Abstract
The soft sensor models constructed based on historical data have poor generalization due to the characters of strong non-linearity and time-varying dynamics. Moving window and recursively sample updating online modeling methods can not achieve a balance between accuracy and training speed. Aiming at these problems, a novel online learning neural network (LNN) selects high-quality samples with just-in-time learning (JITL) for modeling. And the local samples could be further determined by principal component analysis (PCA). The LNN model shows better performance but poor stability. Weighted multiple sub models, the hybrid model improves accuracy by covering deficiencies. Additionally, the weights could be developed with mean square error (MSE) of each sub model. And the detailed simulation results verify the superiority of adaptive weighted hybrid model.
This work is supported by the National Natural Science Foundation of China (Grant No. 61273187); the Major Program of the National Natural Science Foundation of China (Grant No. 61590921); the Fundamental Research Funds for the Central Universities of Central South University (Grant No. 502210008).
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
Zweiri, Y.H., Seneviratne, L.D., Althoefer, K.: Stability analysis of a three-term back-propagation algorithm. Neural Netw. 18(10), 1341–1347 (2005)
Yam, Y.F., Leung, C.T., Tam, P.K.S., et al.: An independent component analysis based weight initialization method for multilayer perceptrons. Neurocomputing 48(1), 807–818 (2002)
Leung, F.H.F., Lam, H.K., Ling, S.H., et al.: Tuning of the structure and parameters of a neural network using an improved genetic algorithm. IEEE Trans. Neural Netw. 14(1), 79–88 (2003)
Valian, E., Mohanna, S., Tavakoli, S.: Improved cuckoo search algorithm for feedforward neural network training. Int. J. Artif. Intell. Appl. 2(3), 36–43 (2011)
Castillo, E., Cobo, A., Gómez-Nesterkin, R., et al.: A general framework for functional networks. Networks 1, 70–82 (2000)
Yang, S.M., Wang, Y.L., Wang, M.Y.: Active functions learning neural network. J. Jiangnan Univ. (Nat. Sci. Ed.) 14(6), 689–694 (2015)
Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70(1), 489–501 (2006)
Bontempi, G., Birattari, M., Bersini, H.: Lazy learning for local modeling and control design. Int. J. Control 72(7–8), 643–658 (1999)
Cheng, C., Chiu, M.S.: A new data-based methodology for nonlinear process modeling. Chem. Eng. Sci. 59(13), 2801–2810 (2004)
Fujiwara, K., Kano, M., Hasebe, S., et al.: Soft - sensor development using correlation - based just – in - time modeling. AIChE J. 55(7), 1754–1765 (2009)
Yang, S., Wang, Y., Sun, B., et al.: ELM weighted hybrid modeling and its online modification. In: 28th Chinese Control and Decision Conference, May 2016
Zeng, X.: The algorithm of CFNN image data fusion in multi-sensor data fusion. Sens. Transducers 166(3), 197 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Yang, SM., Wang, YL., Xue, Yf., Sun, B., Yang, Bs. (2016). Online Learning Neural Network for Adaptively Weighted Hybrid Modeling. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9948. Springer, Cham. https://doi.org/10.1007/978-3-319-46672-9_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-46672-9_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46671-2
Online ISBN: 978-3-319-46672-9
eBook Packages: Computer ScienceComputer Science (R0)