Digital Twin Feedback for Additive Manufacturing Variance Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Additive manufacturing processes introduce complexity due to inherent variances that are not quantified, leading to scrap material and uncertainty in component performance, as traditional destructive testing fails to consider aggregate variance effects on operational fitness.
Innovation Solution
A digital integrated process that links as-built, as-manufactured, as-designed, as-simulated, as-operated, and as-serviced components through a digital twin ecosystem, providing automated, quantitative assessments to optimize manufacturing and repair processes, reducing material waste and improving performance prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If destructive testing is used to validate component tolerances, then manufacturing precision is improved, but material loss increases significantly
Solution Approach 1:
The patent creates a digital twin (virtual copy) of the physical component that includes all manufacturing process variances. This digital replica is used for virtual testing and validation, eliminating the need for destructive physical testing. The digital model captures as-built geometry, material properties, and process variations, allowing comprehensive tolerance validation without consuming physical material.
Solution Approach 2:
The patent replaces physical destructive testing with computational simulation. Instead of physically destroying components to validate tolerances, the system uses finite element analysis and other computational methods on the digital twin to predict and validate component performance and tolerance compliance, substituting mechanical/physical testing with digital simulation.
2Ease of manufacture
If traditional manufacturing processes are used with predetermined tolerances, then ease of manufacture is improved, but reliability deteriorates due to unquantified variance aggregation
Solution Approach 1:
The patent implements a feedback loop where actual manufacturing process data (layer-by-layer build information, thermal histories, material deposition variations) is captured and fed into the digital twin model. This feedback allows the system to learn from actual process variations and improve predictions of component behavior, continuously refining the relationship between manufacturing parameters and final component performance.
Solution Approach 2:
The patent transforms the approach from using fixed predetermined tolerances to using dynamic, data-driven parameter ranges. The system captures actual process parameter variations (temperature, deposition rate, layer thickness) and uses these real measurements to define realistic tolerance bands that reflect actual manufacturing capability, improving both manufacturability and reliability predictions.
3Ease of manufacture
If additive manufacturing processes are used to produce components, then ease of manufacture is improved, but measurement precision deteriorates due to unquantified process variances
Solution Approach 1:
The patent performs preliminary characterization of additive manufacturing process variances by capturing data during the actual build process. Sensors and monitoring systems record layer-by-layer geometry, thermal conditions, and material properties as the component is being manufactured. This preliminary measurement and characterization data is then used to calibrate and validate the digital twin model, enabling precise prediction of process variances before production components are made.
Data Source
AI summary
There are provided methods and systems for making or repairing a specified part. For example, there is provided a method for creating an optimized manufacturing process to make or repair the specified part. The method includes receiving by a system configured to make or repair the specified part and from a machine communicatively coupled with the system, a set of sensor data and/or inspection data associated with at least one of an additive and a reductive manufacturing or repair process or with at least one of a pre-treatment and a post-treatment step. The method includes creating an optimized manufacturing process to make or repair the specified part, the creating including. The method includes updating, in real time, a surrogate model corresponding with a physics-based model of the specified part, wherein the surrogate model forms a digital twin of the specified part. The method includes further updating the surrogate model with the sensor data and/or inspection data. The method includes executing, based on the digital twin, the optimized manufacturing process to either repair or make the specified part.