Simulation Parameterization Using Correlation-Based Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing simulation parameterization methods are time-consuming and lack objective validation, particularly in fields like automotive engineering, due to the sensitivity of quadratic cost functions and the need for extensive physical testing.
Innovation Solution
A computer-implemented method using a validation metric to determine target parameter settings by evaluating training and test data sets, providing a cost function that assesses model quality and reliability, thereby simplifying the modeling process and reducing the need for physical tests.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If quadratic cost function is used for parameter optimization, then simulation accuracy is improved, but phase errors are severely penalized and model validation becomes unreliable
Solution Approach 1:
The patent changes the parameterization approach from using quadratic cost functions to using correlation coefficients (e.g., coefficient of determination R², Pearson correlation coefficient) as validation metrics. This parameter change transforms the optimization criterion from minimizing squared errors to maximizing correlation between simulation and measurement data, thereby reducing sensitivity to phase errors while maintaining accuracy.
2Reliability
If extensive physical testing is conducted for model validation, then model quality is ensured, but development time is significantly increased
Solution Approach 1:
The patent creates virtual copies of physical test scenarios through simulation models that are parameterized using correlation coefficients. Instead of repeatedly conducting physical tests, the method uses simulated data with realistic statistical properties to validate and tune models, thereby reducing the need for extensive physical testing while maintaining validation quality.
Solution Approach 2:
The patent performs preliminary parameter optimization using correlation-based validation metrics before final model deployment. By pre-tuning simulation models using this robust metric approach, the need for time-consuming iterative physical testing is reduced, as the models are already well-parameterized and validated beforehand.
3Manufacturing precision
If model parameterization is repeated due to insufficient validation, then model accuracy is improved, but the process becomes very time-consuming
Solution Approach 1:
The patent implements a feedback mechanism where correlation coefficients provide immediate, interpretable feedback on model-parameterization quality. The coefficient of determination and other correlation metrics clearly indicate whether parameterization is successful, allowing for single-pass or minimal-iteration optimization rather than repeated tuning, thereby improving modeling efficiency.
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
A general aspect of the present disclosure relates to a computer-implemented method. The method comprises determining a validation metric based on the determination of coefficients using an evaluation of a training data set containing initial results of a simulation with a first plurality of parameter settings. The evaluation of the training data set includes the result of a comparison between the training data set and a measurement data set in the form of a face validation. The method comprises receiving a test data set containing second results of a simulation with a second plurality of parameter settings. The method comprises applying the validation metric to the test data set and determining a plurality of validation values depending on the second plurality of parameter settings. The method comprises determining a target parameter setting for the simulation based on the plurality of validation values.