This paper aims to present a robust fault diagnosis structure-based observers for actuator faults in the pitch part system of the wind turbine benchmark. In this work, two linear estimators have been proposed and investigated: the Kalman filter and the Luenberger estimator for observing the...
20 January 2023 in The Journal of Engineering and Exact Sciences
The electrocardiogram (ECG) is an essential tool in the field of cardiology, as it enables the electrical activity of the heart to be measured. It involves placing electrodes on the patient's skin, facilitating the measurement and analysis of cardiac rhythms. This non-invasive and painless test provides essential information about the heart's function and helps in diagnosing various cardiac conditions. The classification of ECG signals using deep learning techniques has garnered substantial interest in recent years; ECG classification tasks have exhibited promising outcomes with the application of deep learning models, particularly convolutional neural networks (CNNs). The GoogleNet, AlexNet, and ResNet Deep-CNN models are proposed in this study as reliable methods for accurately diagnosing and classifying cardiac diseases using ECG data. The primary objective of these models is to predict and classify prevalent cardiac ailments, encompassing arrhythmia (ARR), congestive heart failure (CHF), and normal sinus rhythm (NSR). To achieve this classification, 2D Scalogram images obtained through the continuous wavelet transform (CWT) are utilized as input for the models. The study's findings demonstrate that the GoogleNet, AlexNet and Resnet models achieve an impressive accuracy rate of 96%, 95,33% and 92,66%, in accurately predicting and classifying ECG signals associated with these cardiac conditions, respectively. Overall, the integration of deep learning techniques, such as the GoogleNet, AlexNet, and ResNet models, in ECG analysis holds promise for enhancing the accuracy and efficiency of diagnosing and classifying cardiac diseases, potentially leading to improved patient care and outcomes.
18 May 2024 in Iranian Journal of Science and Technology, Transactions of Electrical Engineering
The monitoring of wind turbine (WT) systems allows operators to maximize their performance, consequently minimizing untimely shutdowns and related hazard situations while maximizing their efficiency. Indeed, the rational monitoring of WT ensures the identification of the main sources of risks at a proper time, such as internal or external failures, hence leading to an increase in their prevention by limiting the faults’ occurrence regarding the different components of wind turbines, achieving production objectives. In this context, the present paper develops a practical monitoring approach using a numerical fault-detection process for the pitch system based on a benchmark wind turbine (WT) model with the main aim of improving safety and security performance. Therefore, the proposed fault-diagnosis procedure deals with eventual faults occurring in the actuators and sensors of the pitch system. In this proposed approach, a simple, logical process is used to generate the correct residuals as fault information based on the redundancy in the actuators and sensors of the pitch sub-systems. The obtained results demonstrate the effectiveness of this proposed process for ensuring the tasks of the fault diagnosis and condition monitoring of the WT systems, and it can be a promising approach for avoiding major damage in such systems, leading to their operational stability and improved reliability and availability.
14 January 2022 in International Journal of System Assurance Engineering and Management