Shot peening enhances fatigue life by inducing compressive residual stresses through high-velocity impacts of steel or ceramic particles that plastically deform the surface. Because particle size and impact location vary stochastically, the resulting residual stress field is spatially heterogeneous. As media recirculate through the blast loop, their morphology evolves by abrasion and fracture, producing transient shifts in the mean stress state that depend on the recharge strategy. This work presents a reduced-order process flowsheet that tracks media size and shape evolution using a three-mode degradation model. Residual stress fields are predicted in real time through a convolutional long short-term memory (ConvLSTM) neural network trained on finite element simulations, enabling fast, mechanistically grounded prediction of surface stress evolution under industrial shot peening conditions.
Feltner et al. (Fri,) studied this question.