Voltage tracking of a DC-DC buck converter using neural network control

• Main Author: Mohamad Narsardin, Mohamad Adhar
• Format: Thesis
• Language: English; English; English
• Published: 2012
• Subjects: TK Electrical engineering. Electronics Nuclear engineering; TK7800-8360 Electronics
• Online Access: http://eprints.uthm.edu.my/2274/1/24p%20MOHAMAD%20ADHAR%20MOHAMAD%20NARSARDIN.pdf; http://eprints.uthm.edu.my/2274/2/MOHAMAD%20ADHAR%20MOHAMAD%20NARSARDIN%20COPYRIGHT%20DECLARATION.pdf; http://eprints.uthm.edu.my/2274/3/MOHAMAD%20ADHAR%20MOHAMAD%20NARSARDIN%20WATERMARK.pdf; http://eprints.uthm.edu.my/2274/

This master report presents a voltage tracking of a neural network for dc-dc buck converter. The mathematical model of Buck converter and artificial neural network algorithm is derived. The dc-dc Buck converter is designed to tracking the output voltage with three variation. This master report consists open loop control, closed loop control and neural network control. The Buck converter has some advantages compare to the others type of dc converter. However the nonlinearity of the dc-dc Buck converter characteristics, cause it is difficult to handle by using conventional method such as open loop control system and close loop control system like proportional-integral-differential (PID) controller. In order to overcome this main problem, a neural network controller with online learning technique based on back propagation algorithm is developed. The effectiveness of the proposed method is verified by develop simulation model in MATLAB-Simulink program. The simulation results show that the proposed neural network controller (NNC) produce significant improvement control performance compare to the PID controller for both condition for voltage tracking output for dc-dc Buck converter.