An integrated system for on-line intelligent monitoring and identifying process variability and its application

To reduce process variability in complex manufacturing processes, a tremendous need exists to integrate monitoring process variability (PV) and identification of source of out-of-control signals (SOS). The advent of advanced measurement and information technology has provided promising opportunities to improve product quality. In this paper, one integrated system is explored for intelligent monitoring PV and identifying of SOS in multivariate manufacturing processes (MMPs). |S| control chart is used as the detector of abnormal signals and an improved particle swarm optimisation with simulated annealing-based selective neural network ensemble (PSOSAEN) is explored for identifying the SOS. The seamless integration of control chart and PSOSAEN provides abnormal warnings, reveals SOS and helps operators to take some necessary corrections and adjustments. A real application is illustrated to validate the usefulness and effectiveness of the developed integrated system. The analysis results indicate that the developed integrated system can perform effectively for monitoring and classifying variance increases. This study provides guidelines for developing integrated neural network ensemble-based multivariate statistical process control identification systems in MMPs.

[1]  Shey-Huei Sheu,et al.  Generally weighted moving average control chart for monitoring process variability , 2006 .

[2]  Richard D. Braatz,et al.  Fault Detection and Diagnosis in Industrial Systems , 2001 .

[3]  Tao Cheng,et al.  A neural network based fuzzy learning controller and its experimental application to milling , 2000, Int. J. Comput. Integr. Manuf..

[4]  Douglas C. Montgomery,et al.  Research Issues and Ideas in Statistical Process Control , 1999 .

[5]  Ruey-Shiang Guh,et al.  On‐line Identification and Quantification of Mean Shifts in Bivariate Processes using a Neural Network‐based Approach , 2007, Qual. Reliab. Eng. Int..

[6]  Shey-Huei Sheu,et al.  Monitoring process mean and variability with generally weighted moving average control charts , 2009, Comput. Ind. Eng..

[7]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[8]  C.-C. Hsu,et al.  A neural network-based adaptive algorithm on the single EWMA controller , 2004 .

[9]  Alice E. Smith,et al.  X-bar and R control chart interpretation using neural computing , 1994 .

[10]  F. Aparisi,et al.  GENERALIZED VARIANCE CHART DESIGN WITH ADAPTIVE SAMPLE SIZES. THE BIVARIATE CASE , 2001 .

[11]  William H. Woodall,et al.  Change-point detection of mean vector or covariance matrix shifts using multivariate individual observations , 2000 .

[12]  José-Luis Guerrero-Cusumano,et al.  Testing Variability in Multivariate Quality Control: A Conditional Entropy Measure Approach , 1995, Inf. Sci..

[13]  Adnan Hassan,et al.  Improved SPC chart pattern recognition using statistical features , 2003 .

[14]  Oleksandr Makeyev,et al.  Neural network with ensembles , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[15]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[16]  S. M. Lo,et al.  Application of evolutionary neural network method in predicting pollutant levels in downtown area of Hong Kong , 2003, Neurocomputing.

[17]  Chandra R. Devireddy.  Feature-based modelling and neural networks-based CAPP for integrated manufacturing , 1999, Int. J. Comput. Integr. Manuf..

[18]  Chih-Ming Hsu,et al.  Analysis of variations in a multi-variate process using neural networks , 2003 .

[19]  J. Healy.  A note on multivariate CUSUM procedures , 1987 .

[20]  Xin Yao,et al.  Evolutionary ensembles with negative correlation learning , 2000, IEEE Trans. Evol. Comput..

[21]  Nandini Das,et al.  Interpreting the out-of-control signal in multivariate control chart — a comparative study , 2008 .

[22]  A. Grigoryan,et al.  Multivariate double sampling |S| charts for controlling process variability , 2005 .

[23]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

[24]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[25]  Amit Mitra,et al.  Statistical Quality Control , 2002, Technometrics.

[26]  Seyed Taghi Akhavan Niaki,et al.  Fault Diagnosis in Multivariate Control Charts Using Artificial Neural Networks , 2005 .

[27]  Ajith Abraham,et al.  An ensemble of neural networks for weather forecasting , 2004, Neural Computing & Applications.

[28]  Tai-Yue Wang,et al.  Mean shifts detection and classification in multivariate process: a neural-fuzzy approach , 2002, J. Intell. Manuf..

[29]  Manoj Kumar Tiwari,et al.  Application of a kin selection based simulated annealing algorithm to solve a complex scheduling problem , 2005, Int. J. Comput. Integr. Manuf..

[30]  Wei Tang,et al.  Ensembling neural networks: Many could be better than all , 2002, Artif. Intell..

[31]  Stelios Psarakis,et al.  Multivariate statistical process control charts: an overview , 2007, Qual. Reliab. Eng. Int..

[32]  Harry Wechsler,et al.  Face recognition using hybrid classifier systems , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[33]  W. Edwards Deming,et al.  Statistical Quality Control, 4th Ed. , 1973 .

[34]  Ping-Teng Chang,et al.  An integrated artificial intelligent computer-aided process planning system , 2000, Int. J. Comput. Integr. Manuf..

[35]  H. Hotelling,et al.  Multivariate Quality Control , 1947 .

[36]  Roberto Battiti,et al.  Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[37]  Manoj Kumar Tiwari,et al.  An interactive approach to solve the operation sequencing problem using simulated annealing , 2006 .

[38]  Neil S Barnett,et al.  DISPERSION CONTROL FOR MULTIVARIATE PROCESSES , 1996 .

[39]  T Çakar,et al.  Artificial neural networks for design of manufacturing systems and selection of priority rules , 2004, Int. J. Comput. Integr. Manuf..