Hot Strip Mill Temperature Prediction using Hybrid Learning Interval Singleton Type-2 FLS

M. Méndez, A. Cavazos, L. Leduc, and R. Soto (Mexico)


Interval type2, temperature prediction, hot strip mill, steel rolling, leastsquared.


This work presents two hybrid learning algorithms interval singleton type-2 Fuzzy Logic System (FLS) parameters estimation. The new proposed algorithms are designed to improve the type-2 FLS learning performance using back-propagation (BP). One of these methods uses recursive least-squared (RLS) and the other a square-root filter (REFIL) [1]. The proposed algorithms are evaluated in a Hot Strip Mill (HSM) Scale Breaker (SB) entry surface temperature prediction. A comparative result shows the advantage of the proposed methods, i.e., BP RLS and BP-REFIL as learning algorithms over that with only back-propagation [2].

Important Links:

Go Back