Publications Scientifiques

Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10

Browse

Filters

2021 - 20255

Settings

Subject: search.filters.subject.Fault detection and diagnosis (FDD)

Search Results

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Fault detection and diagnosis in photovoltaic power systems using fisher random matrix approach
    (2025) Saidi, Ahmed; Draoui, Abdelghani; Touhami, abdelouahed
    This paper proposes a novel methodology for fault detection and diagnosis (FDD) in photovoltaic (PV) systems that combines Fisher's linear discriminant (FLD) with the Mahalanobis distance. The approach utilizes FLD to reduce the dimensionality of operational data while maximising the separation between healthy and faulty states. The Mahalanobis distance is then used to detect anomalies by accounting for correlations among variables such as voltage, current, and temperature. The validity of the method was established using real-world data from a 20 MWp PV plant in Algeria. The results obtained demonstrate the efficacy of the proposed method in classifying various faults, including open-circuit, shading, and short-circuit faults. The approach demonstrates substantial improvements in detection accuracy, efficiency, and false-alarm reduction compared to conventional methodologies. The proposed FDD solution is robust and scalable, rendering it ideal for real-time monitoring of large-scale PV systems.
  • Thumbnail Image
    Item
    Fault detection and diagnosis in photovoltaic power systems using fisher random matrix approach
    (2025) Saidi, Ahmed; Draoui, Abdelghani; Touhami, Abdelouahed
    This paper proposes a novel methodology for fault detection and diagnosis (FDD) in photovoltaic (PV) systems that combines Fisher's linear discriminant (FLD) with the Mahalanobis distance. The approach utilizes FLD to reduce the dimensionality of operational data while maximising the separation between healthy and faulty states. The Mahalanobis distance is then used to detect anomalies by accounting for correlations among variables such as voltage, current, and temperature. The validity of the method was established using real-world data from a 20 MWp PV plant in Algeria. The results obtained demonstrate the efficacy of the proposed method in classifying various faults, including open-circuit, shading, and short-circuit faults. The approach demonstrates substantial improvements in detection accuracy, efficiency, and false-alarm reduction compared to conventional methodologies. The proposed FDD solution is robust and scalable, rendering it ideal for real-time monitoring of large-scale PV systems.
  • No Thumbnail Available
    Item
    Improvement of kernel principal component analysis-based approach for nonlinear process monitoring by data set size reduction using class interval
    (Institute of Electrical and Electronics Engineers Inc, 2024) Kaib, Mohammed Tahar Habib; Kouadri, Abdelmalek; Harkat, Mohamed-Faouzi; Bensmail, Abderazak; Mansouri, Majdi
    Fault detection and diagnosis (FDD) systems play a crucial role in maintaining the adequate execution of the monitored process. One of the widely used data-driven FDD methods is the Principal Component Analysis (PCA). Unfortunately, PCA's reliability drops when data has nonlinear characteristics as industrial processes. Kernel Principal Component Analysis (KPCA) is an alternative PCA technique that is used to deal with a similar data set. For a large-sized data set, KPCA's execution time and occupied storage space will increase drastically and the monitoring performance can also be affected in this case. So, the Reduced KPCA (RKPCA) was introduced with the aim of reducing the size of a given training data set to lower the execution time and occupied storage space while maintaining KPCA's monitoring performance for nonlinear systems. Generally, RKPCA reduces the number of samples in the training data set and then builds the KPCA model based on this data set. In this paper, the proposed algorithm selects relevant observations from the original data set by utilizing a class interval technique (i.e. histogram) to maintain a bunch of representative samples from each bin. The proposed algorithm has been tested on three tank system pilot plant and Ain El Kebira Cement rotary kiln process. The proposed algorithm has successfully maintained homogeneity to the original data set, reduced the execution time and occupied storage space, and led to decent monitoring performance.
  • No Thumbnail Available
    Item
    Wind power converter fault diagnosis using reduced kernel PCA-Based BiLSTM
    (MDPI, 2023) Attouri, Khadija; Mansouri, Majdi; Hajji, Mansour; Kouadri, Abdelmalek; Bouzrara, Kais; Nounou, Hazem
    In this paper, we present a novel and effective fault detection and diagnosis (FDD) method for a wind energy converter (WEC) system with a nominal power of 15 KW, which is designed to significantly reduce the complexity and computation time and possibly increase the accuracy of fault diagnosis. This strategy involves three significant steps: first, a size reduction procedure is applied to the training dataset, which uses hierarchical K-means clustering and Euclidean distance schemes; second, both significantly reduced training datasets are utilized by the KPCA technique to extract and select the most sensitive and significant features; and finally, in order to distinguish between the diverse WEC system operating modes, the selected features are used to train a bidirectional long-short-term memory classifier (BiLSTM). In this study, various fault scenarios (short-circuit (SC) faults and open-circuit (OC) faults) were injected, and each scenario comprised different cases (simple, multiple, and mixed faults) on different sides and locations (generator-side converter and grid-side converter) to ensure a comprehensive and global evaluation. The obtained results show that the proposed strategy for FDD via both applied dataset size reduction methods not only improves the accuracy but also provides an efficient reduction in computation time and storage space
  • No Thumbnail Available
    Item
    Faults classification in Grid-Connected photovoltaic systems
    (IEEE, 2021) Attouri, Khadija; Hajji, Mansour; Mansouri, Majdi; Nounou, Hazem; Kouadri, Abdelmalek; Bouzrara, Kais
    Fault detection and diagnosis (FDD) for Grid-Connected Photovoltaic (GCPV) systems have been received an important measure for improving the operation of these systems. Therefore, in this paper, an enhanced FDD approach, so-called principal component analysis (PCA)-based on a Kullback-Leibler Divergence (KLD), aims to provide the reliability and safety of the overall GCPV system is proposed. The developed approach merges the benefits of PCA model and KLD metric. Firstly, the GCPV features are extracted using PCA model. Secondly, the extracted features are fed to KLD metric for classification purposes. The obtained results confirm the high accuracy of the developed technique. The proposed approach showed superior effectiveness and robustness in process fault diagnosis