Modern Heavy Duty Vehicles consist of a multitude of components and operate in various conditions. As there is value in goods transported, there is an incentive to avoid unplanned breakdowns. For this, condition based maintenance can be applied.\newline This thesis presents a study comparing the applicability of the data-driven Consensus SelfOrganizing Models (COSMO) method and the model-driven patent series introduced by Fogelstrom, applied on the air processing system for leakage detection on Scania Heavy Duty Vehicles. The comparison of the two methods is done using the Area Under Curve value given by the Receiver Operating Characteristics curves for features in order to reach a verdict.\newline For this purpose, three criteria were investigated. First, the effects of the hyper-parameters were explored to conclude a necessary vehicle fleet size and time period required for COSMO to function. The second experiment regarded whether environmental factors impact the predictability of the method, and finally the effect on the predictability for the case of nonidentical vehicles was determined.\newline The results indicate that the number of representations ought to be at least 60, rather with a larger set of vehicles in the fleet than with a larger window size, and that the vehicles should be close to identical on a component level and be in use in comparable ambient conditions.\newline In cases where the vehicle fleet is heterogeneous, a physical model of each system is preferable as this produces more stable results compared to the COSMO method. / Moderna tunga fordon består av ett stort antal komponenter och används i många olika miljöer. Då värdet för tunga fordon ofta består i hur mycket gods som transporteras uppstår ett incitament till att förebygga oplanerade stopp. Detta görs med fördel med hjälp av tillståndsbaserat underhåll. Denna avhandling undersöker användbarheten av den data-drivna metoden Consensus SelfOrganizing Models (COSMO) kontra en modellbaserad patentserie för att upptäcka läckage på luftsystem i tunga fordon. Metoderna ställs mot varandra med hjälp av Area Under Curve-värdet som kommer från Receiver Operating Characteristics-kurvor från beskrivande signaler. Detta gjordes genom att utvärdera tre kriterier. Dels hur hyperparametrar influerar COSMOmetoden för att avgöra en rimlig storlek på fordonsflottan, dels huruvida omgivningsförhållanden påverkar resultatet och slutligen till vilken grad metoden påverkas av att fordonsflottan inte är identisk. Slutsatsen är att COSMO-metoden med fördel kan användas sålänge antalet representationer överstiger 60 och att fordonen inom flottan är likvärdiga och har använts inom liknande omgivningsförhållanden. Om fordonsflottan är heterogen så föredras en fysisk modell av systemet då detta ger ett mer stabilt resultat jämfört med COSMO-metoden.

Hlavní cílem dizertace je poskytnutí uceleného pohledu na problematiku technické prognostiky, která nachází uplatnění v tzv. prediktivní údržbě založené na trvalém monitorování zařízení a odhadu úrovně degradace systému či jeho zbývající životnosti a to zejména v oblasti komplexních zařízení a strojů. V současnosti je technická diagnostika poměrně dobře zmapovaná a reálně nasazená na rozdíl od technické prognostiky, která je stále rozvíjejícím se oborem, který ovšem postrádá větší množství reálných aplikaci a navíc ne všechny metody jsou dostatečně přesné a aplikovatelné pro embedded systémy. Dizertační práce přináší přehled základních metod použitelných pro účely predikce zbývající užitné životnosti, jsou zde popsány metriky pomocí, kterých je možné jednotlivé přístupy porovnávat ať už z pohledu přesnosti, ale také i z pohledu výpočetní náročnosti. Jedno z dizertačních jader tvoří doporučení a postup pro výběr vhodné prognostické metody s ohledem na prognostická kritéria. Dalším dizertačním jádrem je představení tzv. částicového filtrovaní (particle filtering) vhodné pro model-based prognostiku s ověřením jejich implementace a porovnáním. Hlavní dizertační jádro reprezentuje případovou studii pro velmi aktuální téma prognostiky Li-Ion baterii s ohledem na trvalé monitorování. Případová studie demonstruje proces prognostiky založené na modelu a srovnává možné přístupy jednak pro odhad doby před vybitím baterie, ale také sleduje možné vlivy na degradaci baterie. Součástí práce je základní ověření modelu Li-Ion baterie a návrh prognostického procesu.

