Browsing by Author "Adjerid, Smail"

Now showing 1 - 20 of 27

Back propagation algorithm used for tuning parameters of ANN to supervise a compressor in a pharmachimical industry
(2012) Benazzouz, D.; Amrani, M.; Adjerid, Smail
This paper presents the retro-propagation algorithm for tuning the parameter of Artificial Neural Networks used by pharmachemical industry. The obtained numerical test results on lubrication and air circuits shown that the proposal improves the performance in terms of number of iterations and reliability of the models. BEKER Laboratories production line, is a Pharmaceutical production company located at Dar El Beida (Algiers-Algeria), was kept as the main target of this study. After careful inspection, the weakest and the strongest points of the system were identified and the most strategic equipment within the line (the compressor) was taken as the equipment of focus. From this specific point, failure simulations are most adequate and from this selected target, the designed system will be better positioned for failure detection during the production process. The efficiency of this approach is its fast learning, and its accuracy of detecting failure which is of the order of 10-3
Bond Graph model-based fault estimation in presence of uncertainties: Application to mechatronic system
(Université de djelfa, 2018) Lounici, Yacine; Touati, Youcef; Adjerid, Smail
This paper deals with the fault estimation problem of uncertain systems using Bond graph model-based technique.The main objective is to enhance the fault estimation procedure based on the generation of the fault estimation thresh-old, in order to overcome the problem related to errors in the estimated fault. The novelty of the proposed method is the generation of the fault estimation error us-ing the fault estimation equation, which can be generated from the Bond graph model. The proposed methodology is validated via simulationsof a mechatronic system.
Bond Graph Model-Based Methods for Fault Diagnosis: A Comparative Study
(2019) Lounici, Yacine; Touati, Youcef; Adjerid, Smail
Advanced methods of fault diagnosis become increasinglysignificant for improving the safety, reliability and efficiently of dynamic systems in various domains of industrial engineering. This paper reviews and comparesthree bond graph model-based methods for fault diagnosis. These methods are causality inversion method, augmented Analytical redundancy relation method, and fault estimationmethod. Thesemethods are applied toa simulation model of an electricalsystem. This latteris used to simulate the system variables in both normal and faulty situationsand to generate residuals for fault detection and isolation. The results of the case study are compared for highlighting the fault diagnosisperformanceand capability of a method over another.The result showsthat the faultestimationmethodhas a better diagnosis performance when compared to the other methods
A comparison of bond graph Model-Based methods for fault diagnosis in the presence of uncertainties : application to mechatronic system
(IEEE, 2019) Lounici, Yacine; Touati, Youcef; Adjerid, Smail
This paper deals with comparing three methods for robust fault diagnosis that generate their residuals using bond graph model. These methods are the causality inversion method, a sensor data combinations method, and a faults/residuals sensitivity relations method. In addition, both parameter and measurement uncertainties are considered to generate the adaptive residual thresholds. Through simulation on a mechatronic system, the presented methods are studied under sensor and parameter faults. The results of the case study are compared for gaining practical insights about the applicability and performance of these methods. The results show that the faults/residuals sensitivity relations method has a better diagnosis performance as compared to the other methods
Dependability analysis in systems engineering approach using the FMECA extracted from the SysML and failure modes classification by K-means
(Springer, 2021) Chabane, Ali; Adjerid, Smail; Meddour, Ikhlas
