DeepGD3: Unknown-Aware Deep Generative/Discriminative Hybrid Defect Detector for PCB Soldering Inspection

Ching-Wen Ma, Yanwei Liu
Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, PMLR 216:1326-1335, 2023.

Abstract

We present a novel approach for detecting soldering defects in Printed Circuit Boards (PCBs) composed mainly of Surface Mount Technology (SMT) components, using advanced computer vision and deep learning techniques. The main challenge addressed is the detection of soldering defects in new components for which only samples of good soldering are available at the model training phase. To address this, we design a system composed of generative and discriminative models to leverage the knowledge gained from the soldering samples of old components to detect the soldering defects of new components. To meet industrial quality standards, we keep the leakage rate (i.e., miss detection rate) low by making the system "unknown-aware" with a low unknown rate. We evaluated the method on a real-world dataset from an electronics company. It significantly reduces the leakage rate from 1.827% $\pm$ 3.063% and 1.942% $\pm$ 1.337% to 0.063% $\pm$ 0.075% with an unknown rate of 3.706% $\pm$ 2.270% compared to the discriminative and generative approaches, respectively.

Cite this Paper

BibTeX
@InProceedings{pmlr-v216-ma23a, title = {{DeepGD3}: Unknown-Aware Deep Generative/Discriminative Hybrid Defect Detector for {PCB} Soldering Inspection}, author = {Ma, Ching-Wen and Lui, Yanwei}, booktitle = {Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence}, pages = {1326--1335}, year = {2023}, editor = {Evans, Robin J. and Shpitser, Ilya}, volume = {216}, series = {Proceedings of Machine Learning Research}, month = {31 Jul--04 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v216/ma23a/ma23a.pdf}, url = {https://proceedings.mlr.press/v216/ma23a.html}, abstract = {We present a novel approach for detecting soldering defects in Printed Circuit Boards (PCBs) composed mainly of Surface Mount Technology (SMT) components, using advanced computer vision and deep learning techniques. The main challenge addressed is the detection of soldering defects in new components for which only samples of good soldering are available at the model training phase. To address this, we design a system composed of generative and discriminative models to leverage the knowledge gained from the soldering samples of old components to detect the soldering defects of new components. To meet industrial quality standards, we keep the leakage rate (i.e., miss detection rate) low by making the system "unknown-aware" with a low unknown rate. We evaluated the method on a real-world dataset from an electronics company. It significantly reduces the leakage rate from 1.827% $\pm$ 3.063% and 1.942% $\pm$ 1.337% to 0.063% $\pm$ 0.075% with an unknown rate of 3.706% $\pm$ 2.270% compared to the discriminative and generative approaches, respectively.} }
Endnote
%0 Conference Paper %T DeepGD3: Unknown-Aware Deep Generative/Discriminative Hybrid Defect Detector for PCB Soldering Inspection %A Ching-Wen Ma %A Yanwei Liu %B Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2023 %E Robin J. Evans %E Ilya Shpitser %F pmlr-v216-ma23a %I PMLR %P 1326--1335 %U https://proceedings.mlr.press/v216/ma23a.html %V 216 %X We present a novel approach for detecting soldering defects in Printed Circuit Boards (PCBs) composed mainly of Surface Mount Technology (SMT) components, using advanced computer vision and deep learning techniques. The main challenge addressed is the detection of soldering defects in new components for which only samples of good soldering are available at the model training phase. To address this, we design a system composed of generative and discriminative models to leverage the knowledge gained from the soldering samples of old components to detect the soldering defects of new components. To meet industrial quality standards, we keep the leakage rate (i.e., miss detection rate) low by making the system "unknown-aware" with a low unknown rate. We evaluated the method on a real-world dataset from an electronics company. It significantly reduces the leakage rate from 1.827% $\pm$ 3.063% and 1.942% $\pm$ 1.337% to 0.063% $\pm$ 0.075% with an unknown rate of 3.706% $\pm$ 2.270% compared to the discriminative and generative approaches, respectively.
APA
Ma, C. & Liu, Y.. (2023). DeepGD3: Unknown-Aware Deep Generative/Discriminative Hybrid Defect Detector for PCB Soldering Inspection. Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 216:1326-1335 Available from https://proceedings.mlr.press/v216/ma23a.html.

Related Material