This work aims at introducing Bayesian network-based classifiers to predict parameters defining surface roughness (Ra), when texture is produced by Electro Discharge Texturing (EDT) because the non-linearity, instabilities and also somewhat expensive experimentation of the process, robust and reliable algorithms to deal with all the factors that are difficult to characterize are necessary to provide appropriate prediction techniques. A series of experiments were conducted using a modified EDM machine ALIC-1 with traverse motions, providing the means to produce plane surface textures. With data collected were constructed models using Bayesian networks, the validation tests showed acceptable behavior within the operating range. Consistent results were obtained with the physical phenomena governing the process and shows that it is possible to find a surface roughness with particular specifications. Key words: Surface roughness, Bayesian networks, EDT, EDM.
|Title of host publication||Métodos Numéricos y sus Aplicaciones en Diferentes Areas|
|Number of pages||8|
|Publication status||Published - 1 Jan 2013|
|Event||IX Congreso Colombiano de Métodos Numéricos: Simulación en Ciencias y Aplicaciones Industriales, IX CCMN 2013 - |
Duration: 1 Jan 2013 → …
|Conference||IX Congreso Colombiano de Métodos Numéricos: Simulación en Ciencias y Aplicaciones Industriales, IX CCMN 2013|
|Period||1/01/13 → …|