A QUALITY MODEL FOR LARGE-SCALE HOT-STEEL ROLLING PRODUCTION BASED ON FUZZY NEURAL NETWORK

A kind of FNN and learning algorithm is presented in this paper. The FNN is taken as the model of large-scale hot steel rolling quality and a high-dimensional modeling problem is resolved. After modeling and examination using more than nine thousand of examples, the result of forecast shows that 85% of error value between forest value and real value satisfies the practice engineering demand.