[Paper Review] HybridSolarNet: A Lightweight and Explainable EfficientNet-CBAM Architecture for Real-Time Solar Panel Fault Detection

Md. Asif Hossain, G M Mota-Tahrin Tayef+1 more|arXiv (Cornell University)|Jan 6, 2026

Photovoltaic System Optimization Techniques0 citations

TL;DR

HybridSolarNet combines EfficientNet-B0 with CBAM to create a lightweight, explainable model for real-time solar panel fault detection on UAVs, achieving strong accuracy with low memory usage.

ABSTRACT

Manual inspections for solar panel systems are a tedious, costly, and error-prone task, making it desirable for Unmanned Aerial Vehicle (UAV) based monitoring. Though deep learning models have excellent fault detection capabilities, almost all methods either are too large and heavy for edge computing devices or involve biased estimation of accuracy due to ineffective learning techniques. We propose a new solar panel fault detection model called HybridSolarNet. It integrates EfficientNet-B0 with Convolutional Block Attention Module (CBAM). We implemented it on the Kaggle Solar Panel Images competition dataset with a tight split-before-augmentation protocol. It avoids leakage in accuracy estimation. We introduced focal loss and cosine annealing. Ablation analysis validates that accuracy boosts due to added benefits from CBAM (+1.53%) and that there are benefits from recognition of classes with imbalanced samples via focal loss. Overall average accuracy on 5-fold stratified cross-validation experiments on the given competition dataset topped 92.37% +/- 0.41 and an F1-score of 0.9226 +/- 0.39 compared to baselines like VGG19, requiring merely 16.3 MB storage, i.e., 32 times less. Its inference speed measured at 54.9 FPS with GPU support makes it a successful candidate for real-time UAV implementation. Moreover, visualization obtained from Grad-CAM illustrates that HybridSolarNet focuses on actual locations instead of irrelevant ones.

Motivation & Objective

• Address the need for accurate solar panel fault detection on edge devices and UAVs.
• Develop a lightweight, attention-enhanced architecture suitable for real-time inspection.
• Ensure robust evaluation with split-before-augmentation to prevent data leakage.

Proposed method

• Backbone: EfficientNet-B0 pretrained on ImageNet to balance accuracy and efficiency.
• Attention: Insert CBAM after the backbone to refine feature maps via channel and spatial attention.
• Classifier head: Global average pooling, dropout (p=0.4), and a linear layer for six fault classes.
• Training strategies: Focal loss to handle class imbalance and cosine annealing scheduler over 25 epochs.
• Data handling: Split-before-augmentation with 70/15/15 train/val/test, preprocessing to 380x380 and ImageNet normalization.

Experimental results

Research questions

• RQ1 Can a lightweight backbone with attention mechanisms achieve competitive accuracy for solar panel fault detection on edge devices?
• RQ2 Does CBAM improve localization of defects and overall classification metrics compared to EfficientNet-B0 alone?
• RQ3 Do focal loss and cosine annealing contribute to better performance on imbalanced solar fault classes?
• RQ4 Is the model suitable for real-time UAV deployment in terms of speed and memory footprint?

Key findings

• HybridSolarNet achieves 92.37% accuracy and 0.9226 F1-score on the held-out test set.
• CBAM provides an accuracy gain of 1.53% and F1 improvement of 1.54% over EfficientNet-B0.
• Focal loss improves minority class performance and overall F1 score.
• Cosine annealing improves convergence stability over a fixed learning rate.
• HybridSolarNet is 32x smaller than VGG19 (16.3 MB vs. 532.6 MB) and runs at 54.9 FPS on GPU.
• Cross-validation shows mean accuracy 92.37% ± 0.41 and mean F1 0.9226 ± 0.39.
• Grad-CAM visualizations indicate the model focuses on actual defects rather than artifacts.