Browsing by Author "Benazzouz, Djamel"

Now showing 1 - 20 of 61

2D-DOA Estimation performance using split vertical linear and circular arrays
(John Wiley & Sons, 2016) Aouina, Karima; Benazzouz, Djamel
This paper presents a new approach to reduce the computational complexity in two-dimensional (2D) matrix pencil (MP) method for direction of arrival (DOA) estimation of plane wave signals using a combination of vertical uniform linear array (VULA) and uniform circular array (UCA). By applying phase mode excitation based beamforming to the UCA, we can apply the matrix pencil (MP) method to the beamspace data using only a single snapshot. The technique is based on the split array, which is composed of two perpendicular arrays. The vertical uniform linear array used to determine the elevation DOA components is located perpendicularly at the center of the uniform circular array in the horizontal plane used to calculate the azimuth angles. Unlike common planar and circular arrays, this antenna array with its particular geometry requires no pair-matching between the azimuth and the elevation angle estimation and can also remove the drawbacks of estimation failure problems. Using this particular geometry for the 2D MP method leads to an efficient computational methodology for real-time implementation on a digital signal processor. The obtained simulation results of the MP method applied to both uncorrelated and correlated narrowband sources in the presence of white noise show good performance estimation
Augmented analytical redundancy relations to improve the fault isolation
(Elsevier, 2018) Termeche, Adel; Benazzouz, Djamel; Ould Bouamama, Belkacem; Abdallah, Ibrahim
Fault detection and isolation (FDI) is an essential task that allows avoiding the fault consequence on the performance of the system. The bond graph, as a modelling tool, provides through its structural and causal properties, an automatic generation of analytical redundancy relations (ARRs). These relations are used for diagnosis applications, they constitute the mathematical constraints that are used to verify the coherence between the process measurements and the reference of the system behaviour represented by the model. The classical ARR diagnosis approach allows to both detect and isolate the defective component in the system. In this work, the main goal is to increase the number of isolable faults by increasing the number of ARRs, using the output of the bond graph model along with the measured output of the real system. The innovative interest in this work is that the number of the isolated faults can be improved without the addition of more sensors. Following the general discussion of the proposed method, a robotic subsystem (traction of an omnidirectional mobile robot) is considered to validate the proposed procedure. Two faulty scenarios are then presented and discussed using both the classical and the proposed approach.The proposed method is able to isolate 3 faults that can not be isolated using classical ARR.
Automated transformer fault diagnosis using infrared thermography imaging, GIST and machine learning technique
(SAGE, 2022) Mahami, Amine; Rahmoune, Chemseddine; Benazzouz, Djamel
Condition monitoring of electrical systems is vital in reducing maintenance costs and enhancing their reliability. By focusing on the monitoring of electrical transformers, which play a crucial role in electrical systems and are the main equipment for electrical transmission and distribution, drastic damages, undesirable loss of power and expensive curative maintenance could be avoided. In this paper, a novel noncontact and non-intrusive framework experimental method is used for the monitoring and the diagnosis of transformer faults based on an infrared thermography technique (IRT). The basic structure of this work begins with applying (IRT) to obtain a thermograph of the considered machine. Second, GIST features of the reference image and all images in the image database are extracted. At last, various faults patterns in the transformer are automatically identified using a machine learning method called Support Vector Machine (SVM). The proposed method effectiveness and capacity are evaluated based on the experimental infrared thermography (IRT) images and the diagnosis results by identifying nine sorts of electrical transformer states among which one is healthy and the remaining eight are of short circuit faults in common core winding type, and showing that it can be considered as a powerful diagnostic tool with high Classification Accuracy (CA) and stability compared to other previously used methods
Automatic condition monitoring of electromechanical system based on MCSA, spectral kurtosis and SOM neural network
(JVE International, 2019) Zair, Mohamed; Rahmoune, Chemseddine; Benazzouz, Djamel; Ratni, Azeddine
