基于改进北方苍鹰优化算法的激光焊缝图像分类

doi:10.13229/j.cnki.jdxbgxb.20230709

摘要/Abstract

摘要：

针对多种类型激光焊缝识别计算复杂度高、分类准确度低的问题，提出了一种基于改进北方苍鹰算法（UNGO）的激光焊缝图像识别分类算法，在传统支持向量机算法（SVM）的基础上与改进北方苍鹰算法（UNGO-SVM）结合，并通过混沌优化与莱维飞行中贪婪学习策略增加算法搜索能力，同时帮助算法克服陷入局部最优情况，提高算法的收敛精度和图像分类准确度。实验结果表明，UNGO-SVM在保证算法收敛度的同时分类准确率提升至99.15%，相比较SVM、NGO-SVM、DOA-SVM、GOA-SVM分别提升了21%、5%、10%和11%，证明了该方法的可行性和较强的利用价值。

关键词: 北方苍鹰算法, 图像识别分类, 支持向量机, 立方混沌, 贪婪学习策略

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

中图分类号:

TG409

邹红波,李奇隆. 基于改进北方苍鹰优化算法的激光焊缝图像分类[J]. 吉林大学学报(工学版), 2025, 55(4): 1426-1435.

Hong-bo ZOU,Qi-long LI. Laser weld image classification based on improved Northern Goshawk optimization algorithm[J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(4): 1426-1435.

图/表 12

图1

图2

图3

表1

焊缝特征参数分类对照图"

序号	面积	最佳阈值	长度	最小宽度	最大宽度	像素个数	组号
1	93.63	4.51	21.56	2.75	8.21	38 446	4
2	89.36	4.62	20.78	2.65	7.98	36 870	4
3	61.45	3.75	15.48	2.18	6.19	30 452	2
4	24.96	2.12	8.32	1.12	5.78	15 363	1
5	25.12	2.15	8.17	1.24	6.02	17 354	1
6	71.55	4.23	18.65	2.36	6.78	32 452	3
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

表1

表2

图4

图5

图6

图7

图8

表3

图9

参考文献 23

[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.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed