Publications Scientifiques
Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10
Browse
13 results
Search Results
Item Enhancing Fault Diagnosis of Uncertain Grid-Connected Photovoltaic Systems using Deep GRU-based Bayesian optimization(Elsevier B.V., 2024) Yahyaoui, Zahra; Hajji, Mansour; Mansouri, Majdi; Kouadri, Abdelmalek; Bouzrara, Kais; Nounou, HazemThe efficacy of photovoltaic systems is significantly impacted by electrical production losses attributed to faults. Ensuring the rapid and cost-effective restoration of system efficiency necessitates robust fault detection and diagnosis (FDD) procedures. This study introduces a novel interval-gated recurrent unit (I-GRU) based Bayesian optimization framework for FDD in grid-connected photovoltaic (GCPV) systems. The utilization of an interval-valued representation is proposed to address uncertainties inherent in the systems, the GRU is employed for fault classification, while the Bayesian algorithm optimizes its hyperparameters. Addressing uncertainties through the proposed approach enhances monitoring capabilities, mitigating computational and storage costs associated with sensor uncertainties. The effectiveness of the proposed approach for FDD in GCPV systems is demonstrated using experimental application.Item Intelligent fault classification of air compressors using Harris hawks optimization and machine learning algorithms(SAGE, 2024) Afia, Adel; Gougam, Fawzi; Rahmoune, Chemseddine; Touzout, Walid; Ouelmokhtar, Hand; Benazzouz, DjamelDue to their complexity and often harsh working environment, air compressors are inevitably exposed to a variety of faults and defects during their operation. Thus, condition monitoring is critically required for early fault recognition and detection to avoid any type industrial failures. In this paper, an intelligent algorithm for reciprocating air compressor fault diagnosis is developed using real-time acoustic signals acquired from an air compressor with one healthy and seven different faulty states such as leakage inlet valve (LIV), leakage outlet valve (LOV), non-return valve (NRV), piston ring, flywheel, rider-belt and bearing defects. The proposed algorithm mainly consists of three steps: feature extraction, selection, and classification. For feature extraction, experimental acoustic signals are decomposed using maximal overlap discrete wavelet packet transform (MODWPT) by six levels into 64 wavelet coefficients (nodes). Thereafter, time domain features are calculated for each node to build each air compressor’s health state feature matrix. Each feature matrix dimension is reduced by selecting the most useful features using Harris hawks optimization (HHO) in the feature selection step. Finally, for feature classification, selected features are used as inputs for random forest (RF), ensemble tree (ET) and K-nearest neighbors (KNN) to detect, identify, and classify the compressor health states with high classification accuracy. Comparative studies with several feature extraction and selection methods prove the proposed approach’s efficiency in detecting, identifying, and classifying all air compressor faults.Item Bearing faults classification using a new approach of signal processing combined with machine learning algorithms(Springer Nature, 2024) Gougam, Fawzi; Afia, Adel; Soualhi, Abdenour; Touzout, Walid; Rahmoune, Chemseddine; Benazzouz, DjamelVibration analysis plays a crucial role in fault and abnormality diagnosis in various mechanical systems. However, efficient vibration signal processing is required for valuable diagnosis and hidden patterns’ detection and identification. Hence, the present paper explores the application of a robust signal processing method called maximal overlap discrete wavelet packet transform (MODWPT) that supports multiresolution analysis, allowing for the examination of signal details at different scales. This capability is valuable for identifying faults that may manifest at different frequency ranges. MODWPT is combined with covariance and eigenvalues to signal reconstruction. After that, health indicators are specifically applied on the reconstructed vibration signal for feature extraction. The proposed approach was carried out on an experimental test rig where the obtained results demonstrate its effectiveness through confusion matrix analysis of machine learning tools. The ensemble tree model gives more accurate results (accuracy and stability) of bearing faults classification and efficiently identify potential failures and anomalies in mechanical equipment.Item Robust Fault Diagnosis of SCARA Industrial Robot Manipulator(2018) Lounici, Yacine; Touati, Youcef; Adjerid, SmailNowadays, robotic systems are being in increasingly demanding in many industrial activities. In order to achieve the maximal performance, complex nonlinear dynamic robotic systems were developed. However, as a consequence, the rate of component malfunctions augments with the complexity of systems. These malfunctions are called faults, which may appear in different parts of the system and can induce changes in the dynamic behaviour. This paper deals with fault diagnosis of a particular kind of industrial robots called selective compliance assembly robot arm (SCARA), where both parameter and measurement uncertainties are taken into account. Residuals and thresholds are generated using the quantitative model-based method. The inverse geometric model is used to find analytical solutions for joints angles and distances given the trajectory of the end effector. The presented geometric model is then used to derive the kinematic model. Using this kinematic model, the robot controller computes the necessary torque applied to each DC servomotor in order to move the robot from the current position to the next desired position. The proposed robust fault