For modeling a dynamic system in practice, it often faces the difficulty in improving the accuracy of the constructed analytical model, since some components of the dynamic model are often ignored deliberately due to the difficulty of identification. It is also unwise to apply the neural network to approximate the entire dynamic system as a black box, when the comprehensive knowledge of most components of the dynamics of a large system are available. This paper proposes a method that utilizes the backpropagation (BP) neural network to identify the unknown components of the dynamic system based on the experimental front-end inputs–outputs data of the entire system. It can avoid the difficulty in getting the direct training data for the unknown components, and brings great benefits in the practical application, since to get the front-end inputs–outputs data of the entire dynamic system is easier and cost-effective. In order to train such neural network for the unknown components of dynamics, a modified Levenberg–Marquardt algorithm, which can utilize the front-end inputs–outputs data of the entire dynamic system, has been developed in the paper. Three examples from different application points of view are presented in the paper, and the results show that the proposed modified Levenberg–Marquardt algorithm is efficient to train the neural network for the unknown components of the system based on the data of entire system. The constructed dynamics model, in which the unknown components are substituted by the neural network, can satisfy the requisite accuracy successfully in the computation.

References

References
1.
Sun
,
X. D.
, and
Clarke
,
T.
,
1994
, “
Advanced Aircraft Flight Control Using Nonlinear Inverse Dynamics
,”
Control Theory Appl.
,
141
(
6
), pp.
418
426
.
2.
Nakanishi
,
J.
,
Mistry
,
M.
, and
Schaal
,
S.
,
2007
, “
Inverse Dynamics Control With Floating Base and Constraints
,” 2007
IEEE
International Conference on Robotics and Automation
, Apr. 10–14, pp.
1942
1947
.
3.
Mistry
,
M.
,
Buchli
,
J.
, and
Schaal
,
S.
,
2010
, “
Inverse Dynamics Control of Floating Base Systems Using Orthogonal Decomposition
,” 2010
IEEE
International Conference on Robotics & Automation
, pp.
3406
3412
.
4.
Jankowski
,
K. P.
, and
Van Brussel
,
H.
,
1992
, “
An Approach to Discrete Inverse Dynamics Control of Flexible-Joint Robots
,”
IEEE Trans. Rob. Autom.
,
8
(
5
), pp.
651
658
.
5.
Lee
,
S.-H.
,
Song
,
J.-B.
,
Choi
,
W.-C.
, and
Hong
,
D.
,
2003
, “
Position Control of a Stewart Platform Using Inverse Dynamics Control With Approximate Dynamics
,”
Mechatronics
,
13
(
6
), pp.
605
619
.
6.
Croft
,
D.
,
Shedd
,
G.
, and
Devasia
,
S.
,
2001
, “
Creep, Hysteresis, and Vibration Compensation for Piezoactuators: Atomic Force Microscopy Application
,”
ASME J. Dyn. Syst. Meas. Control
,
123
(
1
), pp.
35
43
.
7.
Løvaas
,
C.
,
Seron
,
M. M.
, and
Goodwin
,
G. C.
,
2008
, “
Inverse Minimax Optimality of Model Predictive Control Policies
,”
Syst. Control Lett.
,
58
(
1
), pp.
31
38
.
8.
Narendra
,
K. S.
, and
Parthasarathy
,
K.
,
1989
, “
Neural Networks and Dynamics System
,”
Int. J. Approx. Reason.
,
6
(
2
), pp.
109
131
.
9.
Bhama
,
S.
, and
Singh
,
H.
,
1993
, “
Single Layer Neural Networks for Linear System Identification Using Gradient Descent Technique
,”
IEEE Trans. Neural Networks
,
4
(
5
), pp.
884
888
.
10.
Bhat
,
N. V.
,
Minderman, P. A.
,
Jr.
,
McAvoy
,
T.
, and
Wang
,
N. S.
,
1990
, “
Modeling Chemical Process Systems Via Neural Computation
,”
IEEE Control Syst. Mag.
,
10
(
3
), pp.
24
29
.
11.
Sunil Elanayar
,
V. T.
, and
Shin
,
Y. C.
,
1994
, “
Radial Basis Function Neural Network for Approximation and Estimation of Nonlinear Stochastic Dynamic Systems
,”
IEEE Trans. Neural Networks
,
5
(
4
), pp.
594
603
.
12.
Patra
,
J. C.
,
Pal
,
R. N.
,
Chatterji
,
B. N.
, and
Panda
,
G.
,
1999
, “
Identification of Nonlinear Dynamic Systems Using Functional Link Artificial Neural Networks
,”
IEEE Trans. Syst., Man Cybern.—Part B: Cybern
,
29
(
2
), pp.
252
262
.
13.
Tu
,
J. V.
,
1996
, “
Advantages and Disadvantages of Using Artificial Neural Networks Versus Logistic Regression for Predicting Medical Outcomes
,”
J. Clin. Epidemiol.
,
45
(
11
), pp.
1225
1231
.
14.
Henry
,
N.
, and
Leonardo
,
B.
,
2014
, “
Descriptive Examples of the Limitations of Artificial Neural Networks Applied to the Analysis of Independent Stochastic Data
,” e-print,
arXiv:1404.5598
.
15.
Hunter
,
D.
,
Yu
,
H.
,
Pukish
,
M. S.
, III,
Kolbusz
,
J.
, and
Wilamowski
,
B. M.
,
2012
, “
Selection of Proper Neural Network Sizes and Architectures—A Comparative Study
,”
IEEE Trans. Ind. Inf.
,
8
(
2
), pp.
228
240
.
16.
Yu
,
H.
, and
Wilamowsik
,
B. M.
,
2011
, “
Levenberg–Marquardt Training
,”
The Industrial Electronics Handbook
(Intelligent Systems), Vol.
5
,
2nd ed.
,
CRC Press
,
Boca Raton, FL
.
17.
Carbone
,
G.
,
Ceccarelli
,
M.
,
Oliveira
,
P. J.
,
Saramago
,
S. F. P.
, and
Carvalho
,
J. C. M.
,
2008
, “
Optimum Path Planning of CaPaMan (Cassino Parallel Manipulator) by Using Inverse Dynamics
,”
Rob. Int. J.
,
26
(
2
), pp.
229
239
.
18.
Gómez-Bravo
,
F.
,
Carbone
,
G.
, and
Fortes
,
J. C.
,
2012
, “
Collision Free Trajectory Planning for Hybrid Manipulators
,”
Mechatronics
,
22
(
6
), pp.
836
851
.
19.
Briones-León
,
J. A.
,
Carbone
,
G.
,
Castillo-Castañeda
,
E.
, and
Ceccarelli
,
M.
,
2009
, “
Position and Force Control of the CAPAMAN 2 Bis Parallel Robot for Drilling Tasks
,”
IEEE
Electronics, Robotics and Automotive Mechanics Conference
, Cuernavaca, Mexico, Sept. 22–25, pp.
181
186
.
You do not currently have access to this content.