This paper proposes a new approach for remaining useful life prediction that combines a bond graph, the Gaussian Mixture Model and similarity techniques to allow the use of both physical knowledge and the data available. The proposed method is based on the identification of relevant variables that carry information on degradation. To this end, the causal properties of the bond graph (BG) are first used to identify the relevant sensors through the fault observability. Then, a second stage of analysis based on statistical metrics is performed to reduce the number of sensors to only the ones carrying useful information for failure prognosis, thus, optimizing the data to be used in the prognosis phase. To generate data in the different system state, a simulator based on the developed BG is used. A Gaussian Mixture Model is then applied on the generated data for fault diagnosis and clustering. The Remaining Useful Life is estimated using a similarity technique. An application on a mechatronic system is considered for highlighting the effectiveness of the proposed approach.

The grasshopper optimization algorithm is one of the recently population-based optimization techniques inspired by the behaviours of grasshoppers in nature. It is an efficient optimization algorithm and since demonstrates excellent performance in solving continuous problems, but cannot resolve directly binary optimization problems. Many optimization problems have been modelled as binary problems since their decision variables varied in binary space such as feature selection in data classification. The main goal of feature selection is to find a small size subset of feature from a sizeable original set of features that optimize the classification accuracy. In this paper, a new binary variant of the grasshopper optimization algorithm is proposed and used for the feature subset selection problem. This proposed new binary grasshopper optimization algorithm is tested and compared to five well-known swarm-based algorithms used in feature selection problem. All these algorithms are implemented and experimented assessed on twenty data sets with various sizes. The results demonstrated that the proposed approach could outperform the other tested methods.

In the last recent years, a large community of researchers and industrial practitioners has been attracted by combining different prognostics models as such strategy results in boosted accuracy and robust performance compared to the exploitation of single models. The present work is devoted to the investigation of three new fusion schemes for the remaining useful life forecast. These integrated frameworks are based on aggregating a set of Gaussian process regression models thanks to the Induced Ordered Weighted Averaging Operators. The combination procedure is built upon three proposed analytical weighting schemes including exponential, logarithmic and inverse functions. In addition, the uncertainty aspect is supported in this work, where the proposed functions are used to weighted average the variances released from competitive Gaussian process regression models. The training data are transformed into gradient values, which are adopted as new training data instead of the original observations. A lithium-ion battery data set is used as a benchmark to prove the efficiency of the proposed weighting schemes. The obtained results are promising and may provide some guidelines for future advances in performing robust fusion options to accurately estimate the remaining useful life.

In this study, we investigate a production planning problem in hybrid manufacturing remanufacturing production system. The objective is the determine the best mix between the manufacturing of new products, and the remanufacturing of recovered products, based on economic and environmental considerations. It consists to determine the best manufacturing and remanufacturing plans to minimising the total economic cost (start-up and production costs of new and remanufactured products, storage costs of new and returned products and disposal costs) and the carbon emissions (new products, remanufactured products and disposed products). The hybrid system consists of a set of machines used to produce new products and remanufactured products of different grades (qualities). We assume that remanufacturing is more environmentally efficient, because it allows to reduce the disposal of used products. A multi-objective mathematical model is developed, and a non dominated sorting genetic algorithm (NSGA-II) based approach is proposed. Numerical experience is presented to study the impact of carbon emissions generated by new, remanufactured and disposed products, over a production horizon of several periods.

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.

La surveillance est la fonction d’observer toutes activités humaine ou environnementales dans le but de superviser, contrôler ou même réagir sur un cas particulier; ce qu’on appelle la supervision ou le monitoring. La technologie de la radio-identification, connue sous l’abréviation RFID (de l’anglais Radio Frequency IDentification), est l’une des technologies utilisées pour récupérer des données à distance de les mémoriser et même de les traiter. C’est une technologie d’actualité et l’une des technologies de l’industrie 4.0 qui s’intègre dans de nombreux domaines de la vie quotidienne notamment la surveillance et le contrôle d’accès. L’objectif de cet article est de montrer comment protéger et surveiller en temps réel des zones industrielles critiques et de tous types d’accès non autorisés de toute personne (employés, visiteurs…) en utilisant la technologie RFID et cela à travers des exemples de simulation à l’aide d’un simulateur dédié aux réseaux de capteurs.

