Efficient planning of peen-forming patterns via artificial neural networks

TL;DR

This paper introduces a neural network-based method for real-time planning of peen-forming patterns, achieving high accuracy and rapid pattern generation for automated shot peen forming processes.

Contribution

The work presents a novel neural network approach that learns the nonlinear relationship between target shapes and optimal peening patterns from simulation data.

Findings

Neural network achieves 98.8% binary accuracy in pattern prediction.

Pattern generation occurs in microseconds, enabling real-time application.

Method improves automation efficiency in shot peen forming processes.

Abstract

Robust automation of the shot peen forming process demands a closed-loop feedback in which a suitable treatment pattern needs to be found in real-time for each treatment iteration. In this work, we present a method for finding the peen-forming patterns, based on a neural network (NN), which learns the nonlinear function that relates a given target shape (input) to its optimal peening pattern (output), from data generated by finite element simulations. The trained NN yields patterns with an average binary accuracy of 98.8\% with respect to the ground truth in microseconds.