Purpose

This paper aims to propose a deep learning model that can be used to expand the number of samples. In the process of manufacturing and assembling electronic components on the printed circuit board in the surface mount technology production line, it is relatively easy to collect non-defective samples, but it is difficult to collect defective samples within a certain period of time. Therefore, the number of non-defective components is much greater than the number of defective components. In the process of training the defect detection method of electronic components based on deep learning, a large number of defective and non-defective samples need to be input at the same time.

Design/methodology/approach

To obtain enough electronic components samples required for training, a method based on the generative adversarial network (GAN) to generate training samples is proposed, and then the generated samples and real samples are used to train the convolutional neural networks (CNN) together to obtain the best detection results.

Findings

The experimental results show that the defect recognition method using GAN and CNN can not only expand the sample images of the electronic components required for the training model but also accurately classify the defect types.

Originality/value

To solve the problem of unbalanced sample types in component inspection, a GAN-based method is proposed to generate different types of training component samples and then the generated samples and real samples are used to train the CNN together to obtain the best detection results.

中文翻译：

---

基于图像样本生成的电子元件检测

目的

本文旨在提出一种可用于扩展样本数量的深度学习模型。在表面贴装技术生产线在印刷电路板上制造和组装电子元件的过程中，收集无缺陷样品相对容易，但很难在一定时间内收集缺陷样品。因此，无缺陷部件的数量远大于缺陷部件的数量。在训练基于深度学习的电子元件缺陷检测方法的过程中，需要同时输入大量的缺陷和非缺陷样本。

设计/方法/方法

为了获得足够的训练所需的电子元件样本，提出了一种基于生成对抗网络（GAN）生成训练样本的方法，然后将生成的样本和真实样本用于卷积神经网络（CNN）一起训练得到最好的检测结果。

发现

实验结果表明，使用 GAN 和 CNN 的缺陷识别方法不仅可以扩展训练模型所需的电子元件的样本图像，而且可以准确地对缺陷类型进行分类。

原创性/价值

针对组件检测中样本类型不平衡的问题，提出了一种基于GAN的方法，生成不同类型的训练组件样本，然后将生成的样本和真实样本一起训练CNN，以获得最佳检测结果。