Mean shifts detection and classification in multivariate process: a neural-fuzzy approach

For monitoring multivariate quality control process, traditional multivariate control charts have been proposed to detect mean shifts. However, a persistent problem is that such charts are unable to provide any shift-related information when mean shifts occur in the process. In fact, the immediate classification of the magnitude of mean shifts can greatly narrow down the set of possible assignable causes, hence facilitating quick analysis and corrective action by the technician before many nonconforming units are manufactured. In this paper, we propose a neural-fuzzy model for detecting mean shifts and classifying their magnitude in multivariate process. This model is divided into training and classifying modules. In the training module, a neural network (NN) model is trained to detect various mean shifts for multivariate process. Then, in the classifying module, the outputs of NN are classified into various decision intervals by using a fuzzy classifier and an additional two-point-in-an-interval decision rule to determine shift status. An example is presented to illustrate the application of the proposed model. Simulation results show that it outperforms the multivariate T2control chart in terms of out-of-control average run length under fixed type I error. In addition, the correct classification percentages are also studied and the general guidelines are given for the proper use of the proposed model.

[1]  Nola D. Tracy,et al.  Decomposition of T2 for Multivariate Control Chart Interpretation , 1995 .

[2]  N F Hubele,et al.  X¯ CONTROL CHART PATTERN IDENTIFICATION THROUGH EFFICIENT OFF-LINE NEURAL NETWORK TRAINING , 1993 .

[3]  John C. Young,et al.  A Practical Approach for Interpreting Multivariate T2 Control Chart Signals , 1997 .

[4]  R. Crosier.  Multivariate generalizations of cumulative sum quality-control schemes , 1988 .

[5]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[6]  J. D. T. Tannock,et al.  A review of neural networks for statistical process control , 1998, J. Intell. Manuf..

[7]  Shing I. Chang,et al.  A neural fuzzy control chart for detecting and classifying process mean shifts , 1996 .

[8]  Kevin J. Dooley,et al.  Identification of change structure in statistical process control , 1992 .

[9]  H. Hotelling.  Multivariate Quality Control-illustrated by the air testing of sample bombsights , 1947 .

[10]  Shing I. Chang,et al.  A two-stage neural network approach for process variance change detection and classification , 1999 .

[11]  Douglas C. Montgomery,et al.  A review of multivariate control charts , 1995 .

[12]  Shing I. Chang,et al.  An integrated neural network approach for simultaneous monitoring of process mean and variance shifts a comparative study , 1999 .

[13]  Neil H. Timm,et al.  Multivariate Quality Control Using Finite Intersection Tests , 1996 .

[14]  Chuen-Sheng Cheng.  A multi-layer neural network model for detecting changes in the process mean , 1995 .

[15]  Yoshio Hirose,et al.  Backpropagation algorithm which varies the number of hidden units , 1989, International 1989 Joint Conference on Neural Networks.

[16]  J. E. Jackson.  Multivariate quality control , 1985 .

[17]  Charles W. Champ,et al.  A multivariate exponentially weighted moving average control chart , 1992 .

[18]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[19]  John C. Young,et al.  Monitoring a multivariate step process , 1996 .

[20]  Ross Sparks,et al.  Graphical Process Monitoring in the Service Industry – A Case Study , 1996 .

[21]  G. Allen Pugh.  A COMPARISON OF NEURAL NETWORKS TO SPC CHARTS , 1991 .