Evolving Nonlinear Time-Series Models of the Hot Metal Silicon Content in the Blast Furnace
Authors:
- 30 May 2007
- journal article
- research article
- Published by Taylor & Francis in Materials and Manufacturing Processes
- Vol. 22 (5) , 577-584
Abstract
Neural networks are versatile tools for nonlinear modeling, but in time-series modeling of complex industrial processes the choice of relevant inputs and time lags can be a major problem. A novel method for the simultaneous detection of relevant inputs and an appropriate structure of the lower part of the networks has been developed by evolving neural networks by a genetic algorithm, where the approximation error and the number of weights are minimized simultaneously by multiobjective optimization. The networks on the Pareto front are considered possible candidate models that are evaluated on an independent test set. In order to consider the problem of drift in the variables, which may cause parsimonious models to perform poorly on the test set, the weights in the upper layer of the networks are recursively estimated by a Kalman filter. The method is illustrated on a data set from ironmaking industry, where time-series models of the hot metal silicon content in a blast furnace are evolved. The technique is demonstrated to synthesize models with a choice of inputs in agreement with findings presented in the literature and process know-how.Keywords
This publication has 27 references indexed in Scilit:
- Time-dependent Fractal Characteristics on Time Series of Silicon Content in Hot Metal of Blast FurnaceISIJ International, 2005
- Prediction of Silicon Content in Blast Furnace Hot Metal Using Partial Least Squares (PLS)ISIJ International, 2005
- Selection of quasi-optimal inputs in chemometrics modeling by artificial neural network analysisAnalytica Chimica Acta, 2003
- A new pruning heuristic based on variance analysis of sensitivity informationIEEE Transactions on Neural Networks, 2001
- A predictive system for blast furnaces by integrating a neural network with qualitative analysisEngineering Applications of Artificial Intelligence, 2001
- Genetic Algorithms and Evolutionary Programming Hybrid Strategy for Structure and Weight Learning for Multilayer Feedforward Neural NetworksIndustrial & Engineering Chemistry Research, 1999
- Radial basis function network configuration using genetic algorithmsNeural Networks, 1995
- Genetic evolution of the topology and weight distribution of neural networksIEEE Transactions on Neural Networks, 1994
- THE ADAPTIVE AUTOREGRESSIVE MODELS FOR THE SYSTEM DYNAMICS AND PREDICTION OF BLAST FURNACEChemical Engineering Communications, 1986
- Identification of multiinput-multioutput transfer function and noise model of a blast furnace from closed-loop dataIEEE Transactions on Automatic Control, 1974