Neural networks are powerful tools for black box system identification. However, their main drawback is the large number of parameters usually required to deal with complex systems. Classically, the model's parameters minimize a L2-norm-based criterion. However, when using strongly corrupted data, namely, outliers, the L2-norm-based estimation algorithms become ineffective. In order to deal with outliers and the model's complexity, the main contribution of this paper is to propose a robust system identification methodology providing neuromodels with a convenient balance between simplicity and accuracy. The estimation robustness is ensured by means of the Huberian function. Simplicity and accuracy are achieved by a dedicated neural network design based on a recurrent three-layer architecture and an efficient model order reduction procedure proposed in a previous work (Romero-Ugalde et al., 2013, “Neural Network Design and Model Reduction Approach for Black Box Nonlinear System Identification With Reduced Number of Parameters,” Neurocomputing, 101, pp. 170–180). Validation is done using real data, measured on a piezoelectric actuator, containing strong natural outliers in the output data due to its microdisplacements. Comparisons with others black box system identification methods, including a previous work (Corbier and Carmona, 2015, “Extension of the Tuning Constant in the Huber's Function for Robust Modeling of Piezoelectric Systems,” Int. J. Adapt. Control Signal Process., 29(8), pp. 1008–1023) where a pseudolinear model was used to identify the same piezoelectric system, show the relevance of the proposed robust estimation method leading balanced simplicity-accuracy neuromodels.
Skip Nav Destination
Article navigation
May 2016
Research-Article
Robust Estimation of Balanced Simplicity-Accuracy Neural Networks-Based Models
Hector M. Romero Ugalde,
Hector M. Romero Ugalde
INSERM,
U1099;
U1099;
Search for other works by this author on:
Christophe Corbier
Christophe Corbier
Network and Telecommunications,
Université de Lyon,
Saint Etienne F-42023, France;
Université de Lyon,
Saint Etienne F-42023, France;
Network and Telecommunications,
Université de Saint Etienne,
Jean Monnet,
Saint-Etienne F-42000, France;
Université de Saint Etienne,
Jean Monnet,
Saint-Etienne F-42000, France;
LASPI,
IUT de Roanne F-42334, France
IUT de Roanne F-42334, France
Search for other works by this author on:
Hector M. Romero Ugalde
INSERM,
U1099;
U1099;
Christophe Corbier
Network and Telecommunications,
Université de Lyon,
Saint Etienne F-42023, France;
Université de Lyon,
Saint Etienne F-42023, France;
Network and Telecommunications,
Université de Saint Etienne,
Jean Monnet,
Saint-Etienne F-42000, France;
Université de Saint Etienne,
Jean Monnet,
Saint-Etienne F-42000, France;
LASPI,
IUT de Roanne F-42334, France
IUT de Roanne F-42334, France
1Corresponding author.
Contributed by the Dynamic Systems Division of ASME for publication in the JOURNAL OF DYNAMIC SYSTEMS, MEASUREMENT, AND CONTROL. Manuscript received September 2, 2015; final manuscript received January 17, 2016; published online March 3, 2016. Assoc. Editor: Ryozo Nagamune.
J. Dyn. Sys., Meas., Control. May 2016, 138(5): 051001 (8 pages)
Published Online: March 3, 2016
Article history
Received:
September 2, 2015
Revised:
January 17, 2016
Citation
Romero Ugalde, H. M., and Corbier, C. (March 3, 2016). "Robust Estimation of Balanced Simplicity-Accuracy Neural Networks-Based Models." ASME. J. Dyn. Sys., Meas., Control. May 2016; 138(5): 051001. https://doi.org/10.1115/1.4032687
Download citation file:
Get Email Alerts
Cited By
An Adaptive Sliding-Mode Observer-Based Fuzzy PI Control Method for Temperature Control of Laser Soldering Process
J. Dyn. Sys., Meas., Control
Fault detection of automotive engine system based on Canonical Variate Analysis combined with Bhattacharyya Distance
J. Dyn. Sys., Meas., Control
Multi Combustor Turbine Engine Acceleration Process Control Law Design
J. Dyn. Sys., Meas., Control (July 2025)
Related Articles
On the Inclusion of Time Derivatives of State Variables for Parametric Model Order Reduction for a Beam on a Nonlinear Foundation
J. Dyn. Sys., Meas., Control (August,2017)
Methods of Identification of Definite Degenerated and Nonlinear Dynamic System Using Specially Programmed Nonharmonic Enforce
J. Dyn. Sys., Meas., Control (August,2017)
Modified Levenberg–Marquardt Algorithm for Backpropagation Neural Network Training in Dynamic Model Identification of Mechanical Systems
J. Dyn. Sys., Meas., Control (March,2017)
A New Model-Based Control Structure for Position Tracking in an Electro-Hydraulic Servo System With Acceleration Constraint
J. Dyn. Sys., Meas., Control (December,2017)
Related Proceedings Papers
Related Chapters
A Semi-Adaptive Fractional Order PID Control Strategy for a Certain Gun Control Equipment
International Conference on Instrumentation, Measurement, Circuits and Systems (ICIMCS 2011)
Detecting Similarities and Dissimilarities between Families of Bio-Sequences: A Neural Approach
Intelligent Engineering Systems through Artificial Neural Networks, Volume 16
A Novel Approach for LFC and AVR of an Autonomous Power Generating System
International Conference on Mechanical Engineering and Technology (ICMET-London 2011)