Title:
PERMANENT-MAGNET SYNCHRONOUS MOTOR RANDOM-FILTERING NEURAL NETWORK CONTROL METHOD WHICH TAKES IRON LOSS INTO CONSIDERATION
Document Type and Number:
WIPO Patent Application WO/2020/155509
Kind Code:
A1
Abstract:
Provided is a permanent-magnet synchronous motor random-filtering neural network control method which takes iron loss into consideration, belonging to the technical field of permanent-magnet synchronous motor position-tracking control. The method addresses the control accuracy requirements of permanent magnet synchronous motors and the problem of random disturbance and nonlinearity in drive systems; in conventional backstepping methods, a command filtering technology is introduced to solve the problem of "calculation explosion" in the calculation process; at the same time, a neural network is used to approximate the nonlinear function in the system and construct a neural network adaptive position tracking controller. The invention ensures that the tracking error of the system can converge to within a sufficiently small neighborhood of the origin, has higher operating efficiency, stronger interference resistance capability, and better control performance.
More Like This:
Inventors:
YU JINPENG (CN)
MA YUMEI (CN)
LIU ZHANJIE (CN)
CHENG SHUAI (CN)
FU CHENG (CN)
WANG MENGMENG (CN)
MA YUMEI (CN)
LIU ZHANJIE (CN)
CHENG SHUAI (CN)
FU CHENG (CN)
WANG MENGMENG (CN)
Application Number:
PCT/CN2019/090499
Publication Date:
August 06, 2020
Filing Date:
June 10, 2019
Export Citation:
Assignee:
UNIV QINGDAO (CN)
International Classes:
H02P6/34
Foreign References:
| CN106533313A | 2017-03-22 | |||
| CN104993760A | 2015-10-21 | |||
| CN106655962A | 2017-05-10 |
Attorney, Agent or Firm:
QINGDAO ZHIDILINGCHUANG PATENT AGENCY CO.,LTD (CN)
Download PDF: