0
Research Papers

Information Theoretic Causality Measures for System Identification of Mechanical Systems

[+] Author and Article Information
Jared Elinger

Department of Mechanical Engineering,
Georgia Tech,
Atlanta, GA 30313
e-mail: jelinger3@gatech.edu

Jonathan Rogers

Department of Mechanical Engineering,
Georgia Tech,
Atlanta, GA 30313
e-mail: jonathan.rogers@me.gatech.edu

Contributed by the Design Engineering Division of ASME for publication in the JOURNAL OF COMPUTATIONAL AND NONLINEAR DYNAMICS. Manuscript received October 3, 2017; final manuscript received May 2, 2018; published online May 30, 2018. Assoc. Editor: Bogdan I. Epureanu.

J. Comput. Nonlinear Dynam 13(7), 071005 (May 30, 2018) (12 pages) Paper No: CND-17-1442; doi: 10.1115/1.4040253 History: Received October 03, 2017; Revised May 02, 2018

Parameter estimation and model order reduction (MOR) are important system identification techniques used in the development of models for mechanical systems. A variety of classical parameter estimation and MOR methods are available for nonlinear systems but performance generally suffers when little is known about the system model a priori. Recent advancements in information theory have yielded a quantity called causation entropy (CSE), which is a measure of influence between elements in a multivariate time series. In parameter estimation problems involving dynamic systems, CSE can be used to identify which state transition functions in a discrete-time model are important in driving the system dynamics, leading to reductions in the dimensionality of the parameter space. This method can likewise be used in black box system identification problems to reduce model order and limit issues with overfitting. Building on the previous work, this paper illustrates the use of CSE-enabled parameter estimation for nonlinear mechanical systems of varying complexity. Furthermore, an extension to black-box system identification is proposed wherein CSE is used to identify the proper model order of parameterized black-box models. This technique is illustrated using nonlinear differential equation (NDE) models of physical devices, including a nonlinear spring–mass–damper, a pendulum, and a nonlinear model of a car suspension. Overall, the results show that CSE is a promising new tool for both gray-box and black-box system identification that can speed convergence toward a parameter solution and mitigate problems with model overfitting.

FIGURES IN THIS ARTICLE
<>
Copyright © 2018 by ASME
Your Session has timed out. Please sign back in to continue.