This thesis presents a novel hybrid prognostic methodology, integrating physics-based and data-driven prognostic models, to enhance the prognostic accuracy, robustness, and applicability. The presented prognostic methodology integrates the short-term predictions of a physics-based model with the longer term projection of a similarity-based data-driven model, to obtain remaining useful life estimations. The hybrid prognostic methodology has been applied on specific components of two different engineering systems, one which represents accelerated, and the other a nominal degradation process. Clogged filter and fatigue crack propagation failure cases are selected as case studies. An experimental rig has been developed to investigate the accelerated clogging phenomena whereas the publicly available Virkler fatigue crack propagation dataset is chosen after an extensive literature search and dataset analysis. The filter clogging experimental rig is designed to obtain reproducible filter clogging data under different operational profiles. This data is thought to be a good benchmark dataset for prognostic models. The performance of the presented methodology has been evaluated by comparing remaining useful life estimations obtained from both hybrid and individual prognostic models. This comparison has been based on the most recent prognostic evaluation metrics. The results show that the presented methodology improves accuracy, robustness and applicability. The work contained herein is therefore expected to contribute to scientific knowledge as well as industrial technology development.

Switches, which are critical components of the Swedish railway, have a neglected maintenance cost that is three times as high as their current annual maintenance cost. Between 2017 and 2018, switches’ reported faults increased by 38 % and about one-third of them caused delays on the regular railway traffic. The purpose of this master thesis is to present recommendations of how condition-based maintenance could reduce the occurrence of faults in railway switches that affects the regular railway traffic. Condition-based maintenance is a cost-effective strategy designed to monitor and plan maintenance according to the condition of a device and is suitable for remote-controlled monitoring. To fulfill the purpose the thesis was divided into three milestones that were accomplished by applying the problem-solving method DMAIC (Define, Measure, Analyse, Improve and Control). The first milestone included the Define and Measure steps and aimed to investigate which fault caused the largest number of delay minutes per fault. Different categories of causes that affects the railway traffic were analysed. Among them, Material-weakening/Aging and Broken component resulted in many faults and delay minutes. The faults were sorted into groups at component level. Faults caused by Gearbox were identified as those causing the largest delays in the railway traffic. The result from the first milestone with the Define and Measure steps were then used for the second milestone. The second milestone included the Analyse step where it was investigated if the identified faults in Gearbox could be foreseen. This investigation was first conducted through the analysis of alarms recorded in one of Trafikverket’s databases. A graphical analysis of the data showed that no relationship could be identified between the faults in Gearbox and the recorded alarms of the database. Then, it was investigated if faults in Gearbox could be foreseen using statistical process control charts based on switching time. Statistical process control monitors a process using real time data. However, in this thesis we used historical data from 2018 to perform our analysis. The available data had deficiencies in quality due to truncation of the switching time. The truncation meant that the decimals were removed. The control charts issued out-of-control situations where the existing database did not record any alarm. Moreover, data on the switching time of several switches showed significant