Abstract

Machine vision has a wide range of applications in the field of welding. The rise of convolutional neural network (CNN) provides a new way to extract visual features of welding. Due to the limitation of the small size of our molten pool dataset, the regularization of the CNN model is necessary to prevent overfitting. We propose a coarse-grained regularization method for convolution kernels (CGRCKs), which is designed to maximize the difference between convolution kernels in the same layer. The algorithm performance was tested on our self-made dataset and other public datasets. The results show that the CGRCK method can extract multi-faceted features. Compared with L1 or L2 regularization, the proposed method works great on CNNs and introduces little overhead cost to the training.

References

References
1.
Sheng
,
J.
,
Cai
,
Y.
,
Li
,
F.
, and
Hua
,
X.
,
2017
, “
Online Detection Method of Weld Penetration Based on Molten Pool Morphology and Metallic Vapor Radiation for Fiber Laser Welding
,”
Int. J. Adv. Manuf. Technol.
,
92
(
1–4
), pp.
231
245
. 10.1007/s00170-017-0129-0
2.
Yong
,
Y.
,
Fu
,
W.
,
Deng
,
Q.
, and
Chen
,
D.
,
2017
, “
A Comparative Study of Vision Detection and Numerical Simulation for Laser Cladding of Nickel-Based Alloy
,”
J. Manuf. Process.
,
28
(
2
), pp.
364
372
. 10.1016/j.jmapro.2017.03.004
3.
Liu
,
Z.
,
Wu
,
C. S.
, and
Gao
,
J.
,
2013
, “
Vision-Based Observation of Keyhole Geometry in Plasma Arc Welding
,”
Int. J. Therm. Sci.
,
63
, pp.
38
45
.10.1016/j.ijthermalsci.2012.07.006
4.
Xu
,
Y. L.
,
Fang
,
G.
,
Chen
,
S.
,
Ju
,
J. Z.
, and
Zhen
,
Y.
,
2014
, “
Real-Time Image Processing for Vision-Based Weld Seam Tracking in Robotic GMAW
,”
Int. J. Adv. Manuf. Technol.
,
73
(
9–12
), pp.
1413
1425
. 10.1007/s00170-014-5925-1
5.
Shawn
,
L. S.
,
Hyung
,
K. T.
,
Jack
,
H. S.
,
Cai
,
W. W.
, and
Abell
,
J. A.
,
2015
, “
Analysis of Weld Formation in Multilayer Ultrasonic Metal Welding Using High-Speed Images
,”
ASME J. Manuf. Sci. Eng.
,
137
(
3
), p.
031016
. 10.1115/1.4029787
6.
Luo
,
M.
, and
Shin
,
Y. C.
,
2015
, “
Vision-Based Weld Pool Boundary Extraction and Width Measurement During Keyhole Fiber Laser Welding
,”
Opt. Lasers Eng.
,
64
(
12
), pp.
59
70
. 10.1016/j.optlaseng.2014.07.004
7.
Du
,
R.
,
Xu
,
Y.
,
Hou
,
Z.
,
Shu
,
J.
, and
Chen
,
S.
,
2019
, “
Strong Noise Image Processing for Vision-Based Seam Tracking in Robotic Gas Metal Arc Welding
,”
Int. J. Adv. Manuf. Technol.
,
101
(
5–8
), pp.
2135
2149
. 10.1007/s00170-018-3115-2
8.
Zheng
,
P.
,
Chen
,
J.
,
Ye
,
S.
, and
Wang
,
L.
,
2018
, “
Classification of Arc Welding Joints Images Based on Convolutional Neural Network
,”
2018 12th IEEE International Conference on Anti-Counterfeiting, Security, and Identification (ASID)
,
Xiamen, Fujian
,
Nov. 19–21
, pp.
31
34
.
9.
Chen
,
Z.
,
Huang
,
G.
,
Lu
,
C.
, and
Chen
,
G.
,
In press
, “
Automatic Recognition of Weld Defects in TOFD D-Scan Images Based on Faster R-CNN
,”
J. Test. Eval.
,
48,
. 10.1520/JTE20170563
10.
Khumaidi
,
A.
,
Yuniarno
,
E. M.
, and
Purnomo
,
M. H.
,
2017
, “
Welding Defect Classification Based on Convolution Neural Network (CNN) and Gaussian Kernel
,”
2017 International Seminar on Intelligent Technology and Its Applications (ISITIA)
,
Surabaya, Indonesia
,
Aug. 28–29
, pp.
261
265
.
11.
Liu
,
T.
,
Bao
,
J.
,
Wang
,
J.
, and
Zhang
,
Y.
,
2018
, “
A Hybrid CNN–LSTM Algorithm for Online Defect Recognition of CO2 Welding
,”
Sensors
,
18
(
12
),
Article No. 4369
. 10.3390/s18124369
12.
Günther
,
J.
,
Pilarski
,
M. P.
,
Helfrich
,
G.
,
Shen
,
H.
, and
Dieopold,
,
K.
