Research Article
Analysis of the Complementarity of Two Diagnostic Methods on a PV Generator
@INPROCEEDINGS{10.4108/eai.24-11-2022.2329810, author={Ousmane W. Compaore and Ghaleb Hoblos and Zacharie Koalaga}, title={Analysis of the Complementarity of Two Diagnostic Methods on a PV Generator}, proceedings={Proceedings of the 5th edition of the Computer Science Research Days, JRI 2022, 24-26 November 2022, Ouagadougou, Burkina Faso}, publisher={EAI}, proceedings_a={JRI}, year={2023}, month={5}, keywords={diagnostic analytical redundancy relation artificial network neuron roc auc sensor fault system fault pvg}, doi={10.4108/eai.24-11-2022.2329810} }- Ousmane W. Compaore
Ghaleb Hoblos
Zacharie Koalaga
Year: 2023
Analysis of the Complementarity of Two Diagnostic Methods on a PV Generator
JRI
EAI
DOI: 10.4108/eai.24-11-2022.2329810
Abstract
The performance of Photovoltaic Generators (PVG) drops over time due to failures compared with its maximum operating point. So, an early fault diagnosis method would make it possible to restore the PVG to good working order. The quality of this diagnostic method lies in several factors but also in the nature of the detection modes. Thanks to the computing capabilities, the analysis databases, and development of efficient algorithms closer to artificial intelligence, we realize that decision support methods are a great success for data science. This article offers an analysis of the complementarity of two diagnostic methods based on the analysis of redundancy relationships and on artificial neural networks. These two methods are supposed to provide a good return on investment for a PVG and set guidelines for diagnostic research.