autocorrelation that affects the calculation of the control limits. However, the results appeared complex to interpret most likely because of the truncation and the autocorrelation of the data. A further graphical analysis of the switching time and the mean of the switching time indicated that 69 % of the switches had a probable relationship between faults in Gearbox and switching time. The third milestone included the Improve and Control steps and provided recommendations of how to reduce the occurrence of faults in switches. The analysis conducted in the previous milestones led to the following recommendations: Increase measurement accuracy when measuring switching time, Establish control charts for the switching time based on statistical process control and explain potential causes of the observed autocorrelation, and Improve reporting procedures of faults in the database. / Spårväxlar, som är en kritisk komponent på den svenska järnvägen, har ett eftersatt underhållsbehov som motsvarar en kostnad som är tre gånger större än den årliga underhållskostnaden. Från 2017 till 2018 ökade rapporteringen av funktionsfel i spårväxlar med 38 % och ungefär en tredjedel av funktionsfelen var tågstörande fel som orsakar merförseningar i tågtrafiken. Syftet med examensarbetet är att presentera rekommendationer för hur uppkomsten av tågstörande fel i spårväxlar kan reduceras genom tillståndsbaserat underhåll. Tillståndsbaserat underhåll är en kostnadseffektiv strategi som ämnar att övervaka och planera underhållsåtgärder efter tillståndet i enheten och är lämplig vid fjärrstyrd övervakning. För att uppfylla examensarbetets syfte delades projektet upp i tre delmål som besvarades genom tillämpning av problemlösningsmetoden DMAIC (Define, Measure, Analyse, Improve och Control). Det första delmålet innefattade stegen Define och Measure och ämnade undersöka vilket funktionsfel som orsakat flest antal merförseningsminuter per fel. Orsakskategorier till tågstörande fel analyserades där Materialutmattning/Åldrande samt Komponent trasig hade ett stort antal tågstörande fel och merförseningsminuter. Orsakskategorierna bröts ner till komponentnivå varav funktionsfel i Växellåda identifierades att orsaka flest antal merförseningsminuter per fel. Resultatet från Delmål 1 samt de två stegen Define och Measure användes därefter till Delmål 2. Det andra delmålet innefattade steget Analyse och ämnade att undersöka om det identifierade funktionsfelet i Växellåda kunde förutspås. Detta undersöktes genom larm från en av Trafikverkets befintliga databaser. Utifrån en grafisk analys av larmen kunde inget samband identifieras mellan funktionsfelet i Växellåda och larm från databasen. Därför undersöktes istället om funktionsfel i Växellåda kunde förutspås genom styrdiagram baserat på omläggningstid. Statistisk processtyrning är lämpligt vid övervakning av processer i realtid, men i detta examensarbetes analys användes historisk data från 2018. Den tillgängliga data hade brister i kvalitet till följd av trunkering av omläggningstiden. Trunkeringen innebar att decimalerna har avlägsnats. I styrdiagrammen påvisades larm där den befintliga databasen inte innehöll larm. Dessutom påvisade data på omläggningstiden från flera spårväxlar signifikant autokorrelation vilket påverkar beräkning av styrgränserna. Resultatet var således svårt att tolka på grund av trunkering och autokorrelerade data. Grafisk analys av omläggningstider och medelvärdet av omläggningstiderna indikerade att 69 % av spårväxlarna hade ett troligt samband mellan funktionsfel i Växellåda och omläggningstiden. Det tredje delmålet innefattade stegen Improve och Control och ämnade att upprätta rekommendationer för hur uppkomsten av funktionsfel i spårväxlar kan reduceras. Analysen i föregående delmål resulterade i följande rekommendationer:       • Öka mätnoggrannheten vid mätning av omläggningstid,       • Upprätta styrdiagram för omläggningstiden utifrån statistisk processtyrning och identifiera orsaken till autokorrelerade data, och       • Förbättra inrapportering av funktionsfel.

