Nonlinear Rectification for Capacitance Method Measuring the Moisture of Green Sand Based on Functional Link Neural Network

Abstract:

In order to solve the nonlinear output/input problem of the capacitance method measuring the moisture content of green sand, a nonlinear compensation is added into the measurement system and the neural network is used for nonlinear rectification. Based on introducing the principle of non-linear compensation, a functional link artificial network with multi-input and single-output is constructed. In the network, the output voltage of capacitance moisture sensor is taken as the input and the moisture content of green sand is taken as the output. The data samples obtained in laboratory are used to train the network, and the dynamic rectification model is got. The experimental results show that the maximum difference and relative error of the moisture content are ±0.09% and ±1.85% after nonlinear rectification by the functional link neural network, and it is significantly better than those of the least square method.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 806-810
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.806
• Online since: August 2013
• Authors: De Quan Shi, Gui Li Gao, Jing Wei Dong, Li Hua Wang
• Keywords: Capacitance Method, Functional Link Neural Network, Green Sand, Moisture Content, Nonlinear Rectification

References

[1] S. G. Baker, Building the foundation for green sand, Modern Casting, vol. 95, pp.26-29, August (2005).

[2] S. Chen, J. Hu, and S. Zhu, A review of development of mould sand moisture measuring and controlling instruments, Neural Networks, no. 3, pp.47-51, March (2001).

[3] D. B. Karunakar, and G. L. Datta, Controlling green sand mould properties using artificial neural networks and genetic algorithms-A comparison, Appl. Clay Sci., vol. 37, pp.58-66, June (2007).

DOI: 10.1016/j.clay.2006.11.005

[4] Z. Li, Z. Huang, Y. Huang, and S. Deng, Design of microwave moisture measuring instrument, Transactions of the Chinese Society of Agricultural Machinery, vol. 40, pp.81-83, February (2009).

[5] K. L. Du, Clustering: A neural network approach, Neural Networks, vol. 23, pp.89-107, January (2010).

[6] S. D. Ashok, and G. L. Samuel, Least square curve fitting technique for processing time sampled high speed spindle data, International Journal of Manufacturing Research, vol. 6, pp.256-276, July (2011).

DOI: 10.1504/ijmr.2011.041129

[7] W. G. Kim, S. N. Yin, and G. H. Koo, Generation of isochronous stress-strain curves with a nonlinear least square fitting method for modified 9Cr-1Mo steel, Metals and materials international, vol. 15, pp.727-732, May (2009).

DOI: 10.1007/s12540-009-0727-3

[8] B. Surekha, L. K. Kaushik, A. K. Panduy, P. R. Vundavilli, and M. B. Parappagoudar, Multi-objective optimization of green sand mould system using evolutionary algorithms, The International Journal of Advanced Manufacturing Technology, vol. 58, pp.9-17, January (2012).

DOI: 10.1007/s00170-011-3365-8

[9] P. F. Bartelt,  N. G. Bliss, and J. S. Moberle, Application of artificial intelligence to power input control in the modern foundry, AFS Transactions, pp.221-225, April (1996).