基于Faster R-卷积神经网络的金属点阵结构缺陷识别方法

doi:10.3969/j.issn.1000-1093.2019.11.018

兵工学报 ›› 2019, Vol. 40 ›› Issue (11): 2329-2335.doi: 10.3969/j.issn.1000-1093.2019.11.018

基于Faster R-卷积神经网络的金属点阵结构缺陷识别方法

张玉燕^1，2，李永保^1，2，温银堂^1，2，张芝威^1，2

（1.燕山大学电气工程学院，河北秦皇岛 066004； 2.燕山大学测试计量技术及仪器河北省重点实验室, 河北秦皇岛 066004)

收稿日期:2019-04-29 修回日期:2019-04-29 上线日期:2019-12-31
通讯作者: 温银堂（1978—），男，研究员，博士生导师 E-mail:ytwen@ysu.edu.cn
作者简介:张玉燕（1976—），女，教授，博士生导师。E-mail: yyzhang@ysu.edu.cn
基金资助:
河北省自然科学基金项目(E2017203240)

Internal Defect Detection of Metal Three-dimensional Multi-layer Lattice Structure Based on Faster R-CNN

ZHANG Yuyan^1，2， LI Yongbao^1，2， WEN Yintang^1，2， ZHANG Zhiwei^1，2

(1.School of Electrical Engineering，Yanshan University, Qinhuangdao 066004, Hebei, China;2.Hebei Province Key Laboratory of Measuring and Testing technologies and Instruments，Yanshan University, Qinhuangdao 066004, Hebei, China)

Received:2019-04-29 Revised:2019-04-29 Online:2019-12-31

摘要/Abstract

摘要： 采用增材制造技术制备的金属三维点阵结构可能存在裂纹、未熔合、断层等缺陷，导致金属点阵结构的结构-功能性能下降，为此提出一种金属三维多层点阵结构内部缺陷的检测方法。在Faster R-卷积神经网络架构基础上设计特征提取网络，结合工业CT扫描图片，对得到的断层灰度图像中缺陷部位进行快速、准确、智能检测识别和定位。实验验证结果表明，对金属三维多层点阵结构样件的内部典型缺陷识别率达到99.5%.

关键词: 金属点阵结构, 缺陷识别, 无损检测, CT扫描图像, FasterR-卷积神经网络

Abstract: The cracks, incomplete fusion, faults and other defects may exist in the metal three-dimensional lattice structure prepared by additive manufacturing technology, which lead to the decline of structure-functional performance of metal lattice structure. A Faster R-CNN-based internal defect detection method is proposed for metal three-dimensional multi-layer lattice structure. A feature extraction network is designed on the basis of the Faster R-CNN network architecture. It makes the defects in the obtained gray-scale image and the CT scanning image be detected and positioned quickly, accurately and intelligently. The experimental results show that the recognition rate of the typical internal defects of metal three-dimensional multi-layer lattice structure sample is 99.5%. Key

Key words: metallatticestructure, defectdetection, non-destructivetesting, CTscanningimage, FasterR-convolutionalneuralnetwork

中图分类号:

TG115.281

张玉燕，李永保，温银堂，张芝威. 基于Faster R-卷积神经网络的金属点阵结构缺陷识别方法[J]. 兵工学报, 2019, 40(11): 2329-2335.

ZHANG Yuyan， LI Yongbao， WEN Yintang， ZHANG Zhiwei. Internal Defect Detection of Metal Three-dimensional Multi-layer Lattice Structure Based on Faster R-CNN[J]. Acta Armamentarii, 2019, 40(11): 2329-2335.

