Frequency response similarity-based bolt clamping force prediction method using convolutional neural networks

Kim, Do Hyeon; Han, Jeong Sam

doi:10.1007/s12206-022-0703-8

Cited by 4 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Fort et al 21 improved the mathematical model of bolt loosening established by Nassar and studied the effect of clamping length on bolt loosening. Jeong and Sohn 22 and Kim and Han 23 predicted the state of bolt fastening by using the frequency response of bolted structures and machine learning algorithm. The bolt loosening is a complex process with nonlinearity and uncertainty.…”

Section: Introductionmentioning

confidence: 99%

A prediction model of bolted joint loosening based on deep learning network

Liu,

Yan,

Chen

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

The Bolted joint loosening is challenging to describe with an accurate mathematical model. Therefore, a prediction model of bolted joint loosening was proposed based on a deep learning network. Firstly, the loosening experiments of the bolted joint were carried out with an orthogonal test. And the nonlinear and uncertain characteristics of bolted joint loosening process were further analyzed. Furthermore, a prediction model of bolted joint loosening based on a deep learning network was established. The proposed model was trained and verified using the experimental data. The results showed that compared with the traditional mathematical and regression models, the model could not only obtain the change of the mean value of preload but also describe the confidence interval of the change of preload in the sense of probability synchronously. The experiment data and prediction data are in good agreement, which can be used to validate the rationality of the model.

show abstract

Section: Introductionmentioning

confidence: 99%

A prediction model of bolted joint loosening based on deep learning network

Liu,

Yan,

Chen

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

show abstract

Deep learning approach for predicting crack initiation position and size in a steam turbine blade using frequency response and model order reduction

Seo,

Han

2024

J Mech Sci Technol

View full text Add to dashboard Cite

Direct Taylor Expansion of Substructures Constructed Parametric Reduced-Order Modeling Method

Jia,

Cao,

Liang

et al. 2024

AIAA Journal

View full text Add to dashboard Cite

The parametric substructure modeling shows enormous potential for efficiently conducting dynamic reanalysis of large-scale structures with small geometric variability. Parametric substructure mode is a vital component in ensuring the accuracy of the modeling process. This work uses the Craig–Bampton Component Mode Synthesis method to calculate normal and constraint modes of substructures at interpolation points. Instead of using singular value decomposition of augmented fixed-interface modes, the presented approach performs direct Taylor expansion for substructure modes with randomly varying parameters. The parametric substructure modes are approximated by the modes at interpolation points. The global parametric reduced-order model is constructed through the synthesis of parametric substructures. The effectiveness of the proposed approach is validated through 1) a thickness-variable beam, 2) a cantilevered plate with varying thicknesses, and 3) a mistuned blisk. Numerical results demonstrate that the computational accuracy of the parametric reduced-order model aligns closely with a more time-consuming full-order model.

show abstract

Frequency response similarity-based bolt clamping force prediction method using convolutional neural networks

Cited by 4 publications

References 26 publications

A prediction model of bolted joint loosening based on deep learning network

A prediction model of bolted joint loosening based on deep learning network

Deep learning approach for predicting crack initiation position and size in a steam turbine blade using frequency response and model order reduction

Direct Taylor Expansion of Substructures Constructed Parametric Reduced-Order Modeling Method

Contact Info

Product

Resources

About