Yazar "Hafaifa, Ahmed" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Johnson’s SU distribution using Gray Wolf Optimizer algorithm for fitting gas turbine reliability data
    (Springer, 2024) Charrak, Naas; Djeddi, Ahmed Zohair; Hafaifa, Ahmed; Elbar, Mohammed; Iratni, Abdelhamid; Çolak, İlhami
    Controlling failures and degradation of gas turbines is crucial for optimizing efficiency, productivity, and maintaining safe operations in the oil and gas industry. Reliability indices play a vital role in supporting these goals by enabling informed decisions about gas turbine lifespan extension and operational safety. This study proposes a novel approach to estimate reliability indices for a GE MS5002C gas turbine. It leverages the Johnson SU distribution applied to operating data and optimizes the obtained model using the Gray Wolf algorithm to improve prediction accuracy. We compare the proposed method with the three-parameter Weibull distribution to validate its effectiveness. By employing the Johnson SU transformation alongside the Gray Wolf Optimizer, this work offers a more accurate and robust method for determining reliability indicators. This approach, based on survival analysis, unlocks the full operating potential of the turbine while addressing uncertainties and errors in reliability modeling. Consequently, it allows for enhanced control of failure sources throughout the turbine's life cycle, ensuring availability and minimizing environmental impact. © The Author(s), under exclusive licence to Society for Reliability and Safety (SRESA) 2024.
  • Küçük Resim Yok
    Öğe
    Practical implementation based on histogram of oriented gradient descriptor combined with deep learning: Towards intelligent monitoring of a photovoltaic power plant with robust faults predictions
    (Elsevier B.V., 2025) Hadroug, Nadji; Amari, Amel Sabrine; Alayed, Walaa; Iratni, Abdelhamid; Hafaifa, Ahmed; Çolak, İlhami
    The increasing complexity of photovoltaic (PV) system monitoring underscores the importance of precise fault detection and energy loss prediction. This paper proposes a deep learning-based framework that integrates multiple advanced techniques to accurately detect, localize, and predict faults in PV panels. A pre-trained Convolutional Neural Network (CNN), based on the AlexNet architecture, processes thermal imaging data for precise fault extraction. This facilitates the classification of faults, contributing to improved decision-making in PV system management. To further enhance real-time monitoring, the framework integrates the Histogram of Oriented Gradients (HoG) descriptor with Support Vector Machine (SVM) models, enabling efficient detection and localization of hotspots across the panels. Additionally, the system leverages Long Short-Term Memory (LSTM) networks combined with fuzzy logic to predict panel performance degradation and quantify energy losses caused by detected faults. The learning process relies on the Long-Term Recurrent Convolutional Network (LRCN) to accurately forecast defects by analyzing power efficiency loss rates. Experimental results confirm the effectiveness and reliability of the proposed framework. Achieving an accuracy of 95.45%, with a true positive rate of 91.67% and a true negative rate of 100%, the system demonstrates robust fault detection capabilities. These results highlight the framework's potential to mitigate power losses, ensuring optimal operation of PV systems. This intelligent solution offers a significant advancement in PV system maintenance and monitoring, providing a scalable approach for real-world applications. © 2024 Elsevier Inc.