Tesis sobre el tema "Décision en maintenance"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores tesis para su investigación sobre el tema "Décision en maintenance".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
Cherkaoui, Hajar. "Vers une prise de décision robuste en maintenance conditionnelle". Thesis, Troyes, 2017. http://www.theses.fr/2017TROY0040.
Texto completoThis thesis is a contribution to robust decision making in maintenance of systems subject to gradual degradation. Our first contribution is to develop a criterion allowing the joint evaluation of the mean economic performance and the robustness of different types of maintenance strategies. The advantage of the proposed criterion is that it adapts to different types of maintenance strategies and provides access to a simple and relevant evaluation model. The second contribution is devoted to the development and the evaluation of a joint maintenance and spares parts management strategy that applies to multi-component systems with different qualities. For the proposed joint strategy, prognostic indicator is used for both maintenance and procurement decision-making. The evaluation criterion proposed above is used for the evaluation of this policy as well. The third contribution corresponds to the proposal of two conditional maintenance strategies with hybrid inspections for the maintenance of multi-component systems with different and unknown qualities. For the strategies proposed, online monitoring information is used to disclose the quality of system components to be maintained using statistical techniques of classification and estimation
Thomas, Edouard. "Contribution à la prise de décision dynamique en maintenance prévisionnelle par formalisation d'un principe d'opportunité". Phd thesis, Université Henri Poincaré - Nancy I, 2009. http://tel.archives-ouvertes.fr/tel-00420000.
Texto completoCes nouvelles formes de maintenance posent de nombreux défis scientifiques et industriels, dont certains sont étudiés dans les présents travaux : Quel est le " meilleur " instant pour réaliser une intervention de maintenance préventive donnée ? Comment regrouper deux actions de maintenance préventive ? Qu'est-ce qu'une opportunité pour la maintenance ?
Les réponses à ces questions mobilisent des outils mathématiques variés, allant de l'algorithme de Bruss en analyse stochastique aux relations d'équivalence en algèbre.
Enfin, une application industrielle sur la plateforme TELMA est présentée.
Seguy, Anne. "DÉCISION COLLABORATIVE DANS LES SYSTÈMES DISTRIBUÉS - APPLICATION A LA E-MAINTENANCE". Phd thesis, Institut National Polytechnique de Toulouse - INPT, 2008. http://tel.archives-ouvertes.fr/tel-00372996.
Texto completoAdzakpa, Pelope. "MAINTENANCE DES SYSTÈMES DISTRIBUÉS : MÉTHODES D'AIDE À LA DÉCISION TEMPS-RÉEL". Phd thesis, Université de Technologie de Troyes, 2004. http://tel.archives-ouvertes.fr/tel-00371543.
Texto completoAdzakpa, Kossi Pélopé. "Maintenance des systèmes distribués : méthodes d'aide à la décision temps-réel". Troyes, 2004. http://www.theses.fr/2004TROY0007.
Texto completoIn this thesis, we study methods for real-time decision making in the maintenance process of large distributed systems with important set-up times between the different sites in the system and shared maintenance resources. The methods are based on scheduling approaches in which we proved local optimality rules. These rules are adapted in algorithms for real-time decision making in the maintenance process of large size distributed systems. The aim is to ensure a required availability of systems and to minimize the costs of exploitation, while guaranteeing great reactivity in decision-making. The costs are namely due to critical states of systems (great degradation of fortuitous breakdowns), to over-frequent maintenance, and to tardiness of maintenance. The decisions take account of the availability functions, which often reveal the systems degradation states. The results enable not only to minimize costs, but also to dimension the maintenance resources according to the size and according to their operation characteristics
Séguy, Anne. "Décision collaborative dans les systèmes distribués : application à la e-maintenance". Toulouse, INPT, 2008. http://ethesis.inp-toulouse.fr/archive/00000813/.
Texto completoThe Information and Communication Technologies (ICTs) involve many changes in the companies functioning, with the concepts of e-service, collaborative work, distributed organizations and knowledge sharing. We consider this integration of ICTs to the maintenance function, main activity of companies' performance and is widely penetrated by theses technologies with, for example, the e-maintenance concept. Our objectives are to analyze the collaborative decision making process and the influence of ICTs on them and to propose ways to assess the performance of a maintenance service supported by ICTs. The modelling of the problem is multidomain, multiview and multiactor and the performance is multicriteria. First, we propose a situations modelling of e-maintenance based on the process representation and on the formalism object to highlight key components of e-maintenance and influence of ICTs. Then, we investigate the activities of collaborative decision by analyzing and grouping decision making centers which support the decisions and we characterize the intangible resources committed. Finally, we propose a framework for evaluate the performance of e-maintenance and representation models to simulate configurations of distribution of these resources and allow to make organizational choices related
Castanier, Bruno. "Contribution à l'optimisation de la décision sous incertitudes : application à la maintenance". Habilitation à diriger des recherches, Université de Nantes, 2012. http://tel.archives-ouvertes.fr/tel-00862426.
Texto completoDanioko, Fadaba. "Aide à la décision pour la politique de maintenance des systèmes multi-états". Paris 8, 2014. http://octaviana.fr/document/185083145#?c=0&m=0&s=0&cv=0.
Texto completoNowadays, the complexity of industrial systems and the variability of production policy impose on maintenance departments a more and more difficult task. In addition, production systems are sometimes subjected to strong requests (for example: productivity gain, limitation of the human resources). All the evoked requests are going to impose on the systems of production to operate under constraints: less downtime, less damages, etc. , where from the multi-state functioning way. Then it becomes major in the process of degradation called "multi-state" system, to study the problem of improvement of maintenance policy to maintain their continuity of service. Many recent works show the interest of the study of these multi-state systems, their complexity of study, modeling or optimization. Indeed, our work aims among others at the follow-up of the production system during its exploitation phase, to understand the evolution of its behavior in time, to improve its performance. This work is based on the identification of the choice of an optimal maintenance policy among several possible configurations of maintenance actions of the multi-state systems through the simulation. In our proposed approach, the study of the model of the degradation process named "multi-states model ", is led under various angles (scenarios) with or without learning about the decision node maintenance policy. An identification of the maintenance policy selection is conducted by the simulation according to the various configurations rate transitions between states occupied by the system over time. Finally an aggregation of several bayesian sub-models of multi-state systems is proposed according to their structural architectures to close to real case of production study
Huynh, Khac Tuan. "Quantification de l'apport de l'information de surveillance dans la prise de décision en maintenance". Phd thesis, Université de Technologie de Troyes, 2011. http://tel.archives-ouvertes.fr/tel-00788661.
Texto completoHuynh, Khac Tuan. "Qualification de l'apport de l'information de surveillance dans la prise de décision en maintenance". Troyes, 2011. http://www.theses.fr/2011TROY0013.
Texto completoCondition and health monitoring can bring out useful information for the maintenance decision-making but few models allow their integration in the decision process. This thesis aims to construct new probabilistic quantitative models to evaluate the value of this kins of information depending on ith quality and on the nature of the observed variables. The proposed stochastic failure and measurement models take account the degradation/failure sensor data, the impact of operational environment on the degradation, as well as the nature of control techniques. Based on these models, we propose different maintenance policies and we develop the associated cost model to study the best methods for the exploitation of monitoring information. The studies in this thesis show the advantage of developing quantitative maintenance decision framework which allows integrating and evaluating the impact of condition monitoring information on the performance of maintenance operations
Codet, de Boisse Aurélien. "Aide à la décision exploitant de la connaissance générale etcontextuelle : application à la maintenance d’hélicoptère". Thesis, Toulouse, INPT, 2013. http://www.theses.fr/2013INPT0011/document.
