Title :
Application research of PID neutral network control for traction drive inverter
Author :
Ge, Xinglai ; Feng, Xiaoyun
Author_Institution :
Sch. of Electr. Eng., Southwest Jiaotong Univ., Chengdu
Abstract :
This paper presents a study on PID neural network control used in traction inverter drive system. The analysis is based on structure of three level inverter, motor dynamic d-q equivalent circuit, and direct rotor field-oriented vector control mathematical equation. A direct vector control system of synchronous current control with feedforward CEMF compensation is built. Speed loop and flux loop controllers are realized with PID neural network. Training methods of feedforward neural network and back propagation are also given. MATLAB simulation results show good performance of the system in transient and stable stage.
Keywords :
backpropagation; compensation; electric current control; feedforward neural nets; invertors; machine vector control; neurocontrollers; three-term control; traction motor drives; velocity control; PID neural network control; back propagation; direct rotor field-oriented vector control mathematical equation; feedforward CEMF compensation; flux loop controller; motor dynamic d-q equivalent circuit; speed loop controller; synchronous current control; three level inverter; traction inverter drive system; Control systems; Equations; Equivalent circuits; Inverters; Machine vector control; Neural networks; Rotors; Synchronous motors; Three-term control; Traction motors; Neutral network control; space vector; three level inverter; traction drive;
Conference_Titel :
Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-2113-8
Electronic_ISBN :
978-1-4244-2114-5
DOI :
10.1109/WCICA.2008.4593310
