Abstract
Gas flow temperature of blast furnace is one of significant indicators of judging the anterograde state of blast furnace. Aiming at the defects of traditional gas flow temperature prediction model, this paper proposes a prediction model for gas flow temperature based on improved regularized extreme learning machine algorithm (RELM). Firstly, influencing factors are chosen through analyzing the distribution of blast furnace gas flow. Considering the blast furnace production data contain high frequency noise, the Fourier transform method is used for spectrum analysis, and the appropriate digital filter is selected according to the spectrum analysis result to eliminate the high frequency noise. Secondly, this paper establishes the prediction model of gas flow temperature. Regularized extreme learning machine and finite memory recursive least squares are combined to overcome Data saturation problem of ordinary extreme learning machine. And the improved algorithm is named as RFM-RELM. Finally, actual production data are used to train and test this model. Experimental result indicate that the model can quickly and accurately predict gas flow temperature ,which provides effective help and support for blast furnace operators to analyze the conditions of blast furnace.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zhou P, Song H, Wang H et al (2017) Data-driven nonlinear subspace modeling for prediction and control of molten iron quality indices in blast furnace ironmaking. IEEE Trans Control Syst Technol 25(5):1761–1774
Yang Y, Yin Y, Wunsch D et al (2017) Development of blast furnace burden distribution process modeling and control. In: ISIJ International: ISIJINT-2017-002
Fan XL, Feng HH, Yuan M (2013) PCA based on mutual information for feature selection. Control and Decision 28(6):915–919
Zhang K, Wu M, An J et al (2017) Relation model of burden operation and state variables of blast furnace based on low frequency feature extraction. IFAC-PapersOnLine 50(1):13796–13801
Zhang H, Yin Y, Zhang S (2016) An improved ELM algorithm for the measurement of hot metal temperature in blast furnace. Neurocomputing 174:232–237
Bartlett PL (1998) The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network[J]. IEEE Trans Inf Theory 44(2):525–536
Zhang K, Luo M (2015) Outlier-robust extreme learning machine for regression problems. Neurocomputing 151:1519–1527
Lin Z, Chen M, Ma Y (2010) The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. arXiv preprint arXiv:1009.5055
Mirza B, Lin Z, Toh KA (2013) Weighted online sequential extreme learning machine for class imbalance learning. Neural Process Lett 38(3):465–486
Acknowledgments
This work was supported by National Natural Science Foundation (NNSF) of China under Grant 61673056, 61673055 and the Beijing Natural Science Foundation under Grant 4182039.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wu, X., Zhang, S., Su, X., Yin, Y. (2020). The Improved Regularized Extreme Learning Machine for the Estimation of Gas Flow Temperature of Blast Furnace. In: Jia, Y., Du, J., Zhang, W. (eds) Proceedings of 2019 Chinese Intelligent Systems Conference. CISC 2019. Lecture Notes in Electrical Engineering, vol 592. Springer, Singapore. https://doi.org/10.1007/978-981-32-9682-4_30
Download citation
DOI: https://doi.org/10.1007/978-981-32-9682-4_30
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-32-9681-7
Online ISBN: 978-981-32-9682-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)