Browsing by Author "Baiche, Karim"

Now showing 1 - 11 of 11

Bearing damage detection and diagnosis by multi-scale PCA and Power quality distribution of rotating machinery
(2011) Baiche, Karim; Zelmat, M.; Lachouri, A.
Blind source separation filters-based-fault detection and isolation in a three tank system
(Taylor & Francis, 2014) Kouadri, Abdelmalek; Baiche, Karim; Zelmat, Mimoun
Cardio-ankle vascular index (CAVI) is a potential new parameter independent of blood pressure at the time of measurement for arterial stiffness estimation
(2023) Radjef, Lilia; Omari, Tahar; Baiche, Karim
The cardio-ankle vascular index (CAVI) is a robust predictor of cardiovascular events. An innovative, non-invasive approach to measuring arterial stiffness. The (CAVI) approach was developed to overcome the limitations of carotid -femoral pulse wave velocity (cf-PWV), the gold standard indicator of arterial stiffness. The present study aims to propose a new algorithm to calculate the cardio-ankle vascular index (CAVI) parameter from Pulse Wave Database (PWDB), that contains the pulse waves of 500 virtual subjects aged between 25 and 75 years, generated from cardiovascular characteristics. The results obtaine d are promising in terms of sensitivity (SEN) and accuracy (ACC). The sensitivity values are (95.18 %, 95.71%, 92.70 %, 90.33%, 89.28%, and 89.05%), and accuracy (ACC) are (91%, 89.4%, 86.4 %, 80.4%, 80 %, and 81.4%) for normal values of (CAVI, cf-PWV, a-PWV, PPamp, AIx, and ABI) respectively. We confirmed the value of (CAVI) as an indicator of cardiovascular disease by investing th e relationship between (CAVI) and several parameters of arterial stiffness including carotid -femoral pulse wave velocity (cf-PWV, r=0.66), arterial stiffness index (AIx, r=0.72), and aortic pulse wave velocity (a-PWV, r=0,96). Pulse pressure amplification showed a negative correlation (PPamp, r=-0.67). A moderate negative correlation was observed with ankle brachial index (ABI, r=-0.38). A weak dependence on different blood pressures at the time of measurement was confirmed, by the coefficients of determination r2 (systolic SBP, 0.08, diastolic DBP, 0.11, mean MBP, 0.10, and pulsed pressures PP, 0.16). The influence of age on arterial stiffness was found with a strong positive correlation between age and cardio-ankle vascular index (CAVI, r=0.88).
Designing alarm system using modified generalized delay-timer
(Elsevier, 2019) Kaced, Radhia; Kouadri, Abdelmalek; Baiche, Karim
Alarm systems are of crucial importance in ensuring safety and efficiency of industrial installations. In practice, alarm systems are not properly designed or given the attention they deserve; their performance is unsatisfactory. The main role of alarms is to inform the operator of any incident in the plant. Regrettably, most occurred alarms are false and nuisance. To avoid this, industrial community developed techniques like deadbands, filters and delay-timers. Delay-timer is largely exercised in industry. This article presents a new concept for designing a Generalized delay-timer. out of n consecutive samples is not the only condition to activate an alarm, we will use additional setpoints to rise or clear an alarm. Three performance indicators namely, False Alarm Rate (), Missed Alarm Rate () and Average Alarm Delay () are computed for the proposed method. At the end, the modified Generalized delay-timer method is examined and compared with the Generalized delay-timer using a simulation and industrial case studies The obtained results show that alarm system performance is improved and even optimized using the modified Generalized delay-timer
Modern artificial intelligence technics for unmanned aerial vehicles path planning and control
(2025) Zamoum, Yasmine; Baiche, Karim; Benkeddad, Youcef; Bouzida, Brahim
Unmanned aerial vehicles (UAVs) require effective path planning algorithms to navigate through complex environments. This study investigates the application of Deep Q-learning and Dyna Q-learning methods for UAV path planning and incorporates fuzzy logic for enhanced control. Deep Q-learning, a reinforcement learning technique, employs a deep neural network to approximate Q-values, allowing the UAV to improve its path planning capabilities by maximizing cumulative rewards. Conversely, Dyna Q-learning leverages simulated scenarios to update Q- values, refining the UAV’s decision-making process and adaptability to dynamic environments. Additionally, fuzzy logic control is integrated to manage UAV movements along the planned path. This control system uses linguistic variables and fuzzy rules to handle uncertainties and imprecise information, enabling real-time adjustments to speed, altitude, and heading for accurate path following and obstacle avoidance. The research evaluates the effectiveness of these methods individually, with a focus on model-free learning in a gradual training approach, and compares their performance in terms of path planning accuracy, adaptability, and obstacle avoidance. The paper contributes to a deeper understanding of UAV path planning techniques and their practical applications in various scenarios.
