Inventory management in distribution networks remains a challenging task due to the demand nature and the limited storage capacity. In this work, we study a three-level, a multi-product and a multi-period distribution network consisting of a central warehouse, three distribution centres and six wholesalers. Each of them faces a random demand. In order to optimise the inventory management in the distribution network, we first propose to make a horizontal cooperation between actors of the same level in the form of product exchange; then we propose a second approach based on vertical-horizontal cooperation. Both approaches are modelled as a MIP model and solved using the CPLEX solver. The objective of this study is to analyse the performance in terms of costs, quantities in stock and customer satisfaction.

Renewable energies offer new solutions to an ever-increasing energy demand. Wind energy is one of the main sources of electricity production, which uses winds to be converted to electrical energy with lower cost and environment saving. The major failures of a wind turbine occur in the bearings of high-speed shafts. This paper proposes the use of optimized machine learning to predict the Remaining Useful Life (RUL) of bearing based on vibration data and features extraction. Significant features are extracted from filtered band-pass of the squared raw signal where the health indicators are automatically selected using relief technique. Optimized Adaptive Neuro Fuzzy Inference System (ANFIS) by Partical Swarm Optimization (PSO) is used to model the non linear degradation of the extracted indicators. The proposed approach is applied on experimental setup of wind turbine where the results show its effectiveness for RUL estimation.

In this paper, we address the integration of a two-level supply chain with multiple items. This two-level production-distribution system features a capacitated production facility supplying several retailers located in the same region. If production does occur, this process incurs a fixed setup cost and unit production costs. Besides, deliveries are made from the plant to the retailers by a limited number of capacitated vehicles, routing costs incurred. This work aims to implement a minimization solution that reduces the total costs in both the production facility and retailers. The methodology adopted based on a hybrid heuristic, greedy and genetic algorithm uses strong formulation to provide a suitable solution of a guaranteed quality that is as good or better than those provided by the MIP optimizer. The results demonstrate that the proposed heuristics are effective and performs impressively in terms of computational efficiency and solution quality.

With the evolution of the internet of things (IoT), and due to its significant need in the industry, Industrial IoT (IIoT) becomes the suitable naming for this accompaniment. IIoT changed the view of the industry intelligently and over the internet. This overlapping of IoT and industry requires special treatment when systems deal with heterogeneous devices in a distributed environment and complex tasks. In this paper, we propose a middleware solution based on multi-agents system (MAS) to handle the distributed control of complex systems autonomously in an industrial environment. The proposed middleware enables machine-to-machine (M2M) communications among the system’s components. In this work, we also addressed the distributed diagnostic for real industrial system using MAS with a new suitable communication strategy to support the heterogeneity and interoperability issued in IIoT and assure real-time monitoring and control. Finally, we present a qualitative evaluation of our solution on real case study (cement factory).

Modern wind turbines operate in continuously transient conditions, with varying speed, torque, and power based on the stochastic nature of the wind resource. This variability affects not only the operational performance of the wind power system, but can also affect its integrity under service conditions. Condition monitoring continues to play an important role in achieving reliable and economic operation of wind turbines. This paper reviews the current advances in wind turbine condition monitoring, ranging from conventional condition monitoring and signal processing tools to machine-learning-based condition monitoring and usage of big data mining for predictive maintenance. A systematic review is presented of signal-based and data-driven modeling methodologies using intelligent and machine learning approaches, with the view to providing a critical evaluation of the recent developments in this area, and their applications in diagnosis, prognosis, health assessment, and predictive maintenance of wind turbines and farms.

Since bearing deterioration patterns are difficult to collect from real, long lifetime scenarios, data-driven research has been directed towards recovering them by imposing accelerated life tests. Consequently, insufficiently recovered features due to rapid damage propagation seem more likely to lead to poorly generalized learning machines. Knowledge-driven learning comes as a solution by providing prior assumptions from transfer learning. Likewise, the absence of true labels was able to create inconsistency related problems between samples, and teacher-given label behaviors led to more ill-posed predictors. Therefore, in an attempt to overcome the incomplete, unlabeled data drawbacks, a new autoencoder has been designed as an additional source that could correlate inputs and labels by exploiting label information in a completely unsupervised learning scheme. Additionally, its stacked denoising version seems to more robustly be able to recover them for new unseen data. Due to the non-stationary and sequentially driven nature of samples, recovered representations have been fed into a transfer learning, convolutional, long–short-term memory neural network for further meaningful learning representations. The assessment procedures were benchmarked against recent methods under different training datasets. The obtained results led to more efficiency confirming the strength of the new learning path.

