提高检测效率和精度是超声相控阵(phased array,PA)无损探伤的重要研究方向.基于YOLOv5深度学习模型及相控阵扫查成像理论,提出了一种将超声相控阵扇扫与全聚焦法(total focusing method,TFM)相结合的组合式无损检测方法.首先,通过自主训练的YOLOv5s模型对扇扫图像进行初步缺陷识别,实现对缺陷可能区域的快速确定;然后,使用自主研发的TFM成像系统,实现对缺陷可能区域的精确成像.标准试块检测结果表明,该组合检测法能发扬超声相控阵扇扫成像速度快、TFM成像精度高的优点,实现了检测效率和精度的兼顾.
To improve the efficiency and accuracy of ultrasonic phased array (PA) scanning, a nondestructive testing approach that combines sector scanning and the total focusing method (TFM) is proposed with the assistance of a deep learning model, namely, YOLOv5s. Using this method, the self-trained YOLOv5s model was applied for preliminary defect recognition on sector scanning images to enable the rapid identification of possible defect regions. Software was developed for the total focusing method imaging system to image possible defects in possible defect regions based on the Qt platform. The results obtained from the test of the assessment block indicate that this new proposed approach can take advantage of not only the high imaging efficiency of ultrasonic phased array sector scanning but also the high accuracy of the total focusing method to achieve improvements in both test efficiency and accuracy.
[1] 邓菲, 胡方朝, 邵可, 等. 多参量超声相控阵技术的研究进展[J]. 应用技术学报, 2018, 18(3): 264-272.
[2] 靳世久, 杨晓霞, 陈世利, 等. 超声相控阵检测技术的发展及应用[J]. 电子测量与仪器学报, 2014, 28(9): 925-934.
[3] Drinkwater B W, Wilcox P D. Ultrasonic arrays for non-destructive evaluation: a review [J]. NDT & E International, 2006, 39(7): 525-541.
[4] 张鹏辉, 赵扬, 李鹏, 等. 超声成像检测技术研究进展综述[J]. 激光与光电子学进展, 2022, 59(2): 0200003.
[5] Holmes C, Drinkwater B, Wilcox P. The post-processing of ultrasonic array data using the total focusing method [J]. Insight-Non-Destructive Testing and Condition Monitoring, 2004, 46(11): 677-680.
[6] Pillarisetti L S S, Raju G, Subramanian A. Sectorial plane wave imaging for ultrasonic array-based angle beam inspection [J]. Journal of Nondestructive Evaluation, 2021, 40(3): 77.
[7] Von Bernus L, Bulavinov A, Dalichow M, et al. Sampling phased array: a new technique for signal processing and ultrasonic imaging [J]. Insight-Wigston Then Northampton, 2006, 48(9): 545-558.
[8] Yang C, Qin K, Li Y. Real-time ultrasonic imaging for multi-layered objects with synthetic aperture focusing technique [C]// Proceedings of the 2014 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). 2014: 561-566.
[9] Hunter A J, Drinkwater B W, Wilcox P D, et al. The wavenumber algorithm: fast Fourierdomain imaging using full matrix capture [C]// AIP Conference Proceedings. 2009: 856-863.
[10] Le Jeune L, Robert S, Dumas P, et al. Adaptive ultrasonic imaging with the total focusing method for inspection of complex components immersed in water [C]// 41st Annual Review of Progress in Quantitative Nondestructive Evaluation. 2015: 1037-1046.
[11] Posilovi L, Medak D, Subai M, et al. Flaw detection from ultrasonic images using YOLO and SSD [C]// Proceedings of the 201911th International Symposium on Image and Signal Processing and Analysis (ISPA). 2019: 8868929.
[12] Medak D, Posilovic L, Subasic M, et al. Automated defect detection from ultrasonic images using deep learning [J]. IEEE Trans Ultrason Ferroelectr Freq Control, 2021, 68(10): 3126-3134.
[13] Virkkunen I, Koskinen T, Jessen-Juhler O, et al. Augmented ultrasonic data for machine learning [J]. Journal of Nondestructive Evaluation, 2021, 40(1): 1-11.
