Evolutionary Neural Network Modeling of Blast Furnace Burden Distribution

Abstract A neural network-based model of the burden layer thickness in the blast furnace is presented. The model is based on layer thicknesses estimates from a single radar measurement of the burden (stock) level in the furnace and describes the dependence between the layer thickness and key charging variables. An evolutionary algorithm is applied to train the network weights and connectivity by optimizing the model structure and parameters simultaneously, tackling part of the parameter estimation by linear least squares. This enhances convergence and results in parsimonious and transparent network models with actions that can be explained. Finally, the networks are used in a hybrid model for analyzing novel charging programs and for studying the limits of the charging process.

[1]  Gary Yen,et al.  Hierarchical Genetic Algorithm for Near-Optimal Feedforward Neural Network Design , 2002, Int. J. Neural Syst..

[2]  Haiying Wang,et al.  Feature Decomposition Architectures for Neural Networks: Algorithms, Error Bounds, and Applications , 2002, Int. J. Neural Syst..

[3]  Andries Petrus Engelbrecht,et al.  A new pruning heuristic based on variance analysis of sensitivity information , 2001, IEEE Trans. Neural Networks.

[4]  Henrik Saxén,et al.  Neural Network Model of Burden Layer Formation Dynamics in the Blast Furnace , 2001 .

[5]  Gregor Peter Josef Schmitz,et al.  Combinatorial evolution of feedforward neural network models for chemical processes , 1999 .

[6]  Furong Gao,et al.  Genetic Algorithms and Evolutionary Programming Hybrid Strategy for Structure and Weight Learning for Multilayer Feedforward Neural Networks , 1999 .

[7]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[8]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[9]  Frank Pettersson,et al.  A hybrid algorithm for weight and connectivity optimization in feedforward neural networks , 2003, ICANNGA.

[10]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[11]  Vittorio Maniezzo,et al.  Genetic evolution of the topology and weight distribution of neural networks , 1994, IEEE Trans. Neural Networks.

[12]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[13]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[14]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[15]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[16]  鉄鋼基礎共同研究会.  Blast furnace phenomena and modelling , 1987 .

[17]  Yunosuke Maki,et al.  Sensor and Signal Quantification for Blast Furnace Gas Distribution Control , 1982 .