To ensure the continuity of electric power generation for photovoltaic systems, condition monitoring frameworks are subject to major enhancements. The continuous uniform delivery of electric power depends entirely on a well-designed condition maintenance program. A just-in-time task to deal with several naturally occurring faults can be correctly undertaken via the cooperation of effective detection, diagnosis, and prognostic analyses. Therefore, the present review first outlines different failure modes to which all photovoltaic systems are subjected, in addition to the essential integrated detection methods and technologies. Then, data-driven paradigms, and their contribution to solving this prediction problem, are also explored. Accordingly, this review primarily investigates the different learning architectures used (i.e., ordinary, hybrid, and ensemble) in relation to their learning frameworks (i.e., traditional and deep learning). It also discusses the extension of machine learning to knowledge-driven approaches, including generative models such as adversarial networks and transfer learning. Finally, this review provides insights into different works to highlight various operating conditions and different numbers and types of failures, and provides links to some publicly available datasets in the field. The clear organization of the abundant information on this subject may result in rigorous guidelines for the trends adopted in the future.

In this paper, we present a system for handwriting digit recognition using different invariant features extraction and multiple classifiers. In the feature extraction we use four types: cavities, Zernike moments, Hu moments, Histogram of Gradient (HOG). Firstly, the features are used independently by five classifiers: K-nearest neighbor (KNN), Support Vector Machines (SVM) one versus one, SVM one versus all, Decision Tree, MLP. Then to achieve the best possible classification performance in terms of recognition rate, three methods of classifiers Combination rule employed: majority vote, Borda count and maximum rule. Experiments are performed on the well-known MNIST database of handwritten digits. The results demonstrated that the combination of KNN using HOG features with SVMOVA using Zernike moments by Borda count rule have considered to be good based on a geometric transformation invariance.

 As commonly known that living beings cannot survive without natural sources available on earth, technology is no exception; it cannot develop without the inspiring help given by the same nature. The field of biology has extensively participated in the computing field through the "code of life" DNA (Deoxyribo Nucleic Acid) since it was discovered by Adelman in the past century. This combination gave birth to DNA Computing, which is a very interesting new aspect of biochemistry. It works massively parallel with high energy efficiency, and requiring almost no space. The field of molecular computing is still new and as the field progresses from concepts to engineering, researchers will address these important issues.  By the use of encoding data into DNA strands, many NP-complete problems have been solved and many new efficient techniques have been proposed in cryptography field. The aim of this paper is to give an overview of bio-inspired system and to summarize the great role of DNA molecule in servicing of the technology field.

Le 4ème semestre d’un mastère de recherche est consacré à la réalisation d’un travail de recherche qui sera traduit par une conception et une rédaction d’un mémoire de fin d’études et finalement la préparation d’un exposé oral puis une soutenance.Le mémoire de fin d’études est une étape très importante dans la voie des études universitaires, car sans elle, l’étudiant ne peut pas acquérir la qualité de diplômé.Alors, dans ce petit livre vous pouvez trouver un petit guide sur: - La fa\c con d’organisation de votre mémoire. - La présentation de votre soutenance. - La rédaction d’un travail de recherche. - La préparation d’un poster.Le 4ème semestre d’un mastère de recherche est consacré à la réalisation d’un travail de recherche qui sera traduit par une conception et une rédaction d’un mémoire de fin d’études et finalement la préparation d’un exposé oral puis une soutenance.Le mémoire de fin d’études est une étape très importante dans la voie des études universitaires, car sans elle, l’étudiant ne peut pas acquérir la qualité de diplômé.Alors, dans ce petit livre vous pouvez trouver un petit guide sur: La fa\c con d’organisation de votre mémoire. La présentation de votre soutenance. La rédaction d’un travail de recherche. La préparation d’un poster.