Condition monitoring and fault diagnosis play the most important role in industrial applications. The gearbox system is an essential component of mechanical system in fault identification and classification domains. In this paper, we propose a new technique which is based on the Fast-Kurtogram method and Self Organizing Map (SOM) neural network to automatically diagnose two localized gear tooth faults: a pitting and a crack. These faults could have very different diagnostics; however, the existing diagnostic techniques only indicate the presence of local tooth faults without being able to differentiate between a pitting and a crack. With the aim to automatically diagnose these two faults, a dynamic model of an electromechanical system which is a simple stage gearbox with and without defect driven by a three phase induction machine is proposed, which makes it possible to simulate the effect of pitting and crack faults on the induction stator current signal. The simulated motor current signal is then analyzed by using a Fast-Kurtogram method. Self-organizing map (SOM) neural network is subsequently used to develop an automatic diagnostic system. This method is suitable for differentiating between a pitting and a crack fault. © 2019 Zair Mohamed, et al
Automatic condition monitoring of electromechanical system based on MCSA, spectral kurtosis and SOM neural network
(2019) Zair, Mohamed; Rahmoune, Chemseddine; Benazzouz, Djamel; Ratni, Azeddine
Condition monitoring and fault diagnosis play the most important role in industrial applications. The gearbox system is an essential component of mechanical system in fault identification and classification domains. In this paper, we propose a new technique which is based on the Fast-Kurtogram method and Self Organizing Map (SOM) neural network to automatically diagnose two localized gear tooth faults: a pitting and a crack. These faults could have very different diagnostics; however, the existing diagnostic techniques only indicate the presence of local tooth faults without being able to differentiate between a pitting and a crack. With the aim to automatically diagnose these two faults, a dynamic model of an electromechanical system which is a simple stage gearbox with and without defect driven by a three phase induction machine is proposed, which makes it possible to simulate the effect of pitting and crack faults on the induction stator current signal. The simulated motor current signal is then analyzed by using a Fast-Kurtogram method. Self-organizing map (SOM) neural network is subsequently used to develop an automatic diagnostic system. This method is suitable for differentiating between a pitting and a crack fault
Bearing fault detection under time-varying speed based on empirical wavelet transform, cultural clan-based optimization algorithm, and random forest classifier
(SAGE Publications, 2021) Moussaoui, Imane; Rahmoune, Chemseddine; Zair, Mohamed; Benazzouz, Djamel
Bearings are massively utilized in industries of nowadays due to their huge importance. Nevertheless, their defects can heavily affect the machines performance. Therefore, many researchers are working on bearing fault detection and classification; however, most of the works are carried out under constant speed conditions, while bearings usually operate under varying speed conditions making the task more challenging. In this paper, we propose a new method for bearing condition monitoring under time-varying speed that is able to detect the fault efficiently from the vibration signatures. First, the vibration signal is processed with the Empirical Wavelet Transform to extract the AM-FM modes. Next, time domain features are calculated from each mode. Then, the features’ set is reduced using the Cultural Clan-based optimization algorithm by removing the redundant and unimportant parameters that may mislead the classification. Finally, an ensemble learning algorithm “Random Forest” is used to train a model able to classify the fault based on the selected features. The proposed method was tested on a time-varying real dataset consisting of three different bearing health states: healthy, outer race defect, and inner race defect. The obtained results indicate the ability of our proposed method to handle the speed variability issue in bearing fault detection with high efficiency
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, Boualem
Condition 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 method
Bearing faults classification under various operation modes using time domain features, singular value decomposition, and fuzzy logic system
(SAGE, 2020) Gougam, Fawzi; Chemseddine, Rahmoune; Benazzouz, Djamel; Benaggoune, Khaled; Zerhouni, Noureddine
Renewable energies offer new solutions to an ever-increasing energy demand. Wind energy is one of the main sources of electricity production, which uses winds to be converted to electrical energy with lower cost and environment saving. The major failures of a wind turbine occur in the bearings of high-speed shafts. This paper proposes the use of optimized machine learning to predict the Remaining Useful Life (RUL) of bearing based on vibration data and features extraction. Significant features are extracted from filtered band-pass of the squared raw signal where the health indicators are automatically selected using relief technique. Optimized Adaptive Neuro Fuzzy Inference System (ANFIS) by Partical Swarm Optimization (PSO) is used to model the non linear degradation of the extracted indicators. The proposed approach is applied on experimental setup of wind turbine where the results show its effectiveness for RUL estimation.
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, Djamel
Vibration 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.
Bond graph to digraph conversion : a sensor placement optimization for fault detection and isolation by a structural approach
(2014) Alem, Said; Benazzouz, Djamel
In this paper, we consider the optimal sensors placement problem for faults detection and isolation using a novel structural and qualitative approach. This approach is based on the conversion of Bond Graph to Digraph representation of a structural system. When the fault detection and isolation of an existing system’s sensors are impossible or uncertain, a reconfiguration sensor placement of this system should be reconsidered. This paper proposes how this reconfiguration takes place by recovering all missing or redundant parts of the system. This novel approach is illustrated over a thermo-fluid application
CNC milling cutters condition monitoring based on empirical wavelet packet decomposition
(Springer Nature, 2023) Amar Bouzid, Abir; Merainani, Boualem; Benazzouz, Djamel
Machining is a versatile field in the manufacturing industry. In milling operations, tool wear is considered the most critical factor affecting the surface quality of the milled piece. Furthermore, the gradual tool wear impacts the milling process, leading to significant downtime, which has serious financial consequences. Unavoidably, a sustainable and reliable condition monitoring system must be developed to reduce the risk of downtime and enhance production quality. The deployment of prognostic and health management (PHM) solutions is becoming increasingly important. It is regarded as one of the main levers for monitoring tool wear status. In this paper, a novel methodology is proposed for extracting pertinent health indicators (HIs) that reflect the degradation behavior of a set of milling cutters and estimating their remaining useful lives (RULs). First, a new time-frequency signal-analysis approach, titled empirical wavelet packet decomposition (EWPD), is proposed to scrutinize the data collected via multi-sensor acquisition. This technique provides a new segmentation of the signal’s Fourier spectrum, distributed on levels, to investigate a broader variety of frequency bands and enhance the traditional segmentation structure’s performance. Second, a new health indicator is designed based on an innovative selection of the time-domain features computed for each frequency band over each level. Finally, the long short-term memory (LSTM) network is used to estimate the RUL of each cutter. A comparison between the suggested processing method and the wavelet packet transform (WPT) is made to support the hypothesis regarding the effectiveness of the proposed technique. Experimental outcomes seem to be satisfying.
Computer numerical control machine tool wear monitoring through a data-driven approach
(SAGE, 2024) Gougam, Fawzi; Afia, Adel; Ait Chikh, Mohamed Abdessamed; Touzout, Walid; Rahmoune, Chemseddine; Benazzouz, Djamel
The susceptibility of tools in Computer Numerical Control (CNC) machines makes them the most vulnerable elements in milling processes. The final product quality and the operations safety are directly influenced by the wear condition. To address this issue, the present paper introduces a hybrid approach incorporating feature extraction and optimized machine learning algorithms for tool wear prediction. The approach involves extracting a set of features from time-series signals obtained during the milling processes. These features allow the capture of valuable characteristics relating to the dynamic signal behavior. Subsequently, a feature selection process is proposed, employing Relief and intersection feature ranks. This step automatically identifies and selects the most pertinent features. Finally, an optimized support vector machine for regression (OSVR) is employed to predict the evolution of wear in machining tool cuts. The proposed method’s effectiveness is validated from three milling tool wear experiments. This validation includes comparative results with the Linear Regression (LR), Convolutional Neural Network (CNN), CNN-ResNet50, and Support Vector Regression (SVR) methods
Detection of bearing fault using Empirical Wavelet Transform and S Transform methods
(IEEE, 2020) Merainani, Boualem; Bouzid, Abir Amar; Ratni, Azeddine; Benazzouz, Djamel
Rolling-element bearing is one of the crucial mechanical components in induction motors. Since, its fault may produce huge damage; the way to efficiently diagnose the bearing faults is a high issue in signal processing, and its fault detection draw an important significance. In this paper, a hybrid method based on Empirical Wavelet Transform and S Transform has been proposed in order to detect the outer race bearing fault in an induction motor using vibration signals. As the collected signals are disturbed by noise, EWT is used to filter the raw signals in conjunction with isolating the region containing fault characteristic frequencies. Then ST is used to represent an Amplitude-Frequency and a Time-Frequency contour of the filtered signals, which allow to detect the bearing fault. Finally, experimental vibration data have been investigated to assess the reliability of the developed method. The results obtained show a good performance
Detection of shaft crack fault in gearbox using hilbert transforms
(IEEE, 2017) Ratni, Azeddine; Rahmoune, Chemseddine; Benazzouz, Djamel; Ould bouamama, Belkacem; Merainani, Boualem
Development of a New Strategy to Extract Dangerous Scenarios from Petrochemical Industry Installation
(Springer, 2020) Aggad, Maya; Adjerid, Smail; Benazzouz, Djamel
The use of Petri net reachability graph remains one of themost popular methods to extract critical scenarios that lead the system to a dangerous state. However, in complex systems, explosion states space and confusion between causality and precedence relationship between events are the two major limits making reachability graph inefficient to perform such analysis. In the last decade, the first limitation was tackled by an approach that uses the Petri net structure. It considers only the last normal state and ignores the rest of the network. Nevertheless, no research work appears in the literature, to consider the second limitation. In this sense, this paper proposes a novel approach based on Petri net and linear logic, to overcome the two limits. To prove the effectiveness of this proposal, the approach was applied on a petrochemical installation consisting of a cooling flammable fluids storage bins system. The obtained results are compared with the two existing approaches, the first using reachability graph and the second using the Petri net structure. The new proposed approach has shown higher performances compared to the previously mentioned methods.
