Les ouvrages hydrauliques – barrages et digues – sont des ouvrages de génie civil à risque. Leur rupture engendre des conséquences humaines et matérielles souvent dramatiques. Parmi eux, les barrages en remblai représentent une part importante du parc de barrages au niveau national comme mondial, auxquels s’ajoutent d’importants linéaires de digues en remblai fluviales et maritimes. La sécurité structurale de ces ouvrages est traditionnellement évaluée par des méthodes déterministes ou semi-probabilistes aux états-limites. Cependant, la réglementation française en matière d’ouvrages hydrauliques a récemment évolué en préconisant pour les grands barrages la réalisation d’études de dangers (EDD) basées sur les méthodes d’analyse de risques et impliquant l’utilisation de démarches probabilistes. Dans ce cadre, l’objectif principal de la thèse est de développer une démarche probabiliste pour l’évaluation de la fiabilité structurale des ouvrages hydrauliques en remblai vis-à-vis du mécanisme de glissement, qui constitue l’état-limite conditionnant la géométrie de ces ouvrages. Le développement d’une telle démarche nécessite de traiter trois questions scientifiques principales : · l’élaboration d’un modèle hydromécanique pour l’évaluation déterministe de la stabilité de l’ouvrage vis-à-vis du mécanisme de glissement ; · la modélisation probabiliste de la variabilité spatiale des propriétés mécaniques et hydrauliques des matériaux constituant le remblai ; · le couplage mécano-fiabiliste intégrant les modèles de variabilité spatiale au modèle hydromécanique. De nombreux travaux de recherche ont été réalisés sur ces questions et sont disponibles dans la littérature scientifique. Cependant, ils ne traitent qu’une partie des aspects de la problématique globale d’évaluation de la fiabilité et l’absence de recherches intégratrices est à déplorer. Notre travail, propose une démarche méthodologique complète intégrant l’ensemble des questions scientifiques, en mettant en oeuvre des démarches de modélisation hydraulique et mécanique s’appuyant sur des données réelles disponibles sur un barrage en remblai. La démarche générale développée est appliquée à un barrage bien documenté servant de cas d’étude. Le modèle hydromécanique utilise la méthode des éléments finis et est développé avec le code élément finis Cast3M ouvert et compatible avec un usage en recherche scientifique. Le modèle développé permet le calcul du facteur de sécurité de l’ouvrage par la méthode de réduction de paramètres en intégrant un champ de pressions interstitielles calculé en régime transitoire. La variabilité spatiale des paramètres des matériaux du remblai est modélisée à partir d’une analyse géostatistique des mesures de contrôle de compactage sous forme de champs aléatoires qui sont intégrés au modèle éléments finis. Un couplage mécano-fiabiliste entre le code de calcul Cast3M et le logiciel de fiabilité OpenTURNS permet au final de propager les incertitudes et d’évaluer la fiabilité de l’ouvrage. / Hydraulic works – dams and dikes – are risky civil engineering structures. Dramatic consequences in terms of human and material losses may be induced by their failure. Embankment dams represent an important part of the whole dams in France and the majority of dams worldwide, without considering the important lengths of fluvial and coastal dikes. The structural safety of such structures is traditionally evaluated with limit-state deterministic or semi-probabilistic methods. Nevertheless, French regulations regarding hydraulic works has recently evolved and now impose for all large dams the realization of risk assessment studies based on probabilistic approach. In this purpose, the principal objective of this thesis work is to develop a probabilistic approach to evaluate earth dam reliability concerning the sliding mechanism, which is one of the designing limit-state of such structures. Three scientific issues have to be treated for developing such approach: · elaboration of an hydro-mechanical model for the dam deterministic evaluation towards sliding mechanism; · probabilistic modeling of hydraulic and mechanical soil properties spatial variability; · mechanical-reliability coupling with integration of the spatial variability representations in the hydro-mechanical model. Some research studies already exist on these issues. However these works concern generally only a part of the general issue: the lack of global work is to be deplored. Our work proposes a global methodologic approach taking into account the whole scientific issues and applying hydraulic and mechanical modeling approaches based on real data available in the earth dam. The developed approach is then applied on a dam case study. Hydro-mechanical model uses finite element method and is developed with the user-free code Cast3M which is compatible for a research use. This code allows the safety factor calculation through the strength reduction technique with integration of the pore pressures field estimated in transient condition. The spatial variability of embankment properties is represented with random fields based on a geostatistical analysis of construction controls data. These random fields are then integrated into the finite element model. A coupling between the physical finite element code Cast3M and the reliability software OpenTURNS finally allows assessing the uncertainties propagation and the reliability evaluation of the studied dam.

