WorldCat Identities

Nicod, Jean-Marc

Overview
Works: 24 works in 48 publications in 2 languages and 778 library holdings
Roles: Opponent, Thesis advisor, Other, Author
Classifications: TS173, 620.00452
Publication Timeline
.
Most widely held works by Jean-Marc Nicod
From Prognosis and Health Systems Management to Predictive Maintenance 2: Knowledge, Reliability and Decision by Brigitte Chebel-Morello( )

2 editions published in 2017 in English and held by 453 WorldCat member libraries worldwide

A second volume in a set of books dealing with the evolution of technology, IT and organizational approaches and what this means for industrial equipment. The authors address this increasing complexity in two parts, focusing specifically on the field of Prognostics and Health Management (PHM). Having tackled the PHM cycle in the first volume, the purpose of this book is to tackle the other phases of PHM, including the traceability of data, information and knowledge, and the ability to make decisions accordingly
From prognostics and health systems management to predictive maintenance by Brigitte Chebel-Morello( )

11 editions published in 2017 in English and held by 256 WorldCat member libraries worldwide

This book is the second volume in a set of books dealing with the evolution of technology, IT and organizational approaches and what this means for industrial equipment. The authors address this increasing complexity in two parts, focusing specifically on the field of Prognostics and Health Management (PHM)
Du concept de PHM à la maintenance prédictive by Brigitte Chebel-Morello( Book )

5 editions published in 2017 in French and held by 37 WorldCat member libraries worldwide

La 4ème de couverture indique : "Avec les évolutions technologiques, informatiques et organisationnelles, les équipements industriels deviennent plus complexes et automatisés. Cette complexité est à l'origine de nombreux incidents, défaillances ou dégâts sur les biens, l'environnement et les personnes et nécessite la mise en place d'une stratégie de maintenance efficiente, notamment au niveau du pronostic. Le processus de traçabilité et de capitalisation des données est un élément clé dans la perspective de l'évolution de la maintenance vers des stratégies prédictives. Ainsi, on dispose d'informations pertinentes et de connaissances appropriées permettant de prendre des décisions éclairées préalables à la mise en place d'une politique stratégique de maintenance prédictive. Cet ouvrage traite des stratégies de maintenance prédictive d'équipements industriels. Il fait suite au premier volume dédié aux premiers modules du cycle PHM et expose les modules relatifs à l'aide à la décision, la traçabilité de l'information et la capitalisation des connaissances."
EXTRACTION DE SURFACES EN IMAGERIE MEDICALE : APPROCHES PARALLELES by Jean-Marc Nicod( Book )

2 editions published in 1997 in French and held by 2 WorldCat member libraries worldwide

