Deep learning framework for fault detection and diagnosis in grid-connected PV systems using GAN-based data augmentation

Diagnosis of PV faults using digital twin and convolutional mixer with LoRa notification system

Prognostics and health management of photovoltaic systems based on deep learning: A state-of-the-art review and future perspectives

Photovoltaic (PV) fault detection is crucial because undetected PV faults can lead to significant energy losses, with some cases experiencing losses of up to 10%. The efficiency of PV systems depends upon the reliable detection and diagnosis of faults. The integration of Artificial Intelligence (AI) techniques has been a growing trend in addressing these issues. The goal of this systematic review is to offer a comprehensive overview of the recent advancements in AI-based methodologies for PV fault detection, consolidating the key findings from 31 research papers. An initial pool of 142 papers were identified, from which 31 were selected for in-depth review following the PRISMA guidelines. The title, objective, methods, and findings of each paper were analyzed, with a focus on machine learning (ML) and deep learning (DL) approaches. ML and DL are particularly suitable for PV fault detection because of their capacity to process and analyze large amounts of data to identify complex patterns and anomalies. This study identified several AI techniques used for fault detection in PV systems, ranging from classical ML methods like k-nearest neighbor (KNN) and random forest to more advanced deep learning models such as Convolutional Neural Networks (CNNs). Quantum circuits and infrared imagery were also explored as potential solutions. The analysis found that DL models, in general, outperformed traditional ML models in accuracy and efficiency. This study shows that AI methodologies have evolved and been increasingly applied in PV fault detection. The integration of AI in PV fault detection offers high accuracy and effectiveness. After reviewing these studies, we proposed an Artificial Neural Network (ANN)-based method for PV fault detection and classification.

Sentiment classification involves determining the sentiment expressed in text, such as positive, negative, or neutral, but social media data presents challenges due to its high dimensionality, noise, and unstructured nature. This study proposes a novel sentiment classification approach by combining hybrid feature selection methods with deep learning techniques. Social media platforms generate vast amounts of data daily, which is often noisy, redundant, and irrelevant for sentiment analysis. Hybrid feature selection techniques, which integrate filter and wrapper-based methods, assist in reducing the feature space while retaining the most informative features. By applying deep learning models, such as recurrent neural networks (RNNs) and long short-term memory (LSTM) networks, classification performance can be substantially enhanced. The proposed framework uses hybrid feature selection to eliminate noisy and irrelevant features, thereby improving the model's generalization capabilities. Experimental results reveal that the combination of hybrid feature selection and deep learning techniques not only boosts sentiment classification accuracy but also decreases computational overhead. This study highlights the effectiveness of merging traditional feature selection methods with modern deep learning models to better address the complexities of social media datasets and deliver more precise sentiment analysis. The results achieved by proposed model is 98.50% on social media dataset which is higher than conventional approaches.

Photovoltaic (PV) systems have immense potential to generate clean energy, and their adoption has grown significantly in recent years. A PV fault is a condition of a PV module that is unable to produce optimal power due to environmental factors, such as shading, hot spots, cracks, and other defects. The occurrence of faults in PV systems can present safety risks, shorten system lifespans, and result in waste. Therefore, this paper discusses the importance of accurately classifying faults in PV systems to maintain optimal operating efficiency, thereby increasing the financial return. Previous studies in this area have largely relied on deep learning models, such as transfer learning, with high computational requirements, which are limited by their inability to handle complex image features and unbalanced datasets. The proposed lightweight coupled UdenseNet model shows significant improvements for PV fault classification compared to previous studies, achieving an accuracy of 99.39%, 96.65%, and 95.72% for 2-class, 11-class, and 12-class output, respectively, while also demonstrating greater efficiency in terms of parameter counts, which is particularly important for real-time analysis of large-scale solar farms. Furthermore, geometric transformation and generative adversarial networks (GAN) image augmentation techniques improved the model’s performance on unbalanced datasets.