,
2016
, “
Intelligent Laser Welding Through Representation, Prediction, and Control Learning: an Architecture With Deep Neural Networks and Reinforcement Learning
,”
Mechatronics
,
34
, pp.
1
11
.10.1016/j.mechatronics.2015.09.004
13.
Zhang
,
W. J.
,
Yang
,
G.
,
Lin
,
Y.
,
Ji
,
C.
, and
Gupta
,
M. M.
,
2018
, “
On Definition of Deep Learning
,”
IEEE 2018 World Automation Congress (WAC)
,
Stevenson, WA
,
June 3–6
, pp.
232
236
.
14.
Deng
,
J.
,
Dong
,
W.
,
Socher
,
R.
,
Li
,
L. J.
, and
Li
,
F. F.
,
2009
, “
ImageNet: A Large-Scale Hierarchical Image Database
,”
2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009)
,
Miami, FL
,
June 20–25
, pp.
248
255
.
15.
Lin
,
T. Y.
,
Maire
,
M.
,
Belongie
,
S.
,
Hays
,
J.
, and
Zitnick
,
C. L.
,
2014
, “
Microsoft COCO: Common Objects in Context
,”
The 13th European Conference on Computer Vision (ECCV 2014)
,
Zurich, Switzerland
,
Sept. 6–12
, pp.
740
755
.
16.
Krizhevsky
,
A.
,
Sutskever
,
I.
, and
Hinton
,
G.
,
2012
, “
ImageNet Classification With Deep Convolutional Neural Networks
,”
Adv. Neural Inform. Process. Syst.
,
25
(
2
), pp.
1097
1105
. 10.1145/3065386
17.
Simonyan
,
K.
, and
Zisserman
,
A.
,
2015
, “
Very Deep Convolutional Networks for Large-Scale Image Recognition
,”
The 3rd International Conference on Learning Representations (ICLR2015)
,
San Diego, CA
,
May 7–9
,
arXiv: 1409.1556
.
18.
Sabour
,
S.
,
Frosst
,
N.
, and
Hinton
,
G. E.
,
2017
, “
Dynamic Routing Between Capsules
,”
31st Confetence on Neural Information Processing Systems (NIPS2017)
,
Long Beach, CA
,
Dec. 4–9
, pp.
3856
3866
.
19.
Girshick
,
R.
,
Donahue
,
J.
,
Darrelland
,
T.
, and
Malik
,
J.
,
2014
, “
Rich Feature Hierarchies for Object Detection and Semantic Segmentation
,”
2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR2014)
,
Columbus, OH
,
June 23–28
, pp.
580
587
.
20.
Girshick
,
R.
,
2015
, “
Fast R-CNN
,”
2015 IEEE International Conference on Computer Vision (ICCV)
,
Santiago, Chile
,
Dec. 7–13
, pp.
1440
1448
.
21.
Ren
,
S.
,
He
,
K.
,
Girshick
,
R.
, and
Sun
,
J.
,
2015
, “
Faster R-CNN: Towards Real-Time Object Detection With Region Proposal Networks
,”
IEEE Trans. Pattern Anal. Mach. Intell.
,
39
(
6
), pp.
1137
1149
. 10.1109/TPAMI.2016.2577031
22.
Inc
,
G.
,
2015
, “
Convolutional, Long Short-Term Memory, Fully Connected Deep Neural Networks
,”
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
,
South Brisbane
,
Apr. 19–24
, pp.
4580
4584
.
23.
Sainath
,
T. N.
,
Kingsbury
,
B.
,
Saon
,
G.
, and
Soltau
,
H.
,
2015
, “
Deep Convolutional Neural Networks for Large-Scale Speech Tasks
,”
Neural Networks
,
64
, pp.
39
48
.10.1016/j.neunet.2014.08.005
24.
Hazirbas
,
C.
,
Ma
,
L.
,
Domokos
,
C.
, and
Cremers
,
D.
,
2016
, “
FuseNet: Incorporating Depth Into Semantic Segmentation Via Fusion-Based CNN Architecture
,”
2016 Asian Conference on Computer Vision (ACCV 2016)
,
Taipei, Taiwan
,
Nov. 20–24
, pp.
213
228
.
25.
Lin
,
G.
,
Milan
,
A.
,
Shen
,
C.
, and
Reid
,
I.
,
2017
, “
RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
,”
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR2017)
,
Honolulu, HI
,
July 21–26
, pp.
5168
5177
.
26.
Goodfellow
,
I.
,
Pouget
,
A. J.
,
Mirza
,
M.
,
Bing
,
X.
,
Warde
,
F. D.
, and
Ozair
,
S.
,
2014
, “
Generative Adversarial Nets
,”
International Conference on Neural Information Processing Systems
,
Montreal
,
Dec. 8–13
, pp.
2672
2680
.
27.
Arjovsky
,
M.
,
Chintala
,
S.
, and
Bottou
,
L.
,
2017
, “
Wasserstein GAN
,”
The 34th International Conference on Machine Learning (ICML 2017)
,
Sydney
,
Aug. 11–15
, pp.