Embankment dams are widely used as water-retaining structures through the world. Two principal structural failure modes of embankment dams are internal erosion and slope instability. The objective of this thesis is to investigate the feasibility of applying probabilistic methods in embankment dam assessment. Compared to deterministic methods, probabilistic methods considers the variability in material properties and the results are more assessable. Meanwhile, the derived sensitivity factors of the variables can be used to find the most influential one.Through a literature review, it is found that the difficulties in defining a limit state function for the full process of internal erosion for embankment dams hold back the application of reliability-based methods. However, reliability-based methods have been recognized as suitable for slope stability assessment.In this thesis, both deterministic and probabilistic calculations have been performed for a homogenous embankment dam. The deterministic calculation is carried out in Slope/W to first find out the most critical slip surface. The failure probability of this slip surface is estimated by both Monte Carlo simulations in Slope/W and FORM analysis in Comrel. Then, the 34 most critical slip surfaces from Slope/W are chosen to calculate the system reliability with simple bounds and applied integration. The results from the deterministic and probabilistic calculations showed that the studied dam has a higher risk of failure than allowed. In the system reliability calculation, simple bounds gives a wide range, especially the upper bounds. It was found that classification of different slip surfaces into different groups with respect to geometry and material was useful to simplify the calculations. Not much improvement in accuracy of the system probability of failure is found when increasing the numbers (from 1 to 5) of the most critical slip surfaces from each group. Even the combination of 1 slip surface from each group only gives an error of 6.5%. Categorizing slip surfaces before performing a system reliability analysis is a good way for simplification of the calculations. Due to this, the criteria used for categorization of the slip surfaces are of interest. In this work, it was found that the slip geometry in combination with the materials included in the slip surface constitute a possible way forward to do this. / Fyllningsdammar används ofta som dämmande konstruktioner runt om i världen. Två potentiella brottmoder för fyllningsdammar är inre erosion och släntinstabilitet.Syftet med detta examensarbete är att undersöka möjligheten att tillämpa probabilistiska metoder vid utvärdering av fyllningsdammars säkerhet för dessa brottmoder. Jämfört med deterministiska metoder betraktar probabilistiska metoder även variationen i materialegenskaper. Erhållna känslighetsfaktorer för ingående variabler kan även användas för att hitta de som har störst inverkan på det studerade problemet.I litteraturstudien framkom att det är svårt att definiera en gränsfunktion som beskriver inre erosion för fyllnadsdammar, vilket begränsar dess användbarhet med probabilistiska metoder. För analys av släntstabilitet är dock probabilistiska metoder användbara. Både deterministiska och probabilistiska beräkningar av släntstabiliteten för en fyllnadsdamm har genomförts inom ramen för detta arbete. De deterministiska beräkningarna har utförts med programmet Slope/W, där den mest kritiska glidytan först har analyserats. Brottsannolikheten för dammen har beräknats med både Monte Carlo-simulering i Slope/W och FORM-analys i Comrel. En begränsning med att enbart beräkna brottsannolikheten för den mest kritiska glidytan är att brottsannolikheten kan underskattas då inverkan från andra potentiella glidytor inte beaktas. De potentiella glidytorna kan betraktas som ett seriesystem, där glidytorna är delvis korrelerade med varandra. För att studera denna fråga valdes de 34 mest kritiska glidytorna från Slope/W ut för att beräkna systemets tillförlitlighet. Resultaten från de deterministiska och probabilistiska beräkningarna visade att den studerade dammen hade en oacceptabel brottsannolikhet. I beräkningarna av gränserna för systemets brottsannolikhet visade resultaten att brottsannolikheten kan variera stort beroende på korrelationen mellan glidytorna. Genom att klassificera glidytorna i olika grupper med hänsyn till geometri och ingående material kan beräkningarna för systemets brottsannolikhet förenklas. Resultaten visade att noggrannheten i beräkningarna för brottsannolikheten av systemet inte förbättrades i någon större utsträckning när antalet valda glidytor (från 1 till 5) från varje grupp av likartade glidytor inkluderades i beräkningen. Kombinationen av 1 glidyta från varje grupp gav endast ett fel på 6,5% jämfört med om alla 34 glidytorna inkluderades. Kategorisering av glidytor av samma karaktär i olika grupper rekommenderas därför att genomföras innan systemets tillförlitlighet analyseras. I detta arbete framkom att glidytan geometri i kombination med ingående material i glidytan utgör ett lämpligt kriterium för att göra denna indelning.

