基于忆阻模糊神经网络的PID参数自适应调节系统
By using a memristor-based fuzzy neural network, the conductance characteristics of the memristor are utilized to achieve full analog calculation and adaptive parameter adjustment. This solves the problems of timing delay and large hardware overhead in PID parameter adjustment of traditional fuzzy neural networks, and improves the performance and response speed of the control system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HUBEI UNIV
- Filing Date
- 2025-09-26
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional fuzzy neural networks suffer from timing delays, high hardware overhead, and poor parameter coupling in adaptive PID parameter adjustment, making it difficult to achieve effective adaptive PID parameter adjustment in dynamic environments.
A fuzzy neural network based on memristors is adopted to achieve full simulation calculation through the physical characteristics of memristor units. The mapping relationship between memristors and the activation intensity of fuzzy rules is established, and the PID parameters are dynamically updated using the conductivity characteristics. Independent proportional, integral, and derivative memristor arrays are designed to achieve adaptive adjustment of parameters.
It improves the performance and response speed of the control system, breaks through the timing bottleneck of traditional digital computing, reduces hardware overhead, and achieves collaborative optimization of PID parameters.
Smart Images
Figure CN121189378B_ABST