School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China.
Sensors (Basel). 2022 Aug 28;22(17):6478. doi: 10.3390/s22176478.
In the field of electronics manufacturing, electronic component classification facilitates the management and recycling of the functional and valuable electronic components in electronic waste. Current electronic component classification methods are mainly based on deep learning, which requires a large number of samples to train the model. Owing to the wide variety of electronic components, collecting datasets is a time-consuming and laborious process. This study proposed a Siamese network-based classification method to solve the electronic component classification problem for a few samples. First, an improved visual geometry group 16 (VGG-16) model was proposed as the feature extraction part of the Siamese neural network to improve the recognition performance of the model under small samples. Then, a novel channel correlation loss function that allows the model to learn the correlation between different channels in the feature map was designed to further improve the generalization performance of the model. Finally, the nearest neighbor algorithm was used to complete the classification work. The experimental results show that the proposed method can achieve high classification accuracy under small sample conditions and is robust for electronic components with similar appearances. This improves the classification quality of electronic components and reduces the training sample collection cost.
在电子制造领域，电子元件分类有助于管理和回收电子废物中具有功能和价值的电子元件。目前的电子元件分类方法主要基于深度学习，这需要大量的样本进行模型训练。由于电子元件种类繁多，收集数据集是一个耗时费力的过程。本研究提出了一种基于孪生网络的分类方法，用于解决小样本量的电子元件分类问题。首先，提出了一种改进的视觉几何组 16（VGG-16）模型作为孪生神经网络的特征提取部分，以提高模型在小样本下的识别性能。然后，设计了一种新的通道相关损失函数，使模型能够学习特征图中不同通道之间的相关性，进一步提高模型的泛化性能。最后，采用最近邻算法完成分类工作。实验结果表明，该方法在小样本条件下能够达到较高的分类精度，对外观相似的电子元件具有较强的鲁棒性。这提高了电子元件的分类质量，降低了训练样本采集成本。
