Artificial Intelligence based chatbot for solar panels quality assurance

Sara Kolac; Luka Katava

doi:10.31449/upinf.272

Authors

Sara Kolac University of Zagreb, Faculty of Organization and Informatics
Luka Katava University of Zagreb, Faculty of Organization and Informatics

DOI:

https://doi.org/10.31449/upinf.272

Keywords:

Solar panels, Large Language Models, Quality assurance, Chatbot system, Artificial Intelligence

Abstract

The paper addresses the need for improved solar panel quality assurance by developing an AI-based chatbot system tailored for installers and manufacturers. Traditional quality assurance is often slow, resource-intensive, and subject to human error. Leveraging advances in large language models, the chatbot provides automated support for performance testing, failure detection, and maintenance guidance. Implemented using Promptly and Flowise AI platforms, the system incorporates domain-specific knowledge through Retrieval-Augmented Generation. It delivers technical recommendations, identifies frequent failure points, and offers actionable advice to enhance diagnostic efficiency and maintenance effectiveness. Performance comparisons between platforms show distinct operational characteristics, underscoring the impact of system choice on user experience. Overall, the chatbot demonstrates promising potential to streamline solar panel testing, maintenance, and decision-making processes for industry professionals.

Author Biographies

Sara Kolac, University of Zagreb, Faculty of Organization and Informatics

Sara Kolac is a first year graduate student of Information and Software Engineering. She received a bachelor’s degree in Information and Business Systems from the Faculty of Organization and Informatics, University of Zagreb. She is interested in the field of Data Science.
Luka Katava, University of Zagreb, Faculty of Organization and Informatics

Luka Katava is a young researcher at the Laboratory for Data Mining and Intelligent Systems at Faculty of Organization and Informatics, University of Zagreb, where he works on the OptiSolar AI project focused on intelligent analysis and optimization of solar energy systems. He holds a bachelor's degree in Information and Business Systems and specializes in data mining, intelligent systems, and applied artificial intelligence.