一种基于四维表征指标构建的关键区域识别方法
By constructing a four-dimensional characterization index system and using Latin hypercube sampling and Pareto dominance relation to identify key regions of aero-engines, the problems of low identification accuracy and efficiency in existing technologies have been solved, and the precise allocation of test resources and cost reduction have been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NAT UNIV OF DEFENSE TECH
- Filing Date
- 2026-04-21
- Publication Date
- 2026-07-17
AI Technical Summary
Existing key area identification methods lack a unified metric standard in digital twin testing of aero-engines, and cannot accurately capture gradient abrupt changes near the compressor surge line and local extreme values of turbine blade thermal load, resulting in unreasonable allocation of test resources and low identification accuracy and efficiency.
Sample points are generated using Latin hypercube sampling. Response values are calculated using a digital space-driven engine performance model. A four-dimensional characterization index vector is constructed, including information surface entropy, maximum gradient consistency, local-global similarity divergence, and local-global extreme point ratio. Combined with Pareto dominance and non-dominated sorting, key regions are selected.
It achieves comprehensive capture of key regional features, provides unified quantitative standards and verification basis, guides the precise allocation of experimental resources, improves experimental efficiency and reduces costs, and enhances the utilization efficiency of digital twin experimental resources.
Smart Images
Figure CN122113449B_ABST