A physics-constrained framework for fatigue data augmentation of post-weld treated joints: censored S–N estimation with an exploratory generative component

Abstract The fatigue performance of welded joints has been significantly enhanced through various post-weld improvement techniques, with Tungsten Inert Gas (TIG) dressing and High-Frequency Mechanical Impact (HFMI) treatment emerging as prominent methods. While extensive experimental research has demonstrated the effectiveness of these techniques, the scarcity of comprehensive fatigue data across different geometries and loading conditions presents challenges for traditional assessment methods. This study presents a physics-constrained computational framework for the analysis and augmentation of sparse fatigue databases. Its validated elements are a unified preprocessing pipeline, a censored maximum-likelihood S–N estimator that retains run-outs as right-censored observations, a corrected stress-range extension, and a Basquin generation constraint that anchors every synthetic specimen to the S–N manifold. Bayesian hierarchical pooling, a Gaussian copula and a conditional variational autoencoder are included as exploratory components and are reported as such. Under group-level clustered inference the Basquin constraint is the only component with a demonstrated positive effect on characteristic-strength accuracy (contrast $$+3.29\\%$$ + 3.29 % , 95% CI $$[+1.65,+6.24]$$ [ + 1.65 , + 6.24 ] ); the conditional VAE degrades the estimate when that constraint is inactive, the copula contrast is not significant, and the copula is identifiable in only 7 of the 17 detail-stress-ratio cells. Leave-one-study-out validation across 23 independent source studies shows no predictive benefit from augmentation, with mean RMSE rising from 0.4529 to 0.4670. Two quantified defects bound the scope of the generated data: the generation-band filter biases characteristic strength upward by 9.8% on average, and the generated residual scatter averages 0.83 of the experimental value. Both are non-conservative. The synthetic data is therefore restricted to exploratory and distributional analysis and is not admissible for characteristic-strength or design-curve estimation, for which the censored fits to the experimental data should be used directly.