Browsing by Author "Afia, Adel"

Now showing 1 - 12 of 12

A data driven fault diagnosis approach for robotic cutting tools in smart manufacturing
(International Society of Automation, 2025) Afia, Adel; Gougam, Fawzi; Soualhi, Abdenour; Wadi, Mohammed; Tahi, Mohamed; Tahi, Mohamed
In smart manufacturing within Industry 4.0, tool condition monitoring (TCM) is used to improve productivity and machine availability by leveraging advanced sensors and computational intelligence to prevent tool damage. This paper develops a hybrid methodology using heterogeneous sensor measurements for monitoring robotic cutting tools with four tool states: healthy, surface damage, flake damage and broken tooth. The proposed approach integrates the maximal overlap discrete wavelet packet transform (MODWPT) with health indicators to construct feature matrices for each tool state. Feature selection is performed using the tree growth algorithm (TGA) to reduce computation time and improve feature space separation by selecting only relevant features. The selected features are input into a Gaussian mixture model (GMM) to detect, identify and classify each tool state with high accuracy. The proposed method provides a classification accuracy of 99.04 % for vibration, 95.51 % for torque, and 91.67 % for force signals. Using unseen vibration data, the model achieved a test accuracy of 98.44 %, demonstrating a high degree of generalizability. Comparative analysis demonstrates that our proposed approach provides superior feature discrimination and model stability, balancing computational efficiency and classification accuracy, validating the TGA-GMM framework as an effective solution for tool fault diagnosis in noisy, high-dimensional data.
An improved artificial neural network using weighted mean of vectors algorithm for precise GTAW weld quality prediction and parameter optimization
(Springer Science and Business Media, 2026) Boucetta, Brahim; Boumediene, Faiza; Ait Chikh, Mohamed Abdessamed; Afia, Adel
Accurate prediction of mechanical properties in gas tungsten arc welding (GTAW) remains challenging due to the complex, nonlinear relationships between process parameters and weld quality. This study introduces a novel framework that systematically evaluates seven state-of-the-art metaheuristic algorithms: spider wasp optimizer (SWO), weighted mean of vectors (INFO), gradient-based optimizer (GBO), artificial rabbits optimization (ARO), blood-sucking leech optimizer (BSLO), RUN beyond the metaphor (RUN), and successive history adaptive differential evolution (SHADE), for training artificial neural networks (ANNs) to predict ultimate tensile strength in GTAW of Inconel 825 alloy. The primary novelty lies in identifying the gradient-based optimizer as the most effective algorithm for this application, presenting superior generalization capability and establishing a new benchmark for welding parameter prediction. The optimized ANN-GBO model achieved significant performance improvements over conventional ANN approaches, with the coefficient of determination () increasing from 0.6844 to 0.8669 (26.7% improvement) and root mean square error (RMSE) decreasing from 51.89 MPa to 33.71 MPa (35.0% reduction). These substantial enhancements in prediction accuracy provide critical insights for optimizing high-performance nickel-based alloy welding processes
Application of signal processing techniques in systems monitoring
(2020) Afia, Adel
As key mechanical parts in rotating machines, gears are often the heart of a wide range of industrial mechanisms. They are considered as the most important components in several industrial plants such as wind turbines, helicopters, compressors and internal combustion engines. Therefore, a sudden gear malfunctioning may decrease the performance of the entire system and even lead to fatal damage or breakdown. To maintain efficient and safe operations, predictive maintenance based on condition monitoring has received massive attention in recent years. Condition Based Maintenance (CBM) plays a crucial role in maintaining the system in a perfect operational functioning. CBM minimizes maintenance costs by reducing unnecessary planned preventive maintenance where equipment outages are predicted. Many CBM methodologies have been extensively used to monitor the gearbox condition such as acoustic emission, thermal monitoring, chemical analysis, current measurement and vibration analysis. Vibration condition monitoring has attracted substantial research attention worldwide, as the vibrations generated by a gearbox carry a great amount of information regarding its health status. Vibration signals have a non-linear and non-stationary behavior and the defect signature is always embedded in overwhelming and disturbing content, especially in the early stages. In addition, vibration signals are also are buried in a relatively strong non-Gaussian noise which renders the defective frequencies non-dominant in the spectrum compared to discrete components, reducing by that the performance of several