Deep learning techniques have recently brought many improvements in the field of neural network training, especially for prognosis and health management. The success of such an intelligent health assessment model depends not only on the availability of labeled historical data but also on the careful samples selection. However, in real operating systems such as induction machines, which generally have a long reliable life, storing the entire operation history, including deterioration (i.e., bearings), will be very expensive and difficult to feed accurately into the training model. Other alternatives sequentially store samples that hold degradation patterns similar to real ones in damage behavior by imposing an accelerated deterioration. Labels lack and differences in distributions caused by the imposed deterioration will ultimately discriminate the training model and limit its knowledge capacity. In an attempt to overcome these drawbacks, a novel sequence-by-sequence deep learning algorithm able to expand the generalization capacity by transferring obtained knowledge from life cycles of similar systems is proposed. The new algorithm aims to determine health status by involving long short-term memory neural network as a primary component of adaptive learning to extract both health stage and health index inferences. Experimental validation performed using the PRONOSTIA induction machine bearing degradation datasets clearly proves the capacity and higher performance of the proposed deep learning knowledge transfer-based prognosis approach.

Complex engineering manufacturing systems require efficient online fault diagnosis methodologies to improve safety and reduce maintenance costs. Traditionally, diagnosis and prognosis approaches are centralised, but these solutions are difficult to implement on distributed systems; whereas a distributed approach of multiple diagnosis and prognosis agents can offer a solution. Also, controlling process plant from a remote location has several benefits including the ability to track and to assist in solving a problem that might arise. This paper presents a distributed and over prognosis and diagnosis approach for physical systems basing on multi agent system and service-oriented architecture. Specifics prognostic and diagnostic procedures and key modules of the architecture for web service-based distributed fault prognostic and diagnosis framework are detailed and developed for the preheater cement cyclones in the workshop of SCIMAT clinker. The experimental case study, reported in the present paper, shows encouraging results and fosters industrial technology transfer.

Digital twins have transformed the industrial world by changing the development phase of a product or the use of equipment. With the digital twin, the object’s evolution data allows us to anticipate and optimize its performance. Healthcare is in the midst of a digital transition towards personalized, predictive, preventive, and participatory medicine. The digital twin is one of the key tools of this change. In this work, DT is proposed for the diagnosis of breast cancer based on breast skin temperature. Research has focused on thermography as a non-invasive scanning solution for breast cancer diagnosis. However, body temperature is influenced by many factors, such as breast anatomy, physiological functions, blood pressure, etc. The proposed DT updates the bio-heat model’s temperature using the data collected by temperature sensors and complementary data from smart devices. Consequently, the proposed DT is personalized using the collected data to reflect the person’s behavior with whom it is connected.

La quatrième révolution industrielle (nommée aussi l’Internet Industriel des Objets) dépend totalement sur la numérisation à travers l’Internet des objets et les réseaux virtuels. Cette révolution qui évolue à un rythme exponentiel, et non plus linéaire, va permettre la création d’usines, d’industries et de processus plus intelligents qui vont ensuite se traduire par une amélioration de la flexibilité, de la productivité et une meilleure utilisation des ressources matérielles et humaines. Cet article est consacré à introduire cette nouvelle révolution industrielle (industrie4.0), les technologies majeurs participant à son apparition, leur bénéfices attendus ainsi que leurs enjeux à prendre en considération.

The infill walls are usually considered as nonstructural elements and, thus, are not taken into account in analytical models. However, numerous researches have shown that they can significantly affect the seismic response of the structures. The aim of the present study is to examine the role of masonry infill on the damage response of steel frame without and with various types of openings systems subjected to nonlinear static analysis and nonlinear time history analysis. For the purposes of the above investigation, a comprehensive assessment is conducted using twelve typical types of steel frame without masonry, with full masonry and with different heights and widths of openings. The results revealed that the influence of the successive earthquake phenomenon on the structural damage is larger for the infill buildings compared to the bare structures. Furthermore, when buildings with masonry infill are analyzed for seismic sequences, it is of great importance to account for the orientation of the seismic motion. The nonlinear static response indicated that the opening area has an influence on the maximal strength, the ductility and the initial rigidity of these frames. But the shape of the opening will not influence the global behavior. Then, the nonlinear time history analysis indicates that the global displacement is greatly decreased and even the behavior of the curve is affected by the earthquake intensity when opening is considered.

