Abstract
Mechanical properties are the attributes that measure the faculty of a metal to withstand several loads and tensions. In particular, ultimate tensile strength is the force a material can resist until it breaks. This property is one of the variables to control in the foundry process. The only way to examine this feature is to apply destructive inspections that make the casting invalid with the subsequent cost increment. Modelling the foundry process as an expert knowledge cloud allows machine-learning algorithms to forecast the value of a certain variable; in this case, the probability of a certain value of ultimate tensile strength for a foundry casting. Nevertheless, this approach needs to label every instance in the training dataset for generating the model that can foresee the value of ultimate tensile strength. In this paper, we present a new approach for detecting castings with an invalid ultimate tensile strength value based on anomaly detection methods. This approach represents correct castings as feature vectors of information extracted from the foundry process. A casting is then classified as correct or not correct by measuring its deviation to the representation of normality (correct castings). We show that this method is able to reduce the cost and the time of the tests currently used in foundries.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Sertucha, J., Loizaga, A., Suárez, R.: Improvement opportunities for simulation tools. In: Proceedings of the 16th European Conference and Exhibition on Digital Simulation for Virtual Engineering (2006) (invited talk)
Nieves, J., Santos, I., Penya, Y.K., Rojas, S., Salazar, M., Bringas, P.G.: Mechanical properties prediction in high-precision foundry production. In: Proceedings of the 7th IEEE International Conference on Industrial Informatics (INDIN 2009), pp. 31–36 (2009)
Nieves, J., Santos, I., Penya, Y.K., Brezo, F., Bringas, P.G.: Enhanced foundry production control. In: Bringas, P.G., Hameurlain, A., Quirchmayr, G. (eds.) DEXA 2010. LNCS, vol. 6261, pp. 213–220. Springer, Heidelberg (2010)
Santos, I., Nieves, J., Penya, Y.K., Bringas, P.G.: Machine-learning-based mechanical properties prediction in foundry production. In: Proceedings of ICROS-SICE International Joint Conference (ICCAS-SICE), pp. 4536–4541 (2009)
Nieves, J., Santos, I., Bringas, P.: Overcoming data gathering errors for the prediction of mechanical properties on high precision foundries. In: World Automation Congress (WAC), pp. 1–6. IEEE, Los Alamitos (2010)
Gonzaga-Cinco, R., Fernández-Carrasquilla, J.: Mecanical properties dependency on chemical composition of spheroidal graphite cast iron. Revista de Metalurgia 42, 91–102 (2006)
Lung, C.W., March, N.H.: Mechanical Properties of Metals: Atomistic and Fractal Continuum Approaches. World Scientific Pub. Co. Inc., Singapore (1992)
Larrañaga, P., Sertucha, J., Suárez, R.: Análisis del proceso de solidificación en fundiciones grafÃticas esferoidales. Revista de Metalurgia 42(4), 244–255 (2006)
Santos, I., Nieves, J., Penya, Y.K., Bringas, P.G.: Optimising machine-learning-based fault prediction in foundry production. In: Omatu, S., Rocha, M.P., Bravo, J., Fernández, F., Corchado, E., Bustillo, A., Corchado, J.M. (eds.) IWANN 2009. LNCS, vol. 5518, pp. 554–561. Springer, Heidelberg (2009)
Santos, I., Nieves, J., Bringas, P., Penya, Y.: Machine-learning-based defect prediction in highprecision foundry production. In: Becker, L.M. (ed.) Structural Steel and Castings: Shapes and Standards, Properties and Applications, pp. 259–276. Nova Publishers (2010)
Nieves, J., Santos, I., Penya, Y.K., Brezo, F., Bringas, P.G.: Enhanced foundry production control. In: Bringas, P.G., Hameurlain, A., Quirchmayr, G. (eds.) DEXA 2010. LNCS, vol. 6261, pp. 213–220. Springer, Heidelberg (2010)
Santos, I., Nieves, J., Bringas, P.: Enhancing fault prediction on automatic foundry processes. In: World Automation Congress (WAC), pp. 1–6. IEEE, Los Alamitos (2010)
Santos, I., Nieves, J., Penya, Y.K., Bringas, P.G.: Towards noise and error reduction on foundry data gathering processes. In: Proceedings of the International Symposium on Industrial Electronics (ISIE), pp. 1765–1770 (2010)
Kent, J.: Information gain and a general measure of correlation. Biometrika 70(1), 163–173 (1983)
Tata, S., Patel, J.: Estimating the Selectivity of tf-idf based Cosine Similarity Predicates. SIGMOD Record 36(2), 75–80 (2007)
Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the International Joint Conference on Artificial Intelligence, vol. 14, pp. 1137–1145 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Santos, I., Nieves, J., Ugarte-Pedrero, X., Bringas, P.G. (2011). Anomaly Detection for the Prediction of Ultimate Tensile Strength in Iron Casting Production. In: Hameurlain, A., Liddle, S.W., Schewe, KD., Zhou, X. (eds) Database and Expert Systems Applications. DEXA 2011. Lecture Notes in Computer Science, vol 6861. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23091-2_46
Download citation
DOI: https://doi.org/10.1007/978-3-642-23091-2_46
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23090-5
Online ISBN: 978-3-642-23091-2
eBook Packages: Computer ScienceComputer Science (R0)