Journal of Jilin University(Engineering and Technology Edition) ›› 2025, Vol. 55 ›› Issue (4): 1426-1435.doi: 10.13229/j.cnki.jdxbgxb.20230709

Previous Articles     Next Articles

Laser weld image classification based on improved Northern Goshawk optimization algorithm

Hong-bo ZOU1,2(),Qi-long LI1,2   

  1. 1.College of Electrical and New Energy，China Three Gorges University，Yichang 443000，China
    2.Hubei Provincial Key Laboratory of Cascade Hydropower and New Energy Operation and Control，Yichang 443002，China
  • Received:2023-07-27 Online:2025-04-01 Published:2025-06-19

RICH HTML

 0   

PDF (PC)

22

Abstract:

In order to solve the problems of high computational complexity and low recognition and classification accuracy in the recognition of various types of laser welding seams， this paper proposes a laser welding seam image recognition and classification algorithm based on the improved Northern Goshawk algorithm（UNGO）， which combines the traditional support vector machine algorithm（SVM） with the improved Northern Goshawk optimization algorithm（UNGO-SVM）， and increases the algorithm search ability through chaos optimization and Levi's greedy learning strategy in flight. At the same time， it helps the algorithm overcome the situation of falling into local optimum， and improves the convergence accuracy and image classification accuracy of the algorithm. The experimental results show that this algorithm （UNGO-SVM） improves the classification accuracy to 99.15% while ensuring the convergence of the algorithm. Finally， compared with SVM， NGO-SVM，DOA-SVM，GOA-SVM improves by 21%，5% ，10% and 11% respectively， proving the feasibility and strong utilization value of this method.

Key words: Northern Goshawk algorithm, image recognition classification, support vector machine, cubic chaos, greedy learning strategy

CLC Number: 

  • TG409

Fig.1

Sine map chaotic distribution， histogram"

Fig.2

Overall flowchart"

Fig.3

Image processing of various types of seams"

Table 1

Classified comparison chart of weld feature parameters"

序号面积最佳阈值长度最小宽度最大宽度

像素

个数

组号
193.634.5121.562.758.2138 4464
289.364.6220.782.657.9836 8704
361.453.7515.482.186.1930 4522
424.962.128.321.125.7815 3631
525.122.158.171.246.0217 3541
671.554.2318.652.366.7832 4523

7

8

9

10

11

12

72.15

70.69

58.85

62.36

25.52

24.87

4.16

4.06

3.71

3.77

2.20

2.22

17.98

16.61

13.85

14.51

8.25

8.35

2.47

2.33

2.22

2.17

1.62

1.25

7.12

6.81

6.16

6.24

6.11

6.07

33 847

32 993

31 185

30 419

18 854

17 862

3

3

2

2

1

1

13

14

15

16

17

18

19

20

?

369

370

91.65

90.78

62.85

71.63

60.78

61.55

26.01

25.89

?

72.56

94.23

4.68

4.58

3.66

4.11

3.84

3.75.

2.26

2.14

?

4.18

4.80

20.69

21.85

12.96

18.88

15.24

16.22

8.99

8.65

?

19.79

21.00

2.76

2.57

2.19

2.51

2.01

2.21

1.51

1.63

?

2.43

2.70

8.64

8.28

6.16

6.88

6.33

6.22

6.10

6.08

?

7.01

8.06

37 895

36 824

30 855

34 789

31 122

30 888

16 788

15 793

?

33 786

37 321

4

4

2

3

2

2

1

1

?

3

4

Table 2

Comparison of parameter optimization results"

优化

算法

型号

类别

最优

值c

最优

值g

正确率/%运行时间/s
UNGO

U型

L型

O型

S型

1.25

2.16

7.85

5.42

1.76

2.57

4.55

6.13

99.13

98.86

100

97.06

4.89

4.65

5.03

4.73

NGO

U型

L型

O型

S型

1.28

2.45

6.69

6.65

1.77

2.87

5.63

6.01

92.53

93.75

91.77

94.96

2.89

2.88

2.45

2.38

GOA

U型

L型

O型

S型

8.25

15.23

10.15

8.83

0.45

11.99

15.10

4.56

82.45

80.56

81.14

84.28

10.88

11.03

10.45

12.62

DOA

U型

L型

O型

S型

0.15

0.82

0.45

0.32

1.87

1.05

0.98

2.06

86.36

87.50

90.78

89.78

3.06

3.65

3.89

3.97

Fig.4

Comparison of results between training set and test set of support vector machine（SVM） classification algorithm"

Fig.5

Comparison of results between training set and test set of Northern Goshawk optimization support vector machine （NGO-SVM） classification algorithm"

Fig.6

Comparison of results between training set and test set of upgrade Northern Goshawk optimization support vector machine （UNGO-SVM） classification algorithm"

Fig.7

Comparison of results between training and testing sets of Grasshopper Optimization Algorithm support vector machine （GOA-SVM） classification algorithm"

Fig.8

Comparison of results between the training set and the test set of Dragonfly Optimization Algorithm support vector machine （DOA-SVM） classification algorithm"

Table 3

Comparison of recognition rates of various classification algorithms"

分类算法

样本

分类

样本

个数

正确识别个数错误识别个数总识别率/%
DOA-SVM

1

2

3

4

122

85

71

92

110

76

60

82

11

12

11

10

90.03
NGO-SVM

1

2

3

4

122

85

71

92

117

82

69

87

5

3

2

5

95.99
GOA-SVM

1

2

3

4

122

85

71

92

107

71

55

76

15

16

16

16

88.5
SVM

1

2

3

4

122

85

71

92

95

63

53

72

27

22

18

20

78.5
UNGO-SVM

1

2

3

4

122

85

71

92

122

85

70

91

0

0

1

1

99.5

Fig.9

Comparison of fitness convergence curves of UNGO and NGO algorithms"

