AI Virtual Wind Tunnel for Aerodynamic Design Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Aerodynamically optimizing vehicle exterior surface geometries is a complex and time-consuming process, requiring multiple iterations of design and analysis, and traditional methods like clay modeling and wind tunnel testing are limited and labor-intensive.
Innovation Solution
The development of AI-powered virtual wind tunnels (AIVWT) integrated with computational fluid dynamics (CFD) simulation systems, which autonomously generate model training data and update shape-centric AI-based aerodynamics models to improve model accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If clay model process with wind tunnel testing is used, then aerodynamic measurements are obtained, but the process is time-consuming and labor-intensive
Solution Approach 1:
The patent creates digital copies (3D models) of physical clay models and uses computational simulations to replicate wind tunnel testing conditions. This allows aerodynamic measurements to be obtained from digital representations without repeatedly creating physical models and conducting actual wind tunnel tests for each design iteration.
Solution Approach 2:
The patent replaces the mechanical wind tunnel testing system with a computational fluid dynamics simulation system. Instead of physically moving models through a wind tunnel, the system uses computer-based simulations to predict aerodynamic characteristics, dramatically reducing the time and labor required while maintaining measurement capability.
2Productivity
If CFD simulation is used, then analysis time is reduced, but computational resources are required
Solution Approach 1:
The patent performs preliminary actions by creating comprehensive 3D digital models with detailed surface geometry before simulation. This preliminary digital preparation allows the CFD simulation to be more efficient and accurate, reducing the computational resources needed during the actual simulation phase while maintaining high productivity.
Solution Approach 2:
The patent applies CFD simulation selectively to specific design iterations and critical aerodynamic questions rather than performing exhaustive simulations on every possible design variation. This partial application of computational resources optimizes the balance between analysis speed and resource consumption.
3Measurement precision
If traditional wind tunnel testing is used, then static measurements are obtained, but predictive information for future designs is limited
Solution Approach 1:
The patent implements feedback mechanisms where CFD simulation results from current designs inform and guide future design iterations. The computational models provide predictive information about aerodynamic performance that feeds back into the design process, allowing designers to make informed decisions before creating physical models or conducting actual wind tunnel tests.
Solution Approach 2:
The patent performs preliminary CFD simulations on proposed designs before they are built or tested physically. This preliminary computational analysis provides predictive information about aerodynamic performance, allowing designers to evaluate multiple design options and make informed decisions before committing to physical prototyping or wind tunnel testing.
Data Source
AI summary
A method of operating a CFD system includes a system file interface receiving a data file defining a 3D model of a surface geometry, and a system controller extracting select surface information of the 3D model from the data file. The controller generates a DOE model set containing baseline and modified 3D models derived from the 3D model's extracted surface information, and determines for the baseline and modified 3D models if existing training geometry data is stored in a model training database. A CFD simulation module predicts new training model data, which contains a new training geometry data set for each baseline/modified 3D model that does not have existing training geometry data stored in the training database. An AI training module generates a trained model based on the new training model data; the model is integrated into the CFD simulation module for future simulations of aerodynamic characteristics of surface geometries.