LE TRAVAIL PRESENTE DANS CETTE THESE SE SITUE A L'INTERSECTION ENTRE LE PARALLELISME ET LA MODELISATION GEOMETRIQUE POUR L'IMAGERIE MEDICALE. IL S'AGIT DE LA PARALLELISATION D'ALGORITHMES D'EXTRACTION DE SURFACES, A PARTIR DE DONNEES VOLUMIQUES MEDICALES. CES TRAVAUX S'INSERENT DANS UN PROJET DU GROUPE D'IMAGERIE PARALLELE DU LIP, VISANT A LA MISE EN UVRE SUR DES MACHINES MIMD DE TOUTE UNE CHAINE DE TRAITEMENTS D'IMAGERIE MEDICALE. NOUS NOUS FOCALISONS SUR DEUX ALGORITHMES D'EXTRACTION DE SURFACES, L'ALGORITHME DES MARCHING-CUBES ET CELUI DES DIVIDING-CUBES. POUR CES DEUX APPROCHES, NOUS ETUDIONS LES MODELISATIONS GEOMETRIQUES PERMETTANT D'ANALYSER LA COMPLEXITE DES SURFACES EXTRAITES. CES MODELES DE COMPLEXITE PERMETTENT D'OBTENIR UNE EVALUATION DU TEMPS D'EXECUTION. DANS UN SECOND TEMPS, NOUS UTILISONS CETTE EVALUATION POUR REMETTRE EN CAUSE L'ALLOCATION INITIALE DES DONNEES AFIN D'OBTENIR UNE PARALLELISATION EQUILIBREE. EN RAISON DES TRES FORTES CONTRAINTES DE LOCALITE ASSOCIEES A NOS CALCULS, NOUS UTILISONS DES STRATEGIES D'EQUILIBRAGE DIRIGEES PAR LES DONNEES, PERMETTANT D'EXPLOITER AU MIEUX LA PUISSANCE DES MACHINES PARALLELES. NOTRE STRATEGIE D'ALLOCATION DES DONNEES PERMET DE PRENDRE EN COMPTE LA COHERENCE SPATIALE ASSOCIEE A NOS CALCULS, MAIS EGALEMENT LA COHERENCE TEMPORELLE LORS DE LA PRODUCTION D'UNE ANIMATION. AUSSI BIEN POUR LA VARIATION REGULIERE DU SEUIL D'UNE ISO-SURFACE QUE POUR LE CHANGEMENT DES PARAMETRES DE VISUALISATION, NOUS DEMONTRONS LES BENEFICES D'UNE TELLE STRATEGIE: LES DONNEES UTILISEES PAR UN PROCESSEUR LORS DE LA PRODUCTION D'UNE IMAGE SONT PEU DIFFERENTES CELLES QUI SONT UTILISEES PAR LE MEME PROCESSEUR LORS DU CALCUL DE L'IMAGE SUIVANTE. NOUS PROPOSONS UNE PRIMITIVE DE COMMUNICATION QUI EXPLOITE CETTE PROPRIETE. DES EXPERIMENTATIONS SUR UNE MACHINE T3D DE CRAY, DEMONTRENT L'EFFICACITE DE NOTRE APPROCHE ET PERMETTENT D'ENVISAGER D'EFFECTUER CES TRAITEMENTS DE MANIERE INTERACTIVE
Optimizing memory allocation for multistage scheduling including setup times by Anne Benoit( )

1 edition published in 2015 in English and held by 2 WorldCat member libraries worldwide

Contribution à l'ordonnancement post-pronostic de plateformes hétérogènes et distribuées : approches discrète et continue by Nathalie Herr( )

2 editions published in 2015 in French and held by 2 WorldCat member libraries worldwide

This thesis addresses the problem of maximizing the production horizon of a heterogeneous distributed platform composed of parallel machines and which has to provide a global production service. Each machine is supposed to be able to provide several throughputs corresponding to different operating conditions. It is assumed that using a machine with degraded performances compared to nominal ones allows to extend its useful life before maintenance. The study falls within the decisional step of PHM (Prognostics and Health Management), in which a prognostics phase allows to determine remaining useful lives of machines. The optimization problem consists in determining the set of machines to use at each time and a running profile for each of them so as to maximize the production horizon before maintenance. Machines running profiles are defined on the basis of two models. First one depicts the behavior of machines used with a discrete number of performances. For this case, the problem complexity is first studied considering many variants of the optimization problem. Several optimal and sub-optimal resolution methods are proposed to deal with the scheduling problem. Several sub-optimal resolution methods are then proposed for the second model, which applies to machines whose throughput rate can vary continuously between two bounds. These research works allow to determine the time before failure of a system on the basis of its components remaining useful lives
Random Generation for the Performance Evaluation of Scheduling Algorithms by Mohamad El Sayah( )

2 editions published in 2019 in English and held by 2 WorldCat member libraries worldwide

