Designing an ANN-Based MPPT for Solar PV Battery-Powered BLDC Motor
Introduction
We will explore the design and implementation of an Artificial Neural Network (ANN)-based Maximum Power Point Tracking (MPPT) system for a Solar PV (Photovoltaic) battery-powered BLDC (Brushless DC) motor. This system is designed to optimize the power output efficiency of the motor by dynamically adjusting the operating point of the PV panels.
Motor Specifications
The motor under consideration for this project is a 24V, 40W BLDC motor. Here are its key specifications:
Rated Power: 40 watts
Rated Voltage: 24 volts
Rated Speed: 3000 RPM
Rated Torque: 0.125 Nm
Peak Current: 7.5 amps
Peak Torque: 0.375 Nm
Inertia: 0.33 kg cm^2
Torque Constant: 0.05 Nm/A
Voltage Constant: 5.235 volts/krpm
Line-Line Resistance: 1.35 ohms
Line-Line Inductance: 0.9 mH
Power Source: Solar PV System
The power for the BLDC motor is sourced from a solar PV system. The specifications of the solar PV system are:
PV Panel Power: 100 watts
PV Panel Voltage: 17 volts (at maximum power point)
PV Panel Current: 2.941 amps (at maximum power point)
Number of Panels: 2 panels in parallel (total 100 watts)
Battery System
A battery system is also integrated to store excess energy and ensure continuous operation of the motor:
Battery Voltage: 12 volts (nominal), configured to provide 24 volts output
Battery Capacity: 100 Ah
System Components
The system includes:
Boost Converter: Converts lower voltage from PV panels (17V) to the motor's operating voltage (24V).
Bidirectional Converter: Interfaces between the battery system (12V) and the motor (24V), facilitating both charging and discharging operations.
MPPT Algorithm
The MPPT algorithm implemented in this system utilizes an Artificial Neural Network (ANN) to dynamically track and adjust the operating point of the PV panels. It considers irradiation and temperature as inputs to generate a reference voltage for the boost converter, ensuring maximum power extraction from the solar panels.
Control Mechanisms
PV Side Control: Uses an ANN-based MPPT algorithm to adjust the duty cycle of the boost converter based on irradiation and temperature inputs.
Battery Side Control: Maintains the battery voltage at 24 volts using a proportional-integral (PI) controller to regulate the bidirectional converter.
Power Management: Ensures seamless power flow between the PV panels, battery, and the BLDC motor based on real-time power demands and availability.
Operation
The system operates as follows:
Power Generation: PV panels generate power based on available sunlight.
MPPT Tracking: The ANN-based MPPT continuously adjusts the PV panel operating point to maximize power output.
Battery Management: During excess power generation, the battery charges; when power demand exceeds PV output, the battery supplements the motor's power requirement.
Motor Operation: The BLDC motor operates at optimal performance levels, ensuring efficient utilization of available power.
Simulation and Results
Simulation results demonstrate:
PV Panel Output: Power generation and current levels based on varying irradiation (1000 W/m^2, 600 W/m^2, etc.).
Battery Charging: Battery state-of-charge (SoC) changes based on charging and discharging modes.
Motor Performance: Speed, torque, and current consumption of the BLDC motor under different operating conditions.
Conclusion
This project highlights the integration of renewable energy sources (solar PV) with energy storage (battery) and efficient motor control (BLDC) using advanced control algorithms like ANN-based MPPT. Such systems are crucial for sustainable energy applications where maximizing energy efficiency and utilization are paramount.
Comments