Abstract
A hybrid parallel neural network that combined a forward neural network with a recurrent neural network was proposed to predict the biomass concentration in fermentation. Each of forward neural network and recurrent neural network worked as an individual channel of the hybrid neural network and made up each other. Their accumulated error was reduced by another neural network. The maximum error of hybrid neural network was proved be less than or equal to that of the channel and finally the steps of algorithm were given. The simulation shows the proposed approach is effective in the complex environment.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Nucci, E.R., Silva, R.G., Souza, V.R., et al.: Comparing the performance of multilayer perceptrons networks and neuro-fuzzy systems for on-line inference of Bacillus megaterium cellular concentrations. Bioprocess and Biosystems Engineering 30, 429–438 (2007)
Gundale Mangesh, M., Jana, A.K.: A comparison of three sets of DSP algorithms for monitoring the production of ethanol in a fed-batch baker’s yeast fermenter. Measurement: Journal of the International Measurement Confederation 41, 970–985 (2008)
Trelea, I.C., Titica, M.: Predictive modelling of brewing fermentation-from knowledge_based to black_box models. Mathematics and Computers in Simulation 56, 405–424 (2001)
Chen, W., Zhang, K., Lu, C., et al.: Soft-sensing of crucial biochemical variables in penicillin fermentation. In: Proceedings of the 29th Chinese Control Conference, pp. 1391–1396. IEEE Computer Society, United States (2010)
Li, B., Guo, S.-Y., Li, L., et al.: PRNN-based soft-sensing of Bacillus cereus DM423 biomass during batch cultivation. Journal of South China University of Technology (Natural Science) 37, 111–115 (2009)
Silva, T., Lima, P., Roxo-Rosa, M., et al.: Prediction of dynamic plasmid production by recombinant escherichia coli fed-batch cultivations with a generalized regression neural network. Chemical and Biochemical Engineering Quarterly 23, 419–427 (2009)
Saraceno, A., Curcio, S., Calabrò, V., et al.: A hybrid neural approach to model batch fermentation of "ricotta cheese whey" to ethanol. Computers and Chemical Engineering 34, 1590–1596 (2010)
Yang, Q., Wang, F., Chang, Y.: Soft-sensing model for biochemical parameters in Nosiheptide fermentation process based on multiple ’inherent sensor’ inversion. Chinese Journal of Scientific Instrument 28, 2163–2168 (2007)
James, S., Legge, R., Budman, H.: Comparative study of black-box and hybrid estimation methods in fed-batch fermentation. Journal Process Control 12, 113–121 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, D., Cheng, B., Wu, A. (2012). Prediction of Biomass Concentration with Hybrid Neural Network. In: Wang, J., Yen, G.G., Polycarpou, M.M. (eds) Advances in Neural Networks – ISNN 2012. ISNN 2012. Lecture Notes in Computer Science, vol 7368. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31362-2_70
Download citation
DOI: https://doi.org/10.1007/978-3-642-31362-2_70
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31361-5
Online ISBN: 978-3-642-31362-2
eBook Packages: Computer ScienceComputer Science (R0)