Texto completoThe works presented in this thesis aims to contribute to the development of a tool for design decision support exploiting general knowledge and contextual knowledge. The use of general knowledge is performed using a constraint filtering engine the exploitation of contextual knowledge is based on principles derived from case-based reasoning and data mining. The main result relies on a constraint notion called "contextual constraint". The principal idea consists to parameterize a constraint with respect to a context where it must be filtered. Depending on the level of confidence characterizing contextual knowledge, this constraint may either be propagated independently by a filtering engine or being used to provide help to the user. We propose in order to identify the context of the constraint to use the principle of similarity search widely used in case-based reasoning. To complete or refine the information resulting from this constraint contextual filtering, we use counting algorithms developed for data-mining to quantify the occurrence characterizing a kind of confidence in the result. Our work is based on a FUI project relating to helicopter maintenance. The aim of this tool is to better estimate the charge, the cycle, the operational costs of maintenance of an helicopter. The originality of this work is to consider both the manufacturers knowledge (general knowledge) to determine an initial estimate and then to correct it according to the conditions of effective use of the helicopter (contextual knowledge)
Diez, Laëtitia. "Apport de la maintenance prévisionnelle au paradigme de régénération industrielle". Electronic Thesis or Diss., Université de Lorraine, 2017. http://www.theses.fr/2017LORR0348.
Texto completoThis thesis is dedicated to the regeneration paradigm from the principles of sustainable development and circular economy. The intention is to limit the exhaustion of natural resources and to reduce waste production through exploiting “waste” deposits of technosphere. The notion of regeneration emerges from an analogy between the natural and technical sphere. It brings to light the concepts of “nutrients” and “decomposers”. The nutrient concept enables to revisit the end of life of domestic or industrial equipment. These equipment are seen as technical nutrients that can feed industrial sectors. The regenerators, called decomposers in nature, are intermediates processors to process “waste” in technical nutrients. Four regenerators have been identified. For each regenerator, product requirements are identified to ensure the regeneration of “waste” product. Additional requirements have been defined in the regeneration process to specify regeneration actions. These two types of requirements must be maintained throughout the product lifecycle. Maintenance process has been identified as fundamental industrial process to monitor and maintain over time the regeneration capability of a product. When regenerators implement a regeneration strategy, it is necessary to assess its feasibility. That is why we proposed a decision- making tool by modeling the product’s behavior during its lifecycle and the regenerator’s behavior, and the effect of the requirements on the product and process. The selected models are System Dynamics. These models allow the modeling and simulation of interactions between the variables of a complex system. The decision-making tool allow test the proposals of this thesis through a regeneration example of an electronic waste
Hoang, Anh. "Pronostic de la performance d’Efficacité Energétique pour la prise de décision en maintenance dans les systèmes industriels". Thesis, Université de Lorraine, 2017. http://www.theses.fr/2017LORR0086/document.
Texto completoAmong sustainability consideration, energy is today the key for economic growth in industrial systems. Energy resources are however limited and becomes more and more expensive. The energy optimization of manufacturing systems must therefore be considered as a major challenge to be compliant with environmental impact and management of energy resources. This should be reflected primarily by using energy efficiency (EE) as main key lever to deploy sustainability to plants, i.e. reduce the amount of energy required to provide products and services. With regards to this EE context, the aim of this thesis is to investigate the problem of considering energy efficiency and its prediction as a new indicator in maintenance decision-making. In that way, we develop first a concept of energy efficiency, called EEI (energy efficiency indicator), applicable to the different levels of abstraction of an industrial system. Then, we propose a generic formulation to evaluate the EEI (and its evolution) taking into account static and dynamic factors of influence. The temporal evolution of this indicator with respect to the degradation of the system is addressed in a predictive maintenance objective. It leads to found an energy efficiency performance concept called REEL (remaining energy-efficient lifetime), representing the residual energy lifetime. To predict the potential evolution of the IEE to calculate REEL, a generic approach based on existing predictive approaches is also developed. Next, we investigate the use of EE in CBM maintenance decision-making. Finally, all these contributions are validated on the TELMA platform
Le, Son Khanh. "Modélisation probabiliste du pronostic : application à un cas d'étude et à la prise de décision en maintenance". Troyes, 2012. http://www.theses.fr/2012TROY0035.
Texto completoRemaining useful life (RUL) estimation is a major scientific challenge and a principal topic in the scientific community which takes an interest to prognosis problems. The use of tools and methods collected under the terms of prognostic is widely developed in many domains as aerospace industry, electronics, medicine, etc. The common underlying problem is the implementation of models which can take into account on-line the data histories of system and its environment, the diagnosis on its current state and possibly the future operational conditions for predicting the residual lifetime. In this context, the principal problem of our works is the use of probabilistic approaches (type of non-stationary stochastic process) to construct the innovatory prognostic models from a degradation indicator of system and to use the residual lifetime prediction for maintenance implementation. The advantage of these models is to have the regularity proprieties which make easy the probability calculation and RUL estimation. In order to test the performances of our models, a comparative study is carried out on the data provided by the 2008 IEEE Prognostic and Health Management (PHM)
Hoang, Anh. "Pronostic de la performance d’Efficacité Energétique pour la prise de décision en maintenance dans les systèmes industriels". Electronic Thesis or Diss., Université de Lorraine, 2017. http://www.theses.fr/2017LORR0086.
Texto completoAmong sustainability consideration, energy is today the key for economic growth in industrial systems. Energy resources are however limited and becomes more and more expensive. The energy optimization of manufacturing systems must therefore be considered as a major challenge to be compliant with environmental impact and management of energy resources. This should be reflected primarily by using energy efficiency (EE) as main key lever to deploy sustainability to plants, i.e. reduce the amount of energy required to provide products and services. With regards to this EE context, the aim of this thesis is to investigate the problem of considering energy efficiency and its prediction as a new indicator in maintenance decision-making. In that way, we develop first a concept of energy efficiency, called EEI (energy efficiency indicator), applicable to the different levels of abstraction of an industrial system. Then, we propose a generic formulation to evaluate the EEI (and its evolution) taking into account static and dynamic factors of influence. The temporal evolution of this indicator with respect to the degradation of the system is addressed in a predictive maintenance objective. It leads to found an energy efficiency performance concept called REEL (remaining energy-efficient lifetime), representing the residual energy lifetime. To predict the potential evolution of the IEE to calculate REEL, a generic approach based on existing predictive approaches is also developed. Next, we investigate the use of EE in CBM maintenance decision-making. Finally, all these contributions are validated on the TELMA platform
Kaffel, Hédi. "La maintenance distribuée : concept, évaluation et mise en oeuvre". Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2001. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp05/NQ66689.pdf.
Texto completoAflak, Amer. "Elaboration d'un cadre méthodologique pour l'aide à la décision en matière de gestion de la maintenance du réseau technique urbain d'assainissement". Lyon, INSA, 1994. http://www.theses.fr/1994ISAL0086.
