集成电路供电电源解析冗余自愈控制方法及装置
By using multi-sensor data fusion and reinforcement learning algorithms, the problem of unstable secondary power supply output in aging tests was solved, enabling accurate evaluation and adaptive control of the secondary power supply system, thus improving the reliability and efficiency of aging tests.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HANGZHOU INTERNATIONAL INNOVATION INSTITUTE OF BEIHANG UNIVERSITY
- Filing Date
- 2026-04-23
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, the output voltage fluctuations and output power of the secondary power supply do not meet the test requirements during the aging test, resulting in reduced reliability and consistency of the aging test. Insufficient sensor accuracy and untimely signal calibration increase the test risk.
By acquiring operational data from multiple sensors in the aging bench monitoring system, and utilizing an adaptive Kalman filter driven by a hypernetic network and reinforcement learning algorithms, data fusion and multi-task state evaluation are performed to generate output voltage, ripple voltage, and health status evaluation results for the secondary power supply. Based on the evaluation results, the parameters of the PID controller are updated to achieve self-healing control of the secondary power supply.
It improves the accuracy of condition monitoring and output power control of the secondary power system, realizes stable operation and online adaptive adjustment of the secondary power system, and ensures the reliability and consistency of aging tests.
Smart Images
Figure CN122092644B_ABST