MP-GFormer: A 3D-Geometry-Aware Dynamic Graph Transformer Approach for Machining Process Planning

2025-11-14

AI Summary

To address the lack of 3D geometric evolution modeling in machining process planning—particularly for operation sequence prediction—this paper proposes a geometry-aware dynamic graph Transformer. The method jointly embeds STL meshes and B-rep representations into a dynamic graph learning framework, leveraging attention mechanisms to capture fine-grained geometric evolution relationships throughout machining, enabling end-to-end operation sequence prediction. Its key innovations are: (1) a geometry-driven dynamic graph structure that explicitly models state transitions during machining; and (2) integration of multi-source 3D geometric representations to enhance domain awareness. Evaluated on a synthetic dataset, the approach achieves 24% and 36% absolute improvements in main-operation and sub-operation prediction accuracy, respectively, significantly outperforming existing state-of-the-art methods.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Machining process planning (MP) is inherently complex due to structural and geometrical dependencies among part features and machining operations. A key challenge lies in capturing dynamic interdependencies that evolve with distinct part geometries as operations are performed. Machine learning has been applied to address challenges in MP, such as operation selection and machining sequence prediction. Dynamic graph learning (DGL) has been widely used to model dynamic systems, thanks to its ability to integrate spatio-temporal relationships. However, in MP, while existing DGL approaches can capture these dependencies, they fail to incorporate three-dimensional (3D) geometric information of parts and thus lack domain awareness in predicting machining operation sequences. To address this limitation, we propose MP-GFormer, a 3D-geometry-aware dynamic graph transformer that integrates evolving 3D geometric representations into DGL through an attention mechanism to predict machining operation sequences. Our approach leverages StereoLithography surface meshes representing the 3D geometry of a part after each machining operation, with the boundary representation method used for the initial 3D designs. We evaluate MP-GFormer on a synthesized dataset and demonstrate that the method achieves improvements of 24% and 36% in accuracy for main and sub-operation predictions, respectively, compared to state-of-the-art approaches.

Problem

• Capturing dynamic interdependencies in machining process planning
• Incorporating 3D geometric information into dynamic graph learning
• Predicting machining operation sequences with domain awareness

Innovation

• Integrates 3D geometric representations into dynamic graph learning
• Uses attention mechanism for machining operation sequence prediction
• Leverages StereoLithography surface meshes for evolving part geometry