Reactive Flows, Diffusion and Transport pp 117-146 | Cite as
Robustness Aspects in Parameter Estimation, Optimal Design of Experiments and Optimal Control
Summary
Estimating model parameters from experimental data is crucial to reliably simulate dynamic processes. In practical applications, however, it often appears that the data contains outliers. Thus, a reliable parameter estimation procedure is necessary that delivers parameter estimates insensitive (robust) to errors in measurements.
Another difficulty that occurs in practical applications is that the experiments performed to obtain measurements for parameter estimation are expensive, but nevertheless do not guarantee satisfactory parameter accuracy. The optimization of one or more dynamic experiments in order to maximize the accuracy of the results of a parameter estimation subject to cost and further technical inequality constraints leads to very complex non-standard optimal control problems. Newly developed successful methods and software for design of optimal experiments for nonlinear processes are based on the expansion of the problem at the nominal value of parameters which lie in a (possibly large) confidence region. Robust optimal experiments, that are insensitive against uncertainties in parameter values, should be obtained if we optimize the experiments in min-max fashion (worst-case design) over the whole range (confidence region) of an uncertainty set.
The paper presents new effective algorithms for robust parameter estimation and design of robust optimal experiments in dynamic systems. Numerical results for a real-life application from biochemical engineering are presented.
Keywords
Confidence Region Strict Complementarity Parameter Estimation Problem Optimum Experimental Design Sequential Linear ProgrammingPreview
Unable to display preview. Download preview PDF.
References
- 1.Atkinson, A. C., Donev, A. N.: Optimum Experimental Designs. Oxford University Press (1992)Google Scholar
- 2.Baake, E., Baake, M., Bock, H. G., Briggs, K.: Fitting ordinary differential equations to chaotic data. Physical Review A, 45 (1992)Google Scholar
- 3.Bauer, I.: Numerische Verfahren zur Lösung von Anfangswertaufgaben und zur Generierung von ersten und zweiten Ableitungen mit Anwendungen in Chemie und Verfahrenstechnik. Preprint, SFB 359, Universität Heidelberg (2001)Google Scholar
- 4.Bauer, I., Bock, H. G., Körkel, S., Schlöder, J. P.: Numerical methods for initial value problems and derivative generation for DAE models with application to optimum experimental design of chemical processes. In: Keil, F., Mackens, W., Voss, H., Werther, J. (eds) Scientific Computing in Chemical Engineering II. 2, 282–289, Springer, Berlin-Heidelberg (1999)Google Scholar
- 5.Bauer, I., Bock, H. G., Körkel, S., Schlöder, J. P.: Numerical methods for optimum experimental design in DAE systems. Journal of Computational and Applied Mathematics, 120, 1–25 (2000)zbMATHCrossRefMathSciNetGoogle Scholar
- 6.Beck, J. V., Arnold, K. J.:, Parameter estimation in engineering and science Wiley, New York (1977)zbMATHGoogle Scholar
- 7.Birkes, D., Dodge, Y.: Alternative Methods of Regression. John Wiley and Sons (1993)Google Scholar
- 8.Bock, H. G.: Numerical treatment of inverse problems in chemical reaction kinetics. In: Ebert, K.-K., Deuflhard, P., Jäger, W. (eds) Modelling of Chemical Reaction Systems. Springer Series in Chemical Physics 18, 102–125, Springer Verlag (1981)Google Scholar
- 9.Bock, H. G.: Randwertproblemmethoden zur Parameteridentifizierung in Systemen nichtlinearer Differentialgleichungen. Bonner Mathematische Schriften, 187, Bonn (1987)Google Scholar
- 10.Bock, H. G., Kallrath, J., Schlöder, J. P.: Least squares parameter estimation in chaotic differential equations. Celestial Mechanics and Dynamical Astronomy, 56, (1993)Google Scholar
- 11.Bock, H. G., Kostina, E. A., Schlöder, J. P.: On the role of natural level functions to achieve global convergence for damped newton methods. In: Powell, M.J.D., Scholtes, S. (eds) System Modelling and Optimization. Methods, Theory and Applications. Kluwer (2000)Google Scholar
- 12.Bock, H. G., Körkel, S., Kostina, E. A., Schlöder, J. P.: Methods for Design of Optimal Experiments with Application to Parameter Estimation in Enzyme Catalytic Processes. In: Hicks, M. G., Kettner C. (eds) Experimental Standard Conditions of Enzyme Characterizations, Proceedings of the International Beilstein Workshop, Beilstein-Institut zur Förderung der Chemischen Wissenschaften, 45–70 (2004)Google Scholar
