Publications Scientifiques

Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10

Browse

Subject: search.filters.subject.Feature extraction

Search Results

Now showing 1 - 10 of 16
  • No Thumbnail Available
    Item
    Induction motor condition monitoring using infrared thermography imaging and ensemble learning techniques
    (SAGE, 2021) Mahami, Amine; Rahmoune, Chemseddine; Bettahar, Toufik; Benazzouz, Djamel
    In this paper, a novel noncontact and nonintrusive framework experimental method is used for the monitoring and the diagnosis of a three phase’s induction motor faults based on an infrared thermography technique (IRT). The basic structure of this work begins with this applying IRT to obtain a thermograph of the considered machine. Then, bag-of-visual-word (BoVW) is used to extract the fault features with Speeded-Up Robust Features (SURF) detector and descriptor from the IRT images. Finally, various faults patterns in the induction motor are automatically identified using an ensemble learning called Extremely Randomized Tree (ERT). The proposed method effectiveness is evaluated based on the experimental IRT images, and the diagnosis results show its capacity and that it can be considered as a powerful diagnostic tool with a high classification accuracy and stability compared to other previously used methods.
  • No Thumbnail Available
    Item
    Real-Time Fault Detection Scheme for Industrial Chemical Tennessee Eastman Process
    (Institute of Electrical and Electronics Engineers Inc., 2024) Attouri, Khadija; Mansouri, Majdi; Hajji, Mansour; Kouadri, Abdelmalek; Bouzrara, Kais; Nounou, Hazem
    The key idea behind this study is to integrate a moving window dynamic PCA (MW-DPCA) methodology for fault detection within the Tennessee Eastman process (TEP) into a low-computational power system, the Raspberry Pi 4 card, for real-time application. Indeed, the paramount importance of real-time fault detection (FD) in intricate industrial processes presents a critical challenge. Various data-driven techniques have been developed to ensure safety, maintain operational stability, and optimize productivity in such processes. Principal Component Analysis (PCA) is a fundamental data-driven technique that utilizes dimensionality reduction to extract the most informative features from high-dimensional data, simplifying analysis and potentially revealing underlying fault patterns. However, PCA primarily focuses on static relationships and may miss crucial temporal dynamics for fault identification. This is where dynamic PCA (DPCA) excels. By incorporating lagged values of variables, DPCA captures the temporal evolution of features, enabling a more comprehensive understanding of process behavior and improving the detection of faults involving dynamic changes. In order to address the stochastic measurements, a moving average filter tool is also employed. The results obtained and the successful realization of this implementation demonstrate the adaptability of the approach and pave the way for its seamless integration into practical industrial applications.
  • No Thumbnail Available
    Item
    A New Facial Expression Recognition Algorithm Based on DWT Feature Extraction and Selection
    (Zarka Private University, 2024) Boukhobza, Fatima Zohra; Hacine Gharbi, Abdenour; Rouabah, Khaled
    In this paper, we propose an efficient framework to improve accuracy and computational cost of a Facial Expression Recognition (FER) system. This framework is carried out in three stages. In the initial one, corresponding to feature extraction, three descriptors, derived from Discrete Wavelet Transform (DWT), are introduced to extract distinct feature types. In the second stage, focused on feature selection, a Wrapper approach is adopted to carefully select the most relevant features from the previously extracted pool. Following feature selection, the Support Vector Machine (SVM) classifier is employed, in the final stage, to determine an individual's affective state. The experiments were conducted in person-independent mode using both the Japanese Female Facial Expression (JAFFE) and extended Cohn-Kanade (CK+) databases which included the following emotions: anger, disgust, contempt, fear, happy, sad, surprise, and neutral. The obtained results demonstrated the effectiveness of the proposed framework in increasing recognition rate and decreasing response time compared to other state-of-the-art methods. A comparative study between our proposed framework and that based on the Local Binary Patterns (LBP) method demonstrated that our framework outperforms the latter for most emotions. In fact, our proposed framework converges rapidly and achieves good performance, thus allowing us to develop a real-time Facial Expression Recognition (FER) system in person-independent mode. Average recognition rates of 89.66% and 87.76% were obtained using our method with the JAFFE database and the CK+ database, respectively.
  • No Thumbnail Available
    Item
    Classification of Left/Right Hand and Foot Movements from EEG using Machine Learning Algorithms
    (Institute of Electrical and Electronics Engineers Inc, 2023) Cherifi, Dalila; Berghouti, Baha Eddine; Boubchir, Larbi
