Detection and Classification of Faults in Solar PV Array Using Thevenin Equivalent Resistance

Karmakar, Binoy Kumar; Pradhan, Ashok Kumar

doi:10.1109/jphotov.2019.2959951

Cited by 68 publications

(15 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Minimize: ER(𝑋), 𝑆(𝑋) 𝑋 ∈ 𝑅 𝑛 (28) Without loss of generality, the fitness function used to evaluate the quality of each particle can be simplified as following [60,61]:…”

Section: Optimal Feature Selectionmentioning

confidence: 99%

“…The abovementioned feature selection problem described in (28) and ( 29) is solved using the proposed DEOA by minimizing the classification error and number of selected features simultaneously. The convergence curves produced by the proposed DEOA, EOA [67], and MOPSO [68] in solving the feature selection problem are illustrated in Fig.…”

Section: B Performance Comparison On the Extraction And Selection Of Fault Featuresmentioning

confidence: 99%

“…Apart from the above approaches, the idea of using SAE to extract features in deep learning architecture has also been deliberated in other studies. In [25] Other protection techniques were also proposed to solve the fault detection and classification issues of grid-connected PV systems based on Thevenin Equivalent Resistance [28], radial basis function networks [29], wavelet transform [24], statistical monitoring [30], fuzzy inference [31] and etc. Furthermore, several studies were proposed to diagnose the PV faults used in different applications by first identifying the root causes of these faulty situations and then proposing the corresponding solutions to prevent their occurrence in the future, including the fault diagnosis [32,33], prediction [34], cost irradiance monitoring [35], maintenance [10], and islanding [36][37][38].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hybrid Deep Learning Model for Fault Detection and Classification of Grid-Connected Photovoltaic System

et al. 2022

View full text Add to dashboard Cite

Effective fault detection and classification play essential roles in reducing the hazards such as electric shocks and fire in photovoltaic (PV) systems. However, the issues of interest in fault detection and classification for PV systems remain an open-ended challenge due to manual and time-consuming processes that require the relevant domain knowledge and experience of fault diagnoses. This paper proposes a hybrid deep-learning (DL) model-based combined architectures as the novel DL approaches to achieve the real-time automatic fault detection and classification of a PV system. This research employed the wavelet packet transform (WPT) as a data preprocessing technique to handle the PV voltage signal collected and feeding them as the inputs for combined DL architectures that consist of the equilibrium optimizer algorithm (EOA) and long short-term memory (LSTM-SAE) approaches. The combined DL architectures are able to extract the fault features automatically from the preprocessed data without requiring any previous knowledge, therefore can override the traditional shortages of manual feature extraction and manual selection of optimal features from the extracted fault features. These desirable features are anticipated to speed up the fault detection and classification capability of the proposed DL model with higher accuracy. In order to determine the performance of the proposed fault model, we carried out a comprehensive evaluation study on a 250-kW grid-connected PV system. In this paper, symmetrical and asymmetrical faults have been studied involving all the phases and ground faults such as single phase to ground, phases to phase, phase to phase to ground, and three-phase to ground. The simulation results validate the efficacy of the proposed model in terms of computation time, accuracy of fault detection, and noise robustness. Comprehensive comparisons between the simulation results and previous studies demonstrate the multidisciplinary applications of the present study.INDEX TERMS Deep distributed energy, equilibrium optimizer algorithm (EOA), fault detection and classification, grid-connected photovoltaic systems, optimal feature selection, wavelet packet transform (WPT).

show abstract

Section: Optimal Feature Selectionmentioning

confidence: 99%

Section: B Performance Comparison On the Extraction And Selection Of Fault Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Deep Learning Model for Fault Detection and Classification of Grid-Connected Photovoltaic System

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Karmakar and Pradhan 29 have illustrated fault detection and classification method utilizing current, array voltage, temperature measurements, and irradiance. This technique calculates the venin equivalent resistance of the PV sequence to accurately identify the fault.…”

Section: Recent Research Work: a Brief Reviewmentioning

confidence: 99%

A PCA‐NPOGBDT strategy‐based protection scheme to differentiate between inverter and distribution line faults plus detection and identification of faulty section in microgrid

Singaram¹,

Balakrishnan²

2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

An effective hybrid strategy-based protection scheme to differentiate between inverter faults and symmetric/unsymmetric faults on distribution line, in addition to detect and identify that faulty section in a microgrid. The proposed hybrid strategy is combined execution of principal component analysis (PCA) and nomadic people optimizer (NPO) learning process-based gradient boosting decision tree (GBDT). Hence it is commonly named as PCA-NPOGBDT strategy. Here, three stages are occupied using fault analysis on microgrid to differentiate among inverter faults on microgrid and symmetric/unsymmetric faults on distribution line, in addition to detect/classify that faults and recognize that faulty section. They are: data set generation, feature removal and training process. In this paper, the first procedure of the proposed strategy is the microgrid parameters such as voltage and current signals at usual and unusual condition data set preparation with PCA technique. The data set based on PCA preparation process has feature removal of the power flow parameters and describes that characteristics nature of the various signals happened with microgrid system. The removed data set is evaluated with the NPO-based GBDT system to classify that sort of fault happened at microgrid system. The proposed model is performed at MATLAB/Simulink

show abstract

“…Motivation E XPONENTIAL growth in photovoltaic (PV) deployments has raised interest in its reliable operation [1]. As PV panels are installed in harsh environments and subjected to varying weather conditions, they are prone to diverse faults (permanent, incipient, and intermittent) with different severity levels [2]. Such faults could diminish energy production, accelerate aging, and even cause fire hazards [3].…”

Section: Introductionmentioning

confidence: 99%

Explainable Incipient Fault Detection Systems for Photovoltaic Panels

Sairam,

Srinivasan,

Marafioti

et al. 2020

Preprint

View full text Add to dashboard Cite

This paper presents an eXplainable Fault Detection and Diagnosis System (XFDDS) for incipient faults in PV panels. The XFDDS is a hybrid approach that combines the modelbased and data-driven framework. Model-based FDD for PV panels lacks high fidelity models at low irradiance conditions for detecting incipient faults. To overcome this, a novel irradiance based three diode model (IB3DM) is proposed. It is a nine parameter model that provides higher accuracy even at low irradiance conditions, an important aspect for detecting incipient faults from noise. To exploit PV data, an extreme gradient boosting (XGBoost) is used due to its ability to detecting incipient faults. Lack of explainability, feature variability for sample instances, and false alarms are challenges with data-driven FDD methods. These shortcomings are overcome by hybridization of XGBoost and IB3DM, and using eXplainable Artificial Intelligence (XAI) techniques. To combine the XGBoost and IB3DM, a faultsignature metric is proposed that helps reducing false alarms and also trigger explanation on detecting incipient faults. To provide explainability, an eXplainable Artificial Intelligence (XAI) application is developed. It uses the local interpretable model-agnostic explanations (LIME) framework and provides explanations on classifier outputs for data instance. These explanations help field engineers/technicians for performing troubleshooting and maintenance operations. The proposed XFDDS is illustrated using experiments on different PV technologies and our results demonstrate the perceived benefits.

show abstract

Detection and Classification of Faults in Solar PV Array Using Thevenin Equivalent Resistance

Cited by 68 publications

References 17 publications

Hybrid Deep Learning Model for Fault Detection and Classification of Grid-Connected Photovoltaic System

Hybrid Deep Learning Model for Fault Detection and Classification of Grid-Connected Photovoltaic System

A PCA‐NPOGBDT strategy‐based protection scheme to differentiate between inverter and distribution line faults plus detection and identification of faulty section in microgrid

Explainable Incipient Fault Detection Systems for Photovoltaic Panels

Contact Info

Product

Resources

About