Chen Mengchi, Zhang Cheng, Yang Wen, Zhang Suyi, Huang Wenjun
College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China.
Luzhou Laojiao Co., Ltd., Luzhou 646000, China.
Sensors (Basel). 2023 Jul 21;23(14):6582. doi: 10.3390/s23146582.
Accurate measurements of the bubble size distribution (BSD) are crucial for investigating gas-liquid mass transfer mechanisms and describing the characteristics of chemical production. However, measuring the BSD in high-density bubbly flows remains challenging due to limited image algorithms and high data densities. Therefore, an end-to-end BSD detection method in dense bubbly flows based on deep learning is proposed in this paper. The bubble detector locates the positions of dense bubbles utilizing objection detection networks and simultaneously performs ellipse parameter fitting to measure the size of the bubbles. Different You Only Look Once (YOLO) architectures are compared, and YOLOv7 is selected as the backbone network. The complete intersection over union calculation method is modified by the circumferential horizontal rectangle of bubbles, and the loss function is optimized by adding L2 constraints of ellipse size parameters. The experimental results show that the proposed technique surpasses existing methods in terms of precision, recall, and mean square error, achieving values of 0.9871, 0.8725, and 3.8299, respectively. The proposed technique demonstrates high efficiency and accuracy when measuring BSDs in high-density bubbly flows and has the potential for practical applications.
准确测量气泡尺寸分布（BSD）对于研究气液传质机理和描述化工生产特性至关重要。然而，由于图像算法有限和数据密度高，在高密度气泡流中测量BSD仍然具有挑战性。因此，本文提出了一种基于深度学习的高密度气泡流端到端BSD检测方法。气泡探测器利用目标检测网络定位密集气泡的位置，并同时进行椭圆参数拟合以测量气泡尺寸。比较了不同的You Only Look Once（YOLO）架构，并选择YOLOv7作为骨干网络。通过气泡的圆周水平矩形修改完全交并比计算方法，并通过添加椭圆尺寸参数的L2约束来优化损失函数。实验结果表明，所提出的技术在精度、召回率和均方误差方面优于现有方法，分别达到0.9871、0.8725和3.8299。所提出的技术在测量高密度气泡流中的BSD时具有高效率和准确性，具有实际应用潜力。
