An Adaptive Dead-time Compensation Strategy for a Permanent Magnet Synchronous Motor Drive Using Neural Network


Vol. 6, No. 4, pp. 279-289, Oct. 2006
10.6113/JPE.2006.6.4.279


PDF    

 Abstract

This paper presents a neural network based adaptive dead-time compensation strategy for an inverter fed permanent magnet synchronous motor drive. The neural network is used for identifying the dead-time compensation time (DTCT) that includes an equivalent dead-time, turn-on/off time and on-state voltage components of the voltage source inverter. In order to train the neural network, desired DTCTs for eight operating points are prepared as training data. The trained neural network can identify a desired DTCT for any operating point because it has the capability of the interpolation. The accuracy of the identified DTCT is experimentally confirmed by comparing the calculated active power with a measured one


 Statistics
Show / Hide Statistics

Cumulative Counts from September 30th, 2019
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.



Cite this article

[IEEE Style]

N. Urasaki, T. Senjyu, T. Funabashi and H. Sekine, "An Adaptive Dead-time Compensation Strategy for a Permanent Magnet Synchronous Motor Drive Using Neural Network," Journal of Power Electronics, vol. 6, no. 4, pp. 279-289, 2006. DOI: 10.6113/JPE.2006.6.4.279.

[ACM Style]

Naomitsu Urasaki, Tomonobu Senjyu, Toshihisa Funabashi, and Hideomi Sekine. 2006. An Adaptive Dead-time Compensation Strategy for a Permanent Magnet Synchronous Motor Drive Using Neural Network. Journal of Power Electronics, 6, 4, (2006), 279-289. DOI: 10.6113/JPE.2006.6.4.279.