Differential Drive Mobile Robot Energy Model Integration into ROS–Based Simulation Environment
(2019) Touzout, Walid; Benazzouz, Djamel; Ouelmokhtar, Hand; Benmoussa, Yahia
Nowadays, mobile robots are used in different applications however they are constrained by the limitation of their batteries making reducing energy consumption a significant challenge for mobile robots’ community. Thus, energy consumption modelling is therefore becoming an important approach to reducing energy cost. However, power reduction techniques evaluation and approbation may require much hardware configuration and can be time consuming especially in case of huge scenarios. We present in this paper a methodology used to enrich the Robot Operating System (ROS) infrastructure with modelling, monitoring, and energy management tools by integrating an energy consumption model of a differential drive mobile robot into ROS and Gazebo-based simulator. The simulation results illustrate the instantaneous power consumption of the robot for three different scenarios. Thereafter, the total energy consumption can be monitored without any hardware requirement at the end of each scenario
Early detection of pitting failure in gears using a spectral kurtosis analysis
(2012) Rahmoune, Chemseddine; Benazzouz, Djamel
Early detection of tooth crack damage in gearbox using empirical wavelet transform combined by Hilbert transform
(Sage, 2017) Merainani, Boualem; Benazzouz, Djamel; Rahmoune, Chemseddine
An early gear fault diagnosis method based on rlmd, hilbert transform and cepstrum analysis
(Acta Press, 2021) Afia, Adel; Rahmoune, Chemseddine; Benazzouz, Djamel
Gear fault diagnosis requires an adaptive decomposition method to extract defect signature. As a self-adaptive approach, local mean decomposition (LMD) decomposes the signal to a set of product functions (PFs). However, LMD suﬀers from two limits: mode mixing and end eﬀect. To overcome this problem, an optimized technique named “robust LMD (RLMD) uses an integrated frame- work: a mirror extending method to ﬁnd the real extrema in data as well as a self-adaptive tool to select the size of the ﬁxed sub- set for the moving average algorithm for the envelope estimation and ﬁnally, a soft sifting stopping criterion to automatically stop the sifting process after determining the most optimum number of sifting iterations. In this article, a combination between RLMD, Hilbert transform (HT), kurtosis and cepstrum analysis is made to monitor a gearbox with chipped tooth using experimental signals. Data are ﬁrst decomposed using RLMD into a couple of PFs, then HT is applied to each PF to get the envelope for every decom- posed component and highlights the modulated signal related to the gear fault. Subsequently, kurtosis is applied to each envelope to obtain the kurtosis vector for each signal. As healthy vibration characteristics are always taken as a reference, in this article every faulty kurtosis vector is subtracted from the healthy vector, and the PF with the largest kurtosis diﬀerence will be selected. Finally, cepstrum analysis is applied to the selected PF to extract the fault signature. Results indicate that our method can detect the chipped tooth in an earlier stage even in a noisy environment
Edge detection of MRI brain images based on segmentation and classification using support vector machines and neural networks pattern recognition
(Springer, 2023) Iourzikene, Zouhir; Benazzouz, Djamel; Gougam, Fawzi
Brain tumor (brain cancer) is a mass of abnormal cells that grow in the brain in an uncontrolled way. Brain CT and brain MRI are the most frequently performed examinations. The objective of this paper is to develop a method for the classification of brain MRI images of healthy cases and tumor cases. MRI brain database is obtained by preprocessing, segmentation, feature extraction. Feature extraction based on support vector machines (clustering) is used in this research. The objective of this method is to create several vectors and each vector contains a number of features of each image, so that we can make the classification by these features