Knowledge management technology for integrated decision support systems in process industries
- Autores: Edrisi Muñoz Mata
- Directores de la Tesis: Luis Puigjaner Corbella (dir. tes.), Antoni Espuña Camarasa (dir. tes.)
- Lectura: En la Universitat Politècnica de Catalunya (UPC) ( España ) en 2011
- Idioma: inglés
- Tribunal Calificador de la Tesis: Bernt Lie (presid.), Moisès Graells Sobré (secret.), Dejan Gradisar (voc.), Rodolfo Gabriel Dondo (voc.), Pedro Miguel Gil Castro (voc.)
- Materias:
- Enlaces
- Tesis en acceso abierto en: TDX
- Resumen
Nowadays, factors such as globalization of trade, market uncertainty and fierce competition involve dwindling error margins in enterprises. Two key aspects for achieve it are the viability and the competitiveness of enterprises, which highly depend on the effectiveness for taking their decisions related to their manufacturing characteristics, such as economic efficiency, product quality, flexibility or reliability. For this reason, companies have taken the task, for many years, of develop better management information systems in order to help the decision makers to exploit data and models, with the final objective of discussing and improving decision-making. In this sense, decision support systems must be improved in order to deal with the large amount of available data and the heterogeneity of existing modeling approaches along the hierarchical levels in the enterprise structure. Hence, this thesis proposes the application of ontologies as a decision support tool, since they are increasingly seen as a key semantic technology for addressing heterogeneities and mitigating the problems they create and for enabling data mining by semantics-driven the knowledge processing. The aim of this thesis is to contribute to the development of decision support tools for the enterprise process industry. As a decision support tool, must be capable of become a robust model which interacts among the different decision hierarchical levels, providing a unified framework of data and information levels integration. On the other hand, this thesis also aims the improvement in the development of the ontologies. Firstly, a detailed state of the art about the different production process systems, knowledge management base on ontologies, as well as decision support systems is carried out. Based on this review, the specific thesis objectives are posed. Next, a methodology is proposed for the development and use of ontologies, based on the analysis and adaptation of previously existing methodologies. Such methodology is based on the improvement cycle (PSDA), allowing a better way to design, construct and apply domain ontologies. The second part of this thesis is devoted to the application of the different parts of the previously proposed methodology for the development of an ontological framework in the process industry domain concerning the strategic, tactical and operational decision levels. Next, the description of the decision areas in which the ontological framework is applied is presented. Namely, in the process control decision level, the coordination control is considered. Regarding scheduling decisions level, mathematical optimization approaches are applied. Finally, the distributed hierarchical decision level considers the mathematical optimization for decentralized supply chain networks is adopted. These decision areas and the performance of the proposed framework interaction are studied along the different case studies presented in the thesis. On the whole, this thesis represents a step forward toward the integration among the enterprise hierarchical levels, the process and enterprise standardization and improved procedures for decision-making. The aforementioned achievements are boosted by the application of semantic models, which are currently increasingly used.