Prognosis and health management (PHM) are mandatory tasks for real-time monitoring of damage propagation and aging of operating systems during working conditions. More definitely, PHM simplifies conditional maintenance planning by assessing the actual state of health (SoH) through the level of aging indicators. In fact, an accurate estimate of SoH helps determine remaining useful life (RUL), which is the period between the present and the end of a system’s useful life. Traditional residue-based modeling approaches that rely on the interpretation of appropriate physical laws to simulate operating behaviors fail as the complexity of systems increases. Therefore, machine learning (ML) becomes an unquestionable alternative that employs the behavior of historical data to mimic a large number of SoHs under varying working conditions. In this context, the objective of this paper is twofold. First, to provide an overview of recent developments of RUL prediction while reviewing recent ML tools used for RUL prediction in different critical systems. Second, and more importantly, to ensure that the RUL prediction process from data acquisition to model building and evaluation is straightforward. This paper also provides step-by-step guidelines to help determine the appropriate solution for any specific type of driven data. This guide is followed by a classification of different types of ML tools to cover all the discussed cases. Ultimately, this review-based study uses these guidelines to determine learning model limitations, reconstruction challenges, and future prospects.

Many cloud providers offer very high precision services to exploit Optical Character Recognition (OCR). However, there is no provider offers Tifinagh Optical Character Recognition (OCR) as Web Services. Several works have been proposed to build powerful Tifinagh OCR. Unfortunately, there is no one developed as a Web Service. In this paper, we present a new architecture of Tifinagh Handwriting Recognition as a web service based on a deep learning model via Google Colab. For the implementation of our proposal, we used the new version of the TensorFlow library and a very large database of Tifinagh characters composed of 60,000 images from the Mohammed Vth University in Rabat. Experimental results show that the TensorFlow library based on a Tensor processing unit constitutes a very promising framework for developing fast and very precise Tifinagh OCR web services. The results show that our method based on convolutional neural network outperforms existing methods based on support vector machines and extreme learning machine.

In this paper, numerous experimental tests were carried out to study the behavior of concrete containing glass fibers and confined with glass fiber-reinforced polymer (GFRP). Concrete specimens containing different fiber percentages ( 0.3 wt.%, 0.6 wt.%, 0.9 wt.% or 1.2 wt.%) and with different strengths of concrete (8.5 MPa, 16 MPa and 25 MPa) and different confinement levels (two, four and six layers of GFRP) were used as research parameters. The samples were tested to failure under pure axial compression. The results imply that the confinement effect with GFRP is relatively higher for concrete samples containing glass fiber (GFCC) with a percentage equal to 0.6 wt.%. The theoretical of stress ratios (fcc/fco) estimated by using existing ultimate strength models are found to be close to the experimental results for high strength of GFCC, but not close to the experimental results for low strength of GFCC.

During the last two decades, the attention of researchers has been focused on repairing and retrofitting concrete frames to make them more earthquake-resistant. Two methods have been developed to increase the seismic resistance of previously undamaged structures before they are subjected to an earthquake. The first is through the addition of new structural members, such as steel braces and the second is by selectively strengthening structural elements, for instance through steel caging. Seismic response analysis results have been utilized in multi-story RC frames that were designed without seismic design criteria. This study aims to determine whether the retrofitting technique is effective based on comparisons between steel braces, steel cages, and their combinations. The seismic performance is defined by the seismic code for Algeria RPA 2003 according to the latest recommendations. Static nonlinear analysis was used to compare seismic responses of existing non-ductile reinforced concrete RC frames under a variety of retrofit schemes. The results show that retrofitting with steel caging gives excellent performance in terms of ductility and low shear capacity. The retrofitting with steel bracing increased the shear capacity but led to a severe ductility deficiency. The retrofitting structure combined with steel bracing and steel caging shows good performance in shear capacity and ductility. Using the Zipper system (steel bracing) and V system in combination with steel caging gives similar results to the RPA model.