Texto completoThe actual situation of the management of urban sewerage systems is distinguished by the conditions more and more exacting in various domains, such as: respect of the natural environment, prevention against the risks in urban milieu, amelioration of the performance of the system's state, arrangement of this state with the urbanization, control of the financial charges and valorization of the working quality. For solving such situation and for optimizing the action, the responsible of the networks maintenance requires a global methodology to bring, in the context of a determined epoch, an aid to decision processes. Our thesis propose a methodology for the diagnosis of drainage performances and the choice of maintenance actions of the managed network situation
Serquin, Yann. "Gestion scientifique de la maintenance des grands systèmes : l'apport de l'aide à la décision par utilité multiattribut généralisée". Cachan, Ecole normale supérieure, 1998. http://www.theses.fr/1998DENS0025.
Texto completoThesis studies formal methodologies that will be helpful in the maintenance decision- making process and preconises to use an extension of multi-attribut utility theory to non-expected utility theories. Thesis does not only discuss attribute independence axioms and their decompositional effects on non-expected utility theories, but focuses rather on practical procedures and methods to elicit the multi-attributed utility function that remain valid in non-expected utility framework. In chapter 1, basic maintenance concepts are explained. Chapter 2 deals with maintenance optimisation models issu of operation research area. Chapters 3 and 4 preconise to use multi-attributed generalized expected utility framework in nuclear power plants maintenance. Chapter 5 presents a multi-attributed utility assessment program under risk based on generalized expected utility models. Chapter 6 consists in a case study
Ausloos, Alexandre. "Surveillance et diagnostic pour la conduite de la maintenance prévisionnelle". Troyes, 2010. http://www.theses.fr/2010TROY0022.
Texto completoThis thesis deals with the detection and localisation of degradation allowing predictive or corrective maintenance actions. The work was done within an application to a civil turbofan start, which is very important for airline companies. A detailed failure mode analysis of the starting phase, based on expert opinion and experience feedback, enabled the definition of indicators that characterize the components health involved in the engine start. In addition, the indicator values depend on the start operating conditions which could mask the degradation effects. The proposed approach consists to calculate for each indicator the difference between its measured value and its estimated value using the measured operating conditions and assuming a healthy situation. The estimation is done using models based on regression and the parameters are determined using a data base. The learning data base has been built using available engine start bench tests. Then indicators model parameters in the case of a healthy behavior were learned considering polynomial regression and support vector regression. However the estimation validity is guaranteed only when the operating conditions are within the domain covered by the learning data base. Thus the proposed system architecture includes a preliminary control on the operating conditions using one-class SVM. The thesis concludes with a study of the com-promise between the control severity and the estimation error
Cotaina, Perez Norberto. "Méthodologie d'aide à la décision et à la mise en place de politiques de maintenance pour les PME. L'apport de la MBF, Maintenance basée sur la fiabilité". Nancy 1, 1999. http://www.theses.fr/1999NAN10176.
Texto completoDiez, Laëtitia. "Apport de la maintenance prévisionnelle au paradigme de régénération industrielle". Thesis, Université de Lorraine, 2017. http://www.theses.fr/2017LORR0348/document.
Texto completoThis thesis is dedicated to the regeneration paradigm from the principles of sustainable development and circular economy. The intention is to limit the exhaustion of natural resources and to reduce waste production through exploiting “waste” deposits of technosphere. The notion of regeneration emerges from an analogy between the natural and technical sphere. It brings to light the concepts of “nutrients” and “decomposers”. The nutrient concept enables to revisit the end of life of domestic or industrial equipment. These equipment are seen as technical nutrients that can feed industrial sectors. The regenerators, called decomposers in nature, are intermediates processors to process “waste” in technical nutrients. Four regenerators have been identified. For each regenerator, product requirements are identified to ensure the regeneration of “waste” product. Additional requirements have been defined in the regeneration process to specify regeneration actions. These two types of requirements must be maintained throughout the product lifecycle. Maintenance process has been identified as fundamental industrial process to monitor and maintain over time the regeneration capability of a product. When regenerators implement a regeneration strategy, it is necessary to assess its feasibility. That is why we proposed a decision- making tool by modeling the product’s behavior during its lifecycle and the regenerator’s behavior, and the effect of the requirements on the product and process. The selected models are System Dynamics. These models allow the modeling and simulation of interactions between the variables of a complex system. The decision-making tool allow test the proposals of this thesis through a regeneration example of an electronic waste
Ruin, Thomas. "Contribution à la quantification des programmes de maintenance complexes". Electronic Thesis or Diss., Université de Lorraine, 2013. http://www.theses.fr/2013LORR0202.
Texto completoTo face with new legislatives and environmental contexts in which they have to operate, it is needed now that the industrials systems have to satisfy to many different requirements and constraints. Thus, these requirements are not only conventional ones such as availability and costs, but also emergent ones such as safety and sustainability. This report implies for the specific French company EDF (energy power supplier) to evolve from its usual approach of reliability centered maintenance (RCM) to a new approach. It is consisting mainly in developing a tool able to support the Complex Maintenance Programs Quantification (CMPQ). This Ph.D. is dealing with this the engineering and deployment of this tool in the frame of the GIS 3SGS - DEPRADEM 2 project. The first step of the work is to generalize EDF needs, then to propose a framework enabling to identify required generic knowledge needed to assess the Key Performances Indicators (KPIs) for supporting quantification. The next step is to model the generic knowledge in two complementary ways: a formalization of the static, interactional and behavioral knowledge based on different SysML diagrams; and a formalization of the dynamic and executable knowledge formalized by AltaRicaDF (ADF) language, allowing to perform stochastic simulation and to assess required KPIs. The path to elaborate dynamic executable vision from SysML diagrams is released by means of rules between each element of interest of both languages. All this approach/tool is applied to a specific EDF case study: the ARE system
Ruin, Thomas. "Contribution à la quantification des programmes de maintenance complexes". Phd thesis, Université de Lorraine, 2013. http://tel.archives-ouvertes.fr/tel-00944825.
Texto completoApedome, Kouami Seli. "Proposition d’une démarche d’intégration des aspects cognitifs au retour d’expérience statistique : application à la maintenance industrielle". Paris 8, 2012. http://octaviana.fr/document/167322427#?c=0&m=0&s=0&cv=0.
Texto completoPerformance of an industrial enterprise resides in part in his staff's capacity to create value through his experience. Thousands of hours are lost in the industrial enterprises, to repeat tasks already achieved by others, to redefine the same inefficient actions in the past, and millions euros are spent to repair some mistakes. Some how- know disappears with the departure of the oldest, that doesn't have forcing transferred their knowledge. Sometimes, some enterprises have data base, those are confronted here always to problems at the time of the decision makings due to incomplete and imprecise information. Fact that information contained in data bases are not contextual and are not followed by a good practice formulation, cheek greatly on quality of their exploitation. It represents to our sense, a part of procedure of treatment of experiences that is not always simple to formalize and for which several more or less adapted are foreseeable. In our, work we propose a gait of formalism and exploitation of experiences from Bayesian network. Bayesian network is a graphic, mathematical and statistical model that helps to manage uncertainty. It permits to represent a domain of knowledge, to manage a set of incomplete data, intuitively and can represent a real tool of help to decision
Paterna, Hidalgo Angel. "Gestion patrimoniale des infrastructures de la ratp : développement d'un processus d'aide à la décision pour optimiser la stratégie de maintenance". Thesis, Paris Est, 2015. http://www.theses.fr/2015PESC1200/document.
