Abstract
The dynamic characteristic of a drum boiler is complex and this complication leads to the difficulty in controlling the output of the system, i.e., steam pressure. Therefore, this study attempts to investigate the application of two model predictive methods, artificial neural network (ANN) and system identification, in order to assess the performance of each method. According to the system, the inputs are feed water flow rate and applied heat while the output is the steam pressure. The ANN method used is based on a training algorithm, Levenberg-Marquardt back propagation. On the other hand, the optimal model of system identification method is the output error (OE). The performance measurement is compared by considering the mean squared error (MSE) after fitting the simulated prediction from each model to the observation. The results show that ANN slightly outperforms the system identification technique. Moreover, another finding is that ANN method is capable of identifying the outlier among the observations so it is robust to the disturbances.
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
Astrom, K.J., Bell, R.D.: Drum-Boiler Dynamic. Automatica 36, 363–378 (2000)
Rodriquez Vasquez, J.R., Rivas Perez, R., Sotomayor Moriano, J., Peran Gonzalez, J.R.: System Identification of Steam Pressure in A Fire-tube Boiler. Comput. Chem. Eng. 9, 2839–2848 (2008)
Vasickaninova, A., Bakosova, M., Meszaros, A., Klemes, J.J.: Neural Network Predictive Control of A Heat Exchange. Appl. Therm. Eng. 31, 2094–2100 (2011)
Yu, W., Li, X.: Some New Results on System Identification with Dynamic Neural Networks. IEEE T. Neural Networks 12, 412–417 (2001)
Subudhi, B., Jena, D.: A Differential Evolution Based Neural Network Approach to Nonlinear System Identification. Appl. Soft Comput. 11, 861–871 (2011)
Wu, J.-D., Tsai, Y.-J.: Speaker Identification System Using Empirical Mode Decomposition and An Artificial Neural Network. Expert Syst. Appl. 38, 6112–6117 (2011)
Xia, P.-Q.: An Inverse Model of MR Damper Using Optimal Neural Network and System Identification. Journal of Sound and Vibration 266, 1009–1023 (2003)
Mohanty, S.: Artificial Neural Network Based System Identification and Model Predictive Control of A Floatation Column. J. Process Contr. 19, 991–999 (2009)
Habbi, H., Zelmat, M., Bouamama, B.O.: A Dynamic Fuzzy Model for A Drum-Boiler-Turbine System. Automatica 39, 1213–1219 (2003)
Adaleesan, P., Miglan, N., Sharna, R., Saha, P.: Nonlinear System Identification Using Wiener Type Laguerre-Wavelet Network Model. Chem. Eng. Sci. 63, 3932–3941 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Kandananond, K. (2015). The Regulation of Steam Pressure in A Drum Boiler by Neural Network and System Identification Technique. In: Ali, M., Kwon, Y., Lee, CH., Kim, J., Kim, Y. (eds) Current Approaches in Applied Artificial Intelligence. IEA/AIE 2015. Lecture Notes in Computer Science(), vol 9101. Springer, Cham. https://doi.org/10.1007/978-3-319-19066-2_41
Download citation
DOI: https://doi.org/10.1007/978-3-319-19066-2_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19065-5
Online ISBN: 978-3-319-19066-2
eBook Packages: Computer ScienceComputer Science (R0)