On Breakout Prediction Systems Based On Fuzzy Neural Network

Breakout is the most catastrophic incident in continuous casting. It shatters equipment, reduces task efficiency and break the produce balance. There are two main methods to avoid or reduce it internationally, one is to study the mechanism of breakout; the other is to explore techniques of breakout prediction.In the paper, the mechanism of breakout incident is firstly introduced. From this, it is necessary to predict the breakout in continuous casting. The author decides to modify the model and arithmetic of neural network for more accurate and faster prediction model.I establish some databases of technical parameter and temperature according to the investigation and study on the spot of a steelworks. A new pre-processing method is proposed. This method has shown its effectiveness on our own developing breakout prediction system based on fuzzy neural network.. These results are employed to optimize the fuzzy neural network structure and parameters. The speed and curacy of breakout prediction system are improved.At last, the breakout prediction system is developed with Visual Basic and MATLAB based on the Windows platform, which can simultaneously see all the function and circulation of all parts in continuous casting. The technique of fuzzy neural network, subtractive clustering and binary data window is used in this system, which has intuitionistic, clear, friendly interface and on-line help system.In practice, it is indicated that breakout prediction system in continuous casting can be used in production filed. Also it has stronger direct action for the worker training before work and teaching of some colleges.