Texto completoThe RATP is the operator and asset manager of the public railway transport of Paris and the next suburbs. Nowadays, with more than 10 million trips per day, this transport network is one of the most crowded in the world. In this context of high service requirements, the RATP asset managers must assure the structural integrity, the quality of service and the sustainability of an aging and heterogeneous asset. However, available budgets are, by nature, limited and, in this context, two tasks become essential: to justify budget requirements and to optimize the programming of maintenance actions. The current asset strategy is based on visual inspections to detect degradation symptoms that concern the structural integrity of the structure. Depending on these results, managers must select and prioritize the maintenance actions taking into account the constraints involved in asset management. This decision-making process is based on the expert knowledge and is not formalized. In this context, the purpose of this thesis is to develop a multicritera decision support tool which reduces the inherent variability degree of visual inspections and the lack of transparency in the decision-making process. In order to provide RATP's managers a decision support tool, this research is based on the next stages :- The development of a functional model of degradation mechanisms by the application of the operational safety methods. The Functional Analyse (FA), the Failure Mode and Effect Analysis (FMEA) and the casual graphs are applied to know how infrastructures function, degrade and interact with the environment.- The construction of a decision support tool based on multicriteria methods. The first stage is the construction of a lot of criteria formalizing the technical, economic and social aspects involved in the RATP's asset management (rule based assignment model). The second stage is the application of ELECTRE methods to develop a multicriteria decision support tool which optimizes the management of the RATP's asset. This tool is tested on the line 4 of the Paris metro in order to study development prospects. The main prospect is the operational development of this tool in the context of the management of the RATP's asset
Wang, Zhouhang. "Modèles de processus de collecte de données et d'évaluation de performance de disponibilité pour l'aide à la décision en maintenance". Thesis, Université de Lorraine, 2013. http://www.theses.fr/2013LORR0287/document.
Texto completoThis thesis proposes a modeling approach of an adaptive and iterative data collection process, and a validation tool via operational effectiveness features for equipment. An approach, named "Tropos", established based on the information theory, is developed to modeling and evaluating data collection processes. This is an original approach, which allows synthesizing three features that characterize the effectiveness of a data collection process: 1) data usefulness, 2) process complexity, 3) gain of information by a basic process activity. An original model, based on colored stochastic Petri nets coupled to the Monte Carlo simulation, has also been developed to validate the effectiveness of the data collection process. This model uses as input, stochastic process models of degradation, of failure and of maintenance of equipment components. The input parameters of the models are assumed to be known and obtained from the collected data. The properties of colored stochastic Petri net model are also used to derive the minimum cuts required to assess the equipment condition and operational effectiveness. These properties also allow to treating systems of k/n structures. The effectiveness of the proposed approach is finally illustrated on a multi-source renewable energy production system, by implementing the algorithms of the model under the Silab software environment
Wang, Zhouhang. "Modèles de processus de collecte de données et d'évaluation de performance de disponibilité pour l'aide à la décision en maintenance". Electronic Thesis or Diss., Université de Lorraine, 2013. http://www.theses.fr/2013LORR0287.
Texto completoThis thesis proposes a modeling approach of an adaptive and iterative data collection process, and a validation tool via operational effectiveness features for equipment. An approach, named "Tropos", established based on the information theory, is developed to modeling and evaluating data collection processes. This is an original approach, which allows synthesizing three features that characterize the effectiveness of a data collection process: 1) data usefulness, 2) process complexity, 3) gain of information by a basic process activity. An original model, based on colored stochastic Petri nets coupled to the Monte Carlo simulation, has also been developed to validate the effectiveness of the data collection process. This model uses as input, stochastic process models of degradation, of failure and of maintenance of equipment components. The input parameters of the models are assumed to be known and obtained from the collected data. The properties of colored stochastic Petri net model are also used to derive the minimum cuts required to assess the equipment condition and operational effectiveness. These properties also allow to treating systems of k/n structures. The effectiveness of the proposed approach is finally illustrated on a multi-source renewable energy production system, by implementing the algorithms of the model under the Silab software environment
Séfiane, Hakim. "Aide au choix d'une méthode de diagnostic pour l'amélioration des performances en maintenance des systèmes de production". Valenciennes, 2008. https://ged.uphf.fr/nuxeo/site/esupversions/d3a8c77b-8f94-4ce3-abbf-ed2c5aa11d63.
Texto completoThe maintenance devotion to prevent and solve production systems malfunctions represents a major factor in enterprises performance. Baring in mind diagnostic important role in maintenance, the selection of the most suitable diagnostic systems influences maintenance the system performance. Given the numerous available diagnostic methods (the choice of the most relevant diagnostic method with respect to the problem), the choice of the best method is a tedious procedure. This research tries to solve this complex problem. The proposed methodology ensures that the chosen diagnostic method is taken in a consistent, clear and rational way to help decision maker to justify their choices
Sanchez, Céline. "Spécification et Implémentation du Système d’Aide à la Décision Multicritère pour la Maintenance Préventive et la Gestion du Patrimoine de la Société d’Autoroute ESCOTA : le projet SINERGIE". Paris, ENMP, 2007. https://pastel.archives-ouvertes.fr/tel-00202653.
Texto completoDue to the ageing of the infrastructure, the toll motorway company ESCOTA aims at the formalization and improvement of the decisional process for preventive maintenance and assets management in a multi actors and multi criteria (MC) environment. The information processing used by ESCOTA can be formalized in three steps: measure, evaluation and decision. Periodic inspections are performed to detect any malfunction symptoms. The expert in charge of a domain (carriageways, bridges …) evaluates the situation seriousness and associates an emergency degree to the corresponding maintenance operation. The official in charge of the operating network attribute a priority degree according to strategic criteria. To each step of this process a specific set of criteria and an aggregation operator (Weighted Average Mean WAM) correspond. Each MC evaluation step is modelled as the aggregation of partial scores attributed to an operation w. R. T. A set of n criteria. Scores are expressed over a finite scale as labels. Our work has been to set up a consistent evaluation process that enables 1) experts to express their judgement values in their own discrete semantic universe, 2) to convert the labels in adequate numerical values using the MACBETH method and clustering techniques, 3) to compute the WAM based aggregated value and convert it in return into the experts’ semantic universe 4) to carry out a robustness analysis of the evaluation process to assess the risk of misclassification of the operations and to diagnose them. This method is implemented in an IPS —SINERGIE — that supports decisions concerning maintenance operations planning through adequate information processing procedure
Feng, Haitang. "Data management in forecasting systems : optimization and maintenance". Phd thesis, Université Claude Bernard - Lyon I, 2012. http://tel.archives-ouvertes.fr/tel-00997235.
Texto completoJacob, Christelle. "Management de l'incertitude pour les systèmes booléens complexes - Application à la maintenance préventive des avions". Thesis, Toulouse, ISAE, 2014. http://www.theses.fr/2014ESAE0010/document.
Texto completoStandard approaches to reliability analysis relies on a probabilistic analysis of critical events based on fault tree representations. However in practice, and especially for preventive maintenance tasks, the probabilities ruling the occurrence of these events are seldom precisely known. The aim of this thesis is to study the impact of epistemic uncertainty on probabilities of elementary events such as failures over the probability of some higher level critical event. The fundamental problem addressed by the thesis is thus to compute the probability interval for a Boolean proposition representing a failure condition, given the probability intervals of atomic propositions. When the stochastic independence is assumed, we face a problem of interval analysis, which is NP-hard in general. We have provided an original algorithm that computes the output probability interval exactly, taking into account the monotonicity of the obtained function in terms of some variables so as to reduce the uncertainty. We have also considered the evolution of the probability interval with time, assuming parameters of the reliability function to be imprecisely known. Besides, taking advantage of the fact that a probability interval on a binary space can be modelled by a belief function, we have solved the same problem with a different assumption, namely information source independence. While the problem of computing the belief and plausibility of a Boolean proposition are even harder to compute, we have shown that in practical situations such as usual fault-trees, the additivity condition of probability theory is still valid, which simplifies this calculation. A prototype has been developed to compute the probability interval for a complex Boolean proposition
Ribes, Jean-Christophe. "Définition d'une stratégie de surveillance de l'installation AIRIX dans un but de maintenance prédictive". Reims, 2001. http://www.theses.fr/2001REIMS016.
