| Revista: | Brazilian journal of chemical engineering |
| Base de datos: | PERIÓDICA |
| Número de sistema: | 000308981 |
| ISSN: | 0104-6632 |
| Autores: | Andrade, M.C.V1 Nascimento, C. A. O2 Migliavacca, S. C. P3 |
| Instituciones: | 1Centro Tecnologico da Marinha, Sao Paulo. Brasil 2Universidade de Sao Paulo, Escola Politecnica, Sao Paulo. Brasil 3Comissao Nacional de Energia Nuclear, Instituto de Pesquisas Energeticas e Nucleares, Sao Paulo. Brasil |
| Año: | 2005 |
| Periodo: | Sep |
| Volumen: | 22 |
| Número: | 3 |
| Paginación: | 389-400 |
| País: | Brasil |
| Idioma: | Inglés |
| Tipo de documento: | Artículo |
| Enfoque: | Experimental |
| Resumen en inglés | Isotope separation with a gas centrifuge is a very complex process. Development and optimization of a gas centrifuge requires experimentation. These data contain experimental errors, and like other experimental data, there may be some gross errors, also known as outliers. The detection of outliers in gas centrifuge experimental data is quite complicated because there is not enough repetition for precise statistical determination and the physical equations may be applied only to control of the mass flow. Moreover, the concentrations are poorly predicted by phenomenological models. This paper presents the application of a three-layer feed-forward neural network to the detection of outliers in analysis of performed on a very extensive experiment |
| Disciplinas: | Química |
| Palabras clave: | Ingeniería química, Separación isotópica, Centrifugación de gas, Uranio, Detección de valores desviados, Redes neuronales |
| Keyword: | Chemistry, Chemical engineering, Isotopic separation, Gas centrifugation, Uranium, Outlier detection, Neural networks |
| Texto completo: | Texto completo (Ver HTML) |
