A Novel Exhaust Gas Temperature Prediction Method of Hot Blast Stove

Hot blast Stoves (HBSs) is a piece of important equipment to provide hot air for the blast furnace. In order to control its operation process and save resources, it is necessary to predict its exhaust gas temperature. Considering a large amount of production data in this system, a novel prediction method based on echo state network (ESN), correlation analysis and differential evolution (DE) algorithm are presented in the paper. ESN is a special kind of recurrent neural network. Due to its simple training and fast convergence, the ESN model is widely used in time series prediction of a nonlinear system. To improve the availability of samples and the accuracy of results, we analyze the correlation between different features of samples for time hysteresis search before prediction. Besides, the differential evolution algorithm is used to search optimal solutions for crucial parameters of the echo state network. Simulation results show that the proposed method can effectively predict the exhaust gas temperature in a short time.

[1]  P. N. Suganthan,et al.  Differential Evolution: A Survey of the State-of-the-Art , 2011, IEEE Transactions on Evolutionary Computation.

[2]  Ioannis P. Panapakidis,et al.  Day-ahead electricity price forecasting via the application of artificial neural network based models , 2016 .

[3]  P. N. Suganthan,et al.  Differential Evolution Algorithm With Strategy Adaptation for Global Numerical Optimization , 2009, IEEE Transactions on Evolutionary Computation.

[4]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[5]  John G. Harris,et al.  Minimum mean squared error time series classification using an echo state network prediction model , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[6]  Fernando José Von Zuben,et al.  An extended echo state network using Volterra filtering and principal component analysis , 2012, Neural Networks.

[7]  Jun Wang,et al.  Chaotic Time Series Prediction Based on a Novel Robust Echo State Network , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Herbert Jaeger,et al.  Optimization and applications of echo state networks with leaky- integrator neurons , 2007, Neural Networks.

[9]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[10]  Henrik Madsen,et al.  Wind Power Forecasting Based on Echo State Networks and Long Short-Term Memory , 2018 .

[11]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[12]  Herbert Jaeger,et al.  Adaptive Nonlinear System Identification with Echo State Networks , 2002, NIPS.

[13]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[14]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[15]  Vivek Srikumar,et al.  Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks , 2018 .