Texto completoPonchet-Durupt, Amélie. "Modèles stochastiques pour l'évaluation de politiques de maintenance sur des systèmes à dégradation graduelle". Troyes, 2010. http://www.theses.fr/2010TROY0018.
Texto completoMost of systems in the industry are gradually deteriorating systems or devices which undergo a change in their deterioration rate, e. G. , be-cause of environmental or use conditions. This change can impact the degradation of the sys-tem and leads to a sudden increase of the system's deterioration rate. The consideration of such changes leads to a more realistic degradation model and opens perspectives in a maintenance decision making point of view. Several condition-based maintenance policies are then suggested and each of them is adapted to the available, or used, information on the system. The impact of the available information on the average long-run cost rate of the maintained system is studied for each maintenance policy considering perfect maintenance actions. In practical cases, maintenance actions do not lead to the renewal of the system. Hence a second study is performed on a maintenance policy adapted to large structures such as bridges, dikes, or pipelines. Such systems are built in order to be operational for a given finite time span which can be seen, for example, as an insurance deadline. Based on existing imperfect maintenance models, several improvement functions which model the impact of an imperfect maintenance action on the system, are proposed. A systematic maintenance policy is then considered and evaluated on a finite time span
Latrous, Mohamed Othman. "Modèle d’intégration maintenance conditionnelle, prévisionnelle et maitrise statistique des procédés". Electronic Thesis or Diss., Compiègne, 2021. http://www.theses.fr/2021COMP2639.
Texto completoIntegrated solutions are evolving to cope with the digitalization of manufacturing processes. One area of improvement is developing new strategies joining maintenance and quality control. A popular hypothesis used in these integrated models is considering that quality control comes down to monitoring a single process or product characteristic. However, for complex systems, this assumption is seldom satisfied as the number of characteristics grows and they can have potential correlations. In fact, a multivariate control chart is more suitable to guarantee better performances of drift detection. Following this perspective, the main objective of this thesis consists in developing new maintenance decision rules based on produced items’ quality data. Multivariate control charts are used to provide detection and identification of potential process shifts and adaptive maintenance actions are triggered, targeting system components responsible for the deterioration of the produced items’ quality. First, a preliminary study is led to highlight the impact of multivariate control charts on the decision making process. Next, integrated maintenance decision rules for condition based and predictive maintenance are proposed using multimodal control charts. The developed decision rules are applied in the context of a simulated manufacturing process exhibiting a quality defect appearing in different dynamics (fast and slow drifts). The new strategies proposed in this thesis have been validated through the development of analytical models expressing the profit of the manufacturing system. This profit was maximized based on decision variables (sampling period and critical intervention threshold) and the existence of optimal solutions has been demonstrated through simulation. The robustness of the developed models has been proven by sensitivity studies, followed by comparative studies in order to highlight the impact of the proposed strategies
Malandain, Julien. "Modélisation de l'état de sante des réseaux de distribution d'eau pour l'organisation de la maintenance : étude du patrimoine de l'agglomération de Lyon". Lyon, INSA, 1999. http://www.theses.fr/1999ISAL0040.
Texto completoThe objective of this research is to provide elements of method and models making it possible to diagnose the state and to predict the ageing of the water mains to help the managers to satisfy, with short and long-term, their objectives of performance. This study is based on a state of knowledge relating to the pipes degradation phenomena, on the analysis of the data available and usable to describe the symptomatic history, the constitution, the aggressive environment and the sensitive environment of the infrastructure, and on the study and use of tools such as Geographic: Information systems, hydraulic modeling and models of reliability, which make it possible to represent and to evaluate the functioning of the networks. The principal results of this research are : - A new formulation of the technical problematic of infrastructure management, based on the operational constraints and the current stakes of customer service and system profitability ; - The organization of information relating to the network description and of the tools used for the analysis and prediction processes, within the framework of a decision support system ; - The proposal of two new models, adapted to the data available on water supply systems, one contributing to design and simulate long term renewal strategies, the other contributing to the reactive programming of maintenance actions
Li, Heping. "Condition-based maintenance policies for multi-component systems considering stochastic dependences". Thesis, Troyes, 2016. http://www.theses.fr/2016TROY0030/document.
Texto completoNowadays, industrial systems contain numerous components so that they become more and more complex regarding the logical structures as well as the various dependences (economic, stochastic and structural dependences) between components. The dependences between components have an impact on the maintenance optimization as well as the reliability analysis. Condition-based maintenance which enables to manage maintenance activities based on information collected through monitoring has gained a lot of attention over recent years but stochastic dependences are rarely used in the decision making process. Therefore, this thesis is devoted to propose condition-based maintenance policies which take advantage of both economic and stochastic dependences for multi-component systems. In terms of economic dependence, the proposed maintenance policies are designed to be maximally effective in providing opportunities for maintenance grouping. A decision rule is established to permit the maintenance grouping with different inspection periods. Stochastic dependence due to a common degradation part is modelled by Lévy and Nested Lévy copulas. Condition-based maintenance policies with non-periodic inspection scheme are proposed to make use of stochastic dependence. Our studies show the necessity of taking account of both economic and stochastic dependences in the maintenance decisions. Numerical experiments confirm the advantages of our maintenance policies when compared with other existing policies in the literature
Dubillard, Marine. "Efficience et résilience de la planification des opérations de maintenance d'un réseau de distribution d'eau". Electronic Thesis or Diss., Ecole nationale des Mines d'Albi-Carmaux, 2023. http://www.theses.fr/2023EMAC0019.
Texto completoThe maintenance of critical infrastructure networks such as water distribution networks requires complex planning processes. Preventive maintenance, which consists in monitoring and ensuring the proper functioning of infrastructure and equipment, within known timeframes and on a tactical scale, is mixed with reactive maintenance, which consists in intervening as early as possible in the face of disruptions and unforeseen malfunctions, on an operational scale. The aim of this thesis is to provide a research framework for analyzing the levers for improving planning processes, through efficiency and resilience indicators.Thanks to the business expertise provided by the players involved in the Veolia Eau Sud-Ouest case study, the requirements in terms of planning maintenance operations are defined, modeled, compared with other routing problems in the literature, and formalized in the form of Mixed Integer Linear Program (MILP). The resulting optimization problem is a variant of the Vehicle Routing Problem (VRP), with many additional constraints, and is not yet studied as such in the literature.This formalization enables the development of algorithmic resolution approaches. Three methods are proposed. One aims to reproduce the current planning processes in a local department of Veolia Eau Sud-Ouest. Calibrated and validated with field experts, it will be used as a theoretical basis of comparison for the other two. The second is an adaptation of the Ant Colony System meta-heuristic, widely used in the literature for solving large routing problems. Finally, the last one is a new Cluster-first, Route-second (CFRS) approach which decomposes the initial planning problem into two sub-problems formalized in PLNE. In the first stage, clusters are formed, assigning each maintenance worker a set of tasks to be carried out on each day. In a second step, precise routes are created within each cluster. Several versions of this approach are modeled, depending on the planning horizon considered.The results obtained on the various indicators using different experimental designs show that a substantial gain can be obtained by using the CFRS approach, and particularly for the consideration of due date compliance. They also show that it is possible to use an algorithmic approach which takes into account all the constraints of the industrial problem, can be applied to instances of realistic size, in a deterministic context (definition of forecast schedules) as well as in a dynamic context (re-planning when emergencies occur)
Fabbe-Costes, Nathalie. "Aléa et modélisation de la décision logistique : réalisation d'un système expert de maintenance au coeur de l'efficience du passage portuaire à Marseille-Fos". Aix-Marseille 2, 1989. http://www.theses.fr/1989AIX24002.