The work presented in this article is a contribution to the implementation of an approach dedicated to the behavioral analysis of industrial systems starting from the design Maintenance engineering techniques inspire the suggested approach, and it aims at deducing and classifying the industrial systems' probable failure modes. The latter modes can alter the systems proper functioning. Our suggested approach is a combination of three complementary tools. The SysML language is applied to express customers' needs and requirements, such as future systems' functions and operating conditions. Besides, the FMECA method analyzes systems' potential dysfunction and the recommendation of appropriate maintenance actions. Finally, the K-means method classifies failure modes to get detailed mode criticality instead of calculating this latter according to ancient methods. The result will objectively make it possible to develop systems with reliable and maintainable components. It also helps to recommend optimal maintenance strategies according to the equipment evolution state. The approach is carried out through two application cases. The first is a practical and straightforward system used to check the methods feasibility, and the second is a more elaborated one, used to observe the effectiveness of the approach
Development of a New Strategy to Extract Dangerous Scenarios from Petrochemical Industry Installation
(Springer, 2020) Aggad, Maya; Adjerid, Smail; Benazzouz, Djamel
The use of Petri net reachability graph remains one of themost popular methods to extract critical scenarios that lead the system to a dangerous state. However, in complex systems, explosion states space and confusion between causality and precedence relationship between events are the two major limits making reachability graph inefficient to perform such analysis. In the last decade, the first limitation was tackled by an approach that uses the Petri net structure. It considers only the last normal state and ignores the rest of the network. Nevertheless, no research work appears in the literature, to consider the second limitation. In this sense, this paper proposes a novel approach based on Petri net and linear logic, to overcome the two limits. To prove the effectiveness of this proposal, the approach was applied on a petrochemical installation consisting of a cooling flammable fluids storage bins system. The obtained results are compared with the two existing approaches, the first using reachability graph and the second using the Petri net structure. The new proposed approach has shown higher performances compared to the previously mentioned methods.
Fault detection and isolation based on neural networks case study : steam turbine
(2011) Benazzouz, D.; Benammar, Samir; Adjerid, Smail
The real-time fault diagnosis system is very important for steam turbine generator set due serious fault re-sults in a reduced amount of electricity supply in power plant. A novel real-time fault diagnosis system is proposed by using Levenberg-Marquardt algorithm related to tuning parameters of Artificial Neural Network (ANN). The model of novel fault diagnosis system by using ANN are built and analyzed. Cases of the diag-nosis are simulated. The results show that the real-time fault diagnosis system is of high accuracy and quick convergence. It is also found that this model is feasible in real-time fault diagnosis. The steam turbine is used as a power generator by SONELGAZ, an Algerian company located at Cap Djinet town in Boumerdes dis-trict. We used this turbine as our main target for the purpose of this analysis. After deep investigation, while keeping our focus on the most sensitive parts within the turbine, the weakest and the strongest points of the system were identified. Those are the points mostly adequate for failure simulations and at which the de-signed system will be better positioned for irregularities detection during the production process
Inverse bond graph Model-Based active fault tolerant control for health monitoring of electric vehicle path tracking
(IEEE, 2020) Lounici, Yacine; Touati, Youcef; Adjerid, Smail; Touzout, Walid
This article deals with the integration of fault estimation with inverse Bond Graph model for health monitoring of an electric vehicle. This autonomous vehicle is a multiple-input multiple-output system with four electromechanical traction subsystems. The innovative interest of this work is to exploit one graphical approach not only for vehicle dynamics modeling and diagnosis but also for fault estimation and fault-tolerant control. For robust fault diagnosis, residuals are generated in the presence of uncertainties. The purpose of using fault estimation is to generate an accurate fault magnitude to the inverse bond graph system. The latter aims to compensate for the power generated by the fault. This structure is then applied to an electric vehicle in order to monitor the system in real-time and to correct the tracking in faulty situations
Modelling and simulation of mechatronic system to integrated design of supervision : using a bond graph approach
(2011) Mellal, Mohamed Arezki; Adjerid, Smail; Benazzouz, Djamel
