Patent
1996-05-08
1998-03-10
Moore, David K.
395 20, 395 21, 395 23, G06F 1500
Patent
active
057271283
ABSTRACT:
A process modeling system and method develop a set of process model inputs for a process model, such as a neural network, from values for a number of process input variables and at least one process output variable. The system and method first determine a correlation measurement between each of the process input variables and the process output variable and select a set of potential model input variables based on the correlation measurements. The system and method then iteratively determine a succession of sets of potential model input variables by performing a regression analysis on the selected set of potential model input variables and the model output variable and by then refining the set of potential model input variables based on the result of the regression analysis and on the correlation measurements. After a number of iterations, the system and method choose a set of potential model input variables as the set of model inputs and develop a process model from the chosen set of model inputs.
REFERENCES:
patent: 3891836 (1975-06-01), Lee
patent: 5200816 (1993-04-01), Rose
patent: 5222196 (1993-06-01), Bigus
patent: 5265192 (1993-11-01), McCormack
patent: 5325298 (1994-06-01), Gallant
patent: 5420810 (1995-05-01), Yamakawa et al.
patent: 5526407 (1996-06-01), Russell et al.
patent: 5546503 (1996-08-01), Abe et al.
PCT International Search Report for International Application No. PCT/US 97/07802, mailed Aug. 28, 1997.
Bill Machrone, "Care and Feeding of Neural Nets," P.C. Week, p. 63 (Jun. 5, 1995).
Alex Lane, "Engineering Neural Networks with Genetic Algorithms," AI Expert, p. 11 (May 1995).
Qin, "Partial Least Squares Regression for Recursive System Identification," IEEE Decision and Control, 1993, 32nd Annual Conf. pp. 2617-2622, Dec. 30, 1993.
Qin, "A Statistical Perspective of Neural Networks for Process Modeling and Control," IEEE Intelligent Control, 1993 Int'l. Symposium, pp. 599-604, Dec. 30, 1993.
Fisz, "Probability Theory and Mathematical Statistics," John Wiley and Sons, pp. 79-91, Dec. 30, 1963.
Dong et al., "Batch Tracking Via Nonlinear Principal Component Analysis," pp. 1-34, presented at NN Club Meeting (Sep. 28, 1995).
Dong et al., "Batch to Batch Optimization Using Neural Network Models," pp. 1-32, presented at NN Club Meeting (Sep. 28, 1995).
Geladi, "Notes on the History and Nature of Partial Least Squares (PLS) Modelling," 2 J. Chemometrics, pp. 231-246 (1988).
Geladi et al., "Partial Least-Squares Regression: A Tutorial," 185 Analytica Chimica Acta 1 (1986).
Hayes et al. "Experience Using a Neural Network to Model Polymer Molecular Weight," pp. 1-5, presented at ISA Trade Show (Oct. 4, 1995).
Helland, "On the Structure of Partial Least Squares Regression," 17(2) Commun. Statist.-Simula., pp. 581-607 (1988).
Kasper et al., "Dynamic PLS Modelling for Process Control, " 48 Chemical Engineering Science, pp. 3447-3461 (1993).
Kresta et al., "Multivariate Statistical Monitoring of Process Operating Performance," 69 Canadian J. Chem. Engineering, pp. 35-47 (Feb. 1991).
Kresta et al., "Developmental of Inferential Process Models Using PLS," 18 Computers Chem. Engng., pp. 597-611 (1994).
Kosanovich et al., "Multi-Way PCA Applied to an Industrial Batch Process," Proceedings of Am. Control Conference, pp. 1294-1298 (Jun. 1994).
MacGregor et al., "Monitoring Batch Processes," NATO Advanced Study Institute (ASI) for Batch Processing Systems Eng., pp. 1-20 (May 1992).
MacGregor et al., "Multivariate Statistical Process Control of Batch Processes Using PCA and PLS," pp. 525-529 (1995).
MacGregor et al., "Process Monitoring and Diagnosis by Multiblock PLS Methods," 40 AIChE J., pp. 826-838 (May 1994).
MacGregor, "Statistical Process Control of Multivariate Processes," presented at Advanced Control of Chemical Processes, IFAC ADCHEM, 11 pages (May 1994).
MacGregor et al., "Statistical Process Control of Multivariate Processes," 3 Control Eng. Practice, pp. 403-414 (1995).
Manne, "Analysis of Two Partial-Least Squares Algorithms for Multivariate Calibration," 2 Chemometrics and Intelligent Laboratory Systems, pp. 187-197 (1987).
Morrison et al., "Neural Networks for Process Prediction," 8 pp., presented at ISA Trade Show (Oct. 3, 1995).
Nomikos et al., "Multivariate SPC Charts for Monitoring Batch Processes," 37 Technometrics, pp. 41-59 (Feb. 1995).
Qin et al., "A Data-Based Process Modeling Approach and Its Applications," Pre-prints of the Third IFAC Dycord+ Symposium, pp. 321-326 (1992).
Qin et al., "Combining Statitics and Expert Systems With Neural Networks For Empirical Process Modeling," presented at ISA International Conf., pp. 1711-1720 (Sep. 1993).
Qin, "Integration and Comparison of Neural Networks and Conventional Modeling Techniques," Dissertation for Ph.D. at the University of Maryland, (1992).
Qin et al., "Nonlinear PLS Modeling Using Neural Networks," 16 Computers Chem. Engng., pp. 379-391 (1992).
Wise, "Tutorial: Using the PLS Toolbox in PAC Applications" 5 Process Control and Quality, pp. 73-85 (1993).
Wold et al., "Multi-Way Principal Components and PLS-Analysis," 1 J. Chemometrics, pp. 41-56 (1987).
Wold et al., "Principal Component Analysis," 2 Chemometrics and Intelligent Laboratory Systems, pp. 37-52 (1987).
User Manual, Intelligent Sensor Tool Kit (Version 1.1), Fisher Rosemount Systems, Inc., pp. 6-1 to 6-21 (1995).
Chung Ji-Yong D.
Fisher-Rosemount Systems Inc.
Moore David K.
LandOfFree
System and method for automatically determining a set of variabl does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for automatically determining a set of variabl, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for automatically determining a set of variabl will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-147452