Self-Organizing-Maps en el estudio del concreto de alto rendimiento

• Autor: Moromi Nakata y Colls., Isabel
• Formato: artículo
• Fecha de Publicación: 2018
• Institución: Centro de Preparación para la Ciencia y Tecnología
• Repositorio: ECIPERÚ
• Lenguaje: español
• OAI Identifier: oai:revistas.eciperu.net:article/44
• Enlace del recurso: https://revistas.eciperu.net/index.php/ECIPERU/article/view/44
• Nivel de acceso: acceso abierto
• Materia: Concreto de alta resistencia; microsílice; redes neuronales; base de datos; High-strength concrete; microsilica; neural networks; database

The manufacture of this type of concrete is carried out taking into account the selection and characterization of materials to produce a high concrete compressive strength and mix designs suitable for these purposes. The materials used are hydraulic Portland cement Type I, fine and coarse aggregates. It follows the design of mixed methods in ACI 211.4R-93. Be added the microsílices, also superplasticizers additives which may reduce demand for water and cement content and can produce concrete with low water-cement ratio, high strength and normal or high workability. On the other hand there is the use of neural networks called Self-Organizing-Maps (RNSOM) that are not supervised by a single layer networks. The objective in this part of the work is to create an enabling RNSOM form groups or clusters of samples from manufacturing variables without involving resistance and tensile strength of the specimens and compare these results with larger groups of probes lower resistance or resistance with time and designs that are optimal.