Fault Detection and Classification in PV Arrays with Machine Learning Algorithms

Fault detection and classification in photovoltaic arrays are important for improving the reliability, safety, and energy production of photovoltaic systems. This study presents a two-stage evaluation of machine learning-based PV fault diagnosis using both simulation-generated and measured experimental data. First, a ۶۴-module PV array with an ۸×۸ configuration is modeled in MATLAB/Simulink under ten normal and faulty operating conditions. Support Vector Machine and Naive Bayes classifiers are evaluated before and after Principal Component Analysis preprocessing. PCA-SVM achieves the highest accuracy of ۹۷.۹۳% in the ten-class simulation study, compared with ۸۶.۵۰% and ۴۳.۱۲۵% for SVM and Naive Bayes, respectively. Second, external validation is performed using twelve measured current-voltage curves obtained from six physical PV panels under clean and partial-shading conditions. The measured curves are processed into ۳,۶۰۰ observations and evaluated using leave-one-panelout validation. Six classifier families, including SVM, Naive Bayes, Random Forest, XGBoost, LightGBM, and MLP are investigated both with and without PCA. Random Forest achieves the highest experimental-data accuracy of ۹۷.۵۳%. PCA increases SVM accuracy from ۶۸.۱۴% to ۷۹.۶۹% and XGBoost accuracy from ۸۳.۳۳% to ۹۰.۰۳%, while its effect is unfavorable for several other classifiers. The results demonstrate that PCA can improve feature separability, but its effectiveness is classifier- and dataset-dependent. The external validation confirms the usefulness of electrical and environmental features for measured partialshading diagnosis while also highlighting the need for broader field validation.

کلیدواژه ها:

Photovoltaic Array ، Fault diagnosis ، Fault classification ، Principal Component Analysis ، External validation ، Support Vector Machine ، Random Forest