Temperature Prediction in Hot Strip Mill Bars Using a Hybrid Type-2 Fuzzy Algorithm
نویسندگان
چکیده
A new learning methodology based on a hybrid algorithm for interval type-2 fuzzy logic systems (FLS) parameter estimation is presented. The new proposal consists of Back-Propagation with Recursive Least-Squares (BP-RLS) and BackPropagation with square-root filter (BP-REFIL). A system with the proposed methodology was simulated to test its capability for output surface temperature prediction of a transfer bar at Hot Strip Mill (HSM) Scale Breaker (SB) entry zone for three different types of coils. The inputs of the system are the surface temperature of the transfer bar and the travelling time required to reach the SB entry zone. The inputs are modelled as singleton, type-1 or type2 fuzzy sets depending on whether the noise was taken into account or not. The following combinations were simulated: a) interval singleton type-2 FLS (type-2 SFLS), b) interval type-1 nonsingleton type-2 FLS (type-2 NSFLS-1) and c) interval type-2 non-singleton type-2 FLS (type-2 NSFLS-2), where the bold face terms indicate the kind of input. Modelling results show the feasibility of the proposed methodology to be implemented into an intelligent process controller for the HSM industry.
منابع مشابه
First-order Interval Type-2 TSK Fuzzy Logic Systems Using a Hybrid Learning Algorithm
This article presents a new learning methodology based on a hybrid algorithm for interval type-2 TSK fuzzy logic systems (FLS). Using input-output data pairs during the forward pass of the training process, the interval type-2 TSK FLS output is calculated and the consequent parameters are estimated by recursive least-squares (RLS) method. In the backward pass, the error propagates backward, and...
متن کاملOrthogonal-least-squares and backpropa- gation hybrid learning algorithm for interval A2-C1 singleton type-2 Takagi-Sugeno-Kang fuzzy logic systems
A novel learning methodology based on a hybrid mechanism for training interval singleton type-2 Takagi-SugenoKang fuzzy logic systems uses recursive orthogonal least-squares to tune the type-1 consequent parameters and the steepest descent method to tune the interval type-2 antecedent parameters. The proposed hybrid-learning algorithm changes the interval type-2 model parameters adaptively to m...
متن کاملHybrid Hot Strip Rolling Force Prediction using a Bayesian Trained Artificial Neural Network and Analytical Models
The authors discuss the combination of an Artificial Neural Network (ANN) with analytical models to improve the performance of the prediction model of finishing rolling force in hot strip rolling mill process. The suggested model was implemented using Bayesian Evidence based training algorithm. It was found that the Bayesian Evidence based approach provided a superior and smoother fit to the re...
متن کاملPrediction of Work Roll Initial Crown according to Desired Strip Profile in Hot Rolling
The final hot strip profile is a superposition of the roll initial crown, the roll bending and flattening crown, the roll wearing crown and the roll thermal crown. In this research, linear regression models are proposed to predict the roll force, the roll wearing crown and the roll thermal crown using experimental data provided by Mobarake Steel Complex (MSC). The short beam theory based on ela...
متن کاملPrediction of Work-Piece Constitutive Equation in Hot Rolling of Strip
Dimensional control of the work-piece in steel industry is of important interest. The main aspects in overcoming the thickness control are variations in material strength due to variations in chemical composition, work-piece temperature, reduction and the strain rate applied to the work-piece. In this paper based on the main parameters affecting the rolling force an attempt been made to give a ...
متن کامل