References

Juang, J.-N. , and Pappa, R. S. , 1985, “ An Eigensystem Realization Algorithm for Modal Parameter Identification and Model Reduction,” J. Guid., Control, Dyn., 8(5), pp. 620–627. [CrossRef]
Juang, J.-N. , Phan, M. , Horta, L. G. , and Longman, R. W. , 1993, “ Identification of Observer/Kalman Filter Markov Parameters: Theory and Experiments,” J. Guid., Controls, Dyn., 16(2), pp. 320–329. [CrossRef]
Ljung, L. , 1998, “ System Identification,” Signal Analysis and Prediction. Applied and Numerical Harmonic Analysis, A. Prochazka , J. Uhlir , P. Rayner , and N. Kingsbury , eds., Birkhauser, Boston, MA, pp. 163–173.
Keesman, K. J. , 2011, System Identification, Springer-Verlag, London. [CrossRef]
Juang, J.-N. , 1994, Applied System Identification, Prentice Hall, Upper Saddle River, NJ.
Luenberger, D. G. , and Ye, Y. , 2016, Linear and Nonlinear Programming, 4th ed., Springer, New York. [CrossRef]
Kabaila, P. , 1983, “ On Output-Error Methods for System Identification,” IEEE Trans. Autom. Control, 28(1), pp. 12–13. [CrossRef]
Iliff, K. , 1989, “ Parameter Estimation for Flight Vehicles,” J. Guid., Control, Dyn., 12(5), pp. 609–622. [CrossRef]
Taylor, B. , and Rogers, J. , 2014, “ Experimental Investigation of Real-Time Helicopter Weight Estimation,” J. Aircr., 51(3), pp. 1047–1051. [CrossRef]
Kim, P. , Rogers, J. , Sun, J. , and Bollt, E. , 2017, “ Causation Entropy Identifies Sparsity Structure for Parameter Estimation of Dynamic Systems,” J. Comput. Nonlinear Dyn., 12(1), p. 011008. [CrossRef]
Sun, J. , and Bollt, E. , 2014, “ Causation Entropy Identifies Indirect Influences, Dominance of Neighbors and Anticipatory Couplings,” Phys. D, 267, pp. 49–57. [CrossRef]
Nelles, O. , 2013, Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models, Springer Science & Business Media, Berlin.
Patra, A. , and Unbehauen, H. , 1995, “ Identification of a Class of Nonlinear Continuous-Time Systems Using Hartley Modulating Functions,” Int. J. Contro, 62(6), pp. 1431–1451. [CrossRef]
Tokunbo, O. , 2007, Adaptive Nonlinear System Identification the Volterra and Wiener Model Approaches, Springer eBooks, New York.
Zou, H. , Hastie, T. , and Tibshirani, R. , 2007, “ On the Degrees of Freedom of the Lasso,” Ann. Stat., 35(5), pp. 2173–2192. [CrossRef]
Zou, H. , and Hastie, T. , 2004, “ Regularization and Variable Selection Via the Elastic Net,” J. R. Stat. Soc. Stat. Methodology Ser. B, 67(2), pp. 301–320. [CrossRef]
Shannon, C. , 1948, “ A Mathematical Theory of Communication,” Bell Syst. Tech. J., 27(4), pp. 379–423. [CrossRef]
Cover, T. , and Thomas, J. , 1991, Elements of Information Theory, Wiley, New York. [CrossRef]
Schreiber, T. , 2000, “ Measuring Information Transfer,” Phys. Rev. Lett., 85(2), pp. 461–464. [CrossRef] [PubMed]
Sun, J. , Cafaro, C. , and Bollt, E. , 2014, “ Identifying the Coupling Structure in Complex Systems Through the Optimal Causation Entropy Principle,” Entropy, 16(6), pp. 3416–3433. [CrossRef]
Sun, J. , Taylor, D. , and Bollt, E. M. , 2015, “ Causal Network Inference by Optimal Causation Entropy,” SIAM J. Appl. Dyn. Syst., 14(1), pp. 73–106. [CrossRef]
Barrat, A. , Barthelemy, M. , and Vespignani, A. , 2008, Dynamical Processes on Complex Networks, Cambridge University Press, Cambridge, UK. [CrossRef]
Kraskov, A. , and S. A. G. P. , 2004, “ Estimating Mutual Information,” Phys. Rev. E, 69(6), p. 066138.
Moon, Y.-I. , and Rajagopalan, B. , 1995, “ Estimation of Mutual Information Using Kernel Density Estimators,” Phys. Rev. E, 52(3), pp. 2318–2321. [CrossRef]
Archer, E. , Park, I. M. , and Pillow, J. W. , 2014, “ Bayesian Entropy Estimation for Countable Discrete Distributions,” J. Mach. Learn. Res., 15(1), pp. 2833–2868.
Khalil, H. K. , 2015, Nonlinear Control, Prentice Hall, Upper Saddle River, NJ.
McCoy, R. L. , 2012, Modern Exterior Ballistics, Schiffer Publishing, Atglen, PA.
Gross, M. , Rogers, J. , and Costello, M. , 2014, “ Nonlinear Stability Analysis Methods for Guided Artillery Projectiles,” AIAA Paper No. AIAA 2014-2541.
Fresconi, F. , Guidos, B. , Celmins, I. , and Hathaway, W. , 2014, “ Flight Behavior of an Asymmetric Body Through Spark Range Experiments Using Roll-Yaw Resonance for Yaw Enhancement,” AIAA Atmos. Flight Mech. Conf., 15(1).
Nielsen, H. B. , and Madsen, K. , 2010, Introduction to Optimization and Data Fitting, Informatics and Mathematical Modelling, Technical University of Denmark DTU, Kongens Lyngby, Denmark.
Rosen, K. H. , 2002, Discrete Mathematics and Its Applications, McGraw-Hill Higher Education, New York.
Ahmed, A. E.-N. S. , Ali, A. S. , Ghazaly, N. M. , and el Jaber, G. A. , 2015, “ PID Controller of Active Suspension System for a Quarter Car Model,” Int. J. Adv. Eng. Technol., 8(1), pp. 899–909.

Figures

Grahic Jump Location
Fig. 3

Magnitude plots of actual system matrix and estimated CEM for sinusoidal input to pendulum on a cart

Grahic Jump Location
Fig. 4

Diagram of angle of attack dynamics

Grahic Jump Location
Fig. 5

Time history of projectile states with nonzero values for all parameters

Grahic Jump Location
Fig. 6

Magnitude plot for projectile with all parameters set to nonzero values

Grahic Jump Location
Fig. 7

Time history of projectile states with Nα=0, Mα,Mq≠0

Grahic Jump Location
Fig. 8

Magnitude plot for projectile with Nα=0, Mα,Mq≠0

Grahic Jump Location
Fig. 1

Magnitude plots of actual system matrix and estimated CEM

Grahic Jump Location
Fig. 2

Time simulation of pendulum on cart with harmonic cart excitation

Grahic Jump Location
Fig. 9

Flow diagram of parameter optimization process using CSE preprocessor

Grahic Jump Location
Fig. 10

Quarter car suspension model

Grahic Jump Location
Fig. 11

Magnitude plot for the CSE values for suspension model example

Tables

Errata

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In