Texto completoThe generalisation of the logistic policy in organizing container chains which the very nature a such a transport system enables, entails a complete re-evaluation of port status and demands a new approach of transport production, namely of the handling. As a basic element of port passage and as service production, handling must be satisfactory in terms of container circulation quality -rapidity, reliability, rate. Also, handling must be synchronised with the connected links of the chains. A detailed analysis of quayside production -a crucial operation in port handling shows that there is a need for o more adapted management : exploitation and maintenance should be regarded as the two productive aspects of the activity; on the other hand, quayside production should be integrated so that the global efficiency of actions can be evaluated at the strategic level of "port production". Within this management approach, the development of the maintenance function as an effective logistic support allows a technical and economic control of quayside production. In this aim, the improvement of intervention methods during and off exploitation will guarantee control of hazards and of technical production costs and allow a more scientific management of equipment -of unloading cranes especially. .
Sanchez, Céline. "Spécification et implémentation du système d'aide à la décision multicritère pour la maintenance préventive et la gestion du patrimoine de la société d'autoroute ESCOTA : le projet SINERGIE". Phd thesis, École Nationale Supérieure des Mines de Paris, 2007. http://tel.archives-ouvertes.fr/tel-00202653.
Texto completoNguyen, Van-Thai. "AI-based maintenance planning for multi-component systems considering different kinds of dependencies". Electronic Thesis or Diss., Université de Lorraine, 2023. http://www.theses.fr/2023LORR0070.
Texto completoMaintenance planning for systems consisting of multiple components has still been a challenging problem. Particularly, mathematically describing dependencies between components is usually a complicated task, however, omitting component dependencies in maintenance modeling might result in suboptimal plans. Moreover, the number of maintenance decision variables needed to be optimized increases rapidly in the number of components, causing computational expense for optimization algorithms.To face these issues, this PhD aims to propose an artificial-intelligence-based maintenance optimization approach allowing to consider different kinds of dependencies between components (i.e., economic, stochastic, and structural dependence). Particularly, the maintenance approach integrates a deep maintenance cost model, that allows to compute maintenance costs at system level without requiring individual costs at component level (e.g., setup costs, labor costs and costs of maintaining each component), into the framework of multi-agent deep reinforcement learning, which can be applicable for large sequential decision-making problems, to optimize maintenance decisions. Moreover, a novel degradation interaction model for discrete- state components is also developed and then integrated into the proposed maintenance approach. Numerical studied are conducted on multi-component systems with different configurations under different observability scenarios to investigate the performance and the advantage as well as limits of the proposed maintenance approach
Liu, Yinling. "Conception et vérification du système d'Information pour la maintenance aéronautique". Thesis, Lyon, 2019. http://www.theses.fr/2019LYSEI133.
Texto completoOperational support is one of the most important aspects of aeronautical maintenance. It aims to provide a portfolio of services to implement maintenance with a high level of efficiency, reliability and accessibility. One of the major difficulties in operational support is that there is no platform that integrates all aircraft maintenance processes in order to reduce costs and improve the level of service. It is therefore necessary to build an autonomous aircraft maintenance system in which all maintenance information can be collected, organized, analyzed and managed in a way that facilitates decision-making. To do this, an innovative methodology has been proposed, which concerns modelling, simulation, formal verification and performance analysis of the autonomous system mentioned. Three axes were addressed in this thesis. The first axis concerns the design and simulation of an autonomous system for aeronautical maintenance. We offer an innovative design of an autonomous system that supports automatic decision making for maintenance planning. The second axis is the verification of models on simulation systems. We propose a more comprehensive approach to verifying global behaviours and operational behaviours of systems. The third axis focuses on the analysis of the performance of simulation systems. We propose an approach of combining an agent-based simulation system with the “Fuzzy Rough Nearest Neighbor” approach, in order to implement efficient classification and prediction of aircraft maintenance failures with missing data. Finally, simulation models and systems have been proposed. Simulation experiments illustrate the feasibility of the proposed approach
Bernard, Denys. "Un système de raisonnement temporel basé sur le calcul d'évènements pour l'ordonnancement en maintenance aéronautique". Toulouse 3, 1992. http://www.theses.fr/1992TOU30162.
Texto completoImam, Ziad. "L’intégration des activités de maintenance dans la conception des systèmes d’automatisation". Thesis, Lille 1, 2015. http://www.theses.fr/2015LIL10048/document.
Texto completoDuring a design process of automated systems, it’s important to think about maintaining performance which will deteriorate over time. During the operation phase of such systems, preventive maintenance can keep this performance over a required level ; in the same time if these actions were not studied, this may be a disadvantage of the entire process. It is therefore necessary to consider how to reduce these interventions into an optimum number during the system life cycle, this fact will require a design methodology able to organize these operations, and to reduce the time lost under the determination of what to do during the maintenance, and time on unnecessary operations. The designer, is therefore invited to structure an optimum system design to achieve a defined function. This design must allow the system to maintain a reliability level with the minimal costs
Laloix, Thomas. "Méthodologie d’élaboration d’un bilan de santé de machines de production pour aider à la prise de décision en exploitation : application à un centre d’usinage à partir de la surveillance des composants de sa cinématique". Thesis, Université de Lorraine, 2018. http://www.theses.fr/2018LORR0291/document.
Texto completoThis PhD work has been initiated by Renault, in collaboration with Nancy Research Centre in Automatic Control (CRAN), with the aim to propose the foundation of a generic PHM-based methodology leading to machine health check regarding machine-product joint consideration and facing industrial requirements. The proposed PHM-based methodology is structured in five steps. The two first steps are developed in this PhD work and constitute the major contributions. The first originality represents the formalization of machine-product relationship knowledge based on the extension of well-known functioning/dysfunctioning analysis methods. The formalization is materialized by means of meta-modelling based on UML (Unified Modelling Language). This contribution leads to the identification of relevant parameters to be monitored, from component up to machine level. These parameters serve as a basis of the machine health check elaboration. The second major originality of the thesis aims at the definition of health check elaboration principles from the previously identified monitoring parameters and formalized system knowledge. Elaboration of such health indicators is based on Choquet integral as aggregation method, raising the issue of capacity identification. In this way, it is proposed a global optimization model of capacity identification according to system multi-level, by the use of Genetic Algorithms. Both contributions are developed with the objective to be generic (not only oriented on a specific class of equipment), according to industrial needs. The feasibility and the interests of such approach are shown on the case of machine tool located in RENAULT Cléon Factory
Kpakpo, Miguel. "Une approche de gestion de la maintenance de parcs éoliens centrée sur les systèmes multiagents". Thesis, Normandie, 2018. http://www.theses.fr/2018NORMIR33/document.
