MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202521130705 A) filed by Symbiosis International, Pune, Maharashtra, on Dec. 23, 2025, for 'system and method for automated classification of solar panel faults using convolutional neural networks for edge computing deployment.'
Inventor(s) include Dr. Shreyas Rajendra Hole.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "A computer-implemented system for automated classification of solar panel faults using lightweight convolutional neural networks optimized for edge computing is disclosed. The system comprises a processor and memory, an image acquisition module capturing solar panel surface images, and an image preprocessing module resizing images to 224 224 pixels and normalizing pixel values. A feature extraction module implements a MobileNetV3Small convolutional neural network with depthwise separable convolutions and squeeze-and-excitation blocks pretrained on the ImageNet dataset. A fault classification module categorizes features into six classes including clean panels, bird-drop contamination, dusty panels, electrical damage, physical damage, and snow-covered panels using a classification head with dropout regularization and softmax activation. An output module generates predicted labels with confidence scores. The system achieves accuracy above ninety-two percent with low inference latency on embedded processors, enabling real-time photovoltaic fault monitoring without cloud dependency."
Disclaimer: Curated by HT Syndication.
