Publications Internationales
Permanent URI for this collectionhttps://dspace.univ-boumerdes.dz/handle/123456789/13
Browse
9 results
Search Results
Item Fault prediction of pharmaceutical air compressor using the intelligent model based on the bayesian network(University of Zielona Gora, 2025) Amrani, Mohamed; Benazzouz, DjamelThis paper presents a new approach of diagnosis and prognostic in real-time of strategic equipment of pharmaceutical industry. This approach is developed using Bayesian network (BN) which consider industrial data and feedback experience. The objective is to detect, locate and prevent any malfunction of the air compressor (oil-free) without air contamination, dedicated to pharmaceutical industry. The study is based on the functional analysis of the air compressor to obtain the fault tree (FT). This FT is transformed into BN to diagnose automatically the compressor and prevent any malfunctioningItem Machine learning algorithms prediction of methyl orange removal by Fenton oxidation process(Springer Science and Business Media, 2025) Ouazene, Naima; Harrar, Khaled; Gharbi, Amine; Zahi, Salah Eddine; Mokrane, Said; Mokrane, HindFenton oxidation, an advanced oxidation process (AOP), effectively mineralizes azo dyes, mitigating their environmental impact. The Fenton oxidation process (Fe2⁺/H₂O₂) was employed for the degradation of methyl orange (MO) under varying operational conditions, with its efficiency assessed through chemical oxygen demand (COD) analysis. This study aims to develop predictive models for MO degradation efficiency using four machine learning (ML) algorithms: Gaussian process regression (GPR), multilayer perceptron (MLP), decision tree (DT), and support vector regression (SVR). These models were developed and validated using 42 experimental data points obtained under controlled conditions. Experimental findings revealed a 99% COD removal at an initial MO concentration of 125 mg/L, optimized at pH 3.5, [Fe2⁺] = 25 mg/L, reaction time = 90 min, and a molar ratio of [H₂O₂]/[MO] = 42.5. The predictive accuracy of the ML models was evaluated using the coefficient of determination (R2) and root mean square error (RMSE). The GPR model demonstrated the highest predictive performance (R2 = 0.970), followed by DT (R2 = 0.964). The MLP and SVM models exhibited slightly lower predictive capacities, with R2 values of 0.946 and 0.910, respectively. Feature importance analysis indicated that reaction time was the most significant parameter influencing COD removal, underscoring the necessity of its optimization in practical applications. The integration of ML-based predictive modeling with AOPs provides a robust approach for enhancing wastewater treatment efficiency. The outcomes of this study hold particular relevance for water reuse applications in arid and semiarid regions, where effective pollutant removal is critical for sustainable water resource managementItem Stability analysis of the pitch angle control of large wind turbines using different controller strategies(SAGE, 2022) Bouregba, Hicham; Hachemi, M.; Hachemi, M.; Hamidat, A .Reducing the environmental impact necessitates a boost in renewable energy conversion systems. Wind energy is regarded as one of the most essential energy sources. For this purpose, the high wind variations in the energy conver- sion chain require robust and reliable control. This research aims to implement a regulation based on artificial intelli- gence toward a blade orientation mechanism to improve the stability of energy conversion. On the other hand, an energy maximization technique called Maximum Power Point Tracking (MPPT) is integrated into the control system. A developed program in MATLAB estimates the turbine performance with two different strategies, namely the MPPT tech- nique and the Pitch control mechanism. For the best control and more stability of energy conversion, three artificial intelligence controllers, which are Neuronal Network (PI-ANN), Fuzzy Logic (PI-FLC), and Neuro-Fuzzy (PI-NFLC), were employed. They are compared with the conventional controller (PI-C). This comparison is made to distinguish the most robust regulator against wind speed variations. The different performance indices showed that the controller PI- NFLC has an excellent response, with an Integral Time Absolute Error (ITAE) of 375.28, whereas the Integral Absolute Error (IAE) and Integral Time Square Error (ITSE) equal 13.87 and 406.59, respectively.Item Improvement of system reliability in a natural gas processing facility by PSO and DE(Springer Nature, 2024) Saheb, Tafsouthe; Mellal, Mohamed ArezkiThe reliability of the systems as well as its optimization is the first concern of the designers. The elements of a given system can be either in series, parallel, parallel-series, or in a complex configuration. This paper addresses the reliability optimization of a natural gas processing facility. The