Next Article in Journal
Review: Application of Artificial Intelligence in Phenomics
Next Article in Special Issue
Photovoltaic Panels Classification Using Isolated and Transfer Learned Deep Neural Models Using Infrared Thermographic Images
Previous Article in Journal
Psychophysiological Response According to the Greenness Index of Subway Station Space
Previous Article in Special Issue
Statistical Methods for Degradation Estimation and Anomaly Detection in Photovoltaic Plants
Article

Anomaly Detection and Automatic Labeling for Solar Cell Quality Inspection Based on Generative Adversarial Network

Electronics and Computer Science Department, Mondragon University, 20500 Arrasate, Spain
*
Author to whom correspondence should be addressed.
Academic Editor: Andrea Cataldo
Sensors 2021, 21(13), 4361; https://doi.org/10.3390/s21134361
Received: 30 April 2021 / Revised: 12 June 2021 / Accepted: 23 June 2021 / Published: 25 June 2021
Quality inspection applications in industry are required to move towards a zero-defect manufacturing scenario, with non-destructive inspection and traceability of 100% of produced parts. Developing robust fault detection and classification models from the start-up of the lines is challenging due to the difficulty in getting enough representative samples of the faulty patterns and the need to manually label them. This work presents a methodology to develop a robust inspection system, targeting these peculiarities, in the context of solar cell manufacturing. The methodology is divided into two phases: In the first phase, an anomaly detection model based on a Generative Adversarial Network (GAN) is employed. This model enables the detection and localization of anomalous patterns within the solar cells from the beginning, using only non-defective samples for training and without any manual labeling involved. In a second stage, as defective samples arise, the detected anomalies will be used as automatically generated annotations for the supervised training of a Fully Convolutional Network that is capable of detecting multiple types of faults. The experimental results using 1873 Electroluminescence (EL) images of monocrystalline cells show that (a) the anomaly detection scheme can be used to start detecting features with very little available data, (b) the anomaly detection may serve as automatic labeling in order to train a supervised model, and (c) segmentation and classification results of supervised models trained with automatic labels are comparable to the ones obtained from the models trained with manual labels. View Full-Text
Keywords: anomaly detection; electroluminescence; solar cells; neural networks anomaly detection; electroluminescence; solar cells; neural networks
Show Figures

Figure 1

MDPI and ACS Style

Balzategui, J.; Eciolaza, L.; Maestro-Watson, D. Anomaly Detection and Automatic Labeling for Solar Cell Quality Inspection Based on Generative Adversarial Network. Sensors 2021, 21, 4361. https://doi.org/10.3390/s21134361

AMA Style

Balzategui J, Eciolaza L, Maestro-Watson D. Anomaly Detection and Automatic Labeling for Solar Cell Quality Inspection Based on Generative Adversarial Network. Sensors. 2021; 21(13):4361. https://doi.org/10.3390/s21134361

Chicago/Turabian Style

Balzategui, Julen, Luka Eciolaza, and Daniel Maestro-Watson. 2021. "Anomaly Detection and Automatic Labeling for Solar Cell Quality Inspection Based on Generative Adversarial Network" Sensors 21, no. 13: 4361. https://doi.org/10.3390/s21134361

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop