A Lightweight Decision Model Design for FPGA-based HighConcurrency Spacecraft Testing Systems
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
To address the high-concurrency challenges faced by spacecraft testing systems, a widely adopted and effective solution is to migrate the core task module of the testing system, the real-time decision subsystem, from the CPU to a highconcurrency FPGA.However, due to the limited chip area and the need to support programmability, FPGA hardware resources are inherently constrained.To address these resource limitations, we propose a decision model construction method that integrates hierarchical clustering and envelope interval computation.This method is further enhanced by iterative optimization through independent classification and dynamic confidence level adjustment, effectively minimizing errors introduced by the regression model.Additionally, we introduce a regression analysis approach to approximate envelope interval judgment rules with functional expressions, replacing discrete rule sets to achieve significant model storage reduction while maintaining decision accuracy and efficiency.Validation experiments comprehensively verify the accuracy and reliability of the method, demonstrating a substantial reduction in storage footprint (from 500MB to 1.47MB), effectively alleviating the restrictions imposed by FPGA chip storage resources.
Fields of Study & Subjects
Embedded Systems Design Techniques
Embedded Systems and FPGA Design
Embedded Systems and FPGA Applications
Publication details
- Journal / source
- International journal of high school research
- Volume
- 8
- Issue
- 4
- Pages
- 88–95
- Publication date
- 28 February 2026
- Language
- EN