A Novel Fault Identification Method for Photovoltaic Array via Convolutional Neural Network and Residual Gated Recurrent Unit

Abstract

Under the background of the large-scale construction of photovoltaic (PV) power stations, it is crucial to discover and solve module failures in time for improving the service life and maintaining the normal operation efficiency of modules. Based on analyzing the difference of I-V curves of PV arrays under different fault states, the I-V curves, temperatures and irradiances are taken as input data, and a fusion model of convolutional neural network (CNN) and residual-gated recurrent unit (Res-GRU) is proposed to identify the PV array fault. This model consists of a 1-dimensional CNN module with a 4-layer structure and a Res-GRU module. It has the advantages of end-to-end fault diagnosis, no manual feature extraction, strong anti-interference ability, and usable in the absence of irradiances and temperatures. Moreover, it can not only identify a single fault (e.g., short circuit, partial shading, abnormal aging, etc.), but also can effectively identify hybrid faults. Experimental results show that the classification accuracy of the proposed method is 98.61%, which is better than the ones of the artificial neural network (ANN), the extreme learning machine with kernel function (KELM), the fuzzy C-mean (FCM) clustering, the residual neural network (ResNet), and the stage-wise additive modeling using multi-class exponential loss function based on the classification and regression tree (SAMME-CART). In addition, in the absence of temperatures and irradiances, the classification accuracy still reaches 95.23%, which has a broad application prospect in the online fault diagnoses of PV arrays. INDEX TERMS Photovoltaic, fault diagnosis, I-V curve, 1-dimensional convolutional neural network (1-D CNN), residual-gated recurrent unit (Res-GRU)

Advances in the Application of Machine Learning Techniques for Power System Analytics: A Survey

“…Jia [79], Ou et al [84], and Alawad et al [88] also highlighted the need to clean up missing data, while Li et al [44] wrote the missing features as zero to keep the dimension of the matrix constant. Additionally, Gao et al [73] presented an ML-based fault detection system in a photovoltaic array and quantified the impact of missing PV input data (irradiance, temperature, and different combinations of them) on system accuracy. On the other hand, Li et al [83], Vantuch et al [54], and Liao et al [53] discussed the effect of the imbalanced dataset on performance.…”

Application of Artificial Neural Networks to photovoltaic fault detection and diagnosis: A review

“…Chen et al [97] combine I-V curve data with G and TM to form up a 404 feature matrix. Similar I-V curve-based approaches are also applied in [98,99]. Besides, Aziz et al adopted Continuous Wavelet Transform (CWT) [100] to generate scalograms (2-D graphs) from environmental and array electrical parameters.…”

Machine Learning-Based Condition Monitoring for PV Systems: State of the Art and Future Prospects

“…In addition, 1866 cases of healthy operation under working conditions were collected. Gao et al [78] used a set of recorded features (i.e., I-V, solar irradiance, temperature) to train a hybrid CNN for PV fault classification (10 types). The CNN algorithm was consolidated with a Residual Gated Recurrent Unit (Res-GRU) to provide the capability of dynamic online training.…”