参考文献

［1］赵冰, 李志强, 侯红亮, 等. 金属三维点阵结构制备技术研究进展［J］. 稀有金属材料与工程, 2016, 45(8): 2189-2200.
ZHAO B, LI Z Q, HOU H L, et al. Research progress on fabrication methods of metal three dimensional lattice structure［J］. Rare Metal Materials & Engineering, 2016, 45(8): 2189-2200. (in Chinese)
［2］ MINES R A W, TSOPANOS S, SHEN Y, et al. Drop weight impact behaviour of sandwich panels with metallic micro lattice cores［J］. International Journal of Impact Engineering, 2013, 60(10):120-132.
［3］ MASKERY I, HUSSEY A, PANESAR A, et al. An investigation into reinforced and functionally graded lattice structures［J］. Journal of Cellular Plastics, 2017, 53(2): 151-165.
［4］ LIU Y J, LI S J, WANG H L, et al. Microstructure, defects and mechanical behavior of beta-type titanium porous structures manufactured by electron beam melting and selective laser melting［J］. Acta Materialia, 2016, 113:56-67.
［5］ HORN T J, HARRYSSON O L A, MARCELLIN-LITTLE D J, et al. Flexural properties of Ti6Al4V rhombic dodecahedron open cellular structures fabricated with electron beam melting ［J］. Additive Manufacturing, 2014, 1/2/3/4:2-11.
［6］ TANIGUCHI N, FUJIBAYASHI S, TAKEMOTO M, et al. Effect of pore size on bone ingrowth into porous titanium implants fabricated by additive manufacturing: an in vivo, experiment［J］. Materials Science & Engineering C：Materials for Biological Applications, 2016, 59:690-701.
［7］ LIU F, ZHANG D Z, ZHANG P, et al. Mechanical properties of optimized diamond lattice structure for bone scaffolds fabricated via selective laser melting［J］. Materials, 2018, 11(3):374.
［8］ WARMUTH F, OSMANLIC F, ADLER L, et al. Fabrication and characterisation of a fully auxetic 3D lattice structure via selective electron beam melting［J］. Smart Materials & Structures, 2017, 26(2):025013.
［9］ USHIJIMA K, NAGAKURA Y, YOSHIMURA A. Estimation of mechanical properties of micro-lattice structure manufactured by selective laser metal melting［C］∥Proceedings of Mechanical Engineering Congress. Japan: The Japan Society of Mechanical Engineers, 2017.