The aim of this thesis is to develop techniques for the evaluation of the performance of algorithms for specific problems of scheduling. The work will consist in proposing experimental protocolsto assess specific problems of scheduling by restricting themselves to those who share similar instances as graphs. This implies on the one hand analyzing the problems considered in order to define what can berelevant instances. Next, it will be necessary to propose generators (random) of (difficult) instances, then perform an experimental analysis of existing algorithms
Semantic mechanisms for cross-domain system diagnosis by manuella Popescu( Book )

in English and held by 2 WorldCat member libraries worldwide

System diagnosis is a very challenging task due to the variety of symptoms, probable causes, impact analysis and the selection of the most suitable solution. Most system diagnosis activities today are human-based, for this reason, error-prone. The automation of the diagnosis decisions faces several challenges, such as: high complexity, lack of automatic knowledge transfer, and disconnection between context-oriented positive decisions taken in dissimilar domains. To address some of these issues, the contribution of this thesis is tow-fold. Firstly, we propose an adaptive framework for diagnosis validation and transfer of information from successful cases for future use in similar situations. We show that this mechanism allows a post-validation of successful diagnosis actions optimizing the diagnosis process and increasing its accuracy. Secondly, we introduce an event ontology and concepts related to semantic tag clouds; we show how to manage the related activities to build an ontology-driven diagnosis. We formalize these concepts in order to derive diagnosis actions and validate the successful ones. We also propose augmented event and augmented action models to validate the diagnosis. Lastly, we embed a timestamps approach and we consider a series of temporal operators defining the events relative temporal positions; this approach allows a more fine grain interpretation of the system behavior. A combination of the proposed mechanisms is used to complete the main functions of the diagnosis engine. We highlight the complexity of the approach via a case study and we illustrate partial solutions for different concepts introduced
From prognostics and health systems management to predictive maintenancen2 by Brigitte Chebel-Morello( Book )

2 editions published in 2017 in English and held by 2 WorldCat member libraries worldwide

Road to exascale : improving scheduling performances and reducing energy consumption with the help of end-users by David Glesser( )

1 edition published in 2016 in English and held by 2 WorldCat member libraries worldwide

The field of High Performance Computing (HPC) is characterized by the contin-uous evolution of computing architectures, the proliferation of computing resourcesand the increasing complexity of applications users wish to solve. One of the mostimportant software of the HPC stack is the Resource and Job Management System(RJMS) which stands between the user workloads and the platform, the applica-tions and the resources. This specialized software provides functions for building,submitting, scheduling and monitoring jobs in a dynamic and complex computingenvironment.In order to reach exaflops HPC systems, new constraints and objectives havebeen introduced. This thesis develops and tests the idea that the users of suchsystems can help reaching the exaflopic scale. Specifically, we show and introducenew techniques that employ users behaviors to improve energy consumption andoverall cluster performances.To test the proposed techniques, we need to develop new tools and method-ologies that scale up to large HPC clusters. Thus, we designed adequate tools thatassess new RJMS scheduling algorithms of such large systems. These tools areable to run on small clusters by emulating or simulating bigger platforms. Afterevaluating different techniques to measure the energy consumption of HPC clusters,we propose a new heuristic, based on the popular Easy Backfilling algorithm, inorder to control the power consumption of such huge systems. We also demonstrate,using the same idea, how to control the energy consumption during a time period.The proposed mechanism is able to limit the energy consumption while keepingsatisfying performances. If energy is a limited resource, it has to be shared fairly.We also present a mechanism which shares energy consumption among users. Weargue that sharing fairly the energy among users should motivate them to reducethe energy consumption of their applications. Finally, we analyze past and presentbehaviors of users using learning algorithms in order to improve the performancesof the parallel platforms. This approach does not only outperform state of the artmethods, it also shows promising insight on how such method can improve otheraspects of RJMS
Optimisation du débit pour des applications linéaires multi-tâches sur plateformes distribuées incluant des temps de reconfiguration by Mathias Coqblin( )

2 editions published in 2015 in French and held by 2 WorldCat member libraries worldwide