This paper reviews various faults that exist in large solar Photovoltaic (PV) systems. The faults are reviewed in their various classes based on the location and structure. Conventional solutions for fault detection and various research work in PV system monitoring and fault detection are reviewed. It is obvious that PV module level monitoring exhibit advantages over array or string monitoring. Therefore, the paper proposes the use of Long Range (LoRa) Wireless Sensor Networks (WSN) for PV module level monitoring and fault diagnosis. LoRa was proposed for this application due to the advantages it has over other wireless technologies which include long range of data transfer, low cost, low power consumption and multi sensor connection capabilities.

The availability of advanced sensors and computing enables early detection of faults and failures in large-scale solar photovoltaic (PV) systems. However, small variations in current and voltage caused by arcing or other faults/failures are often difficult to detect, potentially leading to a permanent reduction in power output and can potentially cause safety hazard. This work develops novel algorithm for detection and classification of DC arc and AC faults using Conditional Generative Adversarial Networks (CGANs). Three distinct CGAN architectures are developed: two for DC arc fault detection and classification, and another for AC faults. The CGAN networks generate output signals representing probability distributions based on voltage and current measurements at the inverter location of the PV system. The performance of the proposed CGAN architectures is evaluated using rolling precision scores on backcasted datasets and compared against a k-Nearest Neighbors (kNN) model, and also validated using real field data. Results show that the proposed architectures achieve high precision in detecting and classifying both types of faults in a 1 MW solar PV system modeled in a real-time simulator.

The widespread adoption of green energy resources worldwide, such as photovoltaic (PV) systems to generate green and renewable power, has prompted safety and reliability concerns. One of these concerns is fault diagnostics, which is needed to manage the reliability and output of PV systems. Severe PV faults make detecting faults challenging because of drastic weather circumstances. This research article presents a novel deep stack-based ensemble learning (DSEL) approach for diagnosing PV array faults. The DSEL approach compromises three deep-learning models, namely, deep neural network, long short-term memory, and Bi-directional long short-term memory, as base learners for diagnosing PV faults. To better analyze PV arrays, we use multinomial logistic regression as a meta-learner to combine the predictions of base learners. This study considers open circuits, short circuits, partial shading, bridge, degradation faults, and incorporation of the MPPT algorithm. The DSEL algorithm offers reliable, precise, and accurate PV-fault diagnostics for noiseless and noisy data. The proposed DSEL approach is quantitatively examined and compared to eight prior machine-learning and deep-learning-based PV-fault classification methodologies by using a simulated dataset. The findings show that the proposed approach outperforms other techniques, achieving 98.62% accuracy for fault detection with noiseless data and 94.87% accuracy with noisy data. The study revealed that the DSEL algorithm retains a strong generalization potential for detecting PV faults while enhancing prediction accuracy. Hence, the proposed DSEL algorithm detects and categorizes PV array faults more efficiently, reliably, and accurately.

The perpetual increment in energy demand continues to put pressure on the South African Economy. Independent Power Producers (IPPs) have been contracted to relieve the strain by supplementing energy production using solar photovoltaic (PV) technologies. These IPPs are paid per megawatt they produce and face stiff penalties should they fail to deliver on contractual obligations. Naturally solar PV plants are susceptible to numerous PV faults that could lead to a negative return on investment. It therefore makes economic sense to adopt mechanisms that can be able to detect, localize and diagnose PV faults when they occur within a solar PV system. There exists an extensive literature on how to detect and diagnose PV faults, however, localizing PV faults is still in its infancy. This paper proposes to cater to the needs of the IPPs by developing an intelligent PV Array Fault Detection and Diagnostics (PVAFDD) system capable of localizing PV faults which can be embedded into the Supervisory Control and Data Acquisition (SCADA) system used to manage and control such PV systems. The PVAFDD system is based on a machine learning (ML) model implemented using logistic regression algorithm. The ML model is trained using meteorological data ranging over a period of eight years in Alice, Eastern Cape. Using simulations driven by real-life data scenarios, we have been able to train, validate and test the PVAFDD system. When the PVAFDD system detects a fault, a cascade of real-time PVA tests is undertaken to localize the PV fault. The system then carries out PVA fault diagnostics and gives recommendations on the PV fault classification. Corrective measures can therefore be implemented on the affected PVA swiftly reducing the downtime of the PV plant, ergo proving to be a cost-effective measure that offers a competitive edge to IPPs using the PVAFDD system.

