Multiparameter Real-World System Identification using Iterative Residual Tuning

2021 ◽  
pp. 1-12
Author(s):  
Adam Allevato ◽  
Mitch W Pryor ◽  
Andrea L. Thomaz
Keyword(s):  
System Identification ◽  
Robot Control ◽  
Tracking Error ◽  
Nonlinear System Identification ◽  
Visual Observation ◽  
Free System ◽  
Proposed Model ◽  
Derivative Free ◽  
Identification Technique ◽  
Using Data

Abstract In this work we consider the problem of nonlinear system identification, using data to learn multiple and often coupled parameters that allow a simulator to more accurately model a physical system or mechanism and close the so-called reality gap for more accurate robot control. Our approach uses iterative residual tuning (IRT), a recently-developed derivative-free system identification technique that utilizes neural networks and visual observation to estimate parameter differences between a proposed model and a target model. We develop several modifications to the basic IRT approach and apply it to the system identification of a 5-parameter model of a marble rolling in a robot-controlled labyrinth game mechanism. We validate our technique both in simulation—where we outperform two baselines—and on a real system, where we achieve marble tracking error of 4% after just 5 optimization iterations.

Multiparameter Real-World System Identification Using Iterative Residual Tuning

2020 ◽  
Author(s):  
Adam Allevato ◽  
Mitch Pryor ◽  
Andrea L. Thomaz
Keyword(s):  
System Identification ◽  
Robot Control ◽  
Tracking Error ◽  
Nonlinear System Identification ◽  
Visual Observation ◽  
Free System ◽  
Proposed Model ◽  
Derivative Free ◽  
Identification Technique ◽  
Using Data

Abstract In this work we consider the problem of nonlinear system identification, using data to learn multiple and often coupled parameters that allow a simulator to more accurately model a physical system and close the so-called reality gap for more accurate robot control. Our approach uses iterative residual tuning (IRT), a recently-developed derivative-free system identification technique that utilizes neural networks and visual observation to estimate parameter differences between a proposed model and a target model. We develop several modifications to the basic IRT approach and apply it to the system identification of a 5-parameter model of a marble rolling in a robot-controlled labyrinth game mechanism. We validate our technique both in simulation — where we outperform two baselines — and on a real system, where we achieve marble tracking error of 4.02% after just 5 optimization iterations.

Advanced System Identification of Plates Using a Higher-Order-Spectral Approach: Theory and Experiment

2011 ◽  
Author(s):  
Michele Pasquali ◽  
Walter Lacarbonara ◽  
Pier Marzocca
Keyword(s):  
System Identification ◽  
Dynamic Response ◽  
Experimental Testing ◽  
Nonlinear System Identification ◽  
Higher Order ◽  
Detection Mechanism ◽  
Specific Objective ◽  
Structural Nonlinearities ◽  
Identification Technique ◽  
Approach Theory

A nonlinear system identification technique exploiting the dynamic response features of fully nonlinear physics-based plate models extracted by Higher-Order Spectral (HOS) analysis tools is developed. The changes induced by an imperfection in the dynamics through the structural nonlinearities are used as key detection mechanism. The differences in dynamic response of a baseline and a modified/imperfect structure are enhanced by the local nonlinearities induced by the structural modification which thus represent the specific objective of identification. The validation of the procedure and the developed algorithms is carried out through extensive experimental testing employing various plates, including isotropic and composite lay-ups, and excitation sources, including White Gaussian Noise and a train of impulses.

Nonlinear Model for Sub- and Superharmonic Motions of a MDOF Moored Structure, Part 1—System Identification

2005 ◽  
Vol 127 (4) ◽  
pp. 283-290 ◽  
Author(s):  
S. Raman ◽  
S. C. S. Yim ◽  
P. A. Palo
Keyword(s):  
System Identification ◽  
Nonlinear System Identification ◽  
Experimental System ◽  
Degree Of Freedom ◽  
System Model ◽  
Single Degree Of Freedom ◽  
Sdof System ◽  
Single Output ◽  
Motion Responses ◽  
Identification Technique

