Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Proceedings of the Design Society

Towards precision in bolted joint design: a preliminary machine learning-based parameter prediction

View Full Paper
Ask AI
Bookmark
Share

Authors

IBInes BoujnahNANehal AfifiAWAndreas Wettstein

Discussion

Loading...

Member takes

Overview

This study demonstrates machine learning's ability to predict parameters in bolted joints, indicating improved accuracy and efficiency.

Key Points

  • Achieving 95% predictive accuracy, this approach effectively models the nonlinear behavior of bolted joints.
  • By leveraging empirical data with a feed-forward neural network, traditional limitations in accuracy and computational resources are addressed.
  • The study highlights the promise of neural networks as a reliable alternative for bolted joint design despite dataset size limitations.
  • Future efforts focus on expanding datasets and hybrid modeling techniques to improve the applicability of findings.

Cite This Study

Boujnah et al. (2025) studied this question.

synapsesocial.com/papers/68c1d24654b1d3bfb60f84a9https://doi.org/10.1017/pds.2025.10335
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Novel Machine-Learning-Assisted Nonlinear Finite Element Framework for Bolted Joints2025
  2. 2Novel Machine-Learning-Assisted Nonlinear Finite Element Framework for Bolted Joints2025
  3. 3Machine learning-based prediction of the structural performance of a long-bolted steel connection2026 · 1 citations
  4. 4Fatigue life prediction of composite bolted joints based on finite element model and machine learning2024 · 18 citations
  5. 5Interpretable machine learning for predicting the bearing capacity of double shear-bolted connections: a data-driven evaluation2026 · 1 citations