Data cleaning and preprocessing techniques for manufacturing processes
- Ana González Marcos
- Manuel Castejón Limas
- Joaquín Bienvenido Ordieres Meré
- Alpha Verónica Pernía Espinoza
Publisher: Asociación Española de Ingeniería de Proyectos (AEIPRO)
ISBN: 84-95809-22-2
Year of publication: 2005
Congress: CIDIP. Congreso Internacional de Ingeniería de Proyectos (8. 2004. Bilbao)
Type: Conference paper
Abstract
In spite of the fact that data mining methodologies are still infrequently used on a large scale, the may become extremely important to extract previously unknown and potentially useful knowledge from large data sets. The success of the knowledge discovery process, it is not possible without knowing the manufacturing process to which the data mining is applied. For example, this knowledge allows us to understand the importance of each variable. Also, as a previous step of the analysis and interpretation stage, it is necessary to detect and correct the corrupted data in order to make it easier to build precise and reliable models. Data preparation is a diverse and difficult issue. In this paper, we present data cleaning and pre-processing techniques applied to the particular case of a tinplate production line. The obtained results show the advantages of these methodologies based on data.