Photovoltaic (PV) system output electricity is related to PV cells’ conditions, with the PV faults decreasing the efficiency of the PV system and even causing a possible source of fire. In industrial production, PV fault detection is typically laborious manual work. In this paper, we present a method that can automatically detect PV faults. Based on the observation that different faults will have different impacts on a PV system, we propose a method that systematically and iteratively reconfigures the PV array until the faults are located based on the specific current-voltage (I-V) curve of the (sub-)array. Our method can detect several main types of faults including open-circuit faults, mismatch faults, short circuit faults, etc. We evaluate our methods by Matlab/Simulink-based simulation. The results show that the proposed methods can accurately detect and classify the different faults occurring in a PV system.

The meticulous monitoring and diagnosis of faults in photovoltaic (PV) systems enhances their reliability and facilitates a smooth transition to sustainable energy. This paper introduces a novel application of deep learning for fault detection and diagnosis in PV systems, employing a three-step approach. Firstly, a robust PV model is developed and fine-tuned using a heuristic optimization approach. Secondly, a comprehensive database is constructed, incorporating PV model data alongside monitored module temperature and solar irradiance for both healthy and faulty operation conditions. Lastly, fault classification utilizes features extracted from a combination consisting of a Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU). The amalgamation of parallel and sequential processing enables the neural network to leverage the strengths of both convolutional and recurrent layers concurrently, facilitating effective fault detection and diagnosis. The results affirm the proposed technique’s efficacy in detecting and classifying various PV fault types, such as open circuits, short circuits, and partial shading. Furthermore, this work underscores the significance of dividing fault detection and diagnosis into two distinct steps rather than employing deep learning neural networks to determine fault types directly.

ABSTRACTThe establishment of an accurate photovoltaic (PV) arrays model is instrumental in enhancing the precision of PV performance evaluation and fault diagnosis, which holds significant importance for elevating the level of intelligent operation and maintenance of PV power stations. A modelling approach for PV arrays based on the implicit double diode model (IDDM) and the reverse bias model (RBM) is proposed in this paper, along with a rational and efficient method for the model parameters identification. First, an effective PV array modelling method is proposed for series‐connected PV arrays, based on the IDDM and RBM and integrated with the principle of voltage superposition. Then, a two‐stage model parameter identification method is introduced. The first stage employs the maximum power point matching (MPPM) method to swiftly calculate the model parameters corresponding to the voltage‐current (I‐V) characteristics, using these as the initial values for the parameter identification algorithm. The second stage utilises the improved gorilla troops optimizer (IGTO) to achieve precise identification of the model parameters. Ultimately, simulation experiments are conducted to emulate the functionality of the PV array model, with the proposed model achieving a simulation accuracy of 0.0243 A. The parameter identification accuracy of the IGTO reaches 0.0024 A, satisfying the requirements for PV array modelling. This thereby validates the prominent advantages of the model parameter identification method and reflects the application value and prospective development of the PV array model in fault diagnosis.

