Neural Identification of Nonlinear Dynamic Structures

Abstract : Neural networks are applied to the identification of non-linear structural dynamic systems. Two complementary problems inspired from customer surveys are successively considered. Each of them calls for a different neural approach. First, the mass of the system is identified based on acceleration recordings. Statistical experiments are carried out to simultaneously characterize optimal pre-processing of the accelerations and optimal neural network models. It is found that key features for mass identification are the fourth statistical moment and the normalized power spectral density of the acceleration. Second, two architectures of recurrent neural networks, an autoregressive and a state-space model, are derived and tested for dynamic simulations, showing higher robustness of the autoregressive form. Discussion is first based on a non-linear two-degree-of-freedom problem. Neural identification is then used to calculate the load from seven acceleration measurements on a car. Eighty three per cent of network estimations show below 5% error.
Document type :
Journal articles
Complete list of metadatas

https://hal-emse.ccsd.cnrs.fr/emse-00686953
Contributor : Florent Breuil <>
Submitted on : Wednesday, April 11, 2012 - 5:14:37 PM
Last modification on : Thursday, October 17, 2019 - 12:36:13 PM

Links full text

Identifiers

Citation

Rodolphe Le Riche, David Gualandris, Jean Jacques Thomas, F. Hemez. Neural Identification of Nonlinear Dynamic Structures. Journal of Sound and Vibration, Elsevier, 2001, Volume 248 (Issue 2), pp.Pages 247-265. ⟨10.1006/jsvi.2001.3737⟩. ⟨emse-00686953⟩

Share

Metrics

Record views

208