Show simple item record

contributor authorRomero Ugalde, Hector M.
contributor authorCorbier, Christophe
date accessioned2017-05-09T01:27:00Z
date available2017-05-09T01:27:00Z
date issued2016
identifier issn0022-0434
identifier otherds_138_05_051001.pdf
identifier urihttp://yetl.yabesh.ir/yetl/handle/yetl/160676
description abstractNeural 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 L2normbased criterion. However, when using strongly corrupted data, namely, outliers, the L2normbased 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 threelayer architecture and an efficient model order reduction procedure proposed in a previous work (RomeroUgalde et al., 2013, “Neural Network Design and Model Reduction Approach for Black Box Nonlinear System Identification With Reduced Number of Parameters,â€‌ 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,â€‌ 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 simplicityaccuracy neuromodels.
publisherThe American Society of Mechanical Engineers (ASME)
titleRobust Estimation of Balanced Simplicity Accuracy Neural Networks Based Models
typeJournal Paper
journal volume138
journal issue5
journal titleJournal of Dynamic Systems, Measurement, and Control
identifier doi10.1115/1.4032687
journal fristpage51001
journal lastpage51001
identifier eissn1528-9028
treeJournal of Dynamic Systems, Measurement, and Control:;2016:;volume( 138 ):;issue: 005
contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record