Owing to the comeback of small-scale models, this paper presents results of an experimental study based on the effect of underground circular voids on strip footing placed on the edge of a cohesionless slope and subjected to eccentric loads. The bearing capacity-settlement relationship of footing on the slope and impact of diverse variables are expressed using dimensionless parameters such as the top vertical distance of the void from the base of footing, horizontal space linking the void-footing centre, and load eccentricity. The results verified that the stability of strip footing is influenced by the underground void, as well as the critical depth between the soil and top layer of the void. The critical horizontal distance between the void and the centre was also affected by the underground void. Furthermore, the results also verified that the influence of the void appeared insignificant when it was positioned at a depth or eccentricity equal to twice the width of footing.

The aim of this work is to study the mechanical behavior of the sediments extracted from the Koudiet Meddaouar, Timgad dam (Algeria), for a possible valorization in the field for building works in order to minimize this phenomenon which is currently a concern for the operators and the persons in charge of the mobilization of the water resources. This siltation therefore severely limits its storage capacity and consequently it’s operating life. The extraction of the sediments accumulated in the dam’s reservoir is therefore imperative, on the pain of seeing it perish in the medium term. These sediments are, however, of great geotechnical and mechanical value. The results of the tests conducted in the laboratory have enabled us to identify the different sediments from a physical and geotechnical point of view In front of the difficulties noted in the control of the silting up of the dams in Algeria, a very important quantity of silt being deposited annually in the dams. In order to achieve our objective, different mixtures of silt with or without lime treatment, cement glass fibers and powdered fibers were studied for the possible manufacture of Compressed Earth Bricks (CEB). The results obtained show that some of the mixtures present very interesting results in the different tests (compression and bending), verifying the conditions of the standards in force and thus allowing their use in the field of the manufacture of building materials.

This study aimed to investigate whether the seismic fragility and performance of interaction soil-pile-structure (ISPS) were affected by different parameters:  axial load, a section of the pile, and the longitudinal steel ratio of the pile were implanted in different type of sand (loose, medium, dense). In order to better understand the ISPS phenomena, a series of nonlinear static analysis have been conducted for two different cases, namely: (i) fixed system and (ii) ISPS system, to get the curves of the capacity of every parameter for developing the fragility curve. After a comparison of the numerical results of pushover analysis and fragility curves, the results indicate that these parameters are significantly influenced on lateral capacity, ductility and seismic fragility on the ISPS. The increasing in the axial load exhibit high probabilities of exceeding the damage state. The increase in pile section and longitudinal steel ratio, the effect of probability damage (low and high) are not only related to the propriety geometrically, but also related to the values of ductility and lateral capacity of the system.

The objective of the present manuscript is to describe the impact of polypropylene fibers on the behavior of heated concrete subjected to heating and cooling cycles at temperatures of 200, 450 and 600 °C respectively for six hours, through a series of experimental tests on mass loss, water absorption, porosity, compressive and tensile strength. For this purpose, mixes were prepared with a water/cement ratio with the incorporation of polypropylene fibers with a rate varying from 0.5 to 1.5%. These fibers were added in order to improve the thermal stability and to prevent the concrete from splitting. The results show that a considerable loss of strength was noticed for all tested specimens. The relative compressive strengths of the concretes containing polypropylene fibers were higher than those of the concretes without fibers. Also, a greater loss of mass of the polypropylene fibers compared to those without fibers was noticed when increasing the temperature. The flexural tensile strength of the concrete was more sensitive to elevated temperatures than the compressive strength and a rapid increase in porosity was observed for the fiber-reinforced concrete compared to the reference concrete. Furthermore, water absorption by the fibers is proportional to the fiber content of the concrete.

The stability and strength of slender Reinforced Concrete (RC) columns depend directly on the flexural stiffness EI, which is a major parameter in strain calculations including those with bending and axial load. Due to the non-linearity of the stress-strain curve of concrete, the effective bending stiffness EI always remains variable. Numerical simulations were performed for square and L-shaped reinforced concrete sections of slender columns subjected to an eccentric axial force to estimate the variation of El resulting from the actual behavior of the column, based on the moment-curvature relationship. Seventy thousand (70000) hypothetical slender columns, each with a different combination of variables, were used to investigate the main variables that affect the EI of RC slender columns. Using linear regression analysis, a new simple and linear expression of EI was developed. Slenderness, axial load level, and concrete strength have been identified as the most important factors affecting effective stiffness. Finally, the comparison between the results of the new equation and the methods proposed by ACI-318 and Euro Code-2 was carried out in connection with the experimental results of the literature. A good agreement of the results was found.