Sebkha soils are defined as problem soils located in arid, semi-arid, and coastal areas. Generally, they are fine soil, composed of silt, sand, and clay, which are cemented by different salts (e.g., halite, gypsum, and calcite). In nature, sebkha saline soils are exposed to different drying and wetting (D-W) cycles. However, these cycles have a significant effect on the mechanical behavior of these soils. This study aims to characterize the chemical, mineralogical, and geotechnical properties of sebkha soil using an experimental approach. We focus on the effects of D-W cycles on the unconfined compressive strength (UCS) and salinity of sebkha soils from Ain M’Lila, Algeria. In addition, these D-W cycles were applied to the samples dried in the open air to achieve the targeted water content (water content values of 7%, 11.4%, and 13%). The results obtained show that the UCS increases with decrease in water content and decreases with an increase in the number of D-W cycles. In addition, these cycles affect the salinity of the sebkha soil. Indeed, a significant decrease in soil salinity was recorded with an increase in the number of D-W cycles. Finally, a relationship was found between the salinity of the soil and UCS. The latter decreases with a decrease in soil salinity; this relationship becomes very significant for low water content values of 7% or less.

External confinement by the GFRP composites offers an actual process for retrofitting glass fibre reinforced concrete columns (GFRC) subject to static or seismic loads. This paper presents an experimental investigation and analytical modelling of the axial compression of confined circular concrete columns of different strengths (8.5, 16, and 25 MPa). Furthermore, the columns contain different percentages of glass fibres (0.3 to 1.2 %), and their confinement is given by GFRP composites of various thicknesses (0.8 to 2.4 mm). The uniaxial compression test on these specimens reveals that the glass fibre percentage and the thickness of the GFRP play a vital role in improving the load-deformation behaviour and crack propagation. Whatever the concrete strength, the ultimate axial strain and stress predicted using the suggested confinement model almost agrees with the available experimental results.

The study of the collapse of soils under the effect of flooding is a major problem in soil mechanics. Most of the work done on the treatment of these soils has been devoted to the use of binders of hydraulic or organic types. However, little work has been devoted to the use of salt calcium chloride in collapsible soil treatments. The purpose of this study is to evaluate the effect salt calcium chloride on a reconstituted collapsible soil in the laboratory, at different levels of water content, compaction energy and concentration of the saline solution. The results obtained showed a significant reduction in the potential for soil deformation and an illustration and a noticeable interaction between the soil particles and the saline solution resulting in a denser material.

Eccentrically Braced Frames (EBFs) have been widely used in the last decades and proved their efficiency to resist strong earthquake intensities by providing suitable ductility and lateral stiffness. Using the PBPD method for the design, EBFs can fulfill the target performance objectives under major earthquakes. The most commonly used configurations are the K-shaped and the recent Y-shaped EBFs, which have the advantage that the links are independent of the beam and can be easily replaced after an earthquake without serious damage to the beam and slab. This study focused on the lateral reliability of both systems under seismic loading. Nonlinear static pushover and Incremental Dynamic Analysis (IDA) were performed on 5-story and 10-story K- and Y-shaped EBFs. A series of 14 near- and 7 far-field seismic records were considered to analyze and compare the inter-story drifts of both systems using the Seismostruct software. Moreover, Peak Ground Accelerations (PGA) and the different performance levels were also examined.

Seismic fragility curves are considered an effective tool for the evaluation of the behavior of interaction of the soil-pile-structure (ISPS) subjected to earthquake loading. In this research, in order to better understand the ISPS effect, a nonlinear static analysis is applied with a variation of the vertical load, the diameter of pile, and finally the longitudinal steel ratio of the pile in different types of sand (loose, medium, dense) to obtain the capacity curves of each parameter for elaborating the curves of fragility. After a comparison of fragility curves of these parameters, it appears that the effect of the ISPS system is advantageous with respect to the vertical axial load and the diameter of pile, while the longitudinal ratio of the pile depending on the ductility and the lateral resistance of the ISPS system. The proposed equation is intended to help engineers in the design and performance of the soil-pile-structure interaction. The results of this equation provided a convergence with the results of the fragility curves.

