A Neural Network-Based Approach to Identifying Out-of-Control Variables for Multivariate Control Charts

  • Authors:

  • Yuehjen E. Shao;Chien-Ho Wu;Bih-Yih Ho;Bo-Sheng Hsu

  • Affiliations:

  • Department of Statistics and Information Science, Fu Jen Catholic University, Taipei, Taiwan 24205;Department of Statistics and Information Science, Fu Jen Catholic University, Taipei, Taiwan 24205;Department of Statistics and Information Science, Fu Jen Catholic University, Taipei, Taiwan 24205;Graduate Institute of Applied Statistics, Fu Jen Catholic University,

  • Venue:
  • Computer Supported Cooperative Work in Design IV
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

In practice, many process monitoring and control scenarios involve several related variables. However one of the major problems that arise in using a multivariate control chart is the interpretation of out-of-control signals. Although RAM method is a popular approach for interpreting multivariate control chart signals, the accuracy of this method decreases as the number of out-of-control variables increases. In this paper, we proposed a new approach for multivariate control chart interpretation based on the idea of integrating neural network technology and RAM method. In many multivariate control scenarios, simulation results show that the proposed approach out-performs RAM method.