Show simple item record

dc.contributor.authorRomero Ugalde, Hector M.
dc.contributor.authorCorbier, Christophe
dc.date.accessioned2017-05-09T01:27:00Z
dc.date.available2017-05-09T01:27:00Z
dc.date.issued2016
dc.identifier.issn0022-0434
dc.identifier.otherds_138_05_051001.pdf
dc.identifier.urihttp://yetl.yabesh.ir/yetl/handle/yetl/160676
dc.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.
dc.publisherThe American Society of Mechanical Engineers (ASME)
dc.titleRobust Estimation of Balanced Simplicity Accuracy Neural Networks Based Models
dc.typeJournal Paper
dc.journal.volume138
dc.journal.issue5
dc.journal.titleJournal of Dynamic Systems, Measurement, and Control
dc.identifier.doi10.1115/1.4032687
dc.journal.fristpage51001
dc.journal.lastpage51001
dc.identifier.eissn1528-9028
dc.treeJournal of Dynamic Systems, Measurement, and Control:;2016:;volume( 138 ):;issue: 005
dc.contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record