The research in mechatronics focuses on the design and implementation of reliable, secure and economic systems. Our study is to modeling the operative part of a CNC machine using a bond graph approach with optimal placement of sensors in order to achieve a model for an integrated design of supervision. The proposed model allows a conception technically feasible and economically realizable to be integrated into production lines. The generation of analytical redundancy relations can find the FDI (Fault Detection and Isolation) matrix, that optimizes the maintenance function
Multi-objective Pipeline Network Reliability Optimization by Particle Swarm Optimization
(2019) Chebouba, Billal Nazim; Mellal, Mohamed Arezki; Adjerid, Smail
This paper presents the use of a multi-objective optimization algorithm for solving the reliability allocation problem in case of reliability of pipeline installations in a network configuration. Usually, this kind of problem is considered as a single objective subject to one or several nonlinear constraints and solved by using either mathematical programming techniques or more recently by special metaheuristics. In the present work, the problem is considered as a multi-objective optimization problem. The MOPSO algorithm is used and demonstrates its ability to identify the set of optimal solutions (Pareto front) providing to the decision maker the optimal solution space
Multi-objective System Reliability Optimization in a Power Plant
(IEEE, 2018) Chebouba, Billal Nazim; Mellal, Mohamed Arezki; Adjerid, Smail
This paper presents the use of a multi-objective optimization algorithm for solving the reliability-redundancy allocation problem in case of an overspeed protection system of a power plant. Usually, this kind of problem is considered as a single objective subject to one or several nonlinear constraints and solved by using either mathematical programming techniques or more recently by special metaheuristics. In the present work, the problem is considered as a multi-objective optimization problem. The NSGA-II algorithm is used and demonstrates its ability to identify the set of optimal solutions (Pareto front) providing to the decision maker the optimal solution space
Multi-objective system reliability-redundancy allocation in a power plant by considering three targets
(IEEE, 2020) Chebouba, Billal Nazim; Mellal, Mohamed Arezki; Adjerid, Smail; Lounici, Yacine
This paper addresses the overall system reliability-redundancy allocation problem (RRAP) of an overspeed protection system in a power plant. Generally, this type of optimization problem is considered as a single objective optimization problem subject to a set of nonlinear constraints. In the present work, the optimization problem is solved with a multi-objective approach rather than a single-objective one with three conflicting objective functions, namely the reliability, cost, and volume. A fast and elitist multi-objective genetic algorithm (NSGA-II) is implemented to identify the optimal solutions for the decision-maker
A novel fault-tolerant control strategy based on inverse bicausal bond graph model in linear fractional transformation
(SAGE Publications, 2021) Lounici, Yacine; Touati, Youcef; Adjerid, Smail; Benazzouz, Djamel; Chebouba, Billal Nazim
This article presents the development of a novel fault-tolerant control strategy. For this task, a bicausal bond graph model-based scheme is designed to generate online information to the inverse controller about the faults estimation. Secondly, a new approach is proposed for the fault-tolerant control based on the inverse bicausal bond graph in linear fractional transformation form. However, because of the time delay for fault estimation, the PI controller is used to reduce the error before the fault is estimated. Hence, the required input that compensates the fault is the sum of the control signal delivered by the PI controller and the control signal resulting from the inverse bicausal bond graph for fast fault compensation and for maintaining the control objectives. The novelties of the proposed approach are: (1) to exploit the power concept of the bond graph by feeding the power generated by the fault in the inverse model (2) to suitably combining the inverse bicausal bond graph with the PI feedback controller so that the proposed strategy can compensate for the fault with a very short time delay and stabilize the desired output. Finally, the experimental results illustrate the efficiency of the proposed strategy
Obsolescence optimization of electronic and mechatronic components by considering dependability and energy consumption
(Springer, 2013) Mellal, Mohamed Arezki; Adjerid, Smail; Benazzouz, Djamel; Berrazouane, Sofiane; Williams, Edward
Optimal policy for the replacement of industrial systems subject to technological obsolescence using genetic algorithm
(2013) Mellal, Mohamed Arezki; Adjerid, Smail; Benazzouz, Djamel; Berrazouane, Sofiane; Williams, Edward J.
