Feature Extraction of TOFD Signal Based on Spectrum Entropy Analysis Method
-
摘要: 超声TOFD检测技术在厚大焊缝的检测方面具有较强优势,但其检测结果的定性识别目前还依赖人员完成,而自动识别技术能够降低人为因素对检测结果分析的干扰。但若欲实现检测结果的自动识别,特征量提取是关键。通过控制焊接规范,制备了含有气孔、夹渣、裂纹、未焊透和未熔合缺陷的试件,分析了各类缺陷的TOFD信号频域二维信息熵特征,即谱熵和谱的重心频率。结果表明,该二维信息熵可将五类缺陷信号分开,为缺陷的自动识别提供有效的特征量。Abstract: Ultrasonic TOFD method takes advantages in testing thick weld, but the qualitative recognition of testing results now still relies on inspectors, therefore the testing results estimation is affected by personnel experience. By contrast, automatic recognition technology can reduce human factors impact on the testing results analysis. However, in order to implement the automatic recognition, feature extraction is the key point. In this paper, by controlling the welding specification, the specimens with porosity, slag, cracks, incomplete fusion and lack of penetration defect were prepared. Then two-dimensional entropy features in frequency domain of TOFD signal, which were spectral entropy and center frequency of spectral, for above mentioned kinds of defects were analyzed. The results show that the two-dimensional entropy in frequency domain can separate the five types of defect signal. It could provide effective characteristics for automatic identification of defect.
-
Keywords:
- Ultrasonic TOFD /
- Defect classification /
- Signal feature /
- Two-dimensional entropy
-
-
[1] 史俊伟, 刘松平. 搅拌摩擦焊焊缝超声TOFD检测与缺陷评估方法[J]. 无损检测,2011,33(11):1-3. [2] 盛朝阳, 刚 铁, 黄江中. 基于图像线性化的超声TOFD检测缺陷定位方法[J]. 无损检测,2011,33(7):15-17. [3] SHITOLE, C S N, ZZHRAN O, AL-NUAIMY W, et al. Combining fuzzy logic and neural networks in classification of weld defects using ultrasonic time-of-flight diffraction[J]. Insight: Non-Destructive Testing and Condition Monitoring, 2007, 49(2): 79-82. [4] MOURA E P, SILVA R R, SIQUEIRA M H, et al. Pattern recognition of weld defects in preprocessed TOFD signals using linear classifiers[J]. Journal of Nondestructive Evaluation, 2004, 23(4): 163-172. [5] ZAHRAN O, AL-NUAIMY W. Automatic data processing and defect detection in time-of-flight diffraction images using statistical techniques[J]. Insight, 2005, 47(9): 538-542. [6] LAWSON S W ,PARKER G A. Automatic detection of defects in industrial ultrasound images using a neural network[J]. Proceedings of SPIE, 1996 (2786): 37-47. [7] KECHIDA A, DRAI R, KHELIL M. 2D Gabor functions and FCMI algorithm for flaws detection in ultrasonic images[J]. Proceedings of World Academy of Science Engineering and Technology. 2005(9): 184-188 [8] CHARLESWORTH J P, TEMPLE J A G, ZIPIN R B. Engineering Applications of Ultrasonic Time-of-flight Diffraction[M]. Philadelphia, USA: Research Studies Press Ltd., 2001. [9] 刘红星, 左洪福, 姜澄宇,等. 信号频谱的二维向量及其应用[J]. 中国机械工程,1999,10(5):537-539.
计量
- 文章访问数: 2
- HTML全文浏览量: 0
- PDF下载量: 1
下载:
