[1]李 阳,朱文博,静丰羽,等.基于局部离群因子与隔离森林的激光超声缺陷检测[J].郑州大学学报(工学版),2025,46(01):105-112.[doi:10.13705/j.issn.1671-6833.2025.01.003]
 LI Yang,ZHU Wenbo,JING Fengyu,et al.Laser Ultrasonic Defect Detection Based on Local Outlier Factor and Isolated Forest[J].Journal of Zhengzhou University (Engineering Science),2025,46(01):105-112.[doi:10.13705/j.issn.1671-6833.2025.01.003]
点击复制

基于局部离群因子与隔离森林的激光超声缺陷检测()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
46
期数:
2025年01期
页码:
105-112
栏目:
出版日期:
2024-12-23

文章信息/Info

Title:
Laser Ultrasonic Defect Detection Based on Local Outlier Factor and Isolated Forest
文章编号:
1671-6833(2025)01-0105-08
作者:
李 阳1 朱文博1 静丰羽2 叶中飞3 马云瑞3 周 洋1 邹 云1
1.郑州大学 机械与动力工程学院,河南 郑州 450001;2.中国电建集团河南电力器材有限公司,河南 漯河 462000; 3.国网河南省电力公司电力科学研究院,河南 郑州 450052
Author(s):
LI Yang1 ZHU Wenbo1 JING Fengyu2 YE Zhongfei3 MA Yunrui3 ZHOU Yang1 ZOU Yun 1
1.School of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou 450001, China;2.POWERCHINA Henan Electric Power Equipment Co., Ltd., Luohe 462000, China; 3.State Grid Henan Electric Power Research Institute, Zhengzhou 450052, China
关键词:
激光超声 缺陷检测 主成分分析 局部离群因子 隔离森林 铝合金
Keywords:
laser ultrasonic defect detection principal component analysis local outlier factorisolated forest aluminium alloy
分类号:
TH16TB551
DOI:
10.13705/j.issn.1671-6833.2025.01.003
文献标志码:
A
摘要:
针对激光超声(LU)缺陷检测中最大振幅图存在伪像的问题,结合主成分分析(PCA)和两种无监督的机器学习算法局部离群因子(LOF)与隔离森林(IF),以实现对LU数据的无监督异常检测。首先,利用PCA算法对LU数据进行降维处理,减轻了LU数据的复杂度;其次,利用LOF算法和IF算法进行了数据异常值的识别分析,并利用累积分布函数和核密度估计确定异常值的阈值大小;最后,对比了LOF算法、IF算法以及最大振幅图的检测结果。结果表明:LOF算法有更优的缺陷识别精度和更低的误判率。
Abstract:
In response to the issue of artifacts in the maximum amplitude images in laser ultrasonic (LU) defect detection, principal component analysis (PCA) was integrated with two unsupervised machine learning algorithms including local outlier factor (LOF) and isolated forest (IF) to perform unsupervised anomaly detection on LU data. Firstly, the PCA algorithm was used to reduce the dimensionality of the LU data, simplifying its complexity. Secondly, the LOF and IF algorithms were employed to identify outliers in the data, and the thresholds for these outliers were determined using the cumulative distribution function and kernel density estimation. Finally, a comparison of the detection results from the LOF, IF algorithms, and the maximum amplitude images revealed that the LOF algorithm offered superior defect detection precision and a lower false positive rate.

参考文献/References:

[1]SEGOVIA RAMÍREZ I, GARCÍA MÁRQUEZ F P, PAPAELIAS M. Review on additive manufacturing and nondestructive testing[J]. Journal of Manufacturing Systems, 2023, 66: 260-286. 

