Abstract
The precision of conventional PV fault diagnostic methods faces challenges due to the nonlinear output power characteristics of photovoltaic (PV) arrays and the implementation of the maximum power point tracking (MPPT) algorithm. In severe cases, it may lead to power losses and even arouse safety issues. In this study, the variation characteristics of the sequence waveforms at the moment of failure are investigated and used to develop a novel PV fault diagnostic framework. Firstly, the sequence waveforms of string voltages and currents before and after the fault occurred are collected; the normalized sequence data of voltages, currents, and powers are used as analytic data. Then, the fault feature extraction is realized via a stacked autoencoder (SAE) model. After that, an improved multi-grained cascade forest (IgcForest) is proposed to diagnose faults, e.g., line-to-line (L-L) fault, open-circuit (OC) fault, partial-shading of PV arrays, etc. The advantages of the proposed method are that the SAE method to extract features with higher recognition automatically, and the IgcForest to enhance and exploit fault features. Particularly, the proposed improvements can reduce the feature vector dimension and enhance the information connectivity between forests at all levels for further improving the accuracy of diagnoses. In addition, the validity of the proposed method is verified by numerical simulations and measured data, and the corresponding accuracy of fault diagnoses for single failure reach 99.33% and 98.61%, respectively, which are superior to traditional methods, such as softmax, support vector machines, random forest, gcForest, and daForest. Furthermore, it also has a high accuracy of 98.83% for data sets with the occurrence of multiple faults.
Highlights
With the gradual depletion of traditional fossil energy and the increasingly severe environmental pollution in recent years, people’s demand for renewable and clean energy continues to rise
It can be seen from the confusion matrix that the proposed method has a high accuracy for PV array fault identification
The features extracted by the stacked autoencoder (SAE) are classified by six classifiers including the softmax in [13], the support vector machine (SVM) in [17], the Extreme learning machine (ELM)-AE in [29], the random forest (RF) in [30], the gcForest in [25], the daForest in [26], and the proposed IgcForest
Summary
With the gradual depletion of traditional fossil energy and the increasingly severe environmental pollution in recent years, people’s demand for renewable and clean energy continues to rise. The photovoltaic (PV) power generation has become a central issue due to its advantages such as rapid installation, strong environmental adaptability, and low maintenance costs. The associate editor coordinating the review of this manuscript and approving it for publication was Zhehan Yi. device (OCPD) and ground fault detection/interruption (GFDI) are generally equipped on the dc side [2]–[4], the output power characteristic of a PV system is nonlinear, which makes obstacles in the detection and identification of PV system failures [5]. The maximum power point tracking (MPPT) algorithm will affect the judgment of the protection equipment, assuming that the failure occurs under a low irradiance, or the failure is not serious
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
