PULÉTS, École de technologie supérieure, 1100 Notre-Dame Ouest, Montréal, Québec, Canada, H3C 1K3.
PULÉTS, École de technologie supérieure, 1100 Notre-Dame Ouest, Montréal, Québec, Canada, H3C 1K3.
Ultrasonics. 2021 Aug;115:106436. doi: 10.1016/j.ultras.2021.106436. Epub 2021 Apr 16.
Machine learning algorithms are widely used in image recognition. In Phased Array Ultrasonic Testing (PAUT), images are typically formed through constructive and destructive superpositions of signals backscattered from flaws or geometric features. However, all PAUT data acquisition schemes require several emissions and the duration of the acquisition may be too slow in high-speed manufacturing. In this study, the Faster R-CNN was used to identify, locate and size flat bottom holes (FBH) and side-drilled holes (SDH) in an immersed test specimen using a single plane wave insonification. The training was performed on segmented and classified data generated using GPU-accelerated finite element simulations. SDH and FBH of different diameters, depths and lateral positions were included in the training set. The thickness of the test specimen was also variable. An ultrasonic phased array probe of 64 elements was simulated. All elements of the phased array probe were fired at the same time and the time traces from each element were recorded. The individual time traces were concatenated to form a matrix, which was then used in the training. This inspection scenario enables fast acquisition of data at the expense of poor lateral resolution in the resulting image. The trained neural network was initially tested using finite element simulations. Results were assessed in terms of the intersection of the union (IoU) between the ground truth geometry and the predicted geometry. With the simulated cases, the thickness of the test specimen was detected in all cases. When using a 40% IoU threshold, the detection rate of the FBH was 87% while only 20% for the SDH. The smallest detected FBH had a 0.56 wavelength depth and a lateral extent of 1.04 wavelength. Drawing a box using the -6dB drop method around the FBH always led to an IoU under 15%. On average, the lateral extent of the FBH using the -6dB method was three times larger than the diameter predicted by the proposed method. Then, the training was continued with a small augmented dataset of experiments (equivalent to 3% of the simulated dataset). In experiments, the results show that the test specimen was always correctly identified. When using a 40% IoU threshold the experimental detection rate of the FBH was 70%. The smallest detected defect in experiments had a depth of 2 wavelengths.
机器学习算法在图像识别中得到了广泛的应用。在相控阵超声检测（PAUT）中，图像通常是通过回波信号的相长干涉和相消干涉形成的，这些回波信号来自于缺陷或几何特征。然而，所有 PAUT 数据采集方案都需要多次发射，而且在高速制造中，采集的持续时间可能会太长。在这项研究中，使用 Faster R-CNN 来识别、定位和测量浸入式试件中平底孔（FBH）和侧钻孔（SDH）的大小，使用单平面波激励。训练是在使用 GPU 加速有限元模拟生成的分段和分类数据上进行的。训练集中包括不同直径、深度和横向位置的 SDH 和 FBH。试件的厚度也是可变的。模拟了一个 64 个元件的超声相控阵探头。相控阵探头的所有元件同时发射，记录每个元件的时程。将各个时程连接起来形成一个矩阵，然后用于训练。这种检测场景可以以牺牲图像的横向分辨率为代价快速采集数据。训练好的神经网络最初使用有限元模拟进行测试。结果根据真实几何形状和预测几何形状之间的交集（IoU）进行评估。对于模拟情况，在所有情况下都可以检测到试件的厚度。当使用 40%的 IoU 阈值时，FBH 的检测率为 87%，而 SDH 的检测率仅为 20%。检测到的最小 FBH 的深度为 0.56 个波长，横向范围为 1.04 个波长。使用-6dB 下降法在 FBH 周围绘制一个方框，IoU 总是低于 15%。平均而言，使用-6dB 方法的 FBH 横向范围是建议方法预测直径的三倍。然后，使用一个小的实验增强数据集（相当于模拟数据集的 3%）继续训练。在实验中，结果表明试件总是被正确识别。当使用 40%的 IoU 阈值时，FBH 的实验检测率为 70%。实验中检测到的最小缺陷深度为 2 个波长。
