Search

• A principal component analysis (PCA)-based supervised machine learning (SML) method is developed. • PCA-based SML is proposed to enhance fault detection and diagnosis (FDD) of photovoltaic (PV) systems. • The developed FDD approach uses feature extraction and selection, and fault classification tools. • The detection performance is studied using several PV system faults. • The results show good diagnosis efficiency and higher classification accuracy in PV systems. Fault detection and diagnosis (FDD) in the photovoltaic (PV) array has become a challenge due to the magnitudes of the faults, the presence of maximum power point trackers, non-linear PV characteristics, and the dependence on isolation efficiency. Thus, the aim of this paper is to develop an improved FDD technique of PV systems faults. The common FDD technique generally has two main steps: feature extraction and selection, and fault classification. Multivariate feature extraction and selection is very important for multivariate statistical systems monitoring. It can reduce the dimension of modeling data and improve the monitoring accuracy. Therefore, in the proposed FDD approach, the principal component analysis (PCA) technique is used for extracting and selecting the most relevant multivariate features and the supervised machine learning (SML) classifiers are applied for faults diagnosis. The FDD performance is established via different metrics using data extracted from different operating conditions of the grid-connected photovoltaic (GCPV) system. The obtained results confirm the feasibility and effectiveness of the proposed approaches for fault detection and diagnosis. [ABSTRACT FROM AUTHOR]

Fault Detection and Diagnosis (FDD) for overall modern Wind Energy Conversion (WEC) systems, particularly its converter, is still a challenge due to the high randomness to their operating environment. This paper presents an advanced FDD approach aims to increase the availability, reliability and required safety of WEC Converters (WECC) under different conditions. The developed FDD approach must be able to detect and correctly diagnose the occurrence of faults in WEC systems. The developed approach exploits the benefits of the machine learning (ML)-based Hidden Markov model (HMM) and the principal component analysis (PCA) model. The PCA technique is used for efficiently extracting and selecting features to be fed to HMM classifier. The effectiveness and higher classification accuracy of the developed PCA-based HMM approach are demonstrated via simulated data collected from the WEC. The obtained results demonstrate the efficiency of the PCA-based HMM method over the PCA-based support vector machine (SVM) method. The comparison is made based on several performance metrics through different operating conditions of the WEC systems. • Machine learning based- Hidden Markov model (HMM) technique has been developed for faults detection and diagnosis (FDD). • Most relevant features have been extracted and selected via the principal component analysis (PCA) approach. • The extracted and selected features have been used as observables in HMM procedure. • The developed PCA-based HMM approach has shown good FDD efficiency in Wind Energy Conversion systems. [ABSTRACT FROM AUTHOR]

This paper proposes an improved statistical failure detection technique for enhanced monitoring capabilities of PV systems. The proposed technique offers reduced false alarm and missed detection rates compared to the generalized likelihood ratio test (GLRT) by taking into consideration the nature variance of the GLRT statistics and applying a multiscale representation. The multiscale nature of the data provides better robustness to noises and better monitoring quality. The effectiveness of the proposed multiscale weighted GLRT (MS-WGLRT) method in detecting failures is evaluated using a set of synthetic and simulated PV data where the developed chart is used for detecting single and multiple failures (e.g., Bypass, Mix and Shading failures). Moreover, a set of real-data was used in order to prove the effectiveness of the proposed technique in detecting partial shading faults. All results show that the MS-WGLRT method offers better fault detection performances compared to the classical WGLRT and conventional GLRT charts. [ABSTRACT FROM AUTHOR]

The conventional Kernel Principal Component Analysis (KPCA) -based fault detection technique requires more computation time and memory storage space to analyze large-sized datasets. In this context, two techniques, Spectral Clustering (SpC) and Random Sampling (RnS), are developed to reduce the dataset size by retaining the more relevant observations while preserving the main statistical characteristics of the original dataset. These two techniques and others use the training dataset from two different industrial processes, Tennessee Eastman (TEP) and Cement Plant (CP) to be reduced and provided to build the Reduced KPCA (RKPCA) model-based fault detection scheme. The obtained results show the effectiveness of the proposed techniques in terms of some fault detection performance indices and computation costs. • A Reduced kernel PCA methods are developed for process monitoring. • The monitoring performances are studied using several industrial applications. • Two case studies are considered; Tennessee Eastman process and Cement rotary Kiln process. • The results show good monitoring efficiency and higher detection accuracy. [ABSTRACT FROM AUTHOR]

Electrical power generation using photovoltaic (PV) became an active and continuous growing area for academic and industrial research. The complexity of PV systems and the increase in reliability requirement become a very important issue in automation. Grid-connected PV systems are among the top power technologies with the highest rate of development. Therefore, their proper operation and safe handling is a top priority. To respond for this exigency, we develop a novel technique for PV power systems monitoring. Various key variables can be monitored in PV systems, which include the voltage and frequency of the grid, the voltage and the current of the AC and DC converters, as well as climate data, such as the temperature and irradiance. Tight monitoring of these variables will provide more effective and less interrupted energy supplies. The developed monitoring method is applied and validated using simulated data of PV systems. The developed technique combines the advantages of Exponentially Weighted Moving Average (EWMA), multi-objective optimization (MOO) and Wavelet representation. The MOO is used here to solve the problem of choosing an optimal solution of the following two objective functions: (i) missed detection rate (MDR) and (ii) false alarm rate (FAR) where both of them are simultaneously minimized. Additionally, the use of wavelet representation improves the monitoring performances by reducing the MDR and FAR. The wavelet representation is applied to obtain precise deterministic characteristics besides decorrelation of autocorrelated measurements. The new proposed technique, called Wavelet Optimized EWMA (WOEWMA), is compared with the classical EWMA and Shewhart charts where they are used for detecting single and multiple faults (for example, Bypass, Mismatch, Mix and Shading faults). The performances of the monitoring scheme are evaluated using MDR and FAR indicators. [ABSTRACT FROM AUTHOR]