Fault-Tolerant Control of Three-Motor Drive Based on Neural Network Right Inversion

被引：0

作者：

Chen, Jie ^{[1
]}

Liu, Guohai ^{[1
]}

Zhao, Wenxiang ^{[1
]}

Chen, Qian ^{[1
]}

Zhou, Huawei ^{[1
]}

Zhang, Duo ^{[1
]}

机构：

[1] Jiangsu Univ, Sch Elect & Informat Engn, Zhenjiang 212013, Peoples R China

来源：

2016 19TH INTERNATIONAL CONFERENCE ON ELECTRICAL MACHINES AND SYSTEMS (ICEMS 2016) | 2016年

基金：

美国国家科学基金会;

关键词：

Decoupling control; fault-tolerant control; neural network; three-motor drive; PERMANENT-MAGNET MOTOR; DIAGNOSIS; SYSTEM;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Fault-tolerant operation of multi-drive is an important aspect of system reliability in specific fields such as electric vehicles and rail transits. This paper proposes a new fault-tolerant control strategy for three-motor drive based on neural network right inversion (NNRI). The key of this strategy is to use NNRI to approximate the right-inverse system of three-motor drive under both healthy and faulty condition. A pseudo-linear system is completed by constructing the NNRI system and combing it with three-motor drive. The capability of fault tolerance can be enhanced. Meanwhile, the proposed strategy can solve the coupling problem effectively between speed and tension. Simulation results are given for verification.

引用

页数：4

共 13 条

[1] Nonlinear sliding-mode control of a multi-motor web-winding system without tension sensor [J].