The technological obsolescence of industrial systems is characterized by the existence of challenger units possessing identical functionalities but with improved performance. This paper aims to define a new approach that makes it possible to obtain the optimal number of obsolete industrial systems which should be replaced by new-type units. This approach presents a new point of view compared with previous works available in the literature. The main idea and the originality of our approach is that we apply a genetic algorithm (GA) by considering the failure frequency, the influence of the environment/safety factors of the old-type systems and the purchase/implementation cost of the new-type units. These parameters are introduced in order to optimize this type of replacement in the context of engineering
Optimal replacement policy for obsolete components using cuckoo optimization algorithm based-approach : dependability context
(NISCAIR-CSIR, India, 2012) Mellal, Mohamed Arezki; Adjerid, Smail; Williams, Edward J.; Benazzouz, Djamel
Performance evaluation and optimisation of industrial system in a dynamic maintenance
(Scientific & Academic Publishing, 2012) Adjerid, Smail; Aggab, Toufik; Benazzouz, Djamel
Despite the existence of the multitude of behavioral analysis tools for industrial systems, increasingly complex, managers to date find difficulties to define maintenance strategies able to significantly improve the overall performance of companies in terms of production, quality, safety and environment. A static maintenance and not adapted to the evolution of the state system does not meet the expectations of industrialists. However, the behavior of any degradable system is closely related to the state of its components. This random influence is not always sufficiently considered for various reasons, consequently any decision making remains subjective. Our approach based on dynamic Bayesian networks (DBN) consists has the modeling of the system and the functional dependencies of its components. The results obtained then, after the introduction in the model of the most appropriate actions of maintenance show all the importance of this technique and the possible applications
Replacement optimization of industrial components subject to technological obsolescence using artificial intelligence
(IEEE, 2017) Mellal, Mohamed Arezki; Adjerid, Smail; Williams, Edward J.
Robust fault diagnosis of hybrid systems with Interval-Valued uncertainties using hybrid bond graph
(IEEE, 2020) Lounici, Yacine; Touati, Youcef; Ould Bouamama, Belkacem; Adjerid, Smail; Chebouba, Billal Nazim
In this paper, a new robust fault diagnosis procedure for an uncertain hybrid system based on the hybrid bond graph model is proposed. The main objective is to enhance the robustness in the presence of uncertainties in order to minimize the non-detection and false alarm. The scientific interest of the present work remains in integrating the benefits of Hybrid bond graph and Interval analysis properties for effective diagnosis of uncertain hybrid systems. For this task, first, the Intervalvalued Analytical redundancy relations which may undergo discrete mode changes are derived from diagnosis hybrid bond graph with controlled junctions. Secondly, the uncertainties are modelled directly in the hybrid bond graph as interval models for interval-valued thresholds generation. The limitations of the existing methods are alleviated by the proposed method. The effectiveness of the proposed method is demonstrated through simulation on a controlled two-tank hybrid system
Robust Fault Diagnosis of SCARA Industrial Robot Manipulator
(2018) Lounici, Yacine; Touati, Youcef; Adjerid, Smail
Nowadays, robotic systems are being in increasingly demanding in many industrial activities. In order to achieve the maximal performance, complex nonlinear dynamic robotic systems were developed. However, as a consequence, the rate of component malfunctions augments with the complexity of systems. These malfunctions are called faults, which may appear in different parts of the system and can induce changes in the dynamic behaviour. This paper deals with fault diagnosis of a particular kind of industrial robots called selective compliance assembly robot arm (SCARA), where both parameter and measurement uncertainties are taken into account. Residuals and thresholds are generated using the quantitative model-based method. The inverse geometric model is used to find analytical solutions for joints angles and distances given the trajectory of the end effector. The presented geometric model is then used to derive the kinematic model. Using this kinematic model, the robot controller computes the necessary torque applied to each DC servomotor in order to move the robot from the current position to the next desired position. The proposed robust fault diagnosis scheme is then implemented for a SCARA manipulator and simulation results are presented in both normal and faulty situations.