ShapeGen3DCP: A Deep Learning Framework for Layer Shape Prediction in 3D Concrete Printing

2025-10-02

AI Summary

Addressing the challenge of rapidly and accurately predicting the cross-sectional geometry of extruded layers in 3D concrete printing, this paper proposes a physics-informed, data-driven deep learning method. The approach innovatively constructs dimensionless input features by integrating material rheological parameters and process variables, while employing Fourier descriptors to compactly represent layer cross-sectional contours—ensuring both geometric fidelity and model generalizability. Trained on high-fidelity Particle Finite Element Method (PFEM) simulation data, the model achieves sub-millimeter prediction accuracy (mean error < 0.15 mm) across multiple numerical and experimental scenarios. It enables pre-printing parameter calibration and toolpath optimization, providing a deployable predictive foundation for digital twin modeling and closed-loop real-time control.

Technology Category

Machine Learning: Deep Neural Architectures and Foundation ModelsComputer Vision: 3D Computer VisionIntelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

Web Mining and Content Analysis: Large pretrained models with web dataGraph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsUser Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

This work introduces ShapeGen3DCP, a deep learning framework for fast and accurate prediction of filament cross-sectional geometry in 3D Concrete Printing (3DCP). The method is based on a neural network architecture that takes as input both material properties in the fluid state (density, yield stress, plastic viscosity) and process parameters (nozzle diameter, nozzle height, printing and flow velocities) to directly predict extruded layer shapes. To enhance generalization, some inputs are reformulated into dimensionless parameters that capture underlying physical principles. Predicted geometries are compactly represented using Fourier descriptors, which enforce smooth, closed, and symmetric profiles while reducing the prediction task to a small set of coefficients. The training dataset was synthetically generated using a well-established Particle Finite Element (PFEM) model of 3DCP, overcoming the scarcity of experimental data. Validation against diverse numerical and experimental cases shows strong agreement, confirming the framework's accuracy and reliability. This opens the way to practical uses ranging from pre-calibration of print settings, minimizing or even eliminating trial-and-error adjustments, to toolpath optimization for more advanced designs. Looking ahead, coupling the framework with simulations and sensor feedback could enable closed-loop digital twins for 3DCP, driving real-time process optimization, defect detection, and adaptive control of printing parameters.

Problem

• Predicts extruded layer shapes in 3D concrete printing
• Uses material properties and process parameters as inputs
• Overcomes experimental data scarcity with synthetic training

Innovation

• Deep learning predicts filament geometry from material and process parameters
• Fourier descriptors compactly represent smooth symmetric layer profiles
• Synthetic PFEM dataset overcomes experimental data scarcity