该文在考虑了具有模糊化和非模糊化的模糊逻辑系统用于高炉铁水含硅量[Si]时各种噪声干扰的同时,把模糊数学理论和随机系统理论结合在一起,建立了一种新的高炉铁水含硅量[Si]的智能预报模型,该模型是由非单值模糊化、模糊规则库、模糊推理机、特殊非模糊化构成的随机模糊神经网络逻辑系统.通过结合莱钢1号高炉实时在线采集的生产数据,进行仿真研究,结果表明,该套模型能够很好地预测高炉铁水含硅量[Si].
With fuzzy theory and stochastic theory, a new intelligent model is developed to approach the random nonlinear dynamic system of the change of silicon content in molten iron, where noise influencing the fuzzy prediction system is thoroughly considered. It is a SFNN model which includes nonuniform function fuzzification, fuzzy hales, fuzzy inference and special defuzzification. The prediction of hot metal silicon content is very successful with the data collected online from No 1 BF at Laiwu Iron and Steel Group.