上海大学学报(自然科学版) ›› 2026, Vol. 32 ›› Issue (2): 240-250.doi: 10.12066/j.issn.1007-2861.2535

• 通信与信息工程 • 上一篇    

一种基于深度学习的超声相控阵扇扫与全聚焦方法相结合的无损检测方法

储清源1,2,3, 楚海建1,2,3   

  1. 1. 上海大学 力学与工程科学学院, 上海 200444;
    2. 上海大学 上海市应用数学和力学研究所, 上海 200072;
    3. 上海大学 上海市能源工程力学重点实验室, 上海 200444
  • 收稿日期:2023-06-13 发布日期:2026-05-11
  • 通讯作者: 楚海建(1972-), 男, 教授, 博士生导师, 博士, 研究方向为固体力学、微纳米力学. E-mail:hjchu@shu.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(11872237); 上海市自然科学基金资助项目(18ZR1414600); 国防基础科研科学挑战专题项目(GAEP)

A deep learning-based non-destructive testing method by combining ultrasonic phased array sector scanning and total focusing method

CHU Qingyuan1,2,3, CHU Haijian1,2,3   

  1. 1. School of Mechanics and Engineering Science, Shanghai University, Shanghai 200444, China;
    2. Shanghai Institute of Applied Mathematics and Mechanics, Shanghai University, Shanghai 200072, China;
    3. Shanghai Key Laboratory of Energy Engineering Mechanics, Shanghai University, Shanghai 200444, China
  • Received:2023-06-13 Published:2026-05-11

摘要: 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.

关键词: 超声相控阵, 全聚焦法, 深度学习, 组合检测法

Abstract: 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.

Key words: ultrasonic phased array (PA), total focusing method (TFM), deep learning, combined test approach

中图分类号: