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

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


Interval type-2, temperature prediction, hot strip mill, steel rolling, least-squared.


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