In this document we tackle scheduling problems of multitask linear workflow applications ondistributed platforms. In our particular problem the number of available machines on the platformis lower than the number of stages within the pipeline. The machines are then assumed to be able toperform any kind of task on the application given the appropriate reconfiguration (or setup), the catchbeing that any reconfiguration is time consuming. The problem that we try to solve is to maximizethe throughput of such applications, i.e., the mean amount of outputs per unit of time, or to minimizeits period, i.e., the average time between two outputs. As a result this problem is split into two subproblems:mapping tasks onto different machines of the platform (most machines will likely handleseveral tasks), and find an optimal schedule within a machine while taking setup times into account.To solve this we introduce buffers, which are spaces available for each machine to store temporaryproduction results and avoid reconfiguring after each task execution, and which may or may notbe already allocated for each stage. If those buffers are not already allocated to each task then athird problem must be solved to properly allocate the available space onto each buffer, as differentbuffer configurations have a huge impact on the scheduling of a machine. This document presentsan exhaustive coverage of the different problems that are associated with the heterogeneity of theapplication; the problems with homogeneous buffer capacities and setup times are rather simple tosolve, but they get a lot more complex as heterogeneity increases. We study the three main subproblemsfor each heterogeneity combination, and offer heuristic solution to solve them when anoptimal solution cannot be reasonably found
Sizing and management of hybrid renewable energy system for data center supply by Maroua Haddad( )

2 editions published in 2019 in English and held by 2 WorldCat member libraries worldwide

Le secteur du numérique est récemment devenu un secteur majeur de la consommation d'électricité dans le monde, notamment avec l'avènement des data centers qui concentrent un très grand nombre de machines traitant des informations et fournissant des services. L'utilisation de sources d'énergie renouvelables sur site est un moyen prometteur de réduire l'impact écologique des data centers. Cependant, certaines énergies renouvelables comme les énergies solaire et éolienne sont intermittentes, étant liées aux conditions météorologiques. Étant donné qu'un centre de données doit maintenir une certaine qualité de service, l'utilisation efficace de ces sources nécessite l'utilisation de stockages. Cette thèse explore à la fois une méthode dimensionnement et une méthode de gestion optimale d'une infrastructure hybride d'énergie renouvelable, composée de panneaux photovoltaïques, d'éoliennes, de batteries et de système de stockage hydrogène.Une première contribution aborde le problème du dimensionnement de cette infrastructure électrique afin de répondre à la demande du data center. Un outil de dimensionnement est proposé, prenant en compte plusieurs métriques et fournissant trois configurations différentes. L'utilisateur choisit donc la configuration approprié, en fonction de son plan économique global de son écosystème H2. Une deuxième contribution étudie le problème de la gestion de l'énergie par programmation linéaire en nombres entiers. Un outil de gestion optimal est fourni pour trouver différents engagements optimaux des sources en fonction des objectifs de l'utilisateur. Les solutions obtenues sont ensuite discutées avec plusieurs métriques et avec différents horizons temporelles afin de trouver la meilleure solution pour répondre à la demande du data center. Enfin, une troisième contribution vise à prévoir évolution temporelle de l'ensoleillement et de la vitesse du vent à gros grain pour obtenir un dimensionnement plus précis à l'aide du modèle SARIMA
Optimization of parallel scheduling and the use of renewable energy sources to power computing centers by Ayham Kassab( )

2 editions published in 2019 in English and held by 2 WorldCat member libraries worldwide

L'objectif global de la gestion de l'énergie alimentant les centres de calcul est un enjeu reconnu et les travaux se tournent actuellement vers leur alimentation à base de sources renouvelables pour limiter l'impact écologique. Certaines de ces sources d'énergie, comme les panneaux photovoltaïques et les éoliennes, sont intermittentes et doivent être secondées par des dispositifs de stockage réversibles et par des piles à combustible. Le pilotage de cet ensemble de sources dans le but répondre aux sollicitations, elles-mêmes variables, des calculs sont des éléments indissociables du problème d'alimentation « propre » d'un centre de calcul. Ainsi le problème doit être traité d'une manière globale en intégrant le choix et le dimensionnement des sources d'alimentation dans le processus d'optimisation. Ce travail thèse s'intéressera à la partie engagement des sources d'énergie et ordonnancement sur les ressources de calcul. Les travaux serviront de base à une compréhension du lien entre, d'une part, des politiques d'ordonnancement efficaces et, d'autre part, l'engagement de différentes sources d'énergie. Ainsi l'objectif du travail de thèse est de réaliser le travail de modélisation des systèmes étudiés, de concevoir des algorithmes d'ordonnancement et de décision, de les évaluer en vue de réaliser une boucle de commande gérant les sources d'énergie et optimisant l'attribution des ressources de calcul
Contribution aux décisions post-pronostique : nouveau framework basé sur les interactions pronostic-décision by Omar Bougacha( )

