Research Publications (Engineering and Built Environment)
Permanent URI for this collectionhttp://ir-dev.dut.ac.za/handle/10321/215
Browse
Search Results
Item An adaptive neuro-fuzzy inference scheme for defect detection and classification of solar Pv cells(Academy Publishing Center, 2024-09-12) Moyo, Ranganai Tawanda; Dewa, Mendon; Romero, Héctor Felipe Mateo; Gómez, Victor Alonso; Aragonés, Jose Ignacio Morales; Hernández-Callejo, LuisThis research paper presents an innovative approach for defect detection and classification of solar photovoltaic (PV) cells using the adaptive neuro-fuzzy inference system (ANFIS) technique. As solar energy continues to be a vital component of the global renewable energy mix, ensuring the reliability and efficiency of PV systems is paramount. Detecting and classifying defects in PV cells are crucial steps toward ensuring optimal performance and longevity of solar panels. Traditional defect detection and classification methods often face challenges in providing precise and adaptable solutions to this complex problem. In this study the researchers pose an ANFIS-based scheme that combines the strengths of neural networks and fuzzy logic to accurately identify and classify various types of defects in solar PV cells. The adaptive learning mechanism of ANFIS enables the model to continuously adapt to changes in operating conditions ensuring robust and reliable defect detection capabilities. The ANFIS model was developed and implemented using MATLAB and a high predicting accuracy was achieved.