Visualizing Material Quality and Similarity of mc-Si Wafers Learned by Convolutional Regression Networks

Convolutional neural networks can be trained to assess the material quality of multicrystalline silicon wafers. A successful rating model has been presented in a related work, which directly evaluates the photoluminescence (PL) image of the wafer to predict the current-voltage parameters after solar...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE journal of photovoltaics 2019-07, Vol.9 (4), p.1073-1080
Hauptverfasser:	Demant, Matthias, Virtue, Patrick, Kovvali, Aditya, Yu, Stella X., Rein, Stefan
Format:	Artikel
Sprache:	eng
Schlagworte:	Activation Anomalies Artificial neural networks Convolutional neural network (CNN) Data visualization densely connected convolutional neural network (denseNet) Fault detection Feature extraction Image quality machine learning Mapping material multicrystalline silicon (mc-Si) passivated emitter and rear cell Photoluminescence photoluminescence (PL) Photovoltaic cells Production Quality assessment rating Regression regression activation mapping Representations Semiconductor device modeling Silicon Silicon wafers Smoothness solar cell Solar cells t-distributed stochastic neighborhood embedding (t-SNE) Training Wafers
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!