Embankment dams are widely used as water-retaining structures through the world. Two principal structural failure modes of embankment dams are internal erosion and slope instability. The objective of this thesis is to investigate the feasibility of applying probabilistic methods in embankment dam assessment. Compared to deterministic methods, probabilistic methods considers the variability in material properties and the results are more assessable. Meanwhile, the derived sensitivity factors of the variables can be used to find the most influential one.Through a literature review, it is found that the difficulties in defining a limit state function for the full process of internal erosion for embankment dams hold back the application of reliability-based methods. However, reliability-based methods have been recognized as suitable for slope stability assessment.In this thesis, both deterministic and probabilistic calculations have been performed for a homogenous embankment dam. The deterministic calculation is carried out in Slope/W to first find out the most critical slip surface. The failure probability of this slip surface is estimated by both Monte Carlo simulations in Slope/W and FORM analysis in Comrel. Then, the 34 most critical slip surfaces from Slope/W are chosen to calculate the system reliability with simple bounds and applied integration. The results from the deterministic and probabilistic calculations showed that the studied dam has a higher risk of failure than allowed. In the system reliability calculation, simple bounds gives a wide range, especially the upper bounds. It was found that classification of different slip surfaces into different groups with respect to geometry and material was useful to simplify the calculations. Not much improvement in accuracy of the system probability of failure is found when increasing the numbers (from 1 to 5) of the most critical slip surfaces from each group. Even the combination of 1 slip surface from each group only gives an error of 6.5%. Categorizing slip surfaces before performing a system reliability analysis is a good way for simplification of the calculations. Due to this, the criteria used for categorization of the slip surfaces are of interest. In this work, it was found that the slip geometry in combination with the materials included in the slip surface constitute a possible way forward to do this.

La rupture des barrages et des digues en terre est susceptible d’avoir des conséquences importantes en aval et dans les zones protégées. Nous avons mené une analyse hydro-mécanique de la formation et du développement de brèche destinée à améliorer la précision des approches actuelles. Dans le cas de l’érosion interne, un modèle d’agrandissement de conduit a été proposé pour modéliser la rupture des digues et barrages en terre par écoulement concentré. Ce modèle tient compte de l’érosion du sol par un écoulement de conduit turbulent. En ce qui concerne l’élargissement de la brèche, un modèle simple d’estimation de la longueur critique d’afouillement par “headcut” est proposé, fonction de la résistance du sol à la traction. Ce modèle est en bon accord avec les résultats numériques obtenus par équilibre limite. Un modèle simplifé pour la contrainte latérale sur les parois de la brèche a ensuite été proposé. Ce modèle tient compte des écoulements secondaires. Il montre que la contrainte latérale peut être plus grande que la contrainte de fond, suivant la situation. Finalement, une expérimentation de grande dimension de rupture de barrage par erosion de conduit a été modélisée avec le modèle d’érosion de conduit proposé, et quelques composantes des modèles d’élargissement de brèche proposés. L’élargissement de la brèche par paliers a été reproduite au début du processus. Les perspectives de validation et d'application des modèles proposés sont discutées. / The failure of embankment dams and levees can have serious consequence in floodplains. Hydro-mechanical analyses of the breach processes were conducted to develop the accurate estimation of the failure of embankment dams and levees. Considering the internal erosion process, a pipe enlargement model was proposed to simulate the failure of embankment dams and levees by concentrated leak erosion. In this model, the turbulent pipe flow with erosion mechanism was employed as well as the soil erosion law. Considering the breach enlargement process, a simple headcut migration model based on the soil tensile strength was presented to simulate the critical length of the headcut. Good agreements were obtained by comparing with the limit equilibrium numerical model. A simple model was eventually proposed to simulate the lateral shear stress on the breach sides, accounting for the secondary flow. The lateral shear stress can be greater than the bottom shear stress, depending on the situation. . Finally, a large-scale test of dam failure was simulated by using the pipe enlargement and some components of the breach widening models proposed. The simulation of the pipe enlargement process had good agreement with the measured data. Both of the pipe diameter and the discharge flow were well simulated. The stepwise enlargement of the breach width was also well simulated at the beginning of the breach widening process. Validation and application prospects of the proposed models are discussed.

Owners of dams in the Czech Republic are obliged to ensure the safety management. Part of it is measurement that covers comparing of measured values with limit values (threshold limits). Czech legislation provides principles of safety management e.g. regular observation and monitoring, their periodicity or measured variables. Expectation of reducing the probability of failure, automatic data acquisition system and dam ageing are reasons for adjusting limit values systematically. The aim of this thesis is to specify the method of determination the limit values of displacement for making a vertical survey of embankment dams. The method is demonstrated on the case study of Moravka dam. Sensitivity analysis of hydro-mechanical coupled model of embankment dam is included.