A system for estimating an acceleration coefficient interval
CN122020185BActive Publication Date: 2026-07-03HANGZHOU INTERNATIONAL INNOVATION INSTITUTE OF BEIHANG UNIVERSITY
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HANGZHOU INTERNATIONAL INNOVATION INSTITUTE OF BEIHANG UNIVERSITY
- Filing Date
- 2026-04-13
- Publication Date
- 2026-07-03
AI Technical Summary
Technical Problem
Existing acceleration factor estimation techniques lack interval estimation methods, have unsuitable sampling methods, insufficient interval coverage, and lack verification mechanisms, resulting in low reliability assessment credibility.
Method used
Failure sample data were obtained through test-to-failure testing, and a joint likelihood function integrating stress was constructed. A two-level bootstrap sampling method was adopted, combining the stress layer and the degradation feature layer, to directly solve the acceleration coefficient range.
Benefits of technology
It achieves effective coverage and accurate estimation of the acceleration factor, provides a quantitative risk boundary for equipment reliability assessment, and improves the credibility of interval estimation.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122020185B_ABST
Abstract
This invention discloses an acceleration factor interval estimation system. It obtains sufficient and complete failure sample data through test-to-failure testing, designs a dual-layer bootstrap sampling rule of "stress layer and degradation feature layer," and generates multiple sets of failure sample combinations. Simultaneously, it integrates the full-process degradation data of failure samples under dual stress, constructs a cross-stress integrated joint likelihood function, directly solves the acceleration factor for each combination, and finally determines the acceleration factor interval through statistical analysis. This invention addresses the problems of existing acceleration factor estimation methods, which can only achieve point estimation, lack effective interval estimation adapted to the characteristics of test-to-failure data, and fail to cover parameter fluctuations in failure scenarios, as well as the error accumulation issues inherent in traditional step-by-step solutions. This system improves the accuracy of acceleration factor estimation and the reference value of the interval.
Need to check novelty before this filing date? Find Prior Art