Regarding the fault diagnosis of Copper Indium Gallium Selenide (CIGS) PV modules, previously published articles focused on employing statistical analysis of thermography images. This approach failed in many cases to distinguish among fault types. This article presents a novel methodology to diagnose and predict faults of thin-film CIGS PV modules using infrared thermography analysis combined with measurements of I-V characteristics. The proposed methodology encompasses a comprehensive site work to capture images that cover many fault types of the PV module under study. The novelty of the technique depends on utilizing processing and analysis of the captured images using new proposed mathematical parameters to extract different faults’ features. Using I-V measurements combined with thermography analysis, the differences between different types of faults are detected. Then, a general classification matrix of CIGS fault detection and diagnosis, using features based on mathematical parameters and IV measurements has been established. Results show that the analysis of the temperature distribution is proved to be insufficient to identify specific modes of different faults. In addition, the proposed procedure for fault detection and classification, which depends on the pattern of faults, can be used for any type of PV module. This results in more reliance on the proposed technique to increase the confidence level of fault detection.

No abstract

The use of artificial intelligence to automate PV module fault detection, diagnosis, and classification processes has gained interest for PV solar plants maintenance planning and reduction in expensive inspection and shutdown periods. The present article reports on the development of an adaptive neuro-fuzzy inference system (ANFIS) for PV fault classification based on statistical and mathematical features extracted from outdoor infrared thermography (IRT) and I-V measurements of thin-film PV modules. The selection of the membership function is shown to be essential to obtain a high classifier performance. Principal components analysis (PCA) is used to reduce the dimensions to speed up the classification process. For each type of fault, effective features that are highly correlated to the PV module’s operating power ratio are identified. Evaluation of the proposed methodology, based on datasets gathered from a typical PV plant, reveals that features extraction methods based on mathematical parameters and I-V measurements provide a 100% classification accuracy. On the other hand, features extraction based on statistical factors provides 83.33% accuracy. A novel technique is proposed for developing a correlation matrix between the PV operating power ratio and the effective features extracted online from infrared thermal images. This eliminates the need for offline I-V measurements to estimate the operating power ratio of PV modules.