Texto completoOptimization & maintenance in the Industrial sector covers different aspects according to the objectives set by the industrial operator. Their common goal is to reduce downtime and failures. For the windfarm operators the goal is to ensure the wind farms high availibility. We went one step further by asking the question of the efficiency of maintenance costs and the profitability. The answer to this question comes from the results of a cost function associated to a simulation model based on multiagents systems. The choice of the multiagent paradigm is motivated by the use of MAS for other simulation purposes and the fact that they guarantee a kind of flexibility regarding the evolution in a moving business context. This Phd thesis focuses on a multi-agent systems model designed to improve the management of wind farms through the definition of a set of financial criteria specific to the wind farm operators
Rollinger, Raphaël. "Application de la sûreté de fonctionnement à l'optimisation de la maintenance des bâtiments et des infrastructures techniques la méthode SINPATI sélection des investissements pour le patrimoine technique et immobilier". Nancy 1, 1998. http://www.theses.fr/1998NAN10269.
Texto completoRobert, Elodie. "Gestion de l'état de santé de véhicules pour la maintenance de flotte : prise en compte des contraintes opérationnelles et optimisation conjointe des maintenances et des missions". Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAT098.
Texto completoThis thesis work deals with the problems of joint scheduling for maintenance operations and missions for industrial vehicle fleets. The aim is to develop a methodology to adapt the joint scheduling of maintenance and missions according to the vehicles health state but also according to the missions features. These features correspond to the conditions of usage severity that have a significant impact on the truck deterioration and must be taken into account to adapt at best the maintenance operations schedule according to the deterioration evolution. The implementation of a decision support methodology to manage a fleet would improve productivity and reduce the maintenance costs while making the most of the fleet capacity. However, the joint scheduling problem for a fleet is a complex problem to solve and three main dimensions has to be considered. The first one is to jointly schedule missions and maintenance operations in a static case. The second one is to integrate the available monitoring information and the different events that can occur to update the schedule and treat the problem in a dynamic way. The third dimension is the fleet dimension that involves managing several vehicles in parallel.The first step is to jointly schedule the maintenance activity and the missions for a truck in a static case. It is assumed that all the missions to be performed are known and that no monitoring information is available. To do this, a vehicle deterioration model is defined to estimate its remaining useful lifetime to make decisions. It is a model with varying parameters since the vehicle operates under different conditions of usage severity according to the missions. It is the central point for setting up a scheduling algorithm to avoid any excessive risk of failure. The scheduling process is naturally optimized according to a criterion based on either the maintenance costs or the operating incomes.Once this methodology has been defined, it must be completed to include information on the vehicle deterioration, failure occurrences and new missions that may be requested. A dynamic approach has then been developed to solve the scheduling problem for a vehicle. If a breakdown occurs, the schedule must be updated because it is no longer adapted to the evolution of the current vehicle deterioration. Likewise, when a new mission is available, an update is essential because the priority order of the missions, defined by their deadlines, must be considered as soon as possible to avoid delay penalties. On the other hand, deterioration information can have a varying influence on the current schedule. Then, the schedule robustness has to be studied to avoid changing the mission order and the maintenance dates too often.The last step is to integrate the fleet dimension in the decision-making process. It is no longer just a question of mission order and timing for maintenance operations, but also of deciding which vehicle is assigned to which mission. The decision-making process then depends on the whole fleet. An analysis of the impact of considering the fleet dimension in the static case and then in the dynamic case is led.Simulation results are used to illustrate the developed methods and aim at showing their interest and the cost savings they generate
Ghamlouch, Houda. "Modélisation de la dégradation, maintenance conditionnelle et pronostic : usage des processus de diffusion". Thesis, Troyes, 2016. http://www.theses.fr/2016TROY0019/document.
Texto completoA major concern for engineers and managers nowadays is to make high quality products and highly reliable systems. In this context, reliability analysis and failure prediction, besides of efficient maintenance decision-making are strongly required. Deterioration modeling and analysis is a fundamental step for the understanding and the anticipation of system behavior. Consider a functional system operating in unstable conditions or environment where the deterioration level is not observable and could not be determined by direct measures. For this system a set of measurable health indicator that indirectly reflects the system working conditions and deterioration level can be defined and examined. Considering these indicators, the development of a mathematical model describing the system behavior is required.In this thesis, we consider a set of non-monotone indicators evolving in a dynamic environment. Taking into account the major features of the data evolution as well as the impact of dynamic environment consequences and potential shocks, stochastic models based on Wiener and jump processes are proposed for these indicators. Each model is calibrated and tested, and their limits are discussed. A decision-making approach for preventive maintenance strategies is then proposed. In this approach, knowing the RUL of the system, a simulation-based real options analysis is used in order to determine the best date to maintain. Considering a case study of a wind turbine with PHM structure, the decision optimization approach is described
Gay, Antonin. "Pronostic de défaillance basé sur les données pour la prise de décision en maintenance : Exploitation du principe d'augmentation de données avec intégration de connaissances à priori pour faire face aux problématiques du small data set". Electronic Thesis or Diss., Université de Lorraine, 2023. http://www.theses.fr/2023LORR0059.
Texto completoThis CIFRE PhD is a joint project between ArcelorMittal and the CRAN laboratory, with theaim to optimize industrial maintenance decision-making through the exploitation of the available sources of information, i.e. industrial data and knowledge, under the industrial constraints presented by the steel-making context. Current maintenance strategy on steel lines is based on regular preventive maintenance. Evolution of preventive maintenance towards a dynamic strategy is done through predictive maintenance. Predictive maintenance has been formalized within the Prognostics and Health Management (PHM) paradigm as a seven steps process. Among these PHM steps, this PhD's work focuses on decision-making and prognostics. The Industry 4.0 context put emphasis on data-driven approaches, which require large amount of data that industrial systems cannot ystematically supply. The first contribution of the PhD consists in proposing an equation to link prognostics performances to the number of available training samples. This contribution allows to predict prognostics performances that could be obtained with additional data when dealing with small datasets. The second contribution of the PhD focuses on evaluating and analyzing the performance of data augmentation when applied to rognostics on small datasets. Data augmentation leads to an improvement of prognostics performance up to 10%. The third contribution of the PhD consists in the integration of expert knowledge into data augmentation. Statistical knowledge integration proved efficient to avoid performance degradation caused by data augmentation under some unfavorable conditions. Finally, the fourth contribution consists in the integration of prognostics in maintenance decision-making cost modeling and the evaluation of prognostics impact on maintenance decision cost. It demonstrates that (i) the implementation of predictive maintenance reduces maintenance cost up to 18-20% and ii) the 10% prognostics improvement can reduce maintenance cost by an additional 1%
Ben, Salem Abdeljabbar. "Modèles Probabilistes de Séquences Temporelles et Fusion de Décisions.Application à la Classification de Défauts de Rails et à leur Maintenance". Phd thesis, Université Henri Poincaré - Nancy I, 2008. http://tel.archives-ouvertes.fr/tel-00325011.
Texto completoPar rapport aux différentes composantes du MCO, notamment le soutien technique et le soutien logistique, ces travaux de thèse, initiés dans le cadre d'un partenariat avec l'INRETS, se restreignent au contexte du processus pivot du soutien technique: le processus de maintenance. Ce processus est considéré actuellement comme l'un des principaux leviers d'action sur la performance globale des systèmes industriels avec cependant encore de nombreuses problématiques scientifiques à résoudre pour en garantir son optimisation.