2 editions published in 2020 in English and held by 2 WorldCat member libraries worldwide

With the emergence of prognostics and health management (PHM) methodology, companies are trying to fully exploit the data sources they have to build models for their assets and predict their future behavior. Therefore, the decision-making process is no longer based on only historical and actual data, but it integrates future information. On one hand, decisions in the PHM context are based on future information. On the other hand, the estimation of future conditions of the systems requires a knowledge on its future loads and usage (i.e. future decisions).Several works have studied the decision-making process in the PHM context. However, none of these works have addressed the prognostic-decision interdependency. Moreover, most of the post-prognostic decision-making works present several omissions: 1) How to emphasize the relationship between the prognostic and decision-making modules? 2) How often should the PHM process be launched? 3) How long ahead should the decision-making module plan? 4) How to better/fully use prognostic information in the decision process? 5) How to clarify the applicability of the PHM framework? 6) How to make the PHM framework robust to the system's conditions changes? These questions are addressed along this thesis. They resulted in modifying the existing PHM framework to enhance the decision-making process. The main contributions of this thesis are:• A summary of the PHM challenges followed by a thorough survey on post-prognostics decision-making and its growing interest as a strategy to exploit prognostic information to maintain and manage life cycle of critical machinery.• Some adaptation to the existing PHM framework are proposed to enhance the decision-making process. Three loops are proposed to improve the prognostic accuracy by eliminating uncertainty sources that are caused by unknown future loads and conditions, improve the performance of the decision-making process by dynamically incorporating prognostic information, and improve the reactivity of the overall PHM framework to new operating conditions.• The instantiation and implementation of the proposed post-prognostic decision framework on two different case studies. A first application studies the joint problem of maintenance and production scheduling on a single multi-purpose machine. A second application addresses the joint problem of maintenance planning and mission assignment for a fleet of rolling stock units.• The utility of applying the proposed framework, the duration of the decision horizon, and the frequency of execution are discussed
Optimisation de l'énergie et de la performance d'applications sur des micro-serveurs hétérogènes by Massinissa Ait Aba( )

1 edition published in 2020 in English and held by 1 WorldCat member library worldwide

Recent applications, both in industry and research often need massive calculations. They have different hardware requirements in terms of computing speed, which leads to very high energy consumption of hardware platforms. Heterogeneous computing platforms offer a good compromise with high computing power while preserving the energy consumed to run high-performance parallel applications. They are therefore nowadays an interesting computing resource. In order to exploit the advantages offered by heterogeneity in terms of performance, efficient and automatic management of computing resources is becoming increasingly important to execute parallel applications. These new architectures have thus given rise to new scheduling problems that allocate and sequence calculations on the different resources by optimizing one or more criteria. The objective of this thesis is to determine an efficient scheduling of a parallel application on a heterogeneous resource system in order to minimize the total execution time (makespan) of the application while respecting an energy constraint. Two classes of heterogeneous platforms have been considered in our work: fully heterogeneous architectures that combine several processing elements (CPUs, GPUs, FPGAs), and hybrid platforms limited to two types of processors (CPU + GPU for example). We propose several application scheduling strategies on both platforms with two execution models. Preliminary experiments with the proposed algorithms using different applications and platforms of different sizes have shown good results compared to existing methods in the literature
Ordonnancement des activités de manutention dans les terminaux portuaires by Ali Skaf( )

