TubeBEND: A Real-World Dataset for Geometry Prediction in Rotary Draw Bending

2025-09-12

AI Summary

In two-step shear spinning tube bending, inaccurate prediction of the first-bend geometry hinders optimal design of the second-stage tooling and compromises final forming accuracy. Method: This paper proposes a data-driven machine learning approach to predict key geometric features—specifically springback angle and cross-sectional distortion—directly from multi-source sensor signals (displacement, force, torque) and process parameters. We introduce TubeBEND, the first publicly available real-world dataset comprising 318 expert-annotated samples, and develop an end-to-end mapping model that bypasses conventional trial-and-error and computationally expensive finite-element simulations. Contribution/Results: Experimental evaluation demonstrates substantial improvements in geometric prediction accuracy and machine setup efficiency. TubeBEND establishes a reproducible benchmark for tube bending research, and the proposed framework enables practical deployment of data-driven forming process optimization in industrial settings.

Technology Category

• Machine Learning: Learning with Manifolds
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• 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: Machine learning and data science for the Web
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This paper presents TubeBEND, a real-world dataset comprising 318 rotary tube bending processes, which were collected and sorted by experts from various fields to evaluate machine learning and signal analysis methods. The dataset addresses the industrial challenge of predicting the geometry of a first-stage bend, which can be beneficial for designing machine clamping molds for the second-stage bend in two-stage rotary draw bending. Some geometry criteria, such as the tube's final bent angle (or springback) and its cross-sectional deformation, are being recorded in this dataset. This dataset gives us the possibility to build and test machine learning models that can predict the geometry and help the machine operators with a better machine setup to optimize the tube's springback and deformation. Moreover, by recording some process parameters, such as tool movements and forces or torques applied to them, we deliver detailed information about their impacts on the final tube geometry. The focus of our work is to discover solutions that can replace traditional methods, such as trial-and-error or simulation-based predictions, by including experimental process variables in ML algorithms. Our dataset is publicly available at https://github.com/zeyneddinoz/tubebend and https://zenodo.org/records/16614082 as a benchmark to improve data-driven methods in this field.

Problem

• Predicting tube geometry in rotary draw bending processes
• Replacing trial-and-error methods with machine learning solutions
• Analyzing process parameter impacts on final tube geometry

Innovation

• Dataset for machine learning geometry prediction
• Replaces trial-and-error with experimental variables
• Records process parameters and geometry criteria