Proton Exchange Membrane Fuel Cells (PEMFCs) are a key challenger for the world’s future clean and renewable energy solution. Yet, fuel cells are susceptible to operating conditions and hydrogen impurities, leading to performance loss over time in service. Hence, performance degradation prediction is gaining attention recently for fuel cell system reliability. In this work, we present a knowledge transfer approach for online voltage drop prediction. A dual-path convolution neural network is proposed to extract linearity and non-linearity from historical data and performs multi-steps ahead prediction with uncertainty quantification. Online voltage prediction is then evaluated with and without knowledge transfer using two different PEMFC datasets. Results indicate that our proposed approach with transfer knowledge can predict the voltage drop accurately with a small uncertainty range compared to the conventional approach.

In modern Smart Grids (SGs) ruled by advanced computing and networking technologies, condition monitoring relies on secure cyberphysical connectivity. Due to this connection, a portion of transported data, containing confidential information, must be protected as it is vulnerable and subject to several cyber threats. SG cyberspace adversaries attempt to gain access through networking platforms to commit several criminal activities such as disrupting or malicious manipulation of whole electricity delivery process including generation, distribution, and even customer services such as billing, leading to serious damage, including financial losses and loss of reputation. Therefore, human awareness training and software technologies are necessary precautions to ensure the reliability of data traffic and power transmission. By exploring the available literature, it is undeniable that Machine Learning (ML) has become the latest in the timeline and one of the leading artificial intelligence technologies capable of detecting, identifying, and responding by mitigating adversary attacks in SGs. In this context, the main objective of this paper is to review different ML tools used in recent years for cyberattacks analysis in SGs. It also provides important guidelines on ML model selection as a global solution when building an attack predictive model. A detailed classification is therefore developed with respect to data security triad, i.e., Confidentiality, Integrity, and Availability (CIA) within different types of cyber threats, systems, and datasets. Furthermore, this review highlights the various encountered challenges, drawbacks, and possible solutions as future prospects for ML cybersecurity applications in SGs.

The purpose of this paper is to propose an improvement strategy based on multi-criteria decision making approaches, including fuzzy analytic hierarchy process (AHP), preference ranking organisation method for enrichment evaluation II (PROMETHEE) and vi\v sekriterijumsko kompromisno rangiranje (VIKOR) for the objective of simplifying and organising the improvement process in complex manufacturing processes. Firstly, the proposed strategy started with the selection of decision makers’, such as company leaders, to determine performance indicators. Then fuzzy AHP is used to quantify the weight of each defined indicators. Finally, the weights carried out from fuzzy AHP approach are used as input in VIKOR and PROMETHE II to rank the operations according to their improvement priority. The results obtained from each outranking method are compared and the best method is determined.

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.

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.

Cooperation in distribution network has attracted the interest of researchers. In this study we analyse an inventory problem in distribution network, where we propose a cooperative platform that allow the members of the network to share and use local inventory of other members to meet their local demand. We develop a MIP models representing the traditional network and the network with the cooperative platform. Then we solve it using LINGO solver. We found that the proposed approach has reduced the total cost of the network and reduce the overstock and stock-out situation, which lead to improve the quality of service.

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.