GraphCompNet: A Position-Aware Model for Predicting and Compensating Shape Deviations in 3D Printing

2025-02-11

AI Summary

To address spatially non-uniform shape deviations and poor geometric generalization in powder bed fusion (PBF) additive manufacturing, this paper proposes a deviation modeling and real-time compensation framework integrating graph neural networks (GNNs) with adversarial training. We introduce a position-aware dynamic graph convolution architecture and a two-stage adversarial predictor–compensator design to explicitly capture thermal–mechanical coupling effects inducing location-dependent distortions. By representing part geometry as point clouds and incorporating thermal–mechanical positional encoding, our method achieves high-fidelity deviation prediction across the entire build volume. Experimental validation on multi-geometry parts demonstrates 35–65% improvement in compensation accuracy over baseline methods, with millisecond-level closed-loop iteration capability. The approach significantly enhances scalability and robustness of digital twin systems for industrial-scale AM applications.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Multiagent Systems: Adversarial Agents
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

This paper introduces a data-driven algorithm for modeling and compensating shape deviations in additive manufacturing (AM), addressing challenges in geometric accuracy and batch production. While traditional methods, such as analytical models and metrology, laid the groundwork for geometric precision, they are often impractical for large-scale production. Recent advancements in machine learning (ML) have improved compensation precision, but issues remain in generalizing across complex geometries and adapting to position-dependent variations. We present a novel approach for powder bed fusion (PBF) processes, using GraphCompNet, which is a computational framework combining graph-based neural networks with a generative adversarial network (GAN)-inspired training process. By leveraging point cloud data and dynamic graph convolutional neural networks (DGCNNs), GraphCompNet models complex shapes and incorporates position-specific thermal and mechanical factors. A two-stage adversarial training procedure iteratively refines compensated designs via a compensator-predictor architecture, offering real-time feedback and optimization. Experimental validation across diverse shapes and positions shows the framework significantly improves compensation accuracy (35 to 65 percent) across the entire print space, adapting to position-dependent variations. This work advances the development of Digital Twin technology for AM, enabling scalable, real-time monitoring and compensation, and addressing critical gaps in AM process control. The proposed method supports high-precision, automated industrial-scale design and manufacturing systems.

Problem

• Predicting shape deviations in 3D printing
• Compensating position-dependent variations in AM
• Improving geometric accuracy in additive manufacturing

Innovation

• Graph-based neural networks
• Generative adversarial training
• Dynamic graph convolutional networks