Browsing by Keyword "Data mining"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Intelligent maintenance for industrial processes, a case study on cold stamping(Springer Verlag, 2018) Boto, Fernando; Lizuain, Zigor; Cortadi, Alberto Jimenez; Perez Garcia, Hilde; Alfonso-Cendon, Javier; Sanchez Gonzalez, Lidia; Corchado, Emilio; Quintian, Hector; Tecnalia Research & Innovation; FACTORYThe correct diagnosis of tool breakage is fundamental to improve productivity, minimizing the number of unproductive hours and avoiding expensive repairs. The use of Data Mining techniques provides a significant added value in terms of improvements in the robustness, reliability and flexibility of the monitored systems. In this work, a general view of a diagnosis and prognosis of tool breakage in Industrial Processes is proposed. The important issues identified will be analyzed: filtering, process characterization and data based modeling. A case study has been implemented to carry out the prognosis of tool breakage in the cold stamping process. The results provided are qualitative trends and hypothesis to perform the prognosis. Although a validation in real operation is needed, these results are promising and demonstrate the goodness of using these type of techniques in real processes.Item An intelligent process model: predicting springback in single point incremental forming(2015-02) Khan, Muhamad S.; Coenen, Frans; Dixon, Clare; El-Salhi, Subhieh; Penalva, Mariluz; Rivero, Asun; FABRIC_INTEL; SGThis paper proposes an intelligent process model (IPM), founded on the concept of data mining, for predicting springback in the context of sheet metal forming, in particular, single point incremental forming (SPIF). A limitation with the SPIF process is that the application of the process results in geometric deviations, which means that the resulting shape is not necessarily the desired shape. Errors are introduced in a nonlinear manner for a variety of reasons, but a contributor is the geometry of the desired shape. A local geometry matrix (LGM) representation is used that allows the capture of local geometries in such a way that they are suited to input to a classifier generator. It is demonstrated that a rule-based classifier can be used to train the classifier and generate a classification model. The resulting model can then be used to predict errors with respect to new shapes so that some correction strategy can be applied. The reported evaluation of the proposed IPM indicates that very promising results can be obtained with regard to reducing the shape deviations due to springback.