signal processing techniques such as Kurtogram. In this Thesis, a modern vibration signal processing method called Autogram has been proposed to address these circumstances. The proposed method has been tested using experimental vibration signals to verify and affirm its detectability and accuracy with respect to Fast Kurtogram in detecting a chipped gear tooth. Despite, Autogram has the ability to perceive the occurrence of a gear failure, but without giving any information about its nature. This is a complex procedure because the defects affecting the gears have the same frequency signature. Thus, the variation in load and speed of the rotating machine will inevitably lead to erroneous detection results. Yet, it is important to discern the anomaly nature because each gear defect has a different consequences on the mechanism's performance. Thus, faults identification and classification seem to be the most difficult challenge for a gear systems. This thesis deals also with this issue by developing a new automatic approach to detect, identify and classify several gear defects. The intelligent method is a combination of Maximal Overlap Discrete ii Wavelet Packet Transform (MODWPT), Entropy and Multilayer Perceptron (MLP) neural network. MODWPT is an alternative decomposition technique with a uniform frequency bandwidth to avoid any difficulties with detection. Entropy is used to build feature matrix in the feature extraction step. Finally, MLP provides a powerful automatic feature classification tool. Experimental test has been conducted on the data sets collected from a gearbox test rig with healthy state and five different gear defects under varied speed and load conditions to show that the novel approach can successfully detect and identify gear defects in all cases. Keywords: Rotating machines, gears, vibration analysis, condition monitoring, feature extraction
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.
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
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
Gear fault detection, identification and classification using MLP neural network
(Springer, 2023) Afia, Adel; Ouelmokhtar, Hand; Gougam, Fawzi; Touzout, Walid; Rahmoune, Chemseddine; Benazzouz, Djamel
Gear fault detection, identification and classification are highly complicated tasks, as the faults which affect gearboxes tend to share similar frequency signatures. Therefore, load and speed changes in a rotating machinery inevitably provide inaccurate results. However, identifying the fault remains critical, as each individual gear fault influences overall mechanism operation in different manners. Therefore, defect identification and classification appear as the hardest challenge for a geared systems. An automatic method to detect, identify and classify different gear failures is presented in this paper. The intelligent approach consists of a combination of MODWPT, entropy and MLPNN. MODWPT was developed to decompose the signals with a uniform frequency bandwidth. Entropy is employed to build the feature matrix in the feature extraction phase. Then, MLP offers a very efficient classification tool for features classification stage. Based on data sets taken from a gearbox bench test with a good and five varied gear states under various loads and speeds, experimental results presented the efficiency of our technique
Gear fault diagnosis using Autogram analysis
(Sage, 2018) Afia, Adel; Rahmoune, Chemseddine; Djamel, Benazzouz
Rotary machines consist of various devices such as gears, bearings, and shafts that operate simultaneously. As a result, vibration signals have nonlinear and non-stationary behavior, and the fault signature is always buried in overwhelming and interfering contents, especially in the early stages. As one of the most powerful non-stationary signal processing techniques, Kurtogram has been widely used to detect gear failure. Usually, vibration signals contain a relatively strong non-Gaussian noise which makes the defective frequencies non-dominant in the spectrum compared to the discrete components, which reduce the performance of the above method. Autogram is a new sophisticated enhancement of the conventional Kurtogram. The modern approach decomposes the data signal by Maximal Overlap Discrete Wavelet Packet Transform into frequency bands and central frequencies called nodes. Subsequently, the unbiased autocorrelation of the squared envelope for each node is computed to select the node with the highest kurtosis value. Finally, Fourier transform is applied to that squared envelope to extract the fault signature. In this article, the proposed method is tested and compared to Fast Kurtogram for gearbox fault diagnosis using experimental vibration signals. The experimental results improve the detectability of the proposed method and affirm its effectiveness
Hybridization of time synchronous averaging, singular value decomposition, and adaptive neuro fuzzy inference system for multi-fault bearing diagnosis
