基于LabVIEW的电磁超声无损检测系统的设计

doi:10.19595/j.cnki.1000-6753.tces.170473

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (24067 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In the paper, a novel method based on LabVIEW is proposed for the on-line identification of crack to meet the need of intelligent nondestructive testing technology. The features of electromagnetic ultrasonic signal in time domain, frequency domain and time-frequency domain are extracted, while the feature selection is carried out combining the within-class & between-class average distance with sequential forward selection method. Based on support vector machine (SVM), the recognition model about supervised learning and semi supervised learning is constructed. The result shows that S4VM is a safer semi supervised support vector machine. The electromagnetic ultrasonic nondestructive testing system is built and the on-line defect recognition experiment is conducted. Test results show that the system is reliable, and can achieve the visualization, digitization, intellectualization and systematization of the electromagnetic ultrasonic defect recognition.

Key words： Virtual instrument feature extraction SVM semi supervised learning online defect identification

Received: 18 April 2017 Published: 24 May 2018

PACS:

TG115.28

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Liu Suzhen
	Rao Nuoxin
	Zhang Chuang
	Jin Liang
	Yang Qingxin

Cite this article:

Liu Suzhen,Rao Nuoxin,Zhang Chuang等. Design of Electromagnetic Ultrasonic Nondestructive Testing System Based on LabVIEW[J]. Transactions of China Electrotechnical Society, 2018, 33(10): 2274-2281.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.170473 OR https://dgjsxb.ces-transaction.com/EN/Y2018/V33/I10/2274

[1] 马宏伟, 王华玲, 李海宁. 基于LabVIEW的超声检测虚拟仪器开发[J]. 仪器仪表学报, 2006, 27(增刊3): 1785-1787.
Ma Hongwei, Wang Hualing, Li Haining.Developed of ultrasonic-testing virtual instrument besed on LabVIEW[J]. Chinese Journal of Scientific Insturment, 2006, 27(S3): 1785-1787.
[2] 孙金立, 肖兴明, 袁英民, 等. 基于虚拟仪器的综合式无损检测系统[J]. 无损检测, 2005, 27(11): 580-582.
Sun Jinli, Xiao Xingming, Yuan Yingmin, et al.Comprehensive nondestructive testing system based on virtual instrument[J]. Nondestructive Testing, 2005, 27(11): 580-582.
[3] 李铁, 刘时风, 李路明. 基于LabVIEW的虚拟仪器技术在无损检测中的应用[J]. 无损检测, 2001, 23(6): 240-242.
Li Tie, Liu Shifeng, Li Luming.The application of labview-based virtual instrument technique to nonde- structive testing[J]. Nondestructive Testing, 2001, 23(6): 240-242.
[4] 于威. 钢轨超声波探伤信号的处理及分析[D]. 哈尔滨: 哈尔滨理工大学, 2013.
[5] 薛英娟. 基于LabVIEW的焊缝缺陷超声检测与识别[D]. 太原: 中北大学, 2005.
[6] 王桂森, 万熠, 宋明大, 等. 基于LabVIEW的铁磁性材料无损检测系统开发[J]. 工具技术, 2016, 50(11): 96-99.
Wang Guisen, Wan Yi, Song Mingda, et al.Development of nondestructive test device of ferromagnetic material based on LabVIEW[J]. Tool Engineering, 2016, 50(11): 96-99.
[7] 索会迎. 超声波无损检测技术应用研究[D]. 南京:南京邮电大学, 2012.
[8] Du T J, Chen G J, Lei Y.Novel method for power system harmonic detection based on wavelet transform with aliasing compensation[J]. Proceedings of the CSEE, 2005, 25(3): 54-59.
[9] Lei Y, He Z, Zi Y.Application of an intelligent classification method to mechanical fault diagnosis[J]. Expert Systems with Applications, 2009, 36(6): 9941-9948.
[10] 杨茂, 陈郁林. 基于EMD分解和集对分析的风电功率实时预测[J]. 电工技术学报, 2016, 31(21): 86-93.
Yang Mao, Chen Yulin.Real-time prediction for wind power based on EMD and set pair analysis[J]. Transactions of China Electrotechnical Society, 2016, 31(21): 86-93.
[11] 王贺, 胡志坚, 陈珍, 等. 基于集合经验模态分解和小波神经网络的短期风功率组合预测[J]. 电工技术学报, 2013, 28(9): 137-144.
Wang He, Hu Zhijian, Chen Zhen, et al.A hybrid model for wind power forecasting based on ensemble empirical mode decomposition and wavelet neural networks[J]. Transactions of China Electrotechnical Society, 2013, 28(9): 137-144.
[12] 张丽新, 王家钦, 赵雁南, 等. 机器学习中的特征选择[J]. 计算机科学, 2004, 31(11): 180-184.
Zhang Lixin, Wang Jiaqin, Zhao Yannan, et al.Feature selection in machine learning[J]. Computer Science, 2004, 31(11): 180-184.
[13] 章小强, 管霖, 王同文. 针对特征选择问题的改进蚁群算法及其在电力系统安全评估中的应用[J]. 电工技术学报, 2010, 25(12): 154-160, 166.
Zhang Xiaoqiang, Guan Lin, Wang Tongwen.Kernel feature identification based on improved ant colony optimization algorithm for transient stability assessment[J]. Transactions of China Electrotechnical Society, 2010, 25(12): 154-160, 166.
[14] Marcano-Cedeño A, Quintanilla-Domínguez J, Cortina-Januchs M G, et al. Feature selection using sequential forward selection and classification applying artificial metaplasticity neural network[C]// IECON 2010-36th Annual Conference on IEEE Industrial Electronics Society, Glendale, AZ, USA, 2010: 2845-2850.
[15] Japkowicz N.Concept-learning in the presence of between-class and within-class imbalances[C]// Conference of the Canadian Society for Computational Studies of Intelligence. Springer, Berlin, Heidelberg, 2001: 67-77.
[16] 史丽萍, 王攀攀, 胡泳军, 等. 基于骨干微粒群算法和支持向量机的电机转子断条故障诊断[J]. 电工技术学报, 2014, 29(1): 147-155.
Shi Liping, Wang Panpan, Hu Yongjun, et al.Broken rotor bar fault diagnosis of induction motors based on bare-bone particle swarm optimization and support vector machine[J]. Transactions of China Electro- technical Society, 2014, 29(1): 147-155.
[17] Li Y F, Zhou Z H. S4VM: Safe semi-supervised support vector machine[R].2010, arXiv: 1005. 1545.
[18] Li Y F, Zhou Z H.Towards making unlabeled data never hurt[C]//Proceedings of the 28th International Conference on Machine Learning, Bellevue, Washington, USA, 2011: 1081-1088.