Motivés par l'évolution des réglementations en matière d'écologie mais aussi par des contraintes purement économiques, plusieurs secteurs industriels se sont retrouvés dans l'obligation de développer de nouvelles méthodes et modèles pour la gestion des produits en fin de vie. Dans ce contexte, la remanufacturation vise à gérer la récupération de la valeur d’un produit avant sa fin de vie. Elle permet de prolonger le cycle de vie du produit et d’économiser une partie des besoins industriels en matière première. Ces produits remanufacturés seront remis dans le marché et destinés à une autre catégorie de clients, différente de celle des produits neufs. Dans d'autres cas, les produits remanufacturés sont réutilisés sous la forme de pièces de rechange dans les actions de maintenance, mais cette réutilisation peut varier selon la stratégie de maintenance adoptée. Dans ce contexte, cette thèse s'intéresse à l’intégration d'un flux d’approvisionnement hybride en pièces de rechange dans un modèle de maintenance basé sur la dégradation stochastique d’un système de production. Deux types de flux d’approvisionnement en pièces de rechange sont étudiés : un flux direct et un flux inverse. Le flux direct est représenté par l'utilisation de pièces de rechange neuves et le flux inverse est représenté par la réutilisation des pièces récupérées lors des remplacements ultérieurs, avec la possibilité de réaliser une action de remanufacturation pour améliorer l'état de dégradation de ces pièces de rechange. Plusieurs problématiques ont été traitées pour permettre de comprendre l'impact et l'influence d'une politique de remanufacturation sur les performances d'un système de production. En effet, dans un premier temps, nous nous sommes intéressés à des systèmes de production composés d'une seule machine. Dans ce cadre, nous avons proposé des études séquentielles puis intégrées pour optimiser la politique de maintenance et celle de l'approvisionnement hybrides en pièces de rechange destinées aux actions de remplacements. Nous avons étudié également la gestion de production soumise à une contrainte de qualité basée sur l'évolution de la dégradation de la machine. Ensuite, et dans un second temps, nous avons présenté des généralisations des modèles étudiés dans le cadre de systèmes de production composés de plusieurs machines. Enfin, nous avons développé un outil d'aide à la décision pour conception de systèmes de production dans le cadre d'une politique de remanufacturation. Cette problématique - du niveau stratégique - vise à sélectionner le meilleur ensemble de machines pour construire un nouveau système de production capable de satisfaire les contraintes de production définies par décideur / Motivated by the change of regulations in the matter of sustainability, but also by pure economic constraints, several industries have found themselves obligated to develop new methods and models for the management of products that are at the end of their life cycle. In this context, the remanufacturing aims at managing the recovery of the product’s value before its end of life. This type of action will extend the product life cycle and save the use of the raw material. These remanufactured products will be re-injected in a market that serves another class of customers, different from the one using new products. In other cases, the remanufactured products are reused as spare parts for the maintenance, but this reuse may vary according to the maintenance strategy adopted. This thesis focuses on the integration of a hybrid flow supply of spare parts in a service model based on stochastic degradation of a production system. Two types of spare parts supply flows are studied: a direct flow and reverse flow. The direct flow is represented by the use of new spare parts and the reverse flow is represented by the reuse of the recovered parts during the replacements, with the ability to perform remanufacturing action to improve the degradation level of these spare parts. Several issues were treated to better understand the impact of remanufacturing policies over the performance of a production system. At the beginning we started our study with production systems composed of a single machine. In this context, we proposed sequential studies then integrated one to optimize the maintenance policy as well as the Hybrid provisioning in regard to spare parts destined to replacement actions. Similarly, we’ve studied the production management subjected to quality constraint based on the machine’s degradation process. Furthermore, we’ve presented generalizations of studied models within the context of a production system composed of several machines. Finally, we’ve developed an aid-to-decision-design tool for production systems within the remanufacturing process. This problematic aims at –from a strategic point- selecting the best group of machines to build a new system of production that is able to satisfy the constraints of a production defined by the decision maker

