Hot Rolling State Analysis Based on Kernel Principal Component Analysis and Information Entropy

Fei He; Quan Yang; Bao Jian Wang

doi:10.4028/www.scientific.net/AMR.572.7

Paper Titles

Preface, Committee and Sponsors

New Six-High Mills in Cold Tandem Rolling - Control Strategies and Performance Characteristics
p.1

Hot Rolling State Analysis Based on Kernel Principal Component Analysis and Information Entropy
p.7

Rolling Theory Analysis and Forces Calculation of Heavy Cylinder Rolling Mill with Two Drive Rolls
p.13

Calculation of Rolling Force of 3700mm Cylindrical Shell Rolling Mill
p.19

Hot Strip Tail Flick Recognition Based on Morphological Pattern Spectrum
p.25

Research on High Pressure Abrasive Water Jet for Cold Rolling Descaling
p.31

New Methods of Quality Control Systems on Strip Rolling Mills
p.37

Technology Innovation of Short Stress Path Mill and Flying Shear
p.43

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 572Hot Rolling State Analysis Based on Kernel...

Hot Rolling State Analysis Based on Kernel Principal Component Analysis and Information Entropy

Abstract:

With more and more process data acquired from manufacturing process, extracting useful information to build empirical models of past successful operations is urgently required to get higher product quality. Clustering is the important data mining methods, where feature extraction is a significant factor to ensure the accurate rate of clustering and classification. As a common non-linear feature extraction method, kernel principal component analysis (KPCA) uses the variance as the information metric, but the variance is not always effective in some cases. Since information entropy is nonlinear and can effectively represent the dependencies of features, the Renyi entropy is used as the information metric to extract the feature in this paper. Simulation data, Tennessee Eastman and hot rolling process data are used for model validation. As a result the proposed method has better performance on feature extraction, compared with traditional KPCA.