Automated Technical Feature Detection in Electrical Education Projects for Solar Energy Feedback System

The increasing global emphasis on renewable energy has underscored the need for education that not only builds theoretical foundations but also strengthens practical technical skills in solar energy. Electrical projects, such as solar panel design, microgrid integration, and photovoltaic (PV) simulations, are central to learning, yet the manual evaluation of these projects often misses subtle technical features and consumes significant instructor time. The problem lies in the absence of intelligent, automated systems capable of detecting, analyzing, and evaluating technical features in student submissions with consistency and reliability. To address this gap, the paper propose the Automated Technical Feature Detection for Solar systems (ATFD-SS) framework, which integrates natural language processing, image recognition, and rule-based evaluation models to identify design elements, coding structures, simulation parameters, and performance metrics embedded in electrical projects. The system preprocesses inputs such as project reports, source code, and PV simulation files, then applies AI-driven feature extraction to generate structured evaluations. Experimental results from pilot tests with 85 solar education projects showed that ATFD-SE improved detection accuracy of critical features by 31%, reduced instructor evaluation time by 45%, and enhanced feedback quality through precise technical annotations. The findings demonstrate that intelligent automation can significantly augment educational practices by ensuring fairness, consistency, and timely feedback in project-based solar learning environments. In conclusion, ATFD-SE offers a scalable and adaptive framework to strengthen solar energy education, equipping students with clearer insights into their technical progress while enabling educators to focus on higher-level guidance and mentoring.

Hali tarjima qilinmagan