In light of the escalating global concerns regarding energy security and the irregular distribution of daily irradiance affecting photovoltaic (PV) system output, the demand for effective fault detection and diagnosis techniques in PV management systems is on the rise. Machine learning (ML) has emerged as the preferred approach, attracting extensive research attention. As the adoption of solar PV systems continues to surge, the need for robust fault diagnosis and classification techniques becomes paramount to ensure optimal performance, maintenance and scalability across diverse scales of PV arrays in real-world applications. This paper introduces a Solar PV Smart Fault Diagnosis and Classification (SFDC) model that harnesses the Random Forest (RF) algorithm in conjunction with Cross-Validation (CV) and an optimized feature extraction (FE) set. The deployment of CV serves to assess the model's performance and ensure its resilience. Additionally, an optimized FE set is employed to enhance classification accuracy by selecting the most pertinent features for fault classification. Scalable PV array is modelled with the generated power of 10 kW for small-scale, 250 kW for medium-scale and 2 MW for large-scale. In the training and testing of the models, the RF-CV algorithm with set combination of FE was employed to diagnose and classify different types of faults. In this process, each simulated fault that are line-line faults (LLF), open-circuit faults (OCF), ground faults (GF) and partial shading (PS) dataset was divided, with 80% allocated for training and 20% for testing purposes. As the results, all SFDC models (small, medium, large-scale) developed have achieved 100% accuracy for all fault types in training simulations. While in testing the algorithm, it effectively detected multiple fault types, especially OCF and PS, with a perfect score and slightly lower yet high accuracies for GF. These results indicate the robustness and reliability of the SFDC model in diagnosing and classifying faults in PV systems. This research not only holds the potential to advance the field of solar PV for future energy security but also serves as a valuable reference for researchers and policymakers, aiding in the optimization of PV system maintenance and operation.

In recent years, photovoltaic (PV) energy production has witnessed overwhelming growth, which has inspired the search for more effective operations. Nevertheless, different PV faults may appear, which leads to various degradation stages. Furthermore, under different irradiance levels, these faults may be misclassified as a healthy mode owing to the high resemblances between them, thus provoking serious challenges in terms of power losses and maintenance costs. Hence, interposing the irradiance variation in grid-connected PV (GCPV) systems modeling is important for monitoring tasks to ensure the effective operation of these systems, to increase their reliability and to prevent false alarms. Therefore, in this paper, a fault detection and diagnosis (FDD) method for the GCPV systems using machine learning (ML) based on principal component analysis (PCA) is proposed in order to ensure the reliability and security of the whole system under irradiance variations. The proposed strategy consists of three main steps: (i) introduce the irradiance variations in PV system modeling because of its great impact on power production; (ii) feature extraction and selection through PCA; and (iii) fault classification using ML techniques. In this study, we generate a database that is used to compare the proposed strategy with the standard strategy (considering a fixed irradiance during FDD), to make, at first, a complete and significant comparative assessment of fault diagnosis and to demonstrate the efficiency of the proposed strategy. The achieved results show the high effectiveness of the proposed one-class classification-based approach to detect and diagnose PV array anomalies, reaching an accuracy up to 99.68%.

Photovoltaic (PV) systems nowadays represent an essential component of renewable energy production. However, undetected faults often compromise their reliability, leading to significant energy losses and high maintenance costs. Existing deep learning approaches for PV fault diagnosis have achieved high accuracy, but they require massive, labeled datasets and high computational resources, which make them unsuitable for real-time applications. This paper proposes a lightweight, self-supervised hybrid learning framework for real-time PV fault diagnosis to address these limitations. First, the dataset is split into training, testing, and validation subsets. Thereafter, weighted class calculation steps are performed to overcome the issue of imbalance in the data. Then, a self-supervised pre-training phase is established to enable the encoder to produce effective internal representations prior to the implementation of a supervised fine-tuning classifier, characterized as a lightweight feed-forward network (Dense–Dropout–Dense Softmax), which will be trained using categorical cross-entropy and fault-type labels. Finally, a supervised fine-tuning stage is employed based on the pre-trained hybrid CNN–transformer encoder to perform PV fault classification. The experimental results indicate that the proposed approach outperforms existing models by achieving an overall accuracy of 99.8%, a recall of 99.6%, and an outstanding specificity of 100%. The confusion matrix demonstrates that classification is excellent on all operating types. Runtime analysis indicates that the model processes each sample in 2.78 ms and requires 0.07 MB to store weights of 19,429 parameters, confirming its suitability for real-time deployment. These findings highlight that using a hybrid CNN–Transformer encoder with self-supervised learning can improve fault detection and classification performance while significantly reducing inference time, making it an effective and efficient solution for intelligent PV system monitoring.