［10］ MASKERY I, ABOULKHAIR N T, AREMU A O, et al. A mechanical property evaluation of graded density Al-Si10-Mg lattice structures manufactured by selective laser melting［J］. Materials Science & Engineering A, 2016, 670:264-274.
［11］ VAN H B, APERS Y, LIETAERT K, et al. Improving the fatigue performance of porous metallic biomaterials produced by selective laser melting［J］. Acta Biomaterialia, 2016, 47:193-202.
［12］ MERCELIS P, KRUTH J. Residual stresses in selective laser sintering and selective laser melting［J］. Rapid Prototyping Journal, 2013, 12(5): 254-265.
［13］郑世才. 我国射线检测技术近年的发展［J］. 无损检测, 2004, 26(4): 163-167.
ZHENG S C. An overview of the latest advancement of radiology in China［J］. Nondestructive Testing, 2004, 26(4): 163-167. (in Chinese)
［14］敬人可, 李建增, 周海林. 超声无损检测技术的研究进展［J］. 国外电子测量技术, 2012, 31(7): 28-30.
JING R K, LI J Z, ZHOU H L. Research progress of ultrasonic NDT technology［J］. Foreign Electronic Measurement Technology, 2012, 31(7): 28-30. (in Chinese)
［15］郭健, 张丹, 马国义, 等. 无损检测(NDT)——磁粉检测(MT)技术［J］. 工程与试验, 2011, 51(3): 55-58.
GUO J, ZHANG D, MA G Y, et al. Nondestructive testing-magnetic particle testing technology［J］. Engineering & Test, 2011, 51(3): 55-58. (in Chinese)
［16］刘晴岩. 液体渗透检测的可靠性［J］. 无损检测, 2002, 24(9): 381-383.
LIU Q Y. Reliability of liquid penetrant inspection［J］. Nondestructive Testing, 2002, 24(9): 381-383. (in Chinese)
［17］ GARCA-MARTN J, GMEZ-GIL J, VZQUEZ-SNCHEZ E. Non-destructive techniques based on eddy current testing［J］. Sensors, 2011, 11(3): 2525.
［18］ HINTON G E. Reducing the dimensionality of data with neural networks［J］. Science, 2006, 313(5786): 504-507.
［19］ KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks［C］∥Proceedings of International Conference on Neural Information Processing Systems. Lake Tahoe, NV, US:Curran Associates Inc.，2012:1097-1105.
［20］ ZEILER M D, FERGUS R. Visualizing and understanding con-volutional networks［C］∥Proceedings of European Conference on Computer Vision. Zurich, Switzerland：Springer, 2014: 818-833.
［21］ SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions［C］∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA，US: IEEE, 2015: 1-9.
［22］ YAN Z, ZHANG H, PIRAMUTHU R, et al. HD-CNN: hierarchical deep convolutional neural networks for large scale visual recognition［C］∥Proceedings of IEEE International Conference on Computer Vision. Santiago, Chile: IEEE Computer Society, 2015: 1534-1541.
［23］ HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition［C］∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Lake Tahoe, NV, US: IEEE Computer Society, 2016: 770-778.
［24］ SANDE K E A V D, UIJLINGS J R R, GEVERS T, et al. Segmentation as selective search for object recognition［C］∥Proceedings of International Conference on Computer Vision. Barcelona, Spain: IEEE Computer Society, 2011:1879-1886.
［25］ GIRSHICK R. Fast R-CNN［C］∥Proceedings of IEEE International Conference on Computer Vision. Santiago, Chile: IEEE Computer Society, 2015:1440-1448.
［26］ REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(6):91-99.
［27］ XIANG X Z, NING L, GUO X L, et al. Engineering vehicles detection based on modified faster R-CNN for power grid surveillance［J］. Sensors, 2018, 18(7):2258.
［28］ ZHANG Q X, LIN G H, ZHANG Y M, et al. Wildland forest fire smoke detection based on faster R-CNN using synthetic smoke images［J］. Procedia Engineering, 2018, 211:441-446.

第40卷
第11期2019 年11月兵工学报ACTA
ARMAMENTARIIVol.40No.11Nov.2019

[1]	潘勤学，刘帅，肖定国，靳鑫. 基于超声技术的齿轮残余应力测量方法研究[J]. 兵工学报, 2015, 36(9): 1757-1765.
[2]	方海燕，刘小勇，乐静，郭俊杰. 球壳表面缺陷的光学复合式非接触测量[J]. 兵工学报, 2011, 32(7): 860-865.
[3]	朱敏，卢洪义，李海燕. 固体火箭发动机三维可视化无损检测系统设计[J]. 兵工学报, 2008, 29(7): 891-896.
[4]	尹大伟，徐滨士，董世运，董丽虹，冯晨. 不同检测环境下磁记忆信号变化研究[J]. 兵工学报, 2007, 28(3): 319-323.
[5]	杨铁滨，王黎钦，古乐，郑德志. 氮化硅陶瓷球加工缺陷分析与无损检测技术研究[J]. 兵工学报, 2007, 28(3): 353-357.
[6]	1:陈树越;2:路宏年. 工业X射线透视成像中的散射及其校正[J]. 兵工学报, 2004, 25(2): 163-166.
[7]	邵自强、孙江政、仪建红、郝红英. 固体火箭推进剂包覆层激光全息无损检测研究[J]. 兵工学报, 1996, 17(2): 123-126.
[8]	赵川东. 一种新的毫米波CT无损检测系统的理论与实验研究[J]. 兵工学报, 1991, 12(2): 86-92.

基于Faster R-卷积神经网络的金属点阵结构缺陷识别方法

Internal Defect Detection of Metal Three-dimensional Multi-layer Lattice Structure Based on Faster R-CNN

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价