reliability of this system is calculated and two redundancies strategies, active and standby, are optimized under the resource limits to improve reliability. Two bio-inspired optimization algorithms, namely the particle swarm optimization (PSO) and the differential evolution (DE), are implemented with penalty functions to find the optimal redundancy. The results obtained are compared.Item Machine learning-based research for COVID-19 detection, diagnosis, and prediction : a survey(Springer, 2022) Meraihi, Yassine; Gabis, Asma Benmessaoud; Mirjalili, Seyedali; Ramdane-Cherif, Amar; Alsaadi, Fawaz EThe year 2020 experienced an unprecedented pandemic called COVID-19, which impacted the whole world. The absence of treatment has motivated research in all fields to deal with it. In Computer Science, contributions mainly include the development of methods for the diagnosis, detection, and prediction of COVID-19 cases. Data science and Machine Learning (ML) are the most widely used techniques in this area. This paper presents an overview of more than 160 ML-based approaches developed to combat COVID-19. They come from various sources like Elsevier, Springer, ArXiv, MedRxiv, and IEEE Xplore. They are analyzed and classified into two categories: Supervised Learning-based approaches and Deep Learning-based ones. In each category, the employed ML algorithm is specified and a number of used parameters is given. The parameters set for each of the algorithms are gathered in different tables. They include the type of the addressed problem (detection, diagnosis, or detection), the type of the analyzed data (Text data, X-ray images, CT images, Time series, Clinical data,..) and the evaluated metrics (accuracy, precision, sensitivity, specificity, F1-Score, and AUC). The study discusses the collected information and provides a number of statistics drawing a picture about the state of the art. Results show that Deep Learning is used in 79% of cases where 65% of them are based on the Convolutional Neural Network (CNN) and 17% use Specialized CNN. On his side, supervised learning is found in only 16% of the reviewed approaches and only Random Forest, Support Vector Machine (SVM) and Regression algorithms are employedItem Nodes placement in wireless mesh networks using optimization approaches : a survey(Springer, 2022) Mekhmoukh Taleb, Sylia; Meraihi, Yassine; Benmessaoud Gabis, Asma; Mirjalili, Seyedali; Ramdane-Cherif, AmarWireless mesh networks (WMNs) have grown substantially and instigated numerous deployments during the previous decade thanks to their simple implementation, easy network maintenance, and reliable service coverage. Despite these proprieties, the nodes placement of such networks presents many challenges for network operators. In this paper, we present a survey of optimization approaches implemented to address the WMNs nodes placement problem. These approaches are classified into four main categories: exact approaches, heuristic approaches, meta-heuristic approaches, and hybrid approaches. For each category, a critical analysis is drawn according to targeted objectives, considered constraints, type of positioned nodes (Mesh Router and Mesh Gateway), location (discrete or continuous), and environment (static or dynamic). In the end, several new key search areas for WMNs nodes placement are suggestedItem Criticality analysis and maintenance of solar tower power plants by integrating the artificial intelligence approach(MDPI, 2021) Benammar, Samir; Tee, Kong FahMaintenance of solar tower power plants (STPP) is very important to ensure production continuity. However, random and non-optimal maintenance can increase the intervention cost. In this paper, a new procedure, based on the criticality analysis, was proposed to improve the maintenance of the STPP. This procedure is the combination of three methods, which are failure mode effects and criticality analysis (FMECA), Bayesian network and artificial intelligence. The FMECA is used to estimate the criticality index of the different elements of STPP. Moreover, corrections and improvements were introduced on the criticality index values based on the expert advice method. The modeling and the simulation of the FMECA estimations incorporating the expert advice method corrections were performed using the Bayesian network. The artificial neural network is used to predicate the criticality index of the STPP exploiting the database obtained from the Bayesian network simulations. The results showed a good agreement comparing predicted and actual criticality index values. In order to reduce the criticality index value of the critical elements of STPP, some maintenance recommendations were suggestedItem 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 casesItem A new hybrid algorithm for document clustering based on cuckoo search and K-means(Springer, 2014) Ishak Boushaki, Saida; Nadjet, Kamel; Bendjeghaba, Omar