Shape error prediction in 5-axis machining using graph neural networks

TL;DR

This paper introduces a graph neural network-based method for predicting shape errors in 5-axis machining, effectively handling limited labeled data by modeling spatial and temporal relationships in workpiece geometries.

Contribution

It proposes a novel graph neural network approach that captures spatial and temporal dependencies for shape error prediction in complex machining processes.

Findings

The method generalizes shape error prediction across workpiece geometries.

It performs well with limited labeled data compared to traditional methods.

Experimental results validate the effectiveness of the graph-based approach.

Abstract

This paper presents an innovative method for predicting shape errors in 5-axis machining using graph neural networks. The graph structure is defined with nodes representing workpiece surface points and edges denoting the neighboring relationships. The dataset encompasses data from a material removal simulation, process data, and post-machining quality information. Experimental results show that the presented approach can generalize the shape error prediction for the investigated workpiece geometry. Moreover, by modelling spatial and temporal connections within the workpiece, the approach handles a low number of labels compared to non-graphical methods such as Support Vector Machines.