[1] 李想, 黄瑞生, 滕彬, 等. 真空激光焊接技术研究进展[J]. 电焊机, 2023, 53(4): 46-55.
Li Xiang, Huang Rui-sheng, Teng Bin, et al. Research progress of vacuum laser welding technology[J]. Welding Machine, 2023, 53(4): 46-55.
[2] 岳考捷, 贾晨, 王云嵩, 等. 镍基合金薄板激光焊接研究进展[J]. 光电工程, 2022, 49(12): 26-44.
Yue Kao-jie, Jia Chen, Wang Yun-song, et al. Research progress in laser welding of nickel base alloy sheet[J]. Optoelectronics, 2022, 49(12): 26-44.
[3] 孙悦庆, 苏统华, 李松泽. 基于多模型融合的焊接质量检测系统的设计与实现[C]//中国金属学会第十三届中国钢铁年会论文集——4.轧制与热处理,重庆, 中国, 2022: 133-142.
[4] 兰凌霄. 基于视觉的压力容器焊缝识别及缺陷分类[D]. 呼和浩特:内蒙古工业大学机械工程学院,2021.
Lan Ling-xiao. Visual based weld seam recognition and defect classification for pressure vessels[D]. Hohhot: School of Mechanical Engineering, Inner Mongolia University of Technology, 2021.
[5] 伏喜斌. 基于支持向量机的焊缝超声TOFD缺陷分类识别[J]. 无损检测, 2018, 40(6): 52-57.
Fu Xi-bin. Weld ultrasonic TOFD defect classification and identification based on support vector machine[J]. Non Destructive Testing, 2018, 40(6): 52-57.
[6] Thanki R. A deep neural network and machine learning approach for retinal fundus image classification[J]. Healthcare Analytics, 2023, 3(3): No.100140.
[7] 黄宇, 陈渡. 基于轮廓变换域的图像模糊增强算法[J]. 多媒体工具和应用, 2019, 79(47/48): 35017-35032.
Huang Yu, Chen Du. Image blur enhancement algorithm based on contour transformation domain[J]. Multimedia Tools and Applications, 2019, 79(47/48): 35017-35032.
[8] 刘仁云, 孙秋成, 王春艳. 数字图像中边缘检测算法研究[M]. 北京: 科学出版社, 2015.
[9] 王文宁, 王汇源, 牟文英. 一种新的灰度直方图分割阈值的自动检测方法[J]. 计算机工程应用, 2005, 41(26): 1002-1007.
Wang Wen-ning, Wang Hui-yuan, Mou Wen-ying. A new automatic detection method of gray histogram segmentation threshold[J]. Computer Engineering Application, 2005, 41(26): 1002-1007.
[10] 姜旭磊, 孙宝, 范凯,等. 北方苍鹰优化方法可视化实验系统的设计与实现[J]. 数字技术与应用, 2023, 41(1): 168-170.
Jiang Xu-lei, Sun Bao, Fan Kai, et al Design and implementation of a visualization experimental system for the optimization method of northern eagleJ ]. Digital Technology and Applications, 2023, 41(1): 168-170.
[11] 李荣, 徐燕华. 基于视觉信息的图像特征提取算法研究[J]. 电子设计工程, 2016, 24(9): 188-190.
Li Rong, Xu Yan-hua. Research on image feature extraction algorithms based on visual information[J]. Electronic Design Engineering, 2016, 24(9): 188-190.
[12] Bhat N N, Kumari K, Dutta S, et al. Friction stir weld classification by applying wavelet analysis and support vector machine on weld surface images[J]. Journal of Manufacturing Processes, 2015, 20(20):274-281.
[13] 王凌. 智能优化算法及其应用[M]. 北京:清华大学出版社, 2004.
[14] 郭振洲, 刘然, 拱长青,等. 基于灰狼算法的改进研究[J]. 计算机应用研究, 2017, 34(12): 3603-3606, 3610.
Guo Zhen-zhou, Liu Ran, Gong Chang-qing, et al. Research on improvement based on grey wolf algorithm[J]. Computer Application Research, 2017, 34(12): 3603-3606, 3610.
[15] 刘道华, 原思聪, 兰洋,等. 混沌映射的粒子群优化方法[J]. 西安电子科技大学学报, 2010, 37(4): 764-769.
Liu Dao-hua, Yuan Si-cong, Lan Yang, et al. Particle swarm optimization method for chaotic mapping[J]. Journal of Xidian University, 2010, 37(4): 764-769.
[16] Xu M. A modified chaos-based image encryption algorithm[J]. Journal of Software, 2015,10(8): 931-938.
[17] 王宇平, 刘大莲. 基于平滑技术和一维搜索的全局优化进化算法及其收敛性[J]. 计算机学报, 2006(4):4670-4675.
Wang Yu-ping, Liu Da-lian. Global optimization evolutionary algorithm based on smoothing technique and one-dimensional search and its convergence[J]. Journal of Computer Science, 2006 (4): 4670-4675.
[18] 刘晓龙, 宁芊, 赵成萍,等. 基于莱维飞行的鸟群优化算法[J]. 计算机测量与控制, 2016,24(12): 194-197.
Liu Xiao-long, Ning Qian, Zhao Cheng-ping, et al. Bird swarm optimization algorithm based on Levy flight[J]. Computer Measurement and Control, 2016,24 (12): 194-197.
[19] Modelling of photovoltaic solar panel for maximum power point tracking[J]. International Journal of Science and Research (IJSR), 2016, 5(5): 1769-1771.
[20] Zhou Z, Li F, Zhu H, et al. An improved genetic algorithm using greedy strategy toward task scheduling optimization in cloud environments[J]. Neural Computing and Applications, 2019, 32 (6): 1531-1541.
[21] 张素琪, 滕建辅, 顾军华. 基于多维贪婪搜索的人工蜂群算法[J]. 计算机工程, 2014, 40(11): 189-194.
Zhang Su-qi, Teng Jian-fu, Gu Jun-hua. Artificial bee colony algorithm based on multidimensional greedy search[J]. Computer Engineering, 2014, 40(11): 189-194.
[22] 黎静华, 韦化. 适合于机组组合问题的贪婪随机自适应搜索模型[J]. 电网技术, 2010, 34(4): 119-123.
Li Jing-hua, Wei Hua. A greedy random adaptive search model suitable for unit commitment problem[J]. Grid Technology, 2010,34 (4): 119-123.
[23] 陈光英, 张千里, 李星. 基于SVM分类机的入侵检测系统[J]. 通信学报, 2002, 23(5): 51-56.
Chen Guang-ying, Zhang Qian-li, Li Xing. Intrusion detection system based on SVM classifier[J]. Journal of Communications, 2002, 23(5): 51-56.