In this first part of a two-part study, the general nonlinear system identification methodology developed earlier by the authors for a single-degree-of-freedom (SDOF) system using the reverse-multi-input/single-output (R-MI/SO) technique is extended to a multi-degree-of-freedom (MDOF), sub-merged, moored structure with surge and heave motions. The physical nonlinear MDOF system model and the formulation of the R-MI/SO system-identification technique are presented. The corresponding numerical algorithm is then developed and applied to the experimental data of the MDOF system using only the subharmonic motion responses to identify the system parameters. The resulting model is then employed in Part 2 for a detailed analysis of both the sub and superharmonic dynamic behavior of the MDOF experimental system and a comparison of the MDOF response results and observations with those of the corresponding SDOF system examined earlier by the authors.

Nonlinear Model for Sub- and Superharmonic Motions of a MDOF Moored Structure, Part 2—Sensitivity Analysis and Comparison

2005 ◽  
Vol 127 (4) ◽  
pp. 291-299
Author(s):  
S. C. S. Yim ◽  
S. Raman ◽  
P. A. Palo
Keyword(s):  
Sensitivity Analysis ◽  
System Identification ◽  
Nonlinear System ◽  
Nonlinear System Identification ◽  
Detailed Comparison ◽  
Identification Procedure ◽  
System Parameters ◽  
Nonlinear Responses ◽  
Identification Technique ◽  
Single Set

The nonlinear R-MI/SO system identification procedure and the parameters of the MDOF system identified in Part 1 are examined in detail in this paper. A parametric study is conducted and the results are presented on the sensitivity of the system parameters for two key nonlinear responses—subharmonic and superharmonic resonances. The parameters are compared to determine the appropriateness of using a single set of system parameters for both response regions. A detailed comparison of the MDOF and the corresponding SDOF system results is performed. The knowledge gained from the SDOF and MDOF studies on the applicability of the R-MISO technique for the system identification of MDOF submerged moored structures is discussed. The results show that the MDOF extension of the R-MI/SO nonlinear system identification technique works well; the resulting system parameters are relatively constant and can be applied to the both the sub- and superharmonic regions.

System Identification of Jet Engines

1999 ◽  
Vol 122 (1) ◽  
pp. 19-26 ◽  
Author(s):  
N. Sugiyama
Keyword(s):  
System Identification ◽  
Jet Engines ◽  
Turbofan Engine ◽  
Jet Engine ◽  
Performance Change ◽  
Electric Control ◽  
Advanced Control ◽  
Identification Technique ◽  
Using Data ◽  
Engine Components

System identification plays an important role in advanced control systems for jet engines, in which controls are performed adaptively using data from the actual engine and the identified engine. An identification technique for jet engine using the Constant Gain Extended Kalman Filter (CGEKF) is described. The filter is constructed for a two-spool turbofan engine. The CGEKF filter developed here can recognize parameter change in engine components and estimate unmeasurable variables over whole flight conditions. These capabilities are useful for an advanced Full Authority Digital Electric Control (FADEC). Effects of measurement noise and bias, effects of operating point and unpredicted performance change are discussed. Some experimental results using the actual engine are shown to evaluate the effectiveness of CGEKF filter. [S0742-4795(00)00401-4]

scholarly journals ARX System Identification in Biomedical Applications

2019 ◽  
Vol 9 (2S3) ◽  
pp. 467-470
Keyword(s):  
System Identification ◽  
Biomedical Engineering ◽  
Biomedical Applications ◽  
Rapid Development ◽  
Nonlinear System Identification ◽  
Marine Ecology ◽  
Present System ◽  
The Status ◽  
Identification Technique ◽  
Identification Approach

System identification approach is a data driven establishing mathematical model of the system that has been widely applied to the astronomy, automatic control, spaceflight, aviation, economics as well as marine ecology and society. At present, system identification has been widely used in the field of biomedical engineering. The status of system identification technique becomes increasingly important with the rapid development of science and technology in various disciplines. This paper is firstly introduced both linear and nonlinear system identification, then briefly explained the Autoregressive Exogenous (ARX) approach, and finally the applications based on ARX system identification in the biomedical engineering field have been presented.

Sign in / Sign up

Export Citation Format

Share Document