1 edition published in 2020 in French and held by 1 WorldCat member library worldwide

Scheduling problems of handling activities at maritime terminals have attracted much attention in research on operations management. Generally, containers are moved from one port to another by container vessels, unloaded at the quay by quay cranes and transported by yard trucks to a storage location. To obtain optimal operational performance, coordination between all of the port's equipment is a major issue.In this thesis, we study the scheduling problem of loading/unloading operations and placing containers in storage locations by various handling resources, with the practical application of the port of Tripoli-Lebanon.This study revolves around three scenarios. The first scenario considers several quay cranes and a single container vessel. The container vessel is divided into several bays and each bay contains a specific number of containers. Here we do not consider yard trucks, which means that the containers are directly unloaded from the quay crane to an area to deliver them to customers. In the second scenario, we considered a single quay crane and a single container vessel with several yard trucks. After the containers are unloaded by the quay crane from the container vessel , they must be transported to the storage location by a yard truck. Finally, in the storage location, the reach-stacker cranes allow the containers to be unloaded from the yard truck to a specific area for delivery to customers. The third scenario takes into account several quay cranes, several yard trucks and two container vessels in order to unload the containers from the vessel to the storage location and vice versa. In this scenario, we have two types of container ships, the first to be unloaded to the storage location, while the second is to be loaded from the storage location.To solve these different variants, we applied a modeling approach, development of resolution algorithms, tests, analysis and comparison of our results on instances of the literature and from real cases. Several exact and approximate resolution methods were thus explored: mixed-integer linear programming, which allowed us to formalize and model the problem even before its resolution, dynamic programming, as well as metaheuristics. The advantages and disadvantages of these methods are highlighted. A conclusion on the variants studied and algorithms developed is provided at the end of the manuscript, and various perspectives for this work are open, with the backdrop of the objective of further improving the operational management of handling in ports such than the port of Tripoli-Lebanon
Modélisation et algorithmes pour le dimensionnement et l'ordonnancement cyclique d'atelier de traitement de surface by Emna Laajili( )

1 edition published in 2021 in French and held by 1 WorldCat member library worldwide

Dans un environnement industriel compétitif, les entreprises sont en concurrence pour produire des biens de qualité, avec des coûts moindres et des délais raccourcis. Dans ce contexte, l'ordonnancement des activités permet d'améliorer les processus de production. Parmi la multitude des problèmes étudiés dans la littérature scientifique, l'ordonnancement des ateliers de traitement de surface cherche à planifier les déplacements des robots pour maximiser la productivité. Dans les lignes de galvanoplastie, les pièces doivent tremper dans plusieurs cuves contenant des solutions chimiques en suivant une gamme spécifique de production. Les robots programmables qui circulent en général au-dessus de la ligne, assurent la manutention et le transfert des pièces entre les cuves. Ils constituent souvent les ressources critiques de la ligne, quand le nombre de cuves et/ou des produits à manipuler devient grand. Le traitement des pièces, à la différence d'autres ateliers de production, se réalise à durées variables qui doivent se situer dans des fenêtres temporelles définies. Nous considérons des ateliers de production de masse où un nombre important de pièces doit être traité. Les robots répètent alors indéfiniment une même séquence de mouvements, formant un cycle, pour assurer la manutention des pièces tout au long de la ligne. Le problème qui recherche la séquence cyclique minimisant la période du cycle est connu sous le nom de problème d'ordonnancement cyclique des ateliers de traitement de surface (Cyclic Hoist Scheduling Problem ou CHSP).Dans cette thèse, nous étudions les problèmes conjoints de dimensionnement et d'ordonnancement des ateliers de traitement de surface à plusieurs robots. Il s'agit d'une variante du CHSP, appelée Cyclic Hoist Design and Scheduling Problem (CHDSP). Notre objectif est d'optimiser le couple temps de cycle/nombre de robots. Sur ce problème bi-objectif, nous souhaitons apporter une contribution qui conduirait à terme à l'élaboration d'un système d'aide à la décision. Pour résoudre le CHDSP, nous développons des méthodes approchées adaptées, pour lesquelles nous proposons tout d'abord une nouvelle approche de codage des solutions basée sur les mouvements à vide des robots. Un algorithme génétique hybridé avec un programme linéaire en nombres entiers mixte (MILP), est élaboré, qui nous permet de valider ce nouveau codage et d'obtenir de premiers résultats intéressants. Nous développons également une deuxième métaheuristique hybride basée sur la recherche à voisinage variable et faisant appel au même MILP, pour optimiser la recherche des meilleures solutions dans un espace de recherche très vaste. Nous avons conduit une série de tests pour déterminer les meilleurs paramétrages de l'algorithme. Ce dernier a été testé sur plusieurs instances de la littérature sur lesquelles il montre sa performance et sa robustesse. Enfin, nous étendons la modélisation du problème CHDSP pour prendre en compte les contraintes d'évitement des collisions entre les robots qui partagent la même voie de circulation. Les tests réalisés sur les benchmarks de la littérature montrent l'efficacité de ce modèle complet
Documentation héraldique sur les Baillis de Vaud : 1263-1536 by Jean-Marc Nicod( Book )

