3D Deformation Prediction for Complex Additive Manufacturing Shapes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Additive manufacturing (AM) faces challenges in predicting and controlling 3D shape deformation due to process and path dependencies, particularly in complex geometries, where interactions between layers cause shape deviations, necessitating a framework to accurately forecast and mitigate these deformations.
Innovation Solution
A fabrication-aware convolution learning framework is developed, using machine learning techniques to determine input and transfer functions, and cookie-cutter functions, which calculate deformation predictions for 3D printed products made from primitive shapes like spheres and polyhedrons, enabling the generation of machine control instructions to correct shape deviations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If additive manufacturing is used to create complex geometries, then manufacturing versatility is improved, but shape deformation increases
Solution Approach 1:
The framework performs preliminary prediction of shape deformation using machine learning models before the actual additive manufacturing process. By forecasting deformation patterns in advance, the system can pre-compensate for expected deviations, allowing complex geometries to be manufactured with improved shape accuracy despite the inherent process dependencies
Solution Approach 2:
The system incorporates feedback mechanisms by continuously learning from manufacturing data and updating its deformation prediction models. This enables the framework to adapt to specific process conditions and improve prediction accuracy over time, resolving the contradiction between manufacturing versatility and shape precision through data-driven optimization
2Adaptability or versatility
If layer-by-layer fabrication is used, then complex geometries can be manufactured, but process dependencies cause shape deformation
Solution Approach 1:
The framework segments the additive manufacturing process into discrete layer-level predictions, analyzing deformation patterns at each layer independently while considering cumulative effects. This segmentation approach allows the system to manage process dependencies systematically, maintaining shape consistency across multiple layers while enabling complex geometries
Solution Approach 2:
The machine learning model acts as an intermediary between the layer-by-layer fabrication process and the final shape outcome. It mediates the complex interactions between layers by predicting deformation patterns and providing compensation strategies, thereby ensuring shape consistency despite process dependencies
3Measurement precision
If machine learning frameworks are implemented, then prediction accuracy improves, but computational complexity increases
Solution Approach 1:
The framework implements partial machine learning models that focus specifically on predicting deformation patterns rather than analyzing all possible manufacturing parameters. By applying machine learning selectively to the most critical prediction tasks, the system achieves high deformation prediction accuracy while keeping computational complexity manageable
Data Source
AI summary
An apparatus, system, and method is provided for predicting 3D shape deformation in additive manufacturing. A convolution learning framework for shape deviation modeling provides joint learning for a wide class of 3D shapes including both spherical and polyhedral shapes. A 3D cookie-cutter function can effectively capture the unique pattern of the shape deformation for polyhedral shapes. Since 3D freeform shapes can be approximated as a combination of spherical and polyhedral patches, the extended convolution learning framework builds a foundation for modeling and predicting the quality of 3D freeform shapes. By changing the kernel function and considering new distance measures for points from different shapes, the spatial correlations among different shapes can be correctly incorporated. The predicted deformation may be used to offset the machine instructions to an additive manufacturing machine to ameliorate deformation.