NEURAL IDENTIFICATION OF NON-LINEAR DYNAMIC STRUCTURES

✍ Scribed by R. LE RICHE; D. GUALANDRIS; J.J. THOMAS; F. HEMEZ

• Publisher: Elsevier Science
• Year: 2001
• Tongue: English
• Weight: 401 KB
• Volume: 248
• Category: Article
• ISSN: 0022-460X
• DOI: 10.1006/jsvi.2001.3737

✦ Synopsis

Neural networks are applied to the identi"cation of non-linear structural dynamic systems. Two complementary problems inspired from customer surveys are successively considered. Each of them calls for a di!erent neural approach. First, the mass of the system is identi"ed 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 identi"cation 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 "rst based on a non-linear two-degree-of-freedom problem. Neural identi"cation 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.