1 edition published in 2015 in French and held by 1 WorldCat member library worldwide

Behavior study of an evolutionary design for permutation problems by Hind Mohammed Ali( )

1 edition published in 2018 in English and held by 1 WorldCat member library worldwide

Cette thèse étudie une combinaison évolutionnaire représentation_croisement pour des problèmes de permutation. Ceux-ci sont très étudiés dans la littérature en raison de leur complexité et de la diversité de leurs applications. Des méthodes efficaces existent pour résoudre les problèmes de permutation. Mais les états de l'art récents montrent que les applications réelles font émerger de nouvelles instances qui sont fortement dynamiques et conjuguent de nombreux objectifs et contraintes, notamment de synchronisation. Cette contribution se concentre sur les approches évolutionnaires. Elle explore en détail le comportement d'une combinaison représentation_croisement donnée. Le but est de vérifier si cette conception évolutive pourrait constituer un moyen complémentaire intéressant de s'attaquer efficacement à certaines contraintes. Ce travail étudie le lien entre la représentation utilisée, les opérateurs de recombinaison choisis et les caractéristiquesdu problème à résoudre, en se focalisant sur une représentation par code de Lehmer et le croisement à k-points. Ceci permet de déduire certaines hypothèses (certaines d'entre elles étant contradictoires) concernant le comportement de lacombinaison de croisements k-points appliqués à la représentation Lehmer. Une phase d'expérience est utilisée pour vérifier ces hypothèses. Elle est réalisée par comparaison avec un codage direct de permutation classique, couplé à un croisement PMX. Des mesures sont utilisées pour observer le comportement des mécanismes évolutifs, à la fois dans l'espace de recherche (en termes de génotype) et dans l'espace objectif (en termes de phénotype et de critère de qualité associé). Les remarques de conclusion, les implications et les directions de recherche futures concluent le travail
From prognostics and health systems management to predictive maintenance. by Brigitte Chebel-Morello( )

1 edition published in 2017 in English and held by 1 WorldCat member library worldwide

 
moreShow More Titles
fewerShow Fewer Titles
Audience Level
0
Audience Level
1
  General Special  
Audience level: 0.00 (from 0.00 for From Progn ... to 0.00 for From Progn ...)

From Prognosis and Health Systems Management to Predictive Maintenance 2: Knowledge, Reliability and Decision From prognostics and health systems management to predictive maintenancen2 From prognostics and health systems management to predictive maintenance.
Covers
From prognostics and health systems management to predictive maintenanceFrom prognostics and health systems management to predictive maintenancen2From prognostics and health systems management to predictive maintenance.
Languages
English (30)

French (14)