Tecnologia em Metalurgia, Materiais e Mineração
https://tecnologiammm.com.br/article/doi/10.4322/tmm.00502007
Tecnologia em Metalurgia, Materiais e Mineração
Artigo Original

APLICAÇÃO DE TÉCNICAS DE INTELIGÊNCIA COMPUTACIONAL PARA PREDIÇÃO DE PROPRIEDADES MECÂNICAS DE AÇOS DE ALTA RESISTÊNCIA MICROLIGADOS

USING OF COMPUTATIONAL INTELLIGENCE METHODS FOR MECHANICAL PROPERTIES PREDICTION OF HSLA STEELS

Takahashi, Hiroshi Jorge; Rabelo, Gláucio Bórtoli da C.; Teixeira, Roselito de Albuquerque

Downloads: 3
Views: 954

Resumo

A obtenção de propriedades mecânicas especificadas para os produtos é um aspecto fundamental na siderurgia. A abordagem fenomenológica para a modelagem das propriedades mecânicas não tem apresentado resultados satisfatórios, em função da quantidade e diversidade das variáveis e processos envolvidos. Nesse contexto, pelas suas características, as técnicas de inteligência computacional têm sido utilizadas como alternativas viáveis. Este trabalho apresenta o desenvolvimento e a implantação, na Usiminas, de uma ferramenta de apoio à decisão baseada nas técnicas de inteligência computacional, para a predição de propriedades mecânicas de aços de alta resistência microligados, laminados a frio e revestidos por imersão a quente.

Palavras-chave

Rede neural artificial, Sistema híbrido, Aço microligado, Propriedades mecânicas

Abstract

The attainment of desired mechanical properties is a crucial aspect for steelmaking industries. Traditional physical modeling approaches have not been satisfactory, due to the complicated nature of the processes, very complex and multidimensional ones. In this context, by their characteristics, computational intelligence methods have been used and considered as a viable alternative. This paper describes the development and the implementation of a decision support tool for mechanical properties prediction of coated high strength low alloy steel at Usiminas steelworks in Brazil.

Keywords

Artificial neural network, Hybrid neuro-fuzzy systems, HSLA, Mechanical properties

Referências

1 MYLLYKOSKI, P.; LARKIOLA, J.; NYLANDER, J. Development of prediction model for mechanical properties of batch annealed thin steel strip by using artificial neural network modelling. Journal of Materials Processing Technology, v. 60, n. 1, p. 399-404, June 1996.

2 MAHFOUF, M.; CHEN, M.; LINKENS, D.A. Design of heat-treated alloy steels using intelligent multi-objective optimization. ISIJ International, v. 45, n. 5, p. 694-9, Jan. 2005.

3 MYLLYKOSKI, P. A study on the causes of deviation in mechanical properties of thin steel sheets. Journal of Materials Processing Technology, v. 79, n. 1, p. 9-13, July 1998.

4 DATTA, S.; BANERJEE, M.K. Fuzzy modelling of strength-composition-process parameter relationships of HSLA steels. Materials and Manufacturing Processes, v. 20, n. 5, p.761-776. September 2005.

5 JONES, D.M.; WATTON, J.; BROWN, K.J. Comparison of hot rolled steel mechanical property prediction models using linear multiple regression, non-linear multiple regression and non-linear artificial neural networks. Ironmaking and Steelmaking, v. 32, n. 5, p.435-42, Oct. 2005.

6 GOLODNIKOV, A.; MACHERET, Y.; TRINDADE, A. A.; URYASEV, S.; ZRAZHEVSKY, G. Statistical modelling of composition and processing parameters for alloy development. Modelling and Simulation in Materials Science and Engineering, v. 13, no. 4, p. 633-44, June 2005.

7 Haykin, S. Neural networks: a comprehensive foundation. 2. ed. New Jersey: Prentice Hall, 1999.

8 WEIGEND, A.S.; HUBERMAN, B.; RUMELHART, D.E. Predicting the future: a connectionist approach. International Journal of Neural Systems, v. 1, n. 3, p. 193-209, 1990.

9 Mackay, D.J.C. Bayesian interpolation. Neural Computation, v. 4, n. 3, p. 415-47, May 1992.

10 HASSIBI, B.; STORK, D.G.; WOLFF, G.J. Optimal brain surgeon and general network pruning. In: IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, 1993, San Francisco, CA. Proceedings… San Francisco, CA., IEEE Press, 1993. p. 293-9.

11 PERRONE, M.P.; COOPER, L.N. When networks disagree: Ensemble methods for hybrid neural networks. In: MAMMONE, J. (editor). Artificial neural networks for speech and vision. London: Chapman and Hall, 1993. p. 126-42

12 ZADEH, L.A. Fuzzy sets. Information and Control, v. 8, n. 3, p. 338-53, June 1965.

13 JANG, R.J. Anfis: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, v. 23, n. 3, p. 665-85, May/June 1993.

14 ABRAHAM, A. Neuro fuzzy systems: state-of-the-art modeling techniques. Lecture Notes in Computer Science, v. 2084, p. 269-76, 2001.

15 JANG, R.J.; SUN, C.; MIZUTANI, E. Neuro-fuzzy and soft computing. New Jersey: Prentice Hall, 1997.

16 CHEN, M. Y.; LINKENS, D.A. Hybrid fuzzy modelling using simulated annealing and application to materials property prediction. In: INTERNATIONAL CONFERENCE ON INTELLIGENT PROCESSING AND MANUFACTURING MATERIALS, 2., Honolulu, 1999. Proceedings… New York: IEEE Press, 1999. v. 1, p. 395-400.

17 TENNER, J.; LINKENS, D.A.; MORRIS, P.F.; BAILEY, T.J. Prediction of mechanical properties in steel heat treatment process using neural networks. Ironmaking and Steelmaking, v. 28, n. 1, p. 15-22, Feb. 2001.

18 YANG, Y.; LINKENS, D.A. Steel yield strength prediction using ensemble model - performance improvement over single neural network model. In: INTERNATIONAL CONFERENCE ON INTELLIGENT PROCESSING AND MANUFACTURING OF MATERIALS, 3., Richmond, 2001. Proceedings… [S.l.]:: CRC Press, 2001. v. 1, p. 335-46.

19 JARREL, M.G. A comparison of two procedures, the Mahalanobis distance and the Andrews-Pregibon statistic, for identifying multivariate outliers. Research in the Schools, v. 1, n. 1, p. 49-58, 1994.

20 HAWKINS, S.; HE, H.; WILLIAMS, G.J.; BAXTER, R.A. Outlier detection using replicator neural networks. Lecture Notes in Computer Science, v. 2454, p. 170-80, Sept. 2002.

21 FERNANDES, R.C. O efeito da temperatura de encharque no recozimento contínuo e das deformações na laminação de encruamento sobre as propriedades mecânicas de um aço microligado laminado a frio. 2007. 93 p. (Dissertação de Mestrado - Engenharia Metalúrgica e de Minas) – Universidade Federal de Minas Gerais, Belo Horizonte, 2007.

22 MAZZATORTA, P.; BENFENATI, E.; NEAGU, C.D.; GINI, G. Tuning neural and fuzzy-neural networks for toxicity modeling. Journal of Chemical Information and Computer Sciences, v. 43, n. 2, p.513-8. Mar. 2003.
588696be7f8c9dd9008b469b 1573492069 Articles
Links & Downloads

Tecnol. Metal. Mater. Min.

Share this page
Page Sections