Behavioral Modeling of Phase-Locked Loop using Deep Learning

Overview

A Phase-Locked Loop (PLL) is a feedback control system that synchronizes an output signal's phase and frequency with a reference signal. This project focuses on learning the PLL’s dynamic behavior using data-driven deep learning models.

This project focuses on developing a behavioral model of a Phase-Locked Loop (PLL) using deep learning techniques. The goal is to approximate the input-output behavior of a PLL using data-driven models instead of detailed circuit-level simulations.

This project is developed as part of the MathWorks MATLAB & Simulink Challenge.

Objectives

• Design and simulate a basic PLL using Simulink
• Generate input-output datasets from the PLL
• Train a deep learning model to learn PLL behavior
• Compare predicted outputs with actual simulation results

Tools Used

• MATLAB
• Simulink
• Deep Learning Toolbox

Project Structure

PLL-Behavioral-Modeling-DeepLearning/ ├── main.m ├── simulink/ ├── data/ ├── models/ ├── scripts/ ├── results/ └── README.md

Results

Simulation results and prediction plots will be added after model training.

How to Run

1. Open MATLAB
2. Set the project directory as the current folder
3. Run main.m

Status

🚧 Project under active development