Par conséquent les propositions défendues scientifiquement dans cette thèse, et qui s'adossent au contexte industriel du MCO des rails à la RATP, portent globalement sur une contribution au processus de maintenance en se focalisant plus précisément sur les sous processus complémentaires de diagnostic et d'aide à la décision. En effet, une première contribution a pour objet de proposer le développement d'un système de diagnostic (de détection de rail cassé) basé sur une nouvelle approche permettant de fusionner des connaissances a priori avec des résultats du traitement des mesures réelles issues de capteurs. Une deuxième contribution propose deux approches originales d'aide la décision en maintenance des systèmes à n-composants permettant de réduire le coût global de possession (Life Cycle Cost: LCC) d'un système complexe à partir d'une modélisation de la dégradation des composants, et en intégrant simultanément plusieurs types de dépendances telles que les dépendances fonctionnelles et économiques. Ces deux dernières approches portent sur les politiques de maintenance préventive, et plus particulièrement sur la maintenance conditionnelle et prévisionnelle.
Contexte et problématique industriels de la thèse
Le rail est un organe vital dans le transport ferroviaire. Sa sûreté et sa maintenance conditionnent le bon fonctionnement de tout le réseau de transport. Les exploitants ferroviaires, ayant pour priorité d'assurer la sécurité et le bien-être des passagers, accordent un intérêt de plus en plus particulier à cet organe de l'infrastructure. En effet, l'accroissement de la vitesse des trains, de la densité du trafic, des charges par essieux et de la puissance des engins moteurs ont pour conséquence d'exercer sur les voies ferroviaires des sollicitations toujours plus grandes qui peuvent, à la longue, mettre en cause l'intégrité des rails. Le maintien en conditions opérationnelles de cet organe est devenu donc une préoccupation majeure des exploitants ferroviaire.
Par exemple bien que l'occurrence des fissures soit rare sur le métro parisien, la RATP a étudié de près les effets de ces ruptures sur plusieurs plans: mécanique, électrique, économique et sécuritaire, et a mis en évidence la nécessité de concevoir un nouveau système automatique de détection qui permet de remplacer la fonction de détection de rail cassé assurée auparavant par le circuit de voie (CdV).
Dans ce cadre, un capteur à courants de Foucault a été développé par l'INRETS en partenariat avec la RATP dans le cadre du programme national de recherche et d'innovation dans les transports terrestres. Ce dispositif doit assurer une détection de défauts de rails sans contact avec des contraintes électrique, mécanique, de positionnement, de pollution, etc. Ce système avait pour but initial la détection des fissures débouchantes. Étant capable de détecter aussi toute modification de la géométrie de la surface de rail, ou de ses caractéristiques magnétiques, le capteur permet en plus de relever quelques irrégularités sur la voie autre que les ruptures. Un étiquetage de ces points a été mis en œuvre ce qui offre au système de diagnostic, lors du passage du véhicule auquel il est adjoint, la possibilité d'identifier des points singuliers tels que les joints ou les écailles qui sont une source d'information très utile pour la mise en œuvre d'une maintenance plus dynamique et donc plus optimale.
En effet à l'heure actuelle, les actions de maintenance des voies ferrées sont essentiellement correctives ou sont exécutées à intervalles de temps prédéterminés. Dans ses études, la RATP a conclu que ces deux types de politiques sont trop coûteux et peu sûrs, et a mis en évidence le besoin d'évoluer vers de nouvelles stratégies de maintenance pour assurer à la fois la sécurité et la disponibilité des installations à moindre coût. Par ailleurs, des études récentes ont montré que la prise en compte d'un certain nombre de paramètres significatifs de la dégradation de rails devait permettre d'affiner les politiques de maintenance et, ainsi, d'améliorer la qualité de service, la disponibilité, la sécurité et les coûts. Pour aboutir à cette finalité, la maintenance des rails ne doit plus être limitée à la seule vision du composant (portion de rail) siège de la défaillance, mais à l'étude du système dans sa globalité (système à n-composants). Les décisions relatives à la maintenance ne peuvent donc plus être isolées de leur contexte et doivent s'inscrire dans un lien plus fort entre surveillance – diagnostic et aide à la décision.
Sur la base de ce double constat industriel en diagnostic et décision, les travaux de recherche menés dans cette thèse ont pour objet, relativement au contexte RATP, d'investiguer de nouvelles orientations pour les politiques de maintenance des rails permettant à la fois de corriger efficacement les défauts (maintenance corrective), et de les anticiper (maintenance préventive) en suivant des prévisions extrapolées de l'analyse et de l'évaluation des paramètres significatifs de la dégradation des rails (informations issues du diagnostic). Ces approches doivent se baser essentiellement sur les aspects d'optimisation des coûts liés à la maintenance et à ses conséquences.
Approche proposée
Face à la problématique industrielle RATP genèse de cette thèse, la démarche scientifique mise en œuvre se décline naturellement en deux phases complémentaires. Tout d'abord, il s'agit d'améliorer le système de diagnostic existant (capteur à courants de Foucault) pour la détection des défauts afin de garantir des résultats fiables sur l'état de dégradation des rails. Dans ce cadre, nous proposons une méthode de diagnostic originale se basant sur une fusion de deux sources d'informations de natures différentes : Approche Locale et Approche Globale. La deuxième phase de cette étude consiste ensuite à donner deux nouvelles approches pour contribuer à l'optimisation de la maintenance conditionnelle et prévisionnelle des systèmes formés par plusieurs composants en tenant compte de certains type de dépendances, notamment économique et fonctionnelles
Organisation du Rapport
Cette démarche se développe dans le mémoire sous la forme de 4 chapitres :
- Le premier chapitre permet de définir globalement le processus de maintenance à la fois d'un point de vue général mais aussi relativement au contexte industriel. A partir de l'état de l'art sur les différentes politiques de maintenance, sont isolés de façon plus précise les processus clés de diagnostic et d'aide à la décision. Un premier constat est fait aussi sur les insuffisances des politiques de maintenance utilisées actuellement par l'exploitant ferroviaire RATP et la nécessité de proposer des nouvelles politiques qui sont plus efficaces et moins coûteuses. Ce constat permet de positionner le contexte de nos contributions et de les justifier.
- le deuxième chapitre est consacré à l'étude du sous processus de diagnostic. Son objectif est d'expliquer la procédure de mise en œuvre de l'approche locale que nous proposons. En ce sens ce chapitre est structuré en trois grandes parties. La première partie est consacrée à présenter et analyser les données fournies par la RTAP décrivant la structure des voies. A l'issue de cette étape, un état de l'art des méthodes d'analyse et de traitement de ces données est réalisé dans l'optique de choisir la meilleure alternative. La mise en œuvre de la méthode choisie est décrite ensuite en fin du chapitre 2.
- Le troisième chapitre complète le deuxième et présente une généralisation des outils utilisés pour la mise en œuvre de l'approche locale, puis il explique la procédure de fusion entre l'approche locale et l'approche globale.
- Enfin, le dernier chapitre est consacré au développement d'une démarche générique, basée sur une combinaison des réseaux bayésiens dynamiques et des processus décisionnels de Markov, pour l'optimisation de la maintenance conditionnelle et prévisionnelle des systèmes à N-composants.
En synthèse, notre proposition fournit un cadre de modélisation théorique contribuant à l'optimisation du LCC d'un système tout en intégrant différents types de dépendances entre ses composants. La mise en œuvre de notre proposition est déroulée, dans un premier temps, sur un exemple illustratif puis appliquée en dernière étape dans le cadre de la maintenance des rails.