diagnosis scheme is then implemented for a SCARA manipulator and simulation results are presented in both normal and faulty situations.Item Shading fault detection in a grid-connected PV system using vertices principal component analysis(Elsevier, 2021) Rouani, Lahcene; Harkat, Mohamed Faouzi; Kouadri, Abdelmalek; Mekhilef, SaadPartial shading severely impacts the performance of the photovoltaic (PV) system by causing power losses and creating hotspots across the shaded cells or modules. Proper detection of shading faults serves not only in harvesting the desired power from the PV system, which helps to make solar power a reliable renewable source, but also helps promote solar versus other fossil fuel electricity-generation options that prevent making climate change targets (e.g. 2015’s Paris Agreement) achievable. This work focuses primarily on detecting partial shading faults using the vertices principal component analysis (VPCA), a data-driven method that combines the simplicity of its linear model and the ability to consider the uncertainties of the different measurements of a PV system in an interval format. Data from a gridconnected monocrystalline PV array, installed on the rooftop of the Power Electronics and Renewable Energy Research Laboratory (PEARL), University of Malaya, Malaysia, have been used to train the VPCA model. To prove the effectiveness of this VPCA method, four partial shading patterns have been created. The obtained performance has, then, been tested against a regular PCA. In addition to its ability to acknowledge the uncertainty of a PV system, the VPCA method has shown an enhanced performance of detecting partial shading fault in comparison with the standard PCA. Also, included in the article is an extension of the contribution plot diagnosis-based method, of the Q-statistic, to the interval-valued case aiming to pinpoint the out-of-control variables.Item Bearing fault diagnosis based on feature extraction of empirical wavelet transform (EWT) and fuzzy logic system (FLS) under variable operating conditions(JVE International, 2019) Gougam, Fawzi; Rahmoune, Chemseddine; Benazzouz, Djamel; Merainani, BoualemCondition monitoring of rotating machines has become a more important strategy in structural health monitoring (SHM) research. For fault recognition, the analysis is categorized in two essential main parts: Feature extraction and classification; the first one is used for extracting the information from the signal and the other for decision-making based on these features. A higher accuracy is needed for sensitive places to avoid all kinds of damages that can lead to economic losses and it may affect the human safety as well. In this paper, we propose a new hybrid and automatic approach for bearing faults diagnosis. This method uses a combination between Empirical wavelet Transform (EWT) and Fuzzy logic System (FLS), in order to detect and localize the early degradation of bearing state under different working conditions. EWT build a wavelet filter bank to extract amplitude modulated-frequency modulated component of signal. Modes presenting a high impulsiveness is then selected using the kurtosis indicator. Thereafter, time domain features (TDFs) are applied for the reconstructed signal to extract the fault features which are finally used as an inputs of FLS in order to identify and classify the bearing states. The experimental results shows that the proposed method can accurately extract and classify the bearing fault under variable conditions. Moreover, performance of EWT and empirical mode decomposition (EMD) are studied and shows the superiority of the proposed methodItem Multivariate feature extraction based supervised machine learning for fault detection and diagnosis in photovoltaic systems(Elsevier, 2020) Hajji, Mansour; Harkat, Mohamed-Faouzi; Kouadri, Abdelmalek; Abodayeh, Kamaleldin; Mansouri, Majdi; Nounou, Hazem; Nounou, MohamedItem Sensor fault detection, localization, and system reconfiguration with a sliding mode observer and adaptive threshold of PMSM(2016) Aibeche, Abderrazak; Kidouche, MadjidThis study deals with an on-line software fault detection, localization, and system reconfiguration method for electrical system drives composed of three-phase AC/DC/AC converters and three-phase permanent magnet synchronous machine (PMSM) drives. Current sensor failure (outage), speed/position sensor loss (disconnection), and damaged DC-link voltage sensor are considered faults. The occurrence of these faults in PMSM drive systems degrades system performance and affects the safety, maintenance, and service continuity of the electrical system drives. The proposed method is based on the monitoring signals of “abc” currents, DC-link voltage, and rotor speed/position using a measurement chain. The listed signals are analyzed and evaluated with the generated residuals and threshold values obtained from a Sliding Mode Current-Speed-DC-link Voltage Observer (SMCSVO) to acquire an on-line fault decision. The novelty of the method is the faults diagnosis algorithm that combines the use of SMCSVO and adaptive thresholds; thus, the number of false alarms is reduced, and the reliability and robustness of the fault detection system are guaranteed. Furthermore, the proposed algorithm’s performance is experimentally analyzed and tested in real time using a dSPACE DS 1104 digital signal processor boardItem Fault feature extraction and classification based on HEWT and SVD : application to rolling bearings under variable conditions(IEEE, 2017) Merainani, Boualem; Rahmoune, Chemseddine; Benazzouz, Djamel; Ould-Bouamama, Belkacem; Ratni, AzeddineItem Rolling bearing fault diagnosis based empirical wavelet transform using vibration signal(IEEE, 2017) Merainani, Boualem; Rahmoune, Chemseddine; Benazzouz, Djamel; Ould-Bouamama, Belkacem