دوره 15، شماره 4 - ( 8-1404 )
جلد 15 شماره 4 صفحات 525-511 |
برگشت به فهرست نسخه ها
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Zakian P, Zakian P. PREDICTING THE NATURAL FREQUENCIES OF TRUSS DOMES UNDER UNCERTAINTY USING DEEP FEEDFORWARD NEURAL NETWORKS. IJOCE 2025; 15 (4) :511-525
URL: http://ijoce.iust.ac.ir/article-1-652-fa.html
URL: http://ijoce.iust.ac.ir/article-1-652-fa.html
PREDICTING THE NATURAL FREQUENCIES OF TRUSS DOMES UNDER UNCERTAINTY USING DEEP FEEDFORWARD NEURAL NETWORKS. عنوان نشریه. 1404; 15 (4) :511-525
چکیده: (1084 مشاهده)
This study employs Monte Carlo simulation together with a deep feedforward neural network to predict the natural frequencies of truss domes under uncertainty. Material and/or geometric properties of these structures are modeled as random variables, and their influence on the natural frequencies is examined. Monte Carlo simulation is applied to perform stochastic eigenvalue analyses of the finite element models. To reduce computational cost, a deep neural network is trained to predict natural frequencies in place of repeated eigenvalue solves, accelerating the overall simulation. Bayesian optimization is used to tune the network hyperparameters. Numerical examples show that the proposed approach substantially improves computational efficiency and predictive accuracy compared with direct Monte Carlo simulation for domes with random inputs.
نوع مطالعه: پژوهشي |
موضوع مقاله:
Applications
دریافت: 1404/6/20 | پذیرش: 1404/8/11 | انتشار: 1404/8/14
دریافت: 1404/6/20 | پذیرش: 1404/8/11 | انتشار: 1404/8/14
| بازنشر اطلاعات | |
 | این مقاله تحت شرایط Creative Commons Attribution-NonCommercial 4.0 International License قابل بازنشر است. |
