<< Volver atrás

Tesis:

Knowledge Management framework based on an Agents Network to support Continuous Improvement in Manufacturing integrating Case-Based Reasoning and Product Lifecycle Management

  • Autor: CAMARILLO GONZÁLEZ, Alvaro

  • Título: Knowledge Management framework based on an Agents Network to support Continuous Improvement in Manufacturing integrating Case-Based Reasoning and Product Lifecycle Management

  • Fecha: 2018

  • Materia: Sin materia definida

  • Escuela: E.T.S. DE INGENIEROS INDUSTRIALES

  • Departamentos: INGENIERIA MECANICA

  • Acceso electrónico: http://oa.upm.es/53989/

  • Director/a 1º: RÍOS CHUECO, Jose
  • Director/a 2º: ALTHOFF, Klaus-Dieter

  • Resumen: Manufacturing processes have problems that have to be solved systematically to reach and exceed the defined production targets. These problems use to be analyzed and solved by teams with the support of different methodologies working directly in the shopfloor. This Thesis proposes a system to support the Continuous Improvement Process (CIP) at shopfloor level of manufacturing plants in multinational companies by capturing and reusing easily the knowledge generated in the process of Manufacturing Problem Solving (MPS). This Thesis presents a novel ontology to represent knowledge generated during the resolution of Overall Equipment Effectiveness (OEE) problems at shopfloor level of any kind of manufacturing production plants. This ontology has been used to build a Knowledge Management (KM) system that supports CIP in multinational companies by capturing and reusing the knowledge generated in the process of MPS. The architecture of this system integrates the 8D method, as structured method to guide the resolution of problems step by step, Case-Based Reasoning (CBR) on an agent-based distributed architecture, as repository of cases and artificial intelligence application to search for similar manufacturing problem cases collected previously in multiple locations, and a Product Lifecycle Management (PLM) system, as automatic source of extended problem context information (i.e. Products, Processes and Resources (PPR)) that will enrich the similarity calculation of the CBR application. Process Failure Mode and Effect Analysis (PFMEA) is used both as root model to create an ontology, on which the system is built, and as source of the initial set of cases to feed the CBR application. A prototype of this system was developed and tested in Exide Technologies, a manufacturing multinational company provider of electrical energy storage solutions for transportation and industrial markets. The results collected in two different manufacturing plants of this company show the feasibility and validate the conceptual proposal presented in this Thesis. The development proposed in this Thesis allows also setting the foundation to carry out further works to extend and improve the presented conceptual framework.