Tube Bending Parameter Mapping for Springback Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing tube bending processes require numerous trials to achieve the correct geometry, are inefficient across various materials and geometries, and suffer from inaccuracies due to machine wear and material-specific behaviors, leading to increased time, effort, and waste.
Innovation Solution
A method using 3D measurement data and machine learning to create a mapping model that predicts input parameters for a tube bending machine, accounting for material properties, machine state, and geometry, allowing for real-time adjustments and reduced iterations to achieve target tolerances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If complex analytical models are used to account for springback effects, then the number of trials is reduced, but the complexity of modeling increases and it becomes difficult to provide good settings over a variety of different tube materials and characteristics
Solution Approach 1:
The patent transforms the complex analytical modeling problem into a parameter-based lookup system. Instead of solving complex springback equations for each new tube material or geometry, the system pre-calculates springback values for various tube characteristics (diameter, wall thickness, material type) and stores them in lookup tables. During operation, the controller simply retrieves the appropriate springback compensation parameters based on the tube's characteristics, avoiding the need for real-time complex calculations while maintaining accuracy across different materials and geometries.
2Manufacturing precision
If real-time optical measurements are applied during bending, then corrections can be made immediately, but deriving suitable correction measures remains highly dependent on analytical techniques and difficult to provide for many different tube materials
Solution Approach 1:
The patent creates a digital twin or virtual model of the tube bending process that mirrors the physical system. The controller uses lookup tables containing pre-determined correction parameters for various tube characteristics and deviation types. When a deviation is detected during bending, the controller queries the lookup table with the tube's characteristics and the observed deviation, then applies the corresponding pre-calculated correction parameters without needing to perform complex real-time analytical derivations.
Solution Approach 2:
The system implements a feedback loop where optical sensors continuously monitor the tube's geometry during bending, compare it against the target geometry, and automatically adjust bending parameters based on lookup table recommendations. The measured deviations are fed back to the controller, which retrieves appropriate correction values from pre-populated lookup tables and applies them in real-time, creating a closed-loop control system that is both responsive and simple to operate.
3Ease of operation
If manual adjustment by operator intuition is used, then the process is simple to operate, but it requires numerous trials and increases time and waste
Solution Approach 1:
The system enables the tube bending machine to self-adjust and self-optimize without requiring operator expertise or manual intervention. The controller automatically retrieves springback compensation parameters and correction values from lookup tables based on the tube's characteristics and real-time measurements, then applies these parameters autonomously. This allows the machine to self-correct for different materials and geometries without operator training or experience, eliminating the need for manual trial-and-adjustment cycles while maintaining ease of operation.
4Ease of manufacture
If linear extrapolation with inverse error allowance is used, then the process is straightforward, but it does not adequately account for material-specific or geometry-specific behavior
Solution Approach 1:
The patent implements local quality by providing customized springback compensation parameters for different regions of the parameter space. Instead of a single global correction factor, the lookup tables contain specific compensation values tailored to each combination of tube characteristics (diameter, wall thickness, material type) and bending parameters. This allows the system to apply locally optimized corrections that account for material-specific and geometry-specific behaviors, achieving high precision while maintaining the simplicity of a lookup table approach.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach significantly reduces the number of trials needed to achieve the correct tube bending geometry, minimizing waste and effort while ensuring accuracy across a wide range of materials and geometries, even as machine wear occurs.
Implementation Method 1
The outcome of the bending process depends on different physical effects such as springback and degradation
Data Source
AI summary
A method and a system for tube bending by a tube bending machine, wherein values of input parameters of the tube bending machine defining processing steps of the tube bending machine are determined as a function of a mapping of bending parameters defining a target tube bending geometry to the input parameters. The mapping is determined by a data-driven approach, wherein a machine learning based mapping model is fitted to tube bending machine processing data of an ongoing or a previous bending process, thereby providing a machine learning dependency of the input parameters from target bending parameters. For the training of the mapping model, values of the bending parameters and corresponding values of the input parameters are used, as well as a comparison information between the values of the bending parameters and measured actual values of the bending parameters resulting from the tube bending process.