Liang Ying, Xu Ke, Zhou Peng
Collaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, China.
Research Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing 100083, China.
Sensors (Basel). 2020 Aug 12;20(16):4519. doi: 10.3390/s20164519.
The surface quality of aluminum ingot is crucial for subsequent products, so it is necessary to adaptively detect different types of defects in milled aluminum ingots surfaces. In order to quickly apply the calculations to a real production line, a novel two-stage detection approach is proposed. Firstly, we proposed a novel mask gradient response-based threshold segmentation (MGRTS) in which the mask gradient response is the gradient map after the strong gradient has been eliminated by the binary mask, so that the various defects can be effectively extracted from the mask gradient response map by iterative threshold segmentation. In the region of interest (ROI) extraction, we combine the MGRTS and the Difference of Gaussian (DoG) to effectively improve the detection rate. In the aspect of the defect classification, we train the inception-v3 network with a data augmentation technology and the focal loss in order to overcome the class imbalance problem and improve the classification accuracy. The comparative study shows that the proposed method is efficient and robust for detecting various defects on an aluminum ingot surface with complex milling grain. In addition, it has been applied to the actual production line of an aluminum ingot milling machine, which satisfies the requirement of accuracy and real time very well.
铝锭的表面质量对后续产品至关重要，因此有必要对铣削后的铝锭表面的不同类型缺陷进行自适应检测。为了将计算快速应用于实际生产线，提出了一种新颖的两阶段检测方法。首先，我们提出了一种基于掩模梯度响应的阈值分割方法（MGRTS），其中掩模梯度响应是通过二值掩模消除强梯度后的梯度图，从而通过迭代阈值分割从掩模梯度响应图中有效提取各种缺陷。在感兴趣区域（ROI）提取方面，我们将MGRTS与高斯差分（DoG）相结合，有效提高检测率。在缺陷分类方面，我们采用数据增强技术和焦点损失训练Inception-v3网络，以克服类别不平衡问题并提高分类准确率。对比研究表明，该方法对于检测具有复杂铣削纹理的铝锭表面的各种缺陷是高效且稳健的。此外，它已应用于铝锭铣床的实际生产线，很好地满足了精度和实时性要求。
