Vehicle Durability Mesh Data Filtering and Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for evaluating the durability performance of vehicles, such as the Belgian durability test, are time-consuming, especially when conducted in a virtual environment, and lack efficient tools for data extraction and analysis.
Innovation Solution
A method and system that utilize three-dimensional (3D) data to evaluate vehicle durability performance by filtering and processing data from meshes representing the vehicle body, using a data filter, binary classifier, and probability inferring unit to determine durability performance and optimize model parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If Belgian durability test is conducted in a virtual environment, then durability performance data can be extracted for evaluation, but the simulation process takes a lot of time
Solution Approach 1:
The patent segments the vehicle body into multiple meshes and processes durability evaluation for each mesh independently. This allows parallel processing of different mesh regions, significantly reducing the overall simulation time while maintaining accurate durability performance data extraction for each segmented component.
Solution Approach 2:
The patent performs preliminary filtering of mesh data before detailed durability analysis. By pre-identifying and filtering relevant mesh data that meets specific criteria, the system prepares data in advance for faster processing during the actual durability evaluation, reducing the time required for comprehensive analysis.
2Measurement precision
If data filtering criteria are made more stringent to improve durability evaluation accuracy, then measurement precision improves, but the complexity of the evaluation system increases
Solution Approach 1:
The patent employs multiple filtering criteria with different parameter thresholds to evaluate mesh durability. By systematically adjusting and applying different parameter thresholds (such as stress concentration factors, material properties, and geometric constraints), the system achieves high measurement precision through quantitative parameter-based filtering rather than complex qualitative analysis.
Solution Approach 2:
The patent replaces complex manual durability evaluation processes with automated computational algorithms. The filtering and classification of mesh data are performed automatically using programmed criteria, substituting what would otherwise require complex manual mechanical inspection systems with efficient computational methods.
3Measurement precision
If the model parameter is tuned to reduce misclassification rate, then durability evaluation accuracy improves, but the time required for optimization increases
Solution Approach 1:
The patent implements feedback mechanisms where the durability evaluation system continuously assesses classification results and adjusts filtering criteria and model parameters accordingly. By incorporating feedback loops that learn from evaluation outcomes, the system optimizes parameters efficiently without requiring extensive manual tuning, reducing optimization time while maintaining high classification accuracy.
Solution Approach 2:
The patent applies filtering criteria and model parameters that may be more stringent than absolutely necessary, processing slightly more data than minimal requirements. This partial excess approach ensures high classification accuracy by capturing edge cases and rare durability issues, while the systematic methodology prevents excessive optimization time by establishing clear stopping criteria.
Data Source
AI summary
A durability evaluation method performed by a processor including filtering, by a data filter, a first data set for each of a plurality of meshes of a target vehicle and a second data set with an adjusted material or thickness of the target vehicle to output data, determining, by a binary classifier, the first synthetic data for indicating durability performance less than a predetermined threshold value from feature data from the filtered data and the first synthetic data, generating, by a probability inferring unit, second output data for representing the probability belonging to each of a predetermined number of durability probability sections, from the durability performance of the first output data and the second synthetic data, and determining a plurality of hyperparameter values constituting each of the data filter, the binary classifier, and the probability inferring unit.