Solar Hotspot Detection Using VHDL-Simulated Fixed-Point SVM: A Methodology Toward FPGA Realization
Journal of Advances in Engineering and Technology · 22.05.2026 · 4 (2) · 26-40
DOI: 10.54389/fnsb7045 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Advances in Engineering and Technology, online erschienen am 22.05.2026. Verfasst von Nayomi Fernando und 4 weiteren Autor:innen.
Abstract (Originalsprache)
and longevity. This study presents a complete end-to-end methodology for implementing a fixed-point Medium Gaussian Support Vector Machine classifier using VHDL for a Field Programmable Logic Array. The approach begins with feature extraction from thermal images of healthy and defective solar panels, which focuses on MPEG-7 descriptors. The study shows that high impact for hotspot detection comes from blue chrominance contrast. A medium Gaussian SVM model is trained in MATLAB and converted to a fixed-point Q1.15 format for hardware compatibility. Key parameters, including support vectors, Lagrange multipliers, bias, and kernel scale, are extracted and verified in a custom Python environment to ensure numerical alignment with MATLAB results. The validated model is then implemented in synthesizable VHDL. It is verified using GHDL and the GNU Tool Kit waveform viewer, confirming bit-accurate hardware behaviour. Results show classification accuracy exceeding 99.3% with negligible performance loss due to quantization. The design achieves deterministic latency through an FSM-based structure and parallel feature processing for a 300-support vector and 222-feature system. This method enables low-power, real-time inference on a UAV-based edge platform, primarily focusing on drones. CCS CONCEPTS Hardware ~ Electronic design automation ~ Logic synthesis; Computing methodologies ~ Machine learning ~ Learning paradigms ~ Supervised learning; Hardware ~ Integrated circuits ~ Reconfigurable logic and FPGAs; Computer systems organization ~ Real-time systems KEYWORDS: Deep Learning, FPGA, Machine Learning, MPEG-7, Solar PV, SVM, VHDL
Zitieren
APA
Fernando, N., Seneviratne, L., Weerasinghe, N., Rathnayake, N., & Hoshino, Y. (2026). Solar Hotspot Detection Using VHDL-Simulated Fixed-Point SVM: A Methodology Toward FPGA Realization. Journal of Advances in Engineering and Technology, 4(2), 26-40. https://doi.org/10.54389/fnsb7045
Vancouver
Fernando N, Seneviratne L, Weerasinghe N, Rathnayake N, Hoshino Y. Solar Hotspot Detection Using VHDL-Simulated Fixed-Point SVM: A Methodology Toward FPGA Realization. Journal of Advances in Engineering and Technology. 2026;4(2):26-40. doi:10.54389/fnsb7045
BibTeX
@article{Fernando2026,
author = {Fernando, Nayomi and Seneviratne, Lasantha and Weerasinghe, Nisal and Rathnayake, Namal and Hoshino, Yukinobu},
title = {Solar Hotspot Detection Using VHDL-Simulated Fixed-Point SVM: A Methodology Toward FPGA Realization},
journal = {Journal of Advances in Engineering and Technology},
year = {2026},
volume = {4},
number = {2},
pages = {26--40},
doi = {10.54389/fnsb7045}
}
EUVIMED