Research on an efficient prediction for deformations of thread connections based on deep transfer learning

Threaded connections are essential components in mechanical assemblies, subjected to complex deformations under various loading conditions (e.g., tension, torque, bending, and shear), influenced by bolt geometry and material properties. Accurate deformation prediction under complex loading conditions is critical for structural safety. This study presents an efficient method for rapid multi-dimensional deformation prediction in threaded connections under combined loading, utilizing deep transfer learning(TL) to address various bolt types and loading scenarios. A simplified static analysis model is first developed to predict deformations under combined loads, validated through comparisons with finite element analysis (FEA) results. A deep neural network (DNN) is pre-trained on a large deformation dataset to learn complex load-deformation relationships. TL is applied to leverage knowledge from the pre-trained model, improving prediction accuracy and generalization across bolt types. Latin Hypercube Sampling (LHS) is used to generate a sparse dataset for bolts with varying geometries and materials. Experimental results demonstrate that this method reduces computational costs and accurately simulates nonlinear deformations. For complex loading conditions, the proposed model requires only 0.14% of the computation time compared to the FEM (4.2 s vs. 3000 s). For different bolt types, the prediction accuracy reaches up to 96.6% after transfer learning. This approach provides a cost-effective alternative to computationally intensive FEA, enabling real-time, large-scale applications in engineering design and structural assessment.