Identification and control of induction motor stator currents using fast on-line random training of a neural network

被引:40
作者
Burton, B [1 ]
Kamran, F [1 ]
Harley, RG [1 ]
Habetler, TG [1 ]
Brooke, MA [1 ]
Poddar, R [1 ]
机构
[1] GEORGIA INST TECHNOL, SCH ELECT & COMP ENGN, ATLANTA, GA 30332 USA
关键词
induction motor; motor current regulator; neural network; on-line training;
D O I
10.1109/28.585860
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Artificial neural networks (ANN's), which have no off-line pretraining, can be trained continually on-line to identify an inverter-fed induction motor and control its stator currents, Due to the small time constants of the motor circuits, the time to complete one training cycle has to be extremely small, This paper proposes and evaluates a new form of the random weight change (RWC) algorithm, which is based on the method of random search for the error surface gradient, Simulation results show that the new form of the RWC, termed continually online trained RWC (COT-RWC), yields performance very much the same as conventional backpropagation with on-line training, Unlike backpropagation, however, the COT-RWC method can be implemented in mixed digital/analog hardware and still have a sufficiently small training cycle time, The paper also proposes a VLSI implementation which completes one training cycle in as little as 8 mu s. Such a fast ANN can identify and control the motor currents within a few milliseconds and, thus, provide self-tuning of the drive while the ANN has no prior information whatsoever of the connected inverter and motor.
引用
收藏
页码:697 / 704
页数:8
相关论文
共 9 条
[1]   OBSERVERS FOR INDUCTION-MOTOR STATE AND PARAMETER-ESTIMATION [J].
ATKINSON, DJ ;
ACARNLEY, PP ;
FINCH, JW .
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 1991, 27 (06) :1119-1127
[2]  
BUHL MR, 1991, IEEE IAS ANN M, P415
[3]  
BURTON B, 1994, IEEE IND APPLIC SOC, P1836, DOI 10.1109/IAS.1994.377679
[4]  
BURTON B, 1994, IEEE IND APPLIC SOC, P1733, DOI 10.1109/IAS.1994.377662
[5]  
CANCELO G, 1994, IEEE IND ELEC, P1396, DOI 10.1109/IECON.1994.397999
[6]  
EIDE A, 1994, WNN FNN WASH DC DEC
[7]  
HIROTSU K, 1993, P INT JOINT C NEUR N, P3031
[8]  
PARK C, 1993, P INT JOINT C NEUR N, P3035
[9]  
WISHART MT, 1993, IAS 93, PTS 1-3, P703, DOI 10.1109/IAS.1993.298875