The main function of a pavement is to distribute the traffic-induced load over its different layers. While the flexible pavement design methods are based on a linear elastic calculation, the real behavior of the different layers is highly nonlinear and elastic. They can also, in some cases, be plastic and viscous. This research aims to develop a three-dimensional numerical model that is closely similar to the test FWTT conditions. The model will have a real geometry wheel footprint (rather than a rectangular shape). As a substitute for incremental loading, the wheel movement during its passage over the specimen will be simulated by a horizontal displacement. These important characteristics of the model represent the novelty and the major difference between the current research and previous studies. The current model, which is based on the finite elements method, uses Abaqus software and a viscoelastic constitutive model. The materials’ viscoelastic properties have been described by the Prony series, also called the relaxation modulus, which is a function of time. This parameter can be defined in most computer-aided engineering (CAE) software. The procedure for calculating the Prony series from experimental data is explained. The results obtained agree with the stress signal amplitude, the stress rotation principal, and the total displacement rotation when the load approaches the node considered and located in the middle of the specimen.

Sedimentation of dam reservoirs is a complex problem with several dimensions, including filling rates and characteristics of accumulated sediments. Sediment supply from river basins is particularly high in this region because of its semi-arid climate and especially because of poor vegetation protection. The amount of silt accumulated annually since the construction of this dam is estimated at 330000 m3. This silt accumulation strongly limits its storage capacity and consequently its operating duration. The consequences of this serious problem have been catastrophic, including a considerable reduction of 43–84% of the storage capacity of the dams and a clear degradation of water quality that can cause the degradation of the ecosystem functioning and can lead to irreversible changes. The silt present in abundance in the Algerian dams can, thus, constitute a potential resource to be judiciously exploited towards the increase of the performances of the construction materials. The extraction of sediments accumulated in the dam reservoir is, therefore, imperative. These sediments have a great geotechnical value. The objective of this study is to assess the feasibility of the recovery of mud by studying the knowledge of the sediments of the dam of Koudiat Medouar. The results of the tests carried out in laboratory allowed us to identify the various sediments from a physical and geotechnical point of view. These materials must of course meet certain rigorous criteria in terms of mechanical strength and durability and environmental impact. The experimental approach that we adopted allowed us to determine the characteristics of the materials necessary for the realization of compressed earth bricks (BTC) in conformity with the recommendations of the technical guides of construction.

Designing and manufacturing replacement cancellous bone structures by lattice structures and Additive Manufacturing (AM) techniques is an effective method to create lightweight orthopedic implants while ensuring that they are mechanically compatible and their osseointegration ability with the host bone. In this article, we suggest a new design based on three lattice structures from triply periodic minimal surfaces (TPMS) with a different volume porosity to replace cancellous bone based on predicting the mechanical stiffness. To predict the mechanical stiffness, the relationship between the effective modulus of elasticity and different porosity ratios of the lattice structures was determined by using three methods: i) finite element modeling (FEM) simulation, ii) Gibson and Ashby method and iii) a uniaxial compression test after manufacturing the lattice structures by using Fused Filament Fabrication (FFF) Technology. To demonstrate the efficiency of our approach, the comparison of both numerical and experimental results showed that the effect of structure difference and porosity ratio of lattice structures on the mechanical stiffness values effectively match the cancellous bone in terms of elastic modulus and porosity ratio.

The relative scarcity of water resources in Algeria and their unequal distribution induce a rational use of available resources. The Zana-Gada{\"ıne plain appears as an exemplary case study, where the difficulties posed by the problem of crop water needs versus the availability of water resources appear. This article, based on field surveys and in-situ measurements, aims to identify the pressure of irrigation on water resources and the optimization of their use in an agricultural area, where irrigated agriculture represents 85% of the water consumption of the Zana-Gada{\"ıne plain. The piezometric study in correlation with hydrogeological data reveals that groundwater resources are limited, aggravated by wastage resulting in a consequent drawdown of 24 meters over 11 years. The analysis of interannual climate variability has enabled us to draw rainfall maps characteristic of the evolution of rainfall over the past decades where we observe a net deficit in precipitation. We calculated the evapotranspiration and the requirements in irrigation water for each crop in order to compare them with the available hydric resources and the establishment of irrigation schedules for the principal irrigated crops. The analysis of interannual climate variability has enabled us to draw rainfall maps characteristic of the evolution of rainfall over the past decades where we observe a net deficit in precipitation. We calculated the evapotranspiration and the requirements in irrigation water for each crop in order to compare them with the available hydric resources and the establishment of irrigation schedules for the principal irrigated crops.