- 13.Bock, H. G., Kostina, E. A., Kostyukova, O. I.: Covariance matrices for constrained parameter estimation problems. Submitted to SIAM Journal on Matrix Analysis and Applications (2004)Google Scholar
- 14.Bommarius, A., Estler, M., Kluge, A., Werner, H., Vollmer, H., Bock, H. G., Schlöder, J. P., Kostina E.: Method to determine the process stability of enzymes. Patent Application EP 1 067 198 A1, European Patent Office, Patentblatt, 2 (2001)Google Scholar
- 15.Bock, H. G., Körkel, S., Kostina, E. A., Schlöder, J. P.: Numerical Methods for Optimal Control Problems in Design of Robust Optimal Experiments for Nonlinear Dynamic Processes. Optimization Methods and Software, 19, issue 3–4, 327–338 (2004)zbMATHMathSciNetGoogle Scholar
- 16.Boscovic, R.: Theoria Philosophiae naturalis. Vienna (1758)Google Scholar
- 17.Box, G. E. P., Tiao, G. C: Bayesian Inference in Statistical Analysis. Wiley Classics Library, John Wiley and Sons (1992)Google Scholar
- 18.Diehl, M., Bock, H. G., Kostina, E. A.: An Approximation Technique for Robust Nonlinear Optimization. To appear in Mathematical Programming, 2005.Google Scholar
- 19.Fedorov, V. V.: Theory of Optimal Experiments. Probability And Mathematical Statistics. Academic Press, London (1972)Google Scholar
- 20.Gabasov, R., Kirillova, F. M., Kostina, E. A.: An adaptive method of solving l 1 extremal problems. Zhurnal vychislitelnoy matematiki i matematicheskoy fiziki, 38,9, 1461–1472 (1998) (in Russian, trans. to English: Computational Mathematics and Mathematical Physics, 38, 9, 1400–1411, 1998)MathSciNetGoogle Scholar
- 21.Gauss, C. F.: Theory of Combinations of Observations Least Subject to Errors. Original with translation. SIAM (1995)Google Scholar
- 22.Gauss, C. F.: Theoria Motus Corporum Coelestium in Sectionibus Conicis Solem Ambientium. F. Perthes and J. H. Besser, Hamburg (1809)Google Scholar
- 23.Griewank, A.: Evaluating Derivatives. Principles and Techniques of Algorithmic Differentiation. Frontiers in Applied Mathematics. SIAM (2000)Google Scholar
- 24.Hald, J, Madsen, K,: Combined linear programming and quasi-Newton methods for non-linear L 1 optimization. SIAM Journal on Numerical Analysis, 22, 65–80 (1985)CrossRefMathSciNetGoogle Scholar
- 25.Huber, P. J.: Robust Statistics. John Wiley and Sons (1981)Google Scholar
- 26.Körkel, S.: Numerische Methoden für Optimale Versuchsplanungsprobleme bei nichtlinearen DAE-Modellen. PhD thesis, Universität Heidelberg (2002)Google Scholar
- 27.Körkel, S., Bauer, I., Bock, H. G., Schlöder, J. P.: A sequential approach for nonlinear optimum experimental design in DAE systems. In: Keil, F., Mackens, W., Voss, H., Werther, J. (eds) Scientific Computing in Chemical Engineering II. 2, 338–345, Springer, Berlin-Heidelberg (1999)Google Scholar
- 28.Körkel, S., Kostina, E. A.: Numerical methods for nonlinear experimental design. In: Bock, H. G., Kostina E. A., Phu H. X., Rannacher R. (eds) Modeling, Simulation and Optimization of Complex Processes, Proceedings of the International Conference on High Performance Scientific Computing, 2003, Hanoi, Vietnam, Springer (2004)Google Scholar
- 29.Kostina, E. A.: The long step rule in the bounded-variable dual simplex method: numerical experiments. Mathematical Methods of Operations Research, 55,3, 413–429 (2002)zbMATHCrossRefMathSciNetGoogle Scholar
- 30.Kostina, E. A.: Robust Parameter Estimation in dynamic systems. Preprint IWR/ SFB 359 (2001)Google Scholar
- 31.Kostina, E. A.: Robust Parameter estimation in dynamic dystems. Optimization and Engineering, 5(4), 461–484 (2004)zbMATHCrossRefMathSciNetGoogle Scholar
- 32.Kostina, E. A., Prischepova, S. V.: A new algorithm for minimax and Linorm optimization. Optimization (Journal on Mathematical Programming and Operations Research), 44, 263–289, (1998)zbMATHMathSciNetGoogle Scholar
- 33.Murray, M., Overton, M. L.: A projected Lagrangian algorithm for nonlinear l 1 optimization. SIAM Journal on Scientific and Statistical Computing, 2,2, 207–224 (1981)zbMATHCrossRefMathSciNetGoogle Scholar
- 34.Pukelsheim, F.: Optimal Design of Experiments. John Wiley & Sons, Inc., New York (1993)zbMATHGoogle Scholar
- 35.Reemtsen R., Rückmann, J.-J. (eds.): Semi-Infinite Programming. Nonconvex Optimization and its Applications. Kluwer, Boston (1998)Google Scholar
- 36.Schulz V. H., Bock H. G. and Steinbach M. C: Exploiting invariants in the numerical solution of multipoint boundary value problems for DAE. SIAM Journal on Scientific Computing, 19,2, 440–467 (1998).zbMATHCrossRefMathSciNetGoogle Scholar