Robust design of artificial neural network for roll force prediction in hot strip mill

Proceedings of the International Joint Conference on Neural Networks

Volumn 4, Issue , 2001, Pages 2800-2804

  Kim, Y S ^a   Yum, B J ^a   Kim, M ^a  

^a Korea Advanced Institute of Science and Technology (KAIST)   (South Korea)

Author keywords

[No Author keywords available]

Indexed keywords

CONTROL SYSTEM SYNTHESIS; FEEDFORWARD NEURAL NETWORKS; FORCE MEASUREMENT; HOT ROLLING MILLS; LEARNING SYSTEMS; MATHEMATICAL MODELS; MATRIX ALGEBRA; PARAMETER ESTIMATION; ROBUSTNESS (CONTROL SYSTEMS); SIGNAL TO NOISE RATIO; STRIP MILLS;

FULL FACTORIAL DESIGN; HOT STRIP MILL; ROLL FORCE PREDICTION; ROOT MEAN SQUARE ERROR;

MULTILAYER NEURAL NETWORKS;

EID: 0034855267     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Optimal design of neural networks using the Taguchi method
2. Using Taguchi's method of experimental design to control errors in layered perceptions
3. Training the neocognitron network using design of experiment
4. Evaluation of fuzzy-nets training efficiency
5. Neural network design by using Taguchi method
6. Optimal design for artificial neural networks: An example in a bicycle Derailleur systems