Submitted by JOSIANE SANTOS DE OLIVEIRA (josianeso) on 2017-11-17T15:53:07Z No. of bitstreams: 2 Luiz Antonio Canal_.pdf: 1988745 bytes, checksum: 60112cf8ea6029ecad19839973234379 (MD5) Luiz Antonio Canal_.pdf: 1988745 bytes, checksum: 60112cf8ea6029ecad19839973234379 (MD5) / Made available in DSpace on 2017-11-17T15:53:07Z (GMT). No. of bitstreams: 2 Luiz Antonio Canal_.pdf: 1988745 bytes, checksum: 60112cf8ea6029ecad19839973234379 (MD5) Luiz Antonio Canal_.pdf: 1988745 bytes, checksum: 60112cf8ea6029ecad19839973234379 (MD5) Previous issue date: 2017-09-05 / Nenhuma / A busca pela maior segurança industrial em plantas petroquímicas tem sido a pauta principal deste tipo de negócio, já que a possibilidade de acidentes é potencializada pela própria natureza da operação, que envolve inventários inflamáveis, combustíveis ou tóxicos. Muitos dos iniciadores destes eventos advêm de mau funcionamento de seus equipamentos dinâmicos, como motores, bombas e compressores, com causas ligadas a manutenção, operação ou projeto. Neste contexto, é proposto neste trabalho um método para a implantação de melhorias e projetos direcionados para o monitoramento contínuo de equipamentos dinâmicos. O objetivo é de aumentar a segurança industrial e a disponibilidade dos equipamentos, já que o contínuo monitoramento dos equipamentos permite uma melhor supervisão dos mesmos, além de fortalecer a manutenção preventiva baseada em condição. Será apresentada a solução focando no monitoramento de temperatura e vibração em mancais, que normalmente são foco da maior parte das falhas em equipamentos dinâmicos. Inicia-se pela escolha do método para priorização da implantação, baseado em análise multicritério e análise de risco, passando pela proposição e definição dos critérios, culminando com a exemplificação do trabalho em uma planta petroquímica real. Como resultado tem-se uma matriz de risco para apoio na priorização de investimento em monitoramento contínuo, agregando ainda simulações de análise de sensibilidade para a tomada de decisão. / The search for greater industrial safety has been the main guideline in petrochemical business, since the most of accidents are potentiated by the own nature of the operation, which involves flammable, combustible or toxic inventories. Many of the initiators of these events arise from the malfunction of their dynamic equipment, such as motors, pumps and compressors, with causes related to maintenance, operation or design. In this context, it is proposed a method for the implementation of improvements and projects directed to the continuous monitoring of dynamic equipment. The main objective is to increase the industrial safety and the availability, since the continuous monitoring allows a better supervision of the dynamic equipment, besides strengthening the application of condition based maintenance policy. The solution will be presented focusing on the monitoring of equipment temperature and vibration, which indicate of most failures or a situation of non-appropriated operation. This work starts with determining the method to prioritize the implementation, based on multicriteria and risk analysis, explain the criteria and their definition, culminating with the exemplification of the work in a real petrochemical plant. As a result, a risk matrix is presented for support in the prioritization of investment in continuous monitoring, also adding sensitivity analysis simulations for decision making.

Many real-world systems experience deterioration with usage and age, which often leads to low product quality, high production cost, and low system availability. Most previous maintenance and reliability models in the literature do not incorporate condition monitoring information for decision making, which often results in poor failure prediction for partially observable deteriorating systems. For that reason, the development of fault prediction and control scheme using condition-based maintenance techniques has received considerable attention in recent years. This research presents a new framework for predicting failures of a partially observable deteriorating system using Bayesian control techniques. A time series model is fitted to a vector observation process representing partial information about the system state. Residuals are then calculated using the fitted model, which are indicative of system deterioration. The deterioration process is modeled as a 3-state continuous-time homogeneous Markov process. States 0 and 1 are not observable, representing healthy (good) and unhealthy (warning) system operational conditions, respectively. Only the failure state 2 is assumed to be observable. Preventive maintenance can be carried out at any sampling epoch, and corrective maintenance is carried out upon system failure. The form of the optimal control policy that maximizes the long-run expected average availability per unit time has been investigated. It has been proved that a control limit policy is optimal for decision making. The model parameters have been estimated using the Expectation Maximization (EM) algorithm. The optimal Bayesian fault prediction and control scheme, considering long-run average availability maximization along with a practical statistical constraint, has been proposed and compared with the age-based replacement policy. The optimal control limit and sampling interval are calculated in the semi-Markov decision process (SMDP) framework. Another Bayesian fault prediction and control scheme has been developed based on the average run length (ARL) criterion. Comparisons with traditional control charts are provided. Formulae for the mean residual life and the distribution function of system residual life have been derived in explicit forms as functions of a posterior probability statistic. The advantage of the Bayesian model over the well-known 2-parameter Weibull model in system residual life prediction is shown. The methodologies are illustrated using simulated data, real data obtained from the spectrometric analysis of oil samples collected from transmission units of heavy hauler trucks in the mining industry, and vibration data from a planetary gearbox machinery application.