(Sage journals, 2020) Touzout, Walid; Benazzouz, Djamel; Gougam, Fawzi; Afia, Adel; Rahmoune, Chemseddine
Bearing diagnosis has attracted considerable research interest; thus, researchers have developed several signal processing techniques using vibration analysis to monitor the rotating machinery’s conditions. In practical engineering, features extraction with most relevant information from experimental vibration signals under variable operation conditions is still regarded as the most critical concern. Therefore, actual works focus on combining Time Domain Features (TDFs) with decomposition techniques to obtain accurate results for defect detection, identification, and classification. In this paper, a new hybrid method is proposed, which is based on Time Synchronous Averaging (TSA), TDFs, and Singular Value Decomposition (SVD) for the feature extraction, then the Adaptive Neuro-Fuzzy Inference System (ANFIS) which gathers the advantages of both neural networks and fuzzy logic is applied for the classification process. First, TSA is used to reduce noises in the vibration signal by extracting the periodic waveforms from the disturbed data; thereafter, TDFs are applied on each synchronous signal to construct a feature matrix; afterwards, SVD is performed on the obtained matrices to remove the instability of statistical values and select the most stable vectors. Finally, ANFIS is implemented to provide a powerful automatic tool for features classification.
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.
New gear fault diagnosis method based on MODWPT and neural network for feature extraction and classification
(ASTM International, 2019) Afia, Adel; Rahmoune, Chemseddine; Benazzouz, Djamel; Merainani, Boualem; Fedala, Semchedine
Gear fault diagnosis using vibration signals has become the subject of intensive studies to detect any sudden failure. However, these signals exhibit nonlinear and nonstationary behaviors when the rotating machine operates under multiple working conditions. Furthermore, fault features extraction and classification of multiple gear states are always unsatisfactory and considered as a huge task. This is the main reason that motivates us to develop a new intelligent gear fault diagnosis method in order to automatically identify and classify several kinds of gear defects under different work conditions. So in this article, we propose a combination between the maximal overlap discrete wavelet packet transform (MODWPT), entropy indicator, and a multilayer perceptron (MLP) neural network as a new automatic fault diagnosis approach. MODWPT decomposes the data signal into several components using a uniform frequency bandwidth. Each decomposed component is selected to extract feature vector using entropy indicator. Finally, MLP provides a powerful automatic tool for identifying and classifying the aforementioned extracted features. Experimental vibration signals of healthy gear; gear with general surface wear; gear with chipped tooth in length; gear with chipped tooth in width; gear with missing tooth; and gear with tooth root crack are recorded under fifteen different work conditions to test the effectiveness of the suggested technique. Experimental results affirm that our proposed approach can successfully detect, identify, and classify the gear fault pattern in all cases
New intelligent gear fault diagnosis method based on Autogram and radial basis function neural network
(SAGE Publications Inc., 2020) Afia, Adel; Rahmoune, C.; Benazzouz, D.; Merainani, B.; Fedala, S.
Nowadays, fault detection, identification, and classification seem to be the most difficult challenge for gear systems. It is a complex procedure because the defects affecting gears have the same frequency signature. Thus, the variation in load and speed of the rotating machine will, inevitably, lead to erroneous detection results. Moreover, it is important to discern the nature of the anomaly because each gear defect has several consequences on the mechanism’s performance. In this article, a new intelligent fault diagnosis approach consisting of Autogram combined with radial basis function neural network is proposed. Autogram is a new sophisticated enhancement of the conventional Kurtogram, while radial basis function is used for classification purposes of the gear state. According to this approach, the data signal is decomposed by maximal overlap discrete wavelet packet transform into frequency bands and central frequencies called nodes. Thereafter, the unbiased autocorrelation of the squared envelope for each node is computed in order to calculate the kurtosis for each one at every decomposition level. Finally, the feature matrix obtained from the previous step will be the input of the radial basis function neural network to provide a new automatic gear fault diagnosis technique. Experimental results from the gearbox with healthy state and five different types of gear defects under variable speeds and loads indicate that the proposed method can successfully detect, identify, and classify the gear faults in all cases