PID_NN is a project that integrates Proportional-Integral-Derivative (PID) control mechanisms to optimize neural networks in the context of electrical circuits. By leveraging PID controllers, the system dynamically tunes network parameters to improve convergence, stability, and performance for modeling and control tasks in electrical systems.
This project was made for a coursework to demonstrate usage of neural network in electrical systems, which blends control theory with machine learning for advanced circuit applications.
- PID-Driven Optimization: Use PID control loops to fine-tune neural network parameters dynamically.
- Electrical Circuit Simulation: Interface with electrical circuit models to evaluate network predictions and adjust based on feedback.
- Customizable PID Parameters: Flexible configuration for proportional, integral, and derivative gains.
- Performance Tracking: Logs and visualizations for network optimization progress.