Many real-world systems experience deterioration with usage and age, which often leads to low product quality, high production cost, and low system availability. Most previous maintenance and reliability models in the literature do not incorporate condition monitoring information for decision making, which often results in poor failure prediction for partially observable deteriorating systems. For that reason, the development of fault prediction and control scheme using condition-based maintenance techniques has received considerable attention in recent years. This research presents a new framework for predicting failures of a partially observable deteriorating system using Bayesian control techniques. A time series model is fitted to a vector observation process representing partial information about the system state. Residuals are then calculated using the fitted model, which are indicative of system deterioration. The deterioration process is modeled as a 3-state continuous-time homogeneous Markov process. States 0 and 1 are not observable, representing healthy (good) and unhealthy (warning) system operational conditions, respectively. Only the failure state 2 is assumed to be observable. Preventive maintenance can be carried out at any sampling epoch, and corrective maintenance is carried out upon system failure. The form of the optimal control policy that maximizes the long-run expected average availability per unit time has been investigated. It has been proved that a control limit policy is optimal for decision making. The model parameters have been estimated using the Expectation Maximization (EM) algorithm. The optimal Bayesian fault prediction and control scheme, considering long-run average availability maximization along with a practical statistical constraint, has been proposed and compared with the age-based replacement policy. The optimal control limit and sampling interval are calculated in the semi-Markov decision process (SMDP) framework. Another Bayesian fault prediction and control scheme has been developed based on the average run length (ARL) criterion. Comparisons with traditional control charts are provided. Formulae for the mean residual life and the distribution function of system residual life have been derived in explicit forms as functions of a posterior probability statistic. The advantage of the Bayesian model over the well-known 2-parameter Weibull model in system residual life prediction is shown. The methodologies are illustrated using simulated data, real data obtained from the spectrometric analysis of oil samples collected from transmission units of heavy hauler trucks in the mining industry, and vibration data from a planetary gearbox machinery application.

A paradigm shift is emerging in system reliability and maintainability. The military and industrial sectors are moving away from the traditional breakdown and scheduled maintenance to adopt concepts referred to as Condition Based Maintenance (CBM) and Prognostic Health Management (PHM). In addition to signal processing and subsequent diagnostic and prognostic algorithms these new technologies involve storage of large volumes of both quantitative and qualitative information to carry out maintenance tasks effectively. This not only requires research and development in advanced technologies but also the means to store, organize and access this knowledge in a timely and efficient fashion. Knowledge-based expert systems have been shown to possess capabilities to manage vast amounts of knowledge, but an intelligent systems approach calls for attributes like learning and adaptation in building autonomous decision support systems. This research presents an integrated knowledge-based approach to diagnostic reasoning for CBM of engineering systems. A two level diagnosis scheme has been conceptualized in which first a fault is hypothesized using the observational symptoms from the system and then a more specific diagnostic test is carried out using only the relevant sensor measurements to confirm the hypothesis. Utilizing the qualitative (textual) information obtained from these systems in combination with quantitative (sensory) information reduces the computational burden by carrying out a more informed testing. An Industrial Language Processing (ILP) technique has been developed for processing textual information from industrial systems. Compared to other automated methods that are computationally expensive, this technique manipulates standardized language messages by taking advantage of their semi-structured nature and domain limited vocabulary in a tractable manner. A Dynamic Case-based reasoning (DCBR) framework provides a hybrid platform for diagnostic reasoning and an integration mechanism for the operational infrastructure of an autonomous Decision Support System (DSS) for CBM. This integration involves data gathering, information extraction procedures, and real-time reasoning frameworks to facilitate the strategies and maintenance of critical systems. As a step further towards autonomy, DCBR builds on a self-evolving knowledgebase that learns from its performance feedback and reorganizes itself to deal with non-stationary environments. A unique Human-in-the-Loop Learning (HITLL) approach has been adopted to incorporate human feedback in the traditional Reinforcement Learning (RL) algorithm.

