Browsing by Author "Zair, Mohamed"

Now showing 1 - 10 of 10

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
Contribution to the monitoring of industrial systems using artificial neural networks
(2020) Zair, Mohamed
The aim of conditional monitoring based on artificial intelligence in rotating machines is to monitor the onset and development of degradation before a failure occurs. The degradation will eventually lead to a dysfunction of the system (rolling bearing or gearbox), which will affect the availability of the entire system. Detection at an early stage allows for appropriate planned shutdown to avoid catastrophic failure and, as a result, more reliable operation and lower cost. This dissertation divided in two essential parts: the first part is concerned to detection and classification faults in rolling element bearings, and the second part is focalized to modeling crack teeth and pitting teeth in the gear systems. The condition monitoring and multi-fault diagnosis of rotating machines is a very important research content in the field of the rotating machinery health management. In this thesis, a novel methodology for rolling bearing diagnosis has been developed which combines between the fuzzy entropy of self-adaptive time-frequency analysis method (EMD), principal component analysis (PCA) and self-organizing map (SOM) neural network to differentiate between Inner race, Outer race, Cage element and Ball in under operation modes and differ size of faults. The fault feature extraction, selection and classification method has been verified using results from the experimental data of bearings. The obtained results confirm that the proposed method is suitable for assessing bearing degradation and obtaining the recognition of high-sensitivity defects for different types of bearing defects. In the second part of this thesis deals with pitting and crack modeling from a condition monitoring perspective and focuses on the early detection of pitting and cracks propagation and how to differentiate between them in gear teeth using MCSA and Fast Kurtogram. The research approach is based on dynamic modeling of simulation the pitting surface teeth and cracks teeth in gear mesh stiffness. The electromechanical system which is a simple stage spur a 16 DOF gear dynamic model with and without defect driven by a three phase induction machine with 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. The method makes it possible to detect and identify and differentiate at an early stage the crack and pitting fault
Enhancing air compressors multi fault classification using new criteria for Harris Hawks optimization algorithm in tandem with MODWPT and LSSVM classifier
(SAGE, 2023) Rahmoune, Chemseddine; Amine Sahraoui, Mohammed; Gougam, Fawzi; Zair, Mohamed; Meddour, Ikhlas
The evolution of industrial systems toward Industry 4.0 presents the challenge of developing robust and accurate models. In this context, feature selection plays a pivotal role in refining machine learning models. This paper addresses the imperative of accurate fault diagnosis in industrial systems, focusing on air compressors. These systems, vital for efficient operations, demand early fault detection to prevent performance degradation. Conventional methods often encounter challenges due to the occurrence of similar failure patterns under comparable conditions. To address this limitation, our approach delves into a more complex scenario, where air compressors operate under diverse fault conditions. This study introduces novel feature selection criteria achieved through a fusion of the Maximal Overlap Discrete Wavelet Packet Transform (MODWPT), the Harris Hawks Optimization (HHO) algorithm, and the Least Squares Support Vector Machine (LSSVM) classifier. The synthesis of these components aims to bolster the multi-fault diagnosis accuracy and stability for each fault class. The evaluation focuses on key statistical metrics—minimum, maximum, mean, and standard deviation. Experimental outcomes underscore the method’s superiority over traditional feature selection techniques. The approach excels in accuracy and stability, particularly across various fault categories, affirming the efficacy and resilience of the new criteria. The symbiotic integration of MODWPT, HHO, and LSSVM within our framework highlights its potential to elevate classification performance in the realm of industrial fault diagnosis.
Enhancing fault diagnosis of undesirable events in oil & gas systems: A machine learning approach with new criteria for stability analysis and classification accuracy
(SAGE, 2023) Sahraoui, Mohammed Amine; Rahmoune, Chemseddine; Zair, Mohamed; Gougam, Fawzi; Damou, Ali
Petroleum serves as a cornerstone of global energy supply, underpinning economic development. Consequently, the effective detection of faults in oil and gas (O&G) wells is of paramount importance. In response to the limitations observed in prior research, this study presents an innovative fault diagnosis system, rooted in machine learning techniques. Our approach encompasses a comprehensive analysis, incorporating stability assessment via standard deviation (STD), and a meticulous evaluation of accuracy and stability for distinct fault scenarios. By integrating data preprocessing, feature selection methods, and deploying a robust random forest classifier, our model achieves a substantial enhancement in fault classification accuracy and stability. Extensive experimentation substantiates the superiority of our approach, surpassing the performance of previous studies that predominantly emphasized overall accuracy while disregarding stability analysis. Notably, our model attains remarkable accuracies, notably achieving a flawless 100% accuracy for scenario 3 faults. Detailed examination of mean accuracies and STDs further reinforces the precision and consistency of our model's predictive capabilities. Additionally, a qualitative assessment underscores the practical utility and reliability of our model in accurately identifying critical fault types. This research significantly advances fault detection methodologies within the O&G industry, providing valuable insights for decision-making systems in oil well operations.
