集成电路供电电源功率融合自愈控制方法及装置
By monitoring the output voltage and current of the power module and using predictive models and liquid neural networks to predict voltage status, the self-healing control of the power architecture is achieved, solving the problem of voltage quality degradation, ensuring uninterrupted power supply, and improving the utilization rate of the power module.
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 the existing technology, the power architecture with multiple power modules connected in parallel cannot prevent voltage quality degradation when one or more modules fail, resulting in insufficient system output power. Furthermore, the switching process can cause power outages or voltage transients, reducing the system's lifespan utilization.
By synchronously monitoring the output voltage and current of the power module, and using a preset performance degradation prediction model and liquid neural network, the future voltage state of the power module is predicted, the health status is calculated, and power synthesis instructions are generated to achieve power compensation and avoid voltage quality degradation.
It enables preventative compensation before voltage quality deteriorates, avoiding voltage drops and transients, ensuring uninterrupted power supply, and improving the utilization rate of the power module.
Smart Images
Figure CN122092666B_ABST
Abstract
Citation Information
Patent Citations
Predictive control method for bus voltage stabilization of multi-source-load power supply system
CN117674065A
Phase modifier unit state monitoring and load control method and system for reactive power compensation of power grid
CN121485172A