Multivariate nuisance alarm management in chemical processes
(Elsevier, 2021) Kaced, Radhia; Kouadri, Abdelmalek; Baiche, Karim; Bensmail, Abderazak
Alarm systems are of vital importance in the safe and effective functioning of industrial plants, yet they frequently suffer from too many nuisance alarms (alarm overloading). It is necessary to intelligently enhance existing alarm systems and supply accurate information for the operators. Nowadays, process variables are more correlated and complicated. This correlation structure can be used as a basis to manage alarms efficiently. Hence, multivariate approaches are more appropriate. Designing a system aimed at reducing nuisance alarms is an essential phase to guarantee the reliable operation of a plant. Due to the definition of alarm limits, the problem of false alarms is inevitable in multivariate methods. In this paper, the conventional Principal Component Analysis (PCA) is applied to extract the sum of squared prediction error (SPE) known as the statistic and the Hotelling statistic. These statistics are used separately as alarm indicators where their control limits are duly modified. Consequently, for each statistic, a nonlinear combination of alarm duration and alarm deviation, is additionally exploited as a new requirement to activate an alarm or not. The resulting new index is fed to a delay timer with a defined parameter . The implementation of this technique resulted in a significant reduction in the severity of alarm overloading. Historical data collected from the cement rotary kiln operating under healthy conditions are employed to adequately build the PCA model and extract the proposed alarming indexes. Then, various testing data sets, covering different types of faults occurring in the cement process, are used to assess the performance of the developed method. In comparison with the conventional PCA technique, alarms are better managed nd almost nuisance alarms are suppressed. The proposed method is more robust to false alarms and more sensitive to fault detection
Performance comparison of various delay timers on alarm system design
(2018) Kaced, Radhia; Kouadri, Abdelmalek; Baiche, Karim
Alarm systems are critically important for safety and efficiency of industrial plants. Not designed properly or not receiving the attention they deserve, alarm systems suffer from poor performances. Alarms notify the operator of the abnormality on the plant. Unfortunately, most of these alarms are false and nuisance, they can be a real distraction to the operator and may additionally mask vital alarms. Deadbands, filters and delay timers are industrial techniques proposed by the industrial community to reduce false and nuisance alarms. In this paper, we investigate the use of three different delay timers; conventional delay timer, generalized delay timer and multi-setpoint delay timer; in the process and compared their effects on accuracy and detection delay. False alarm rate (FAR), Missed alarm rate (MAR) and average alarm delay (AAD) are the three performance indices used to design optimal alarm system. Simulation results show that alarm performances can be improved and even optimized via delay-timer with proper choice of the delay timer order
Solving graph coloring problem using an enhanced binary dragonfly algorithm
(2019) Baiche, Karim; Meraihi, Yassine; Hina, Manolo Dulva; Ramdane-Cherif, Amar; Mahseur, Mohammed
The graph coloring problem (GCP) is one of the most interesting classical combinatorial optimization problems in graph theory. It is known to be an NP-Hard problem, so many heuristic algorithms have been employed to solve this problem. In this article, the authors propose a new enhanced binary dragonfly algorithm to solve the graph coloring problem. The binary dragonfly algorithm has been enhanced by introducing two modifications. First, the authors use the Gaussian distribution random selection method for choosing the right value of the inertia weight w used to update the step vector (∆X). Second, the authors adopt chaotic maps to determine the random parameters s, a, c, f, and e. The aim of these modifications is to improve the performance and the efficiency of the binary dragonfly algorithm and ensure the diversity of solutions. The authors consider the well-known DIMACS benchmark graph coloring instances to evaluate the performance of their algorithm. The simulation results reveal the effectiveness and the successfulness of the proposed algorithm in comparison with some well-known algorithms in the literature
Surveillance automatisée de processus industriels complexes
(2014) Baiche, Karim
Les processus industriels complexes nécessitent une méthodologie de détection rapide et précoce des défaillances dans leurs systèmes et machines à cause de l'utilisation fréquente de ces derniers dans diverses applications et domaines ainsi que leur impact socio-économique. Le travail présenté dans cette thèse évoque plusieurs approches de traitement et d'analyse appliquées au diagnostic des défauts à savoir certains défauts de machines tournantes (roulement) et défauts de capteurs (système à trois réservoirs -three tank system). Pour mettre en œuvre ce travail de recherche, nous avons établi une feuille de route selon les démarches suivantes : Etablir un état de l'art sur le principe du FDI et les différents défauts pouvant être enregistrés et identifiés. Etablir un prétraitement basé sur l'analyse spectrale avec modèle et sans modèle en utilisant les statistiques d'ordre deux et d'ordre supérieur. le premier type d'approche consiste à utiliser des modèles analytiques du processus, ceux-ci fournissent une estimation en ligne des grandeurs non mesurables. la seconde catégorie d'approche consiste à analyser les signaux mesurés sur la machine en cours de fonctionnement. Les analyses sont réalisées pour la plupart, dans le domaine fréquentiel et en régime permanent. Les informations issues de ces analyses permettent souvent une identification efficace de défaillances présentes au niveau des différents organes du processus. Toutefois ces approches fréquentielles trouvent leurs limites en présence d'importants bruits de mesure qui noient l'information pertinente. Etablir un test statistique basé sur la SPE en utilisant la MSPCA, Identifier les sources de défaillances en utilisant l'ACI
Valuation of Physical Layer Security Under Jamming Attacks Utilizing RIS
(2025) Refas, Souad; Meraihi, Yassine; Ivanova, Galina; Baiche, Karim; Cherif, Amar Ramdane; Acheli, Dalila
Vehicular visible light communication (V VLC) systems, when combined with reconfigurable intelligent surfaces (RIS), present promising opportunities for improving communication reliability and efficiency in vehicle to vehicle (V2V) environments. Nevertheless, safeguarding these systems at the physical layer remains a critical challenge, particularly given their exposure to jamming threats. In this study, we investigate the physical layer security performance of RIS assisted V2V VLC systems under jamming scenarios, employing realistic V2V VLC channel models. We develop a methodology to examine the impact of various security strategies in mitigating the adverse effects of jamming. Our analysis examines key parameters including the signal to noise ratio SNR, the secure communication rate and the count of RIS units. Simulation results confirm that the proposed security systems significantly enhance the resilience of V2V VLC networks in the presence of jamming attacks. These results offer useful perspectives for the reliable design structure and deployment of RIS based V2V VLC systems in practical vehicular communication settings.
Vibration analysis of rotating machine by high resolution methods
(2006) Baiche, Karim; Zelmat, M.