[1] Liang-liang GUAN,Guo-hong TIAN. Fault detection algorithm for indicator diagram of automobile shock absorber based on dynamic analysis [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1221-1226.
[2] Hai-long GAO,Yi-bo XU,Kun LIU,Chun-yang LI,Xiao-yu LU. High-speed highway road network short-term traffic flow parameters based on multi-source data fusion prediction [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(1): 155-161.
[3] En-shen LONG,Guang-ze BAN. Idle noise diagnosis algorithm of air-conditioning refrigeration compressor based on wavelet packet extraction [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(7): 1929-1934.
[4] Ye TIAN,Nan-nan LI,Jun-wei LIU,Sheng-yuan JIANG,Chu WANG,Wei-wei ZHANG. Identification of critical fragments cutting load of simulated lunar soil based on support vector machine [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(7): 2143-2151.
[5] Yan LI,Jiu-peng ZHANG,Zi-xuan CHEN,Guo-jing HUANG,Pei WANG. Evaluation of asphalt pavement performance based on PCA⁃PSO⁃SVM [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(6): 1729-1735.
[6] Jian WU,Bin XU. Displacement interval prediction model and simulation of accumulation landslide based on ceemdan theory [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(2): 562-568.
[7] Shi-jun SONG,Min FAN. Detection method of abnormal data in cube based on spectral clustering [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(10): 2917-2922.
[8] Shi-jie GUO,Xue-wei ZHANG,Nan ZHANG,Guan QIAO,Shu-feng TANG. Thermal key point select and error prediction under typical speed of machine tool spindle [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(1): 72-81.
[9] Kui-yang WANG,Ren HE. Recognition method of braking intention based on support vector machine [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(8): 1770-1776.
[10] Wei LUO,Bo LU,Fei CHEN,Teng MA. Fault diagnosis method of NC turret based on PSO⁃SVM and time sequence [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(2): 392-399.
[11] Chun-ping HOU,Chun-yue ZHAO,Zhi-peng WANG,Hai-rui TIAN. Video anomaly detection algorithm based on effective anomaly sample construction [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(5): 1823-1829.
[12] Lao-hu YUAN,Dong-shan LIAN,Liang ZHANG,Yi LIU. Fault diagnosis of key mechanical components of aircraft based on densenet and support vector machine [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(5): 1635-1641.
[13] Kang WANG,Meng YAO,Li-ben LI,Jian-qiao LI,Xiang-jin DENG,Meng ZOU,Long XUE. Mechanical performance identification for lunar soil in lunar surface sampling [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(3): 1146-1152.
[14] Xiong-fei LI,Jing WANG,Xiao-li ZHANG,Tie-hu FAN. Multi-focus image fusion based on support vector machines and window gradient [J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(1): 227-236.
[15] Yuan-li GU, Yuan ZHANG, Xiao-ping RUI, Wen-qi LU, Meng LI, Shuo WANG. Short⁃term traffic flow prediction based on LSSVMoptimized by immune algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(6): 1852-1857.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] LI Shoutao, LI Yuanchun. Autonomous Mobile Robot Control Algorithm Based on Hierarchical Fuzzy Behaviors in Unknown Environments[J]. 吉林大学学报(工学版), 2005, 35(04): 391 -397 .
[2] Liu Qing-min，Wang Long-shan，Chen Xiang-wei，Li Guo-fa. Ball nut detection by machine vision[J]. 吉林大学学报(工学版), 2006, 36(04): 534 -538 .
[3] Li Hong-ying; Shi Wei-guang;Gan Shu-cai. Electromagnetic properties and microwave absorbing property
of Z type hexaferrite Ba3-xLaxCo2Fe24O41[J]. 吉林大学学报(工学版), 2006, 36(06): 856 -0860 .
[4] Yang Shu-kai, Song Chuan-xue, An Xiao-juan, Cai Zhang-lin . Analyzing effects of suspension bushing elasticity
on vehicle yaw response character with virtual prototype method[J]. 吉林大学学报(工学版), 2007, 37(05): 994 -0999 .
[5] . [J]. 吉林大学学报(工学版), 2007, 37(06): 1284 -1287 .
[6] Che Xiang-jiu，Liu Da-you，Wang Zheng-xuan . Construction of joining surface with G1 continuity for two NURBS surfaces[J]. 吉林大学学报(工学版), 2007, 37(04): 838 -841 .
[7] Liu Han-bing, Jiao Yu-ling, Liang Chun-yu,Qin Wei-jun . Effect of shape function on computing precision in meshless methods[J]. 吉林大学学报(工学版), 2007, 37(03): 715 -0720 .
[8] Zhang Quan-fa，Li Ming-zhe，Sun Gang，Ge Xin . Comparison between flexible and rigid blank-holding in multi-point forming[J]. 吉林大学学报(工学版), 2007, 37(01): 25 -30 .
[9] . [J]. 吉林大学学报(工学版), 2007, 37(04): 0 .
[10] Li Yue-ying，Liu Yong-bing，Chen Hua . Surface hardening and tribological properties of a cam materials[J]. 吉林大学学报(工学版), 2007, 37(05): 1064 -1068 .
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd