# Neural Network-Enabled Process Flowsheet for Industrial Shot Peening

## TL;DR

This paper introduces a neural network model to predict residual stress in industrial shot peening processes, using dynamic media characteristics and real-time simulations.

## Contribution

The novel contribution is a ConvLSTM neural network trained on finite element simulations to predict residual stress evolution in shot peening.

## Key findings

- A ConvLSTM model accurately predicts residual stress fields in real time during shot peening.
- Media recharge strategy significantly affects residual stress outcomes in production peening cycles.

## Abstract

This work presents a dynamic flowsheet model that predicts residual stress from shot peening. The peening medium is characterized by size and shape, and evolves dynamically with abrasion, fracture, classification, and replenishment. Because particle size and impact location vary stochastically, the resulting residual stress field is spatially heterogeneous. 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. We deploy the model in a pair of 10,000-cycle production peening case studies, demonstrating that media recharge strategy has a measurable effect on residual stress outcomes.