[2]李阳, 彭笑永, 李大磊, 等. 激光超声无损测量40Cr钢渗氮层深度的实验研究[J]. 郑州大学学报(工学版), 2020, 41(6): 7-12. 
LI Y, PENG X Y, LI D L, et al. Experimental investigation on non-destructive measuring of the nitriding thickness of 40Cr steel by laser ultrasonic[J]. Journal of Zhengzhou University (Engineering Science), 2020, 41 (6): 7-12. 
[3]弓鹏飞, 张彦杰, 王法雨, 等. 棒材表面缺陷的激光超声无损检测方法研究[J]. 激光杂志, 2022, 43 (9): 44-49. 
GONG P F, ZHANG Y J, WANG F Y, et al. Research on laser ultrasonic nondestructive testing method for surface defects of bar[J]. Laser Journal, 2022, 43(9): 44-49. 
[4]杨连杰, 李阳, 孙俊杰, 等. 激光超声表面波在表面缺陷上的反射与透射[J]. 激光与光电子学进展, 2019, 56(4): 146-151. 
YANG L J, LI Y, SUN J J, et al. Reflection and transmission of laser ultrasonic waves on surface defects[J]. Laser & Optoelectronics Progress, 2019, 56(4): 146-151. 
[5]黄燕杰, 尚建华, 任立红, 等. 用于铝板缺陷无损检测的激光超声有限元模拟研究[J]. 应用光学, 2019, 40(1): 150-156. 
HUANG Y J, SHANG J H, REN L H, et al. Finite element simulation in laser ultrasound for non-destructive testing of aluminum defect materials[J]. Journal of Applied Optics, 2019, 40(1): 150-156. 
[6]LIU S Y, JIA K N, WAN H P, et al. Inspection of the internal defects with different size in Ni and Ti additive manufactured components using laser ultrasonic technology [J]. Optics & Laser Technology, 2022, 146: 107543. 
[7]ZENG W, CAI M M, WANG P, et al. Application of laser ultrasonic technique for detecting weld defect based on FDST method[J]. Optik, 2020, 221: 165366. 
[8]姜瀚彬, 高炜欣, 石萌萌. 基于卷积神经网络的激光超声缺陷检测研究[J]. 激光杂志, 2022, 43(7): 5964. 
JIANG H B, GAO W X, SHI M M. Research on laser ultrasonic defect detection based on convolutional neural network[J]. Laser Journal, 2022, 43(7): 59-64. 
[9]LIU Z X, HU Z L, WANG L X, et al. Effective detection of metal surface defects based on double-line laser ultrasonic with convolutional neural networks[J]. Modern Physics Letters B, 2021, 35(15): 2150263. 
[10] GUO S F, FENG H W, FENG W, et al. Automatic quantification of subsurface defects by analyzing laser ultrasonic signals using convolutional neural networks and wavelet transform[J]. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2021, 68(10): 3216-3225. 
[11]魏博文, 高炜欣, 刘梦溪. 激光超声结合CNN的铸件缺陷检测方法[J]. 激光与红外, 2022, 52(9): 13271334. 
WEI B W, GAO W X, LIU M X. Casting defect detection method combined with laser ultrasound and convolutional neural network[J]. Laser & Infrared, 2022, 52 (9): 1327-1334. 
[12] ZAREI A, PILLA S. An improved theory of thermoelasticity for ultrafast heating of materials using short and ultrashort laser pulses[J]. International Journal of Heat and Mass Transfer, 2023, 215: 124510. 
[13] JAYA RAO V V S, KANNAN E, PRAKASH R V, et al. Fatigue damage characterization using surface acoustic wave nonlinearity in aluminum alloy AA7175-T7351[J]. Journal of Applied Physics, 2008, 104(12):123508. 
[14] SOLODOV I, BAI J X, BUSSE G. Resonant ultrasound spectroscopy of defects: case study of flat-bottomed holes [J]. Journal of Applied Physics, 2013, 113(22): 223512. 
[15] HU H Z, LIU J X, ZHANG X P, et al. An effective and adaptable K-means algorithm for big data cluster analysis [J]. Pattern Recognition, 2023, 139: 109404. 
[16] FAIRLEY N, BARGIELA P, HUANG W M, et al. Principal component analysis (PCA) unravels spectral components present in XPS spectra of complex oxide films on iron foil[J]. Applied Surface Science Advances, 2023, 17: 100447. 
[17] MARUKATAT S. Tutorial on PCA and approximate PCA and approximate kernel PCA[J]. Artificial Intelligence Review, 2023, 56(6): 5445-5477. 
[18]吴志强,张胜,包晓玲,等.针对WSN异常数据检测改进的孤立森林方法[J].小型微型计算机系统, 2021, 42(1):127-131. 
WU Z Q, ZHANG S, BAO X L, et al. Improved isolation forest method for WSN anomaly data detection[J]. Journal of Chinese Computer Systems, 2021, 42(1): 127-131. 
[19]WANG H F, JIANG W, DENG X Y, et al. A new method for fault detection of aero-engine based on isolation forest[J]. Measurement, 2021, 185: 110064. 
[20] JEONG W, TSINGAS C, ALMUBARAK M S. Local outlier factor as part of a workflow for detecting and attenuating blending noise in simultaneously acquired data[J]. Geophysical Prospecting, 2020, 68(5): 1523-1539. 
[21] CHIU A L M, FU A W C. Enhancements on local outlier detection[C]∥The Seventh International Database Engineering and Applications Symposium. Piscataway: IEEE, 2003: 298-307.

更新日期/Last Update: 2024-12-31