Gear Multi-Fault Feature Extraction and Classification Based on Fuzzy Entropy of Local Mean Decomposition, Singular Value Decomposition and MLP Neural Network
(2018) Zair, Mohamed; Rahmoune, Chemseddine; Benazzouz, Djamel
The condition monitoring and fault diagnosis of gears is a very important in industrial machinery. In this paper, we propose a new method, by combining the fuzzy entropy of LMD-SVD and Multilayer Perceptron (MLP) neural network to overcome the problem of identification and classification faults in gearbox system. The LMD process allows the vibration signal to decompose into series of Product functions (PF). The result obtained from fuzzyEn of LMD are defined as the input vectors of the SVD. This SVD is used to reduce the dimension of the feature vectors. Last, the reduced feature vectors are chosen as input of MLP network for fault diagnosis and fault classification. The obtained results through experimental results, show that the proposed method can accurately extract and classify the gear fault features.
Multi-fault diagnosis of rolling bearing using fuzzy entropy of empirical mode decomposition, principal component analysis, and SOM neural network
(Sage journal, 2018) Zair, Mohamed; Rahmoune, Chemseddine; Benazzouz, Djamel
The condition monitoring and multi-fault diagnosis of rolling bearing is a very important research content in the field of the rotating machinery health management. Most researches widely used empirical mode decomposition in tandem with principal component analysis which is applied for feature extraction. But this method may lead to imprecise classification. In this paper, we propose a new method of rolling bearing multi-fault diagnosis, by combining the fuzzy entropy of empirical mode decomposition, principal component analysis, and self-organizing map neural network. The empirical mode decomposition process allows the vibration signal to be decomposed into a series of intrinsic mode functions. For each intrinsic mode function, we obtained the fault feature information. The proposed approach combines the fuzzy function and sample entropy to obtain fuzzy entropy. By this combination, we can reflect the complexity and the irregularity in each intrinsic mode function component. The fuzzy entropy of empirical mode decomposition used to construct the vectors is defined as the input of the principal component analysis. This principal component analysis is used to reduce the dimension of the feature vectors. Finally, the reduced feature vectors are chosen as input of self-organizing map network for automatic fault diagnosis and fault classification. The obtained results show that the proposed approach makes it possible to correctly assess the degradation of rolling bearing and to obtain recognition of high-sensitivity defects for different types of bearing faults
Multi-fault diagnosis of rolling bearingusing fuzzy entropy of empirical modedecomposition, principal componentanalysis, and SOM neural network
(Journal of Mechanical Engineering Science, 2019) Zair, Mohamed; Rahmoune, Chemseddine; Rahmoune, Chemseddine
The condition monitoring and multi-fault diagnosis of rolling bearing is a very important research content in the field ofthe rotating machinery health management. Most researches widely used empirical mode decomposition in tandem withprincipal component analysis which is applied for feature extraction. But this method may lead to imprecise classification.In this paper, we propose a new method of rolling bearing multi-fault diagnosis, by combining the fuzzy entropy ofempirical mode decomposition, principal component analysis, and self-organizing map neural network. The empiricalmode decomposition process allows the vibration signal to be decomposed into a series of intrinsic mode functions. Foreach intrinsic mode function, we obtained the fault feature information. The proposed approach combines the fuzzyfunction and sample entropy to obtain fuzzy entropy. By this combination, we can reflect the complexity and theirregularity in each intrinsic mode function component. The fuzzy entropy of empirical mode decomposition used toconstruct the vectors is defined as the input of the principal component analysis. This principal component analysis isused to reduce the dimension of the feature vectors. Finally, the reduced feature vectors are chosen as input of self-organizing map network for automatic fault diagnosis and fault classification. The obtained results show that theproposed approach makes it possible to correctly assess the degradation of rolling bearing and to obtain recognitionof high-sensitivity defects for different types of bearing faults
New criteria for wrapper feature selection to enhance bearing fault classification
(SAGE, 2023) Sahraoui, Mohammed Amine; Rahmoune, Chemseddine; Meddour, Ikhlas; Bettahar, Toufik; Zair, Mohamed
Classification is a critical task in many fields, including signal processing and data analysis. The accuracy and stability of classification results can be improved by selecting the most relevant features from the data. In this paper, a new criterion for feature selection using wrapper method is proposed, which is based on the evaluation of the classification results according to the accuracy and stability (standard deviation) of each class and the number of selected features. The pro- posed method is evaluated using Random Forest (RF) and Ant Colony Optimization (ACO) algorithms on a benchmark dataset. Results show that the proposed method outperforms classical feature selection methods in terms of accuracy and stability of classification results, especially for the difficult-to-classify combined damage class. This study demon- strates the effectiveness of the proposed new wrapper feature selection criterion to improve the performance of classifi- cation algorithms with higher stability (STD: C1 = 0.5, C2 = 0.8, C3 = 0.6, C4 = 1.8) and better accuracy (average C1 = 98.5%, C2 = 96.6%, C3 = 9.5%, C4 = 93) for the both; the statoric current and the vibration signal compared to other techniques. Machine learning methods had proven their efficiency in time-varying machines fault diagnosis when taking vibration signals and statoric currents extracted features as inputs. However, the use of the both demonstrated a higher robustness and a remarkable superiority.