Zhiyong,et al. Classification of weld defects based on the analytical hierarchy process and dempster-shafer evidence theory[J]. Journal of Intelligent Manufacturing,2017(6):1-12.
[7] GOUMEIDANE A B,BOUZAIENI A,NACEREDDINE N,et al. Bayesian networks-based defects classes discrimination in weld radiographic images[C]//International Conference on Computer Analysis of Images & Patterns. Springer,Malta,2015.
[8] MEKHALFA F,NACEREDDINE N. Multiclass classification of weld defects in radiographic images based on support vector machines[C]//Tenth International Conference on Signal-image Technology & Internet-based Systems. IEEE Computer Society,2014,Marrakech,Morocco.
[9] BANIUKIEWICZ P. Automated defect recognition and identification in digital radiography[J]. Journal of Nondestructive Evaluation,2013,33(3):1-8.
[10] 卢泓宇,张敏,刘奕群,等. 卷积神经网络特征重要性分析及增强特征选择模型[J]. 软件学报,2017,28(11):2879-2890. LU Hongyu,ZHANG Min,LIU Yiqun,et al. Convolution neural network feature importance analysis and feature selection enhanced model[J]. Journal of Software,2017,28(11):2879-2890.
[11] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,37(9):1904-1916.
[12] CHEN Junwen,LIU Zhigang,WANG Hongrui,et al. Automatic defect detection of fasteners on the catenary support device using deep convolutional neural network[J]. IEEE Transactions on Instrumentation & Measurement,2018,67(2):257-269.
[13] LUO Hengliang,YANG Yi,TONG Bei,et al. Traffic sign recognition using a multi-task convolutional neural network[J]. IEEE Transactions on Intelligent Transportation Systems,2017,19(4):1100-1111.
[14] WANG Lihua,ZHAO Xiaoping,WU Jiaxin,et al. Motor fault diagnosis based on short-time fourier transform and convolutional neural network[J]. Chinese Journal of Mechanical Engineering,2017,30(6):1357-1368.
[15] 姜洪开,邵海东,李兴球. 基于深度学习的飞行器智能故障诊断方法[J]. 机械工程学报,2019,55(7):27-34. JIANG Hongkai,SHAO Haidong,LI Xingqiu. Deep learning theory with application in intelligent fault diagnosis of aircraft[J]. Journal of Mechanical Engineering,2019,55(7):27-34.
[16] 胡茑庆,陈徽鹏,程哲,等.基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法[J]. 机械工程学报,2019,55(7):9-18. HU Niaoqing,CHEN Huipeng,CHENG Zhe,et al. Fault diagnosis for planetary gearbox based on EMD and deep convolutional neural networks[J]. Journal of Mechanical Engineering,2019,55(7):9-18.
[17] WANG Yunfeng,ZHOU Wengang,ZHANG Qilin,et al. Weighted multi-region convolutional neural network for action recognition with low-latency online prediction[C]//2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW),July 23-27 San Diego,2018.
[18] WU Xiang,HE Ran,SUN Zhenan,et al. A light CNN for deep face representation with noisy labels[J]. IEEE Transactions on Information Forensics & Security,2018,13(11):2884-2896.
[19] KHUMAIDI A,YUNIARNO E M,PURNOMO M H. Welding defect classification based on convolution neural network (CNN) and Gaussian kernel[C]//International Seminar on Intelligent Technology and ITS Applications,August 28-29,2017,Surabaya,2017:261-265.
[20] XU Juefei,BODDETI V N,SAVVIDES M. Local binary convolutional neural networks[C]//IEEE Conference on Computer Vision and Pattern Recognition,July 22-25,2017,Hawaii,2017:4284-4293.
[21] 王俊,郑彤,雷鹏,等. 基于卷积神经网络的手势动作雷达识别方法[J]. 北京航空航天大学学报,2018,44(6):4-10. WANG Jun,ZHENG Tong,LEI Peng,et al. Hand gesture recognition method by radar based on convolutional neural network[J]. Journal of Beijing University of Aeronustics and Astronautics,2018,44(6):4-10.
[22] 唐浩,黄伟鹏,李哲媛,等. 基于改进的卷积神经网络的负面表情识别方法[J]. 华中科技大学学报,2015(s1):457-460. TANG Hao,HUANG Weipeng,LI Zheyuan,et al. Negative facial expression recongnition based on convolutional neutral network[J]. Journal of Huazhong University of Science and Technology,2015(s1):457-460.
[23] FUKUSHIMA K. Neocognitron:A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological Cybernetics,1980,36(4):193-202.
[24] KIRA K,RENDELL L A. The feature selection problem:traditional methods and a new algorithm[C]//Tenth National Conference on Artificial Intelligence. AAAI Press,1992:129-134.
[25] 刘万军,梁雪剑,曲海成. 不同池化模型的卷积神经网络学习性能研究[J]. 中国图象图形学报,2016,21(9):1178-1190. LIU Wanjun,LIANG Xuejian,QU Haicheng. Learning performance of convolutional neural networks with different pooling models[J]. Journal of Image and Graphics,2016,21(9):1178-1190.
[26] MURSALIN M,ZHANG Y,CHEN Y,et al. Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier[J]. Neurocomputing,2017,241:204-214.
[27] 赵帅,黄亦翔,王浩任,等. 基于随机森林与主成分分析的刀具磨损评估[J]. 机械工程学报,2017,53(21):181-189. ZHAO Shuai,HUANG Yixiang,WANG Haoren,et al. Random forest and principle components analysis based on health assessment methodology for tool wear[J]. Journal of Mechanical Engineering,2017,53(21):181-189.