Pattern recognition on photovoltaic panels

Can a convolutional neural network detect abnormal solar panels?

Pierdicca et al. trained a convolutional neural network (CNN) based on mask regions to detect abnormal solar panels. A VGG-16 network has used to recognize faulty solar cells in thermal images automatically. They do not specify a region of interest before applying the network on images that have been downsized to 224 × 224 pixels.

Can deep learning detect photovoltaic module defects in infrared imagery?

Akram et al. used isolated deep learning and develop-model transfer deep learning approaches to detect photovoltaic module flaws in infrared imagery. The dataset created by the combined data augmentation technique is used to train the classification model. Alves et al. presented a CNN model to categorize PV module defects.

How to classify PV cell faults using convolutional neural networks?

Bu et al. suggested a method for classifying PV cell faults using convolutional neural networks (CNNs) which are trained on a collection of infrared image data. Real-Time Multi Variant Deep Learning Model (RMVDM) was proposed by to train the Gray Scale Quantization Algorithm features.

Why are new data-driven models needed for photovoltaic (PV) energy measurements?

With the rapid growth in computational complexities of statistical pattern recognition of photovoltaic (PV) energy measurements, the need for new data-driven models has emerged.

Can a convolutional neural network detect faults in solar cell El images?

Deitsch et al. employed a convolutional neural network for the detection of various faults in solar cell EL images. The approach in this study increases accuracy on the dataset from the conventional machine vision method by 6 percentage points, to 88.36%.

Can a deep learning model improve PV image classification accuracy?

However, these standard deep learning models could produce errors, especially in the presence of noisy or inter-class small variation data which is the case with PV images. In this paper, we introduce an end-to-end deep learning model that combines handcrafted and automatic feature extraction to produce better PV image classification accuracy.