多目標打靶法是用來預估動態系統中未知參數的最佳化方法之一，而含有成本函數、動態方程式以及其他等式與不等式限制條件的動態系統可以被改寫為一約束二次規劃問題，多目標打靶法即可將動態模型切割成數個子區間並建立分塊矩陣，此方法可增加等式限制條件和未知參數，利用壓縮式演算法將分塊矩陣架構簡化成單目標打靶法可解的數學模型。有別於傳統單目標打靶法，多目標打靶法的優點在於增加參數估計的精度並支援平行計算以提升運算效率。
本篇論文利用兩個動態模型系統並加入隨機亂數充當實驗測量誤差來驗證多目標打靶法在參數估計的精度及演算效率，在此，我們用多目標打靶法來估量質量彈簧系統中動態方程式的未知係數，以及基因定序網絡中動態方程式的未知指數和係數，模擬結果顯示多目標打靶法在針對具有實驗誤差的動態系統中具有優秀的最佳化演算能力。

Multiple shooting method is a strategy for calculating unknown parameters in a dynamic system. With a cost function, dynamic equations and extra equality and inequality constraints, a dynamic model can be formulated as a constrained quadratic program. The approach of multiple shooting is to divide the dynamic state time histories into several sub-intervals and construct a block matrix structure which increases equality constraints and unknown parameters. A condensing algorithm is available to rebuild the model into a mathematical form which can be solved by generalized Gauss-Newton method. The benefits of multiple shooting method include gaining high accuracy of optimal parameters than the original single shooting method, and supporting a parallel computation with higher computational efficiency.
In this thesis, we present two dynamic models to demonstrate the accuracy of optimal parameters and the efficiency of computation for the multiple shooting method. The multiple shooting is used to optimize two unknown coefficients in a linear continuous-time or discrete-time model for mass-spring system, and sixty unknown exponents and coefficients in a nonlinear model for a gene regulatory network, respectively. The results show that the multiple shooting is capable of producing good optimal parameters for dynamic systems with measurement errors.

Bates, M. Douglas; Watts, G. Donald. A Generalized Gauss-Newton Procedure for Multiresponse Parameter Estimation. SIAM Journal of Scientific and Statistical Computing 8(1), 49-55 (2006)

Bock, G. H.; Plitt, J. K.. A Multiple Shooting Algorithm for Direct Solution of Optimal Control Problems. IFAC Proceedings Volumes 17(2),1603-1608 (1984)

Bock, G. H.; Diehl, M. M.; Leineweber, B. D.; Schloeder, P. J.. A Direct Multiple Shooting Method for Real-Time Optimization of Nonlinear DAE Progresses. Nonlinear Model Predictive Control. Progress in Systems and Control Theory 26, 245-467 (2000)

Bonnans, J. F.; Gilbert, J. C.; Lemaréchal, Claude; Sagastizábal, Claudia A.. Numerical optimization: Theoretical and practical aspects. Springer-Verlag. Berlin. pp. xiv+490 (2006)

Demmel, James W.. Applied Numerical Linear Algebra. Society for Industrial and Applied Mathematics. USA. pp. 195-265 (1997)

Diehl, Moritz; Bock, Georg Hans; Diedam, Holger; Wieber Pierre-Brice. Fast Direct Multiple Shooting Algorithms for Optimal Robot Control. Fast Motions in Biomechanics and Robotics. Heidelberg (2005)

Ferreau, Joachim Hans. An Online Active Set Strategy for Fast Solution of Parametric Quadratic Programs with Applications to Predictive Engine Control. Heidelberg (2006)

Ferreau, J. H.; Bock, G. H.; Diehl, M.. An online active set strategy to overcome the limitations of explicit MPC. International Journal of Robust Nonlinear Control 18,816-830. (2008)

Gonzalez, O.R.; Kuper, C.; Jung, K.; Naval Jr, P.C.; Mendoza, E.. Parameter estimation using Simulated Annealing for S system models of biochemical networks. Bioinformatics 23(4), 480-486 (2007)

Horn, Roger A.; Johnson, Charles R.. Matrix Analysis. Cambridge University Press. Cambridge, United Kingdom. pp. 112-118 (1985)

Juang, J.-N.; Pappa, R. S.. An Eigensystem Realization Algorithm for Modal Parameter Identification and Model Reduction. Journal of Guidance, Control and Dynamics 8(5),620-627 (1985)

Juang, Jer-Nan; Shiau, J. H. Steven; Wu, Wesson. A Hybrid Parameter Estimation Algorithm for S-System Model of Gene Regulatory Networks. The Journal of the Astronautical Sciences 60, 559-576 (2013)

Karush, W.. Minima of Functions of Several Variables with Inequalities as Side Constraints. Univ. of Chicago. Chicago (1939)

Kikuchi, S.; Tominaga, D.; Arita, M.; Takahashi, K.; Tomita, M.. Dynamic modeling of genetic networks using genetic algorithm and S system. Bioinformatics 19(5), 643-650 (2003)
Kuhn, H. W.; Tucker, A. W.. Nonlinear programming. Proceedings of 2nd Berkeley Symposium. University of California Press. pp. 481-492 (1951)
Mallet, A.. A maximum likelihood estimation method for random coefficient regression models. Biometrika 73(3), 645-656 (1986)

Meer, A Franciscus; Marcus, Marco; Touw, Daniël; Proost, Johannes; Neef, Cees. Optimal Sampling Strategy Development Methodology Using Maximum A Posteriori Bayesian Estimation. Therapeutic Drug Monitoring 33(2), 133-146 (2011)

Nocedal, Jorge; Wright, Stephen J. Numerical Optimization (2nd ed.). Springer-Verlag. Berlin, New York. pp. 467-480 (2006)

Penrose, Roger. A generalized inverse for matrices. Cambridge Philosophical Society. 51(3), 406-413 (1955)

Potschka, Andreas. Handling Path Constraints in a Direct Multiple Shooting Method for Optimal Control Problems. Heidelberg. (2006)

Press, WH; Teukolsky, SA; Vetterling, WT; Flannery, BP. "Section 18.1. The Shooting Method". Numerical Recipes: The Art of Scientific Computing (3rd ed.). Cambridge University Press. New York (2007)

Rossi, Richard J.. Mathematical Statistics: An Introduction to Likelihood Based Inference. John Wiley & Sons. New York. pp. 227 (2018)

Shi, Zhen-Jun; Shen, Jie. Computational & Applied Mathematics. Elsevier Science Inc. USA. pp.399-461 (2005)

Teschl, Gerald. Ordinary Differential Equations and Dynamical Systems. American Mathematical Society. USA. pp.38 (2012)

Teschl, Gerald. Ordinary Differential Equations and Dynamical Systems. American Mathematical Society. USA. pp.56-57 (2012)

Wales, David J.; Doye, P. K. Jonathan. Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms. The Journal of Physical Chemistry A 101(28), 5111-5116 (1997)

Yamaguchi, Isao; Kida, Takashi. System Identification Experiments of Large Space Structures. Trans. of the Society of Instrument and Control Engineers E-1(1), 312-321 (2001)