Feature extraction and health status prediction in PV systems. (August 2022)

• Record Type: Journal Article
• Authors: Sepúlveda Oviedo, Edgar Hernando; Travé-Massuyès, Louise; Subias, Audine; Alonso, Corinne; Pavlov, Marko
• Is Part Of: Advanced engineering informatics. Volume 53(2022)
• Publication Date: 2022-08
• Subjects: Photovoltaic system -- Fault classification -- Feature extraction -- Wavelet transform -- Multiresolution signal decomposition -- Unsupervised learning -- Fault diagnosis -- Fault detection -- Partial least squares -- Hierarchical clustering -- Dynamic time warping; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2022.101696
• Languages: English
• ISSNs: 1474-0346

Abstract

Abstract: Diagnosis aims at predicting the health status of components and systems. In photovoltaic systems, it is vital to guarantee energy production and extend the useful life of photovoltaic power plants. Multiple prediction and classification algorithms have been proposed for this purpose in the literature. The accuracy of these algorithms depends directly on the quality of the data and the features with which they are tuned or trained. In this paper, an innovative approach for predicting the health status of photovoltaic systems is proposed, which includes a feature selection stage. This approach first discriminates severely affected photovoltaic panels using basic electrical features. In a second step, it discriminates the other faulty panels using more elaborated time–frequency features and selecting the most relevant features through correlation and variance analysis. Finally, the approach predicts the health status of photovoltaic panels using a nonlinear regression method named partial least squares. This later is then combined with linear discriminant analysis and compared. The approach is validated with real current data from a photovoltaic plant composed of twelve photovoltaic panels with power between 205 and 240 Wp in three health states, namely broken glass, healthy, and big snail trails. The results obtained show that the proposed approach efficiently predicts the three health states. It determines the level of degradation of the panels, which indicates priorities to corrective and predictive maintenance actions. Furthermore, it is cost-effective since it uses only electrical measurements that are already available in standard photovoltaic data acquisition systems. Above all, the approach is generic and it can be easily extrapolated to other diagnosis problems in other domains.