Digital Twin Surrogate Modeling for Additive Part Performance Variance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In industrial manufacturing, especially with additive processes, existing methods fail to effectively quantify and validate performance variances in components, leading to unnecessary scrap and inefficiencies due to destructive testing, which does not account for aggregate influences on operational performance.
Innovation Solution
A digital integrated process that links as-built, as-manufactured, as-designed, as-simulated, as-operated, and as-serviced components through a unique digital twin framework, enabling automated, quantitative, and qualitative assessments of additive manufacturing processes to optimize material usage and reduce destructive testing, by aggregating sub-system component level predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If destructive testing is used to validate component tolerances, then manufacturing precision can be confirmed, but material waste increases and productivity decreases
Solution Approach 1:
The patent creates digital twins (virtual copies) of physical components that simulate operational performance and aggregate variance effects. These digital models allow validation of component fitness for operation without destroying physical samples, replacing destructive testing with virtual simulation while maintaining assessment accuracy
Solution Approach 2:
The patent replaces physical destructive testing with computational simulation methods. Digital twins use software-based models to predict component behavior under operational conditions, substituting mechanical/physical testing systems with information-processing systems that eliminate material consumption
2Manufacturing precision
If destructive testing is used to validate component tolerances, then manufacturing precision can be confirmed, but productivity decreases
Solution Approach 1:
The patent performs preliminary digital validation through digital twins before physical production or deployment. By simulating operational performance and aggregate variance effects in the virtual domain first, the system identifies potential issues before committing to physical manufacturing cycles, accelerating the overall validation process
Solution Approach 2:
Digital twins provide virtual replicas that can be tested simultaneously for multiple conditions without sequential physical testing. This parallel validation capability in the digital domain significantly increases throughput compared to serial destructive physical testing
3Ease of manufacture
If traditional manufacturing processes are used with predetermined tolerances, then ease of manufacture is maintained, but reliability decreases due to unquantified variance aggregation
Solution Approach 1:
The patent implements feedback loops where digital twins continuously compare actual operational performance against design specifications and predict the aggregate effects of variance accumulation. This feedback mechanism allows manufacturers to maintain ease of production while reliably assessing whether components will meet operational requirements throughout their service life
Solution Approach 2:
The patent transforms the assessment from static tolerance checking to dynamic parameter evaluation. Digital twins simulate how multiple variance parameters interact and aggregate over time under different operational conditions, providing a more accurate prediction of component reliability while maintaining manufacturing flexibility
4Adaptability or versatility
If additive manufacturing processes are used, then manufacturing flexibility improves, but measurement precision worsens due to difficulty in quantifying process variances
Solution Approach 1:
The patent creates digital twins that replicate the complex additive manufacturing process variables and their interactions. These virtual models capture process variances that are difficult to measure physically, allowing precise quantification and tracking of how manufacturing parameters affect component performance without adding physical measurement complexity
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 a manufacturing process to make or repair the specified part. The method includes receiving data from a plurality of sources, the data including as-designed, as-manufactured, as-simulated, as-operated, as-inspected, and as-tested data relative to one or more parts similar to the specified part. 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 generating a multi-variant distribution including component performance and manufacturing variance, the manufacturing variance being associated with at least one of an additive manufacturing process step and a reductive manufacturing process step. The method includes comparing a performance from the multi-variant distribution with an expected performance of the new part based on the surrogate model. The method includes executing, based on the digital twin, the optimized process to either repair or make the specified part.