    In recent years, there has been growing interest in utilizing Electroencephalography (EEG) data and machine learning techniques to develop innovative solutions for individuals with disabilities. The ability to accurately classify hands and foot motion based on EEG signals holds great potential for enabling individuals to regain control and functionality of their disabled parts, improving their quality of life and independence. Making a better solution than the traditional ones that often require physical contact or can be challenging to operate. In our study, we have focused on hands (right/left) and foot motion disabilities, using supervised Machine Learning algorithms for the classification of EEG data related to left/right hand and foot movements; aiming to reach accurate results that can contribute to providing a solution for people with this kind of motion disabilities. Three supervised machine learning algorithms are considered for the EEG classification, namely Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM), using Common Spatial Patterns (CSP) algorithm and logarithm of the variance (logvar) for feature extraction. In our experiments, we adopted these algorithms to classify the Motor Imagery EEG dataset for hands and foot movements given in BCI Competition IV. The data we used went through different steps before fitting into the models such as filtering, feature extraction, and discrimination. We achieved significant success in accurately classifying hand movements in the initial experiment, attaining an impressive classification accuracy of up to 97.5% with SVM and LDA. Furthermore, in the multi-classification task involving both hand (right/left) and foot movements, KNN and SVM classifiers yielded commendable results up to 87%. These models can be further used and developed, where a hardware implementation will be done as a further work for this study.
  • No Thumbnail Available
    Item
    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.
  • No Thumbnail Available
    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, Djamel
    Due 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.
  • No Thumbnail Available
    Item
    A new transformer condition monitoring based on infrared thermography imaging and machine learning
    (Springer, 2023) Mahami, Amine; Bettahar, Toufik; Rahmoune, Chemseddine; Amrane, Foudil; Touati, Mohamed; Benazzouz, Djamel
    Electrical systems maintenance is becoming a crucial and an important part in the economic policies and that’s due their deep implication in the majority of the industrial installations. Electrical transmission and distribution relay mainly on transformers. Electrical transformers condition monitoring plays a major role in increasing their availability, enhancing their reliability and preventing further major failures and high cost maintenance. A new non-contact and non-intrusive method is adopted in this paper to monitor electrical transformers and diagnose their faults based on infrared thermography imaging techniques (IRT). When thermographs are obtained using an infrared camera for different states of the studied transformer, a dataset is then prepared for the following step. Features extraction was applied on the considered infrared images to be used later as input indicators for an automatic classification and identification of transformer’s healthy and several faulty states based machine learning methods (LS-SVM). This method was applied and compared with several IA techniques in order to select the most efficient one in term of accuracy and stability to be relied on in this purpose. The proposed technique, which is mainly based on IRT, features extraction and machine learning, has shown a remarkable efficiency in transformers condition monitoring and an accurate faults diagnosis, and can be generalized as a reliable and powerful tool in such problematics
  • No Thumbnail Available
    Item
    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
  • No Thumbnail Available
    Item
    Feature extraction using CNN for peripheral blood cells recognition
    (European Alliance for Innovation, 2022) Ammar, Mohammed; Daho, Mostafa El Habib; Harrar, Khaled; Laidi, Amel
    INTRODUCTION: The diagnosis of hematological diseases is based on the morphological differentiation of the peripheral blood cell types. OBJECTIVES: In this work, a hybrid model based on CNN features extraction and machine learning classifiers were proposed to improve peripheral blood cell image classification. METHODS: At first, a CNN model composed of four convolution layers and three fully connected layers was proposed. Second, the features from the deeper layers of the CNN classifier were extracted. Third, several models were trained and tested on the data. Moreover, a combination of CNN with traditional machine learning classifiers was carried out. This includes CNN_KNN, CNN_SVM (Linear), CNN_SVM (RBF), and CNN_AdaboostM1. The proposed methods were validated on two datasets. We have used a public dataset containing 12444 images with four types of leukocytes to find the best optimizer function(eosinophil, lymphocyte, monocyte, and neutrophil images). The second dataset contains 17,092 images divided into eight groups: lymphocytes, neutrophils, monocytes). the second public dataset was used to find the best combination of CNN and the machine learning algorithms. the dataset containing 17,092 images: lymphocytes, neutrophils, monocytes, eosinophils, basophils, immature granulocytes, erythroblasts, and platelets. RESULTS: The results reveal that CNN combined with AdaBoost decision tree classifier provided the best performance in terms of cells recognition with an accuracy of 88.8%, demonstrating the performance of the proposed approach. CONCLUSION: The obtained results show that the proposed system can be used in clinical practice
  • No Thumbnail Available
    Item
    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