The main objective of this thesis is to assess the applicability of methods that are based on the employment of composite indicators when evaluating the 'sustainable development' and 'quality of live' indexes. The first issue observed in here is whether the composite indicators as such even represent a suitable tool for assessing the above mentioned area of analysis; if the answer is yes, then, secondly, under which conditions the composite indicators may be applied in the context of our analysis. After answering the questions above, it is crucial to find suitable methods for the particular steps of constructing the composite indicator for the sustainable development and quality of life categories, whereby it is also necessary to evaluate the advantages and disadvantages resulting from the application of the selected composite indicators for the purposes of the respective analysis. Within this thesis, the comparison of individual methods of constructing the indicators was performed by means of applying the individual indicators on the established set of data, as well as a subsequent comparison of results and the assessment of strengths and weaknesses of the individual methods has been done with respect to the factual side of the particular composite indicators (i.e. with respect to the sustainable development and quality of life in our case). Various composite indicators for the quality of life and sustainable development have already been established; the necessity of composing additional composite indicators for the above mentioned categories reflects the problematic nature of finding a suitable tool that would be generally accepted in this case. This thesis provides for relevant conclusions and recommendations that should contribute to establish a suitable approach towards the construction of composite indicators for the sustainable development and quality of life assessment. Furthermore, the thesis provides for the comparison of methods as employed in practical construction of composite indicators in our context with methods based on a professional theory. The professional theory/literature addresses and recommends certain methods for the construction of composite indicators in the relevant context, however, these methods are typically not applied in the practical construction of the most frequently/commonly used composite indicators for measuring the sustainable development and quality of life. The critical aspects that have been observed within comparison of the individual methods are transparency of calculation, interpretability of results, robustness of the composite indicator closely linked to the nature and character of the data, and the level of applicable compensation of the individual parameters within the respective indicator that is allowed by the particular aggregation mechanism employed. The thesis concludes on a rather questionable use of composite indicators in case of assessing the sustainable development, whereby deduces on recommending the application of composite indicators only in case of assessing the quality of life, which may also be understood as a part (sub-item) of the sustainable development and which is easier to be quantitatively expressed. In parallel, the circumstances of the quality of life are better to be compared across various items, e.g. regions. The results indicate that it is not possible to establish a uniform recommendation when selecting the most suitable method; in case of every construction of the particular composite indicator it is necessary to take into account the strengths and weaknesses of all the considered methods. At the same time, the results lead to consideration of relevancy of conclusions resulting from the evaluation of quality of life by means of composite indicators, especially by means of a single number.

Dans cette thèse est défendu l'intérêt d'évaluer la santé d'un système/objet industriel multi-composants à travers un bilan de santé multi-niveaux hiérarchiques. Elle a donc pour objet principal de justifier les éléments essentiels du concept de bilan de santé générique qui représente l'état réel d'un système sous la forme d'un vecteur d'indicateurs de différentes natures. Vis-à-vis de ce fondement, la thèse se focalise plus spécifiquement sur les fonctions de détection des anomalies-normalisation et agrégation d'indicateurs pour élaborer un index synthétique représentatif de l'état de santé global pour chaque élément du système. Il est ainsi proposé, une nouvelle approche de détection conditionnelle des anomalies. Cette approche a pour intérêt de quantifier la déviation pour chaque indicateur par rapport à son mode de comportement nominal tout en prenant en compte le contexte dans lequel évolue le système. Une extension à l'exploitation de l'intégrale de Choquet en tant qu'opérateur d'agrégation des indicateurs est aussi proposée. Cette extension concerne, d'une part, un processus d'apprentissage non supervisé des capacités pour le niveau le plus inférieur dans l'abstraction, à savoir celui des composants, et d'autre part, une approche de mise en oeuvre de leur inférence d'un niveau à l'autre. Ces propositions sont appliquées sur un moteur diesel de navire, système essentiel du projet BMCI du pôle MER-PACA dans lequel s'inscrit cette thèse / This work is addressing the health assessment of a multi-component system by means of multi-levels health check-up. Thus scientific Ph. D. objective aims to establish items of a generic health check-up concept. It focuses specifically on the functions of anomaly detection, normalization and aggregation of different indicators to develop a synthetic index representing the overall health status for each element within the system. In that way, it is proposed a new approach for detecting conditional anomalies. This approach has the advantage of quantifying the deviation for each indicator compared to its nominal behavior while taking into account the context in which the system operates. An extension of the Choquet integral used as an operator aggregating indicators is also proposed. This extension regards on the one hand, a process of an unsupervised learning of the capacity coefficients for the lowest level of abstraction, namely components level, and on the other hand, an approach to inference them from one level to another. These contributions are implemented on a ship diesel engine which is the most critical system for the BMCI project of the MER-PACA pole to which this thesis is attached