214
223
.
28.
Brock
,
A.
,
Donahue
,
J.
, and
Simon
,
Y. K.
,
2019
, “
Large Scale GAN Training for High Fidelity Natural Image Synthesis
,”
The Seventh International Conference on Learning Representations (ICLR2019)
,
New Orleans, LA
,
May 6–9
,
arXiv: 1809.11096
.
29.
Ioffe
,
S.
, and
Szegedy
,
C.
,
2015
, “
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
,”
International Conference on International Conference on Machine Learning
,
Lille
,
July 6–11
, pp.
448
456
.
30.
Brock
,
A.
,
Lim
,
T.
,
Ritchie
,
J. M.
, and
Weston
,
N.
,
2017
, “
Neural Photo Editing With Introspective Adversarial Networks
,”
The Fifth International Conference on Learning Representations (ICLR2017)
,
Toulon
,
Apr. 24–26
,
arXiv: 1609.07093
.
31.
Xiao
,
L.
,
Bahri
,
Y.
,
Sohl
,
D. J.
,
Schoenholz
,
S. S.
, and
Pennington
,
J.
,
2018
, “
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
,”
The 35th International Conference on Machine Learning (ICML 2018)
,
Stockholm
,
July 10–15
, pp.
5389
5398
.
32.
Ruder
,
S.
,
2017
, “
An Overview of Multi-Task Learning in Deep Neural Networks
,”
e-print arXiv:1706.05098
.
33.
Modi
,
S.
,
Lin
,
Y.
,
Cheng
,
L.
,
Yang
,
G.
,
Liu
,
L.
, and
Zhang
,
W. W. J.
,
2011
, “
A Socially Inspired Framework for Human State Inference Using Expert Opinion Integration
,”
IEEE/ASME Trans. Mechatronics
,
16
(
5
), pp.
874
878
. 10.1109/TMECH.2011.2161094
34.
Szegedy
,
C.
,
Liu
,
W.
,
Jia
,
Y.
,
Sermanet
,
P.
,
Reed
,
S.
, and
Anguelov
,
D.
,
2015
, “
Going Deeper With Convolutions
,”
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR2015)
,
Boston, MA
,
June 8–10
, pp.
1
9
.
35.
He
,
K.
,
Zhang
,
X.
,
Ren
,
S.
, and
Sun
,
J.
,
2015
, “
Deep Residual Learning for Image Recognition
,”
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR2016)
,
Las Vegas, Nevada
,
June 26–July 1
, pp.
770
778
.
36.
Huang
,
G.
,
Liu
,
Z.
,
Laurens
,
V. D. M.
, and
Weinberger
,
K. Q.
,
2017
, “
Densely Connected Convolutional Networks
,”
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR2017)
,
Honolulu, HI
,
July 21–26
, pp.
2261
2269
.
37.
Mahsereci
,
M.
,
Balles
,
L.
,
Lassner
,
C.
, and
Henning
,
P.
,
2017
, “
Early Stopping Without a Validation Set
,”
e-print arXiv:1703.09580
.
38.
Srivastava
,
N.
,
Hinton
,
G.
,
Krizhevsky
,
A.
,
Sutskever
,
I.
, and
Salakhutdinov
,
R.
,
2014
, “
Dropout: A Simple Way to Prevent Neural Networks From Overfitting
,”
J. Mach. Learn. Res.
,
15
(
1
), pp.
1929
1958
.
39.
Ghiasi
,
G.
,
Lin
,
T. Y.
, and
Le
,
Q. V.
,
2018
, “
DropBlock: A Regularization Method for Convolutional Networks
,”
Thirty-Second Conference on Neural Information Processing Systems (NIPS2018)
,
Montreal
,
Dec. 3–8
, pp.
10727
10737
.
40.
Prakash
,
A.
,
Storer
,
J.
,
Florencio
,
D.
, and
Zhang
,
C.
,
2018
, “
RePr: Improved Training of Convolutional Filters
,”
2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR2019)
,
Long Beach, CA
,
June 16–20
, pp.
10666
10675
.
41.
Song
,
K.
, and
Yan
,
Y.
,
2013
, “
A Noise Robust Method Based on Completed Local Binary Patterns for Hot-Rolled Steel Strip Surface Defects
,”
Appl. Surf. Sci.
,
285
(
part_PB
), pp.
858
864
. 10.1016/j.apsusc.2013.09.002
42.
Xiao
,
H.
,
Rasul
,
K.
, and
Vollgraf
,
R.
,
2017
, “
Fashion-MNIST: A Novel Image Dataset for Benchmarking Machine Learning Algorithms
,”
e-print arXiv:1708.07747
.
43.
Zhang
,
W. J.
, and
Lin
,
Y.
,
2010
, “
On the Principle of Design of Resilient Systems—Application to Enterprise Information Systems
,”
Enterp. Inf. Syst.
,
4
(
2
), pp.
99
110
. 10.1080/17517571003763380
You do not currently have access to this content.