Ces travaux de thèse traitent des problèmes de maintenance associés aux véhicules industriels. Ils se concentrent sur la planification des opérations de maintenance et sur le développement d'une méthodologie de conception pour la maintenance. Le but est de proposer une offre de maintenance personnalisée en fonction de chaque véhicule et capable de s'adapter aux contraintes des utilisateurs. Dans l'industrie du transport, ces contraintes se caractérisent par un nombre d'opportunités de maintenance limité et des immobilisations à fortes conséquences financières. Cette offre a vocation à garantir un niveau de disponibilité élevé tout en réduisant l'impact de la maintenance sur les coûts globaux d'exploitation. Dans ce cadre, la politique de maintenance développée vise à assurer, moyennant un certain risque, l'autonomie d'un système multi-composant sur des périodes d'opérations données. Pendant ces périodes, aucune opération de maintenance et aucune défaillance du système ne doivent venir perturber la réalisation des missions. A la fin de chaque période, la politique considérée évalue la nécessité d'une intervention de maintenance pour assurer la prochaine période avec un niveau de confiance spécifié. Lorsque la maintenance est jugée indispensable, des critères intégrant les coûts et l'efficacité de la maintenance sont introduits pour sélectionner les opérations à réaliser. Cette forme originale de regroupement dynamique s'appuie à la fois sur les modèles de fiabilité des composants, sur la structure fiabiliste du système et sur les informations de surveillance disponibles en ligne. Celles-ci se composent d'informations liées à l'état de santé des composants mais également à leurs conditions d'utilisation. La flexibilité du processus permet d'intégrer, dans la décision, des niveaux d'informations différents suivant les composants. Les paramètres de cette politique, à savoir la longueur de la période et le niveau de confiance, sont optimisés en fonction du coût total de maintenance. Ce coût, évalué sur un horizon fini, intègre les coûts directs associés aux opérations de maintenance et les coûts indirects engendrés par les immobilisations. Pour envisager une réduction significative des coûts d'exploitation du système, l'optimisation de la politique de maintenance seule ne suffit pas. Il est primordial de mener une réflexion plus large associant le système et sa maintenance dès la conception. Pour diriger cette réflexion, la méthodologie de conception proposée hiérarchise, à l'aide d'un facteur d'importance original, l'impact des composants sur les coûts d'exploitation. Différentes options de conceptions sont ensuite évaluées, par simulation, sur les composants jugés prioritaires. Les options retenues conduisent à réduire les coûts globaux d'exploitation. Des résultats de simulation permettent d'illustrer les méthodes développées. Une application sur un sous-système du véhicule industriel est également réalisée. / This thesis research work focuses on the maintenance operations scheduling and the development of a design methodology for maintenance. The aim is to suggest a customized maintenance service offer for each vehicle and able to adapt to user constraints. In the transport industry, these constraints are defined by a limited number of maintenance opportunities and vehicle unplanned stops with significant financial consequences. This service offer should enable both to improve the vehicle uptime and to reduce the maintenance impact on operating costs. In this framework, the developed maintenance policy ensures, with a given risk probability, maintenance free operating periods for a multi-component system. During these periods, the system should be able to carry out all its assigned missions without maintenance actions and system fault. And the end of each period, the considered policy evaluates if a maintenance action is required to ensure maintenance-free and fault-free operation on the next period with a specified confidence level. When a maintenance action is mandatory, decision criteria considering the maintenance costs and the maintenance efficiency are used to select the operations to be performed. This form of dynamic clustering, called time-driven clustering, integrates both the component reliability models, the system structure and the available monitoring information. In our case, the monitoring information refers to the component state information and information on the component operating conditions. The process flexibility makes possible to make a maintenance decision in using different information levels for system components. The policy parameters, namely the period length and the confidence level value, are optimized based on the total maintenance cost. This cost, evaluated on a finite horizon, is composed of directs costs related to maintenance operations and indirect costs generated by system immobilizations. In order to reach a significant operating costs reduction, the maintenance policy optimization alone is not sufficient. It is essential to have a broader approach to involve the system and its maintenance since the conception. In this context, the developed design methodology suggests to prioritize the components impact on the operating costs. This prioritization is performed thanks to a defined importance factor. Then, multiple design options are evaluated by simulation in priority component. The selected options lead to reduce the operating costs. This work contains simulation results that illustrate the methods mentioned above. Moreover, a heavy vehicle sub-system is used as a test-case.