Title :
Intelligent Recognition Research of Control Charts Patterns
Author_Institution :
Electron. Eng. Depts., East China Jiaotong Univ., Nanchang, China
Abstract :
Control chart is one of important tools for on-line quality control. It is most difficult to identify unnatural patterns which are associated with a specific set of assignable causes on quality control charts. This paper discusses about control charts patterns recognition, and proposes a method for feature extraction from control chart based on principal component analysis(PCA). First, the principal component analysis is used to pre-process the sample data. Meanwhile, three methods were used to recognise control charts patterns: an improved backpropagation algorithm, PCA_BP and PCA_SVM. Simulation indicates that PCA_SVM is most effective.
Keywords :
backpropagation; control charts; pattern recognition; principal component analysis; quality control; support vector machines; PCA backpropagation; PCA support vector machine; control charts pattern recognition; intelligent recognition; neural network; on-line quality control; principal component analysis; Backpropagation algorithms; Control charts; Manufacturing processes; Neural networks; Pattern recognition; Principal component analysis; Process control; Quality control; Support vector machine classification; Support vector machines;
Conference_Titel :
Computational Intelligence and Software Engineering, 2009. CiSE 2009. International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-4507-3
Electronic_ISBN :
978-1-4244-4507-3
DOI :
10.1109/CISE.2009.5366198
