Research and Simulation of SVPWM Algorithm Based on BP Neural Network

Hua Ji; Zhi Yong Li

doi:10.4028/www.scientific.net/KEM.693.1391

Paper Titles

Fault Feature Extraction Method of the Rolling Element Bearing Based on Reverse Order Tracking
p.1361

Fault Tree Analysis of Pantograph Type Current Collector Based on Ontology Modeling
p.1371

One Abstraction Method for Displacement Response in the Sweep-Frequency Testing of Rotating Spindle
p.1377

Petri Nets in the Emu Pantograph Application of Fault Tree Analysis (FTA)
p.1385

Research and Simulation of SVPWM Algorithm Based on BP Neural Network
p.1391

Research of Multi-Sensor Data Fusion Based on Binocular Vision Sensor and Laser Range Sensor
p.1397

Research on SVM Based Diagnosis System for Oil Tubing
p.1405

Rolling Bearing Fault Evolution Based on Vibration Time-Domain Parameters
p.1412

SIFT-Based Target Recognition in Robot Soccer
p.1419

HomeKey Engineering MaterialsKey Engineering Materials Vol. 693Research and Simulation of SVPWM Algorithm Based...

Research and Simulation of SVPWM Algorithm Based on BP Neural Network

Abstract:

In this paper, a space vector PWM (SVPWM) control algorithm based on BP neural network is proposed to cope with the complex calculation required in SVPWM through analyzing SVPWM for three phase voltage fed inverter. This method uses the strong nonlinear approximation ability of the BP neural network to fit the eqivalent segment SVPWM modulated wave, modulate with the triangular carrier wave, and then get the control signals of the three phase voltage inverter. A simulation model for PMSM control system was developed by MATLAB/Simulink with the neural network Toolbox. The results show that the BP neural network based SVPWM algorithm makes the motor control system has a smaller current harmonics and torque ripple, and reduce the amount of computation in digital control system with strong guidance.

You might also be interested in these eBooks

Advanced Materials and Manufacturing Technology II

View Preview

Info:

Periodical:

Key Engineering Materials (Volume 693)

Pages:

1391-1396

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.693.1391

Citation:

Cite this paper

Online since:

May 2016

Authors:

Hua Ji*, Zhi Yong Li

Keywords:

BP Neural Network, MATLAB Simulation, PMSM, SVPWM

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

* - Corresponding Author

References

[1] Pinto JOP, Bose BK, da Silva LEB, et al. A neural-network-based space-vector PWM controller for voltage-fed inverter induction motor drive[J]. Industry Applications, IEEE Transactions on, 2000, 36(6): 1628-1636.

DOI: 10.1109/28.887215

Google Scholar

[2] Masood Azadi, Wavenet Based Vector Control of a Permanent Magnet Synchronous Motor Drive, in IEEE Digital Object Identifier , vol. 2, 2007, pp.1663-1668.

DOI: 10.1109/iemdc.2007.383679

Google Scholar

[3] YANG X, WANG G, MA J. The Realization of SVPWM Based on ANN with Matlab/Simulink[J]. Micromotors Servo Technique, 2007, 3: 007.

Google Scholar

[4] Yongan Huang, MATLAB7. 0/Simulink6. 0 Modeling Simulation Development and Senior Engineering Application. Beijing: Tsinghua University Press, (2005).

Google Scholar

[5] Tinglong Pan, Zhicheng Ji, Linbo Xie, Yanxia Shen, A New Kind of SVPWM Controller Design Based on ANN, Journal of System Simulation, Vol. 19 No. 2, pp.420-423, (2006).

Google Scholar

[6] KOU Z, LIU W. Research and Simulation of BP Network-based SVPWM Algorithm[J]. Control and Instruments in Chemical Industry, 2011, 2: 017.

Google Scholar

[7] Xianzhong Dai, Guohai Zhang, Xinghua Zhang, Neural Network Inverse Control for AC Drive. Beijing: Mechanical Industry Press, (2007).

Google Scholar

[8] Yafei Tian, Voltage Space Vector Pulse Width Modulation (SVPWM) Algorithm Simulation and Analysis, Proceeding of the CSU-EPSA, Vol. 16 No. 04, pp.68-71, (2004).

Google Scholar