La thématique abordée porte sur la métrologie virtuelle (VM) pour estimer les données manquantes durant les processus de fabrications des semi-conducteurs. L'utilisation de la métrologie virtuelle permet également de fournir les mesures logicielles (estimations) des sorties pour alimenter les régulateurs run-to-run (R2R) mis en place pour le contrôle de la qualité des produits fabriqués. Pour remédier aux problèmes liés au retard de mesures causé par l'échantillonnage statique imposé par la stratégie et les équipements mis en place, notre contribution dans cette thèse est d'introduire la notion de l'échantillonnage dynamique intelligent. Cette stratégie est basée sur un algorithme qui prend en compte la condition de voisinage permettant d'éviter la mesure réelle même si l'échantillonnage statique l'exige. Cela permet de réduire le nombre de mesures réelles, le temps du cycle et le coût de production. Cette approche est assurée par un module de métrologie virtuelle (VM) que nous avons développé et qui peut être intégré dans une boucle de régulation R2R. Les résultats obtenus ont été validés sur des exemples académiques et sur des données réelles fournies par notre partenaire STMicroelectronics de Rousset concernant un processus chemical mechanical planarization (CMP). Ces données réelles ont permis également de valider les résultats obtenus de la métrologie virtuelle pour les fournir ensuite aux régulateurs R2R (ayant besoin de l'estimation de ces données). / The addressed work is about the virtual metrology (VM) for estimating missing data during semiconductor manufacturing processes. The use of virtual metrology tool also makes it possible to provide the software measurements (estimations) of the outputs to feed the run-to-run (R2R) controllers set up for the quality control of the manufactured products.To address these issues related to the delay of measurements caused by the static sampling imposed by the strategy and the equipments put in place, our contribution in this thesis is to introduce the notion of the dynamic dynamic sampling. This strategy is based on an algorithm that considers the neighborhood condition to avoid the actual measurement even if the static sampling requires it. This reduces the number of actual measurements, the cycle time and the cost of production. This approach is provided by a virtual metrology module (VM) that we have developed and which can be integrated into an R2R control loop. The obtained results were validated on academic examples and on real data provided by our partner STMicroelectronics of Rousset from a chemical mechanical planarization (CMP) process. This real data also enabled the results obtained from the virtual metrology to be validated and then supplied to the R2R regulators (who need the estimation of these data).

Distance sampling is one of the most commonly used methods for estimating density and abundance. Conventional methods are based on the distances of detected animals from the center of point transects or the center line of line transects. These distances are used to model a detection function: the probability of detecting an animal, given its distance from the line or point. The probability of detecting an animal in the covered area is given by the mean value of the detection function with respect to the available distances to be detected. Given this probability, a Horvitz-Thompson- like estimator of abundance for the covered area follows, hence using a model-based framework. Inferences for the wider survey region are justified using the survey design. Conventional distance sampling methods are based on a set of assumptions. In this thesis I present results that extend distance sampling on two fronts. Firstly, estimators are derived for situations in which there is measurement error in the distances. These estimators use information about the measurement error in two ways: (1) a biased estimator based on the contaminated distances is multiplied by an appropriate correction factor, which is a function of the errors (PDF approach), and (2) cast into a likelihood framework that allows parameter estimation in the presence of measurement error (likelihood approach). Secondly, methods are developed that relax the conventional assumption that the distribution of animals is independent of distance from the lines or points (usually guaranteed by appropriate survey design). In particular, the new methods deal with the case where animal density gradients are caused by the use of non-random sampler allocation, for example transects placed along linear features such as roads or streams. This is dealt with separately for line and point transects, and at a later stage an approach for combining the two is presented. A considerable number of simulations and example analysis illustrate the performance of the proposed methods.