Anomaly Detection for Solder Joints Using β-VAE

In the assembly process of printed circuit boards (PCBs), most of the errors are caused by solder joints in surface mount devices (SMDs). In the literature, traditional feature extraction-based methods require designing hand-crafted features and rely on the tiered red green blue (RGB) illumination t...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on components, packaging, and manufacturing technology (2011) Vol. 11; no. 12; pp. 2214 - 2221
Main Authors: Ulger, Furkan, Yuksel, Seniha Esen, Yilmaz, Atila
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.12.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">β -variational autoencoder (VAE)
Accuracy
Anomalies
Anomaly detection
Artificial neural networks
automated optical inspection (AOI)
Automatic optical inspection
Circuit boards
Errors
Feature extraction
Illumination
Inspection
Integrated circuits
Model accuracy
Representations
solder joint inspection (SJI)
Soldered joints
Soldering
Solders
Surface-mounted devices
Training
unsupervised anomaly detection
VAE
ISSN:2156-3950, 2156-3985
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the assembly process of printed circuit boards (PCBs), most of the errors are caused by solder joints in surface mount devices (SMDs). In the literature, traditional feature extraction-based methods require designing hand-crafted features and rely on the tiered red green blue (RGB) illumination to detect solder joint errors, whereas the supervised convolutional neural network (CNN)-based approaches require a lot of labeled abnormal samples (defective solder joints) to achieve high accuracy. To solve the optical inspection problem in unrestricted environments with no special lighting and without the existence of error-free reference boards, we propose a new beta-variational autoencoder (beta-VAE) architecture for anomaly detection that can work on both integrated circuit (IC) and non-IC components. We show that the proposed model learns disentangled representation of data, leading to more independent features and improved latent space representations. We compare the activation and gradient-based representations that are used to characterize anomalies and observe the effect of different beta parameters on accuracy and untwining the feature representations in beta-VAE. Finally, we show that anomalies on solder joints can be detected with high accuracy via a model trained directly on normal samples without designated hardware or feature engineering.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2156-3950
2156-3985
DOI:10.1109/TCPMT.2021.3121265