Abstract
Artificial Neural Network (ANN) is an important technique for modeling and optimization in engineering design. It is very suitable in modeling as it needs only the information based on relationship between the input and the output related to the problem. For further improvement in modeling, a priori knowledge about the problem such as an empirical formula, an equivalent circuit model, and a semi-analytical equation is directly embedded in ANN structure through a knowledge based modeling strategy. Three-step modeling strategy that exploits knowledge based techniques is developed to improve some properties of conventional ANN modeling such as accuracy and data requirement. All these improvements ensure better accuracy with less time consumption compared to conventional ANN modeling. The necessary knowledge in this strategy is generated in the first step through conventional ANN. Then this knowledge is embedded in the new ANN model for the second step. Final model is constructed by incorporating the existing knowledge obtained by the second step. Therefore each model generates better accuracy than previous model. Conventional ANN, prior knowledge input, and prior knowledge input with difference techniques are used to improve accuracy, time consumption, and data requirement of the modeling in three-step modeling strategy. The efficiency of three-step modeling strategy is demonstrated on the nonlinear function modeling and the high dimensional shape reconstruction problem.
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
References
Bandler, J.W., Cheng, Q.S., Dakroury, S.A., Mohamed, A.S., Bakr, M.H., Madsen, K., Sondergaard, J.: Space mapping: The state of the artc. IEEE Trans. Microw. Theory Tech. 52(1), 337–361 (2004)
Burrascano, P., Fiori, S., Mongiardo, M.: A review artificial neural networks applications in microwave computer-aided design. Int. J. RF Microw. Comput. Aided Eng. 9(3), 158–174 (1999)l
Devabhaktuni, V.K., Chattaraj, B., Yagoub, M.C.E., Zhang, Q.J.: Advanced microwave modeling framework exploiting automatic model generation, knowledge neural networks, and space mapping. IEEE Trans. Microw. Theory Tech. 51(7), 1822–1833 (2003)
Haykin, S.: Neural network - a comprehensive foundation, 2nd edn. Printice Hall, New Jersey (1999)
Koziel, S., Bandler, J.W.: Modeling of microwave devices with space mapping and radial basis functions. Int. J. Numer. Model Electron. Netw. Dev. Fields 21(1–2), 187–203 (2008)
Koziel, S., Leifsson, L. (ed.): Surrogate-Based Modeling and Optimization. Springer, New York (2013)
Rayas-Sanchez, J.E.: Em-based optimization of microwave circuits using artificial neural networks: the state-of-the-artc. IEEE Trans. Microw. Theory Tech. 52(1), 420–435 (2004)
Simsek, M.: Developing 3-step modeling strategy exploiting knowledge based techniques. In: The 20th European Conference on Circuit theory and Design, Linkoping, 29–31 August 2011
Simsek, M.: The reconstruction of shape with 3-step modeling strategy. In: Scientific Computing in Electrical Engineering, ETH Zurich and ABB Corporate Research, Switzerland, 11–14 September 2012
Simsek, M., Sengor, N.S.: A knowledge-based neuromodeling using space mapping technique: compound space mapping-based neuromodeling. Int. J. Numer. Model Electron. Netw. Dev. Fields 21(1–2), 133–149 (2008)
Simsek, M., Sengor,N.S.: An efficient inverse ANN modeling approach using prior knowledge input with difference method. In: The European Conference on Circuit theory and Design, Antalya, 23–27 August 2009
Simsek, M., Sengor, N.S.: Solving inverse problems by space mapping with inverse difference method. In: Roos, J., Costa, L.R.J. (eds.) Scientific Computing in Electrical Engineering SCEE 2008, Mathematics in Industry, vol. 14, pp. 453–460. Springer, Berlin (2010)
Simsek, M., Sengor, N.S.: The efficiency of difference mapping in space mapping-based optimization. In: Koziel, S., Leifsson, L. (eds.) Surrogate-Based Modeling and Optimization, pp. 99–120. Springer, New York (2013)
Simsek, M., Tezel, N.S.: The reconstruction of shape and impedance exploiting space mapping with inverse difference method. IEEE Trans. Antenna Propag. 60(4), 1868–187 (2012)
Simsek, M., Zhang, Q.J., Kabir, H., Cao, Y., Sengor, N.S.: The recent developments in knowledge based neural modeling. Proc. Comput. Sci. 1(1), 1315–1324 (2010)
Simsek, M., Zhang, Q.J., Kabir, H., Cao, Y., Sengor, N.S.: The recent developments in microwave design. Int. J. Math. Model. Numer. Optim. 2(2), 213–228 (2011)
Sondergard, J.: Optimization using surrogate models by the space mapping technique. PhD thesis, Informatics and Mathematical Modelling, Technical University of Denmark (2003)
Zhang, Q.J., Gupta, K.C.: Neural Networks for RF and Microwave Design. Artech House, Boston (2000)
Zhang, Q.J., Gupta, K.C., Devabhaktuni, V.K.: Artificial neural networks for RF and microwave design—from theory to practice. IEEE Trans. Microw. Theory Tech. 51(4), 1339–1350 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Simsek, M. (2014). Knowledge Based Three-Step Modeling Strategy Exploiting Artificial Neural Network. In: Koziel, S., Leifsson, L., Yang, XS. (eds) Solving Computationally Expensive Engineering Problems. Springer Proceedings in Mathematics & Statistics, vol 97. Springer, Cham. https://doi.org/10.1007/978-3-319-08985-0_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-08985-0_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-08984-3
Online ISBN: 978-3-319-08985-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)