Improved Wavelet Neural Network to Predict Blast Furnace Gas Production in Iron and Steel Enterprises

Byproduct gas is an important secondary energy, which is the crux in the reduction of emission and energy consumption in the iron and steel industries. Due to the high emission rate of blast furnace gas, effective prediction of gas productions significance to the gas scheduling for saving energy and reducing emission. In this paper, dynamic incremental learning is introduced into the wavelet neural network to form an improved wavelet neural network. It is proposed to predict the dynamic occurrence of blast furnace gas after deeply analyzed current situation of byproduct gas in steel enterprises. By using this method to a real industrial problem, it can be seen that the improved wavelet neural network has a smaller relative error and higher prediction accuracy, comparing with the simple gradient descent learning method.

[1]  Xin-Ping Guan,et al.  Ill-posed Echo State Network based on L-curve Method for Prediction of Blast Furnace Gas Flow , 2014, Neural Processing Letters.

[2]  Lan Yang,et al.  The prediction for output of blast furnace gas based on genetic algorithm and LSSVM , 2014, 2014 9th IEEE Conference on Industrial Electronics and Applications.

[3]  A. Maitra,et al.  Entropy-based wavelet de-noising for partial discharge measurement application , 2016, 2016 IEEE First International Conference on Control, Measurement and Instrumentation (CMI).

[4]  J Zhao,et al.  A Two-Stage Online Prediction Method for a Blast Furnace Gas System and Its Application , 2011, IEEE Transactions on Control Systems Technology.

[5]  VASSILIS S. KODOGIANNIS,et al.  A Clustering-Based Fuzzy Wavelet Neural Network Model for Short-Term Load Forecasting , 2013, Int. J. Neural Syst..

[6]  Jun Wu,et al.  Nonlinear time series modeling and prediction using functional weights wavelet neural network-based state-dependent AR model , 2012, Neurocomputing.

[7]  J. G. Peacey,et al.  The Iron Blast Furnace: Theory and Practice , 1979 .

[8]  Wu Yi.  Improved Echo State Network Based on Data-driven and Its Application to Prediction of Blast Furnace Gas Output , 2009 .

[9]  Xiang Yin,et al.  A bottom-up analysis of China’s iron and steel industrial energy consumption and CO2 emissions , 2014 .

[10]  Jun Zhao,et al.  Improved Echo State Network Based on Data-driven and Its Application to vskip0.3 baselineskip Prediction of Blast Furnace Gas Output: Improved Echo State Network Based on Data-driven and Its Application to vskip0.3 baselineskip Prediction of Blast Furnace Gas Output , 2009 .