Abstract
For the purpose of automatic monitoring of the boiler combustion stability and quantifying the degree of combustion stability, a determination model for the combustion stability based on BP neural network is proposed. This model, according to the digital image processing technology, captures flame combustion state images, then extracts combustion states. Aimed at shortcomings of BP algorithm – anti-jamming ability, slow learning rate, easy to fall into local minimum, etc., this paper proposes a BP algorithm based on hierarchical dynamic adjustment of different learning rates. The samples are divided into training samples and test samples for training and testing the established model. Experience has shown that the improved model not only has better fault-tolerance and mapping ability but also improves recognition rates and computing speed, which can meet the real-time requirement of stability determination.
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
Zu, C.G., Zhou, H.C., Lou, C.: Diagnosis and analysis of combustion stability based on flame images. In: Hubei Electric Power (2006)
Kamarthi, S.V., Pittner, S.: Accelerating neural network training using weight extrapolations. Neural Netw. 12(9), 1285–1299 (1999)
Srinvas, M., Patnaik, L.M.: Adaptive probabilities of crossover and mutation in genetic algorithm. IEEE Trans. Syst. Man Cybernet. 24(4), 162–167 (2004)
Chen, R.B., Fan, W.T., Bian, J.C.: Research on stability criterion of furnace flame combustion based on image processing. In: International Conference on Control Engineering and Communication Technology, pp. 568–572 (2012)
Chen, R.B., Bian, J.C., Meng, F.H.: Research on closed-loop control system based on image-signal processing of furnace flame. In: International Conference on Energy, Environment and Sustainable Development, pp. 1095–1100 (2013)
Chen, R.B., Meng, F.H., Xiao, B.X.: Research on combustion stability based on interval number and multiple attribute decision making. Yi Qi Yi Biao Xue Bao/Chin. J. Sci. Instrum. 36(3), 552–559 (2015)
Chen, R.B., Ma, W.Y., Xiao, B.X., Cao, Z.P.: Study on the parameter discretization algorithm of furnace flame image based on rough set theory. In: 35th Chinese Control Conference (2016)
Xu, B.C., Zhang, D.Y., Cheng, L.: Study on combustion stability based on flame images. Comput. Eng. Appl. 48(9), 168–171 (2012)
Liu, H.: Judging boiler combustion stability based on flame image and fuzzy neural network. Chin. J. Sci. Instrum. 29(6), 1280–1284 (2008)
Qiao, J.F., Han, H.G., Qiao, J.F.: Optimal structure design for RBFNN structure. Acta Automatica Sinica 6, 865–872 (2010)
Wang, Y., Cao, C.X.: Analysis of local minimization for BP algorithm and its avoidance methods. Comput. Eng. 28(6), 35–36 (2002)
Liu, Z.G., Yang, Y., Ji, X.H.: Flame detection algorithm based on a saliency detection technique and the uniform local binary pattern in the YCbCr color space. SIViP 2, 1–8 (2016)
Wong, W.K., Yuen, C.W.M., Fan, D.D.: Stitching defect detection and classification using wavelet transform and BP neural network. Expert Syst. Appl. 36(2), 3845–3856 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, R., Cao, Z., Xiao, B. (2017). Stability Determination Method of Flame Combustion Based on Improved BP Model with Hierarchical Rate. In: Yue, D., Peng, C., Du, D., Zhang, T., Zheng, M., Han, Q. (eds) Intelligent Computing, Networked Control, and Their Engineering Applications. ICSEE LSMS 2017 2017. Communications in Computer and Information Science, vol 762. Springer, Singapore. https://doi.org/10.1007/978-981-10-6373-2_4
Download citation
DOI: https://doi.org/10.1007/978-981-10-6373-2_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6372-5
Online ISBN: 978-981-10-6373-2
eBook Packages: Computer ScienceComputer Science (R0)