File Exchange

image thumbnail

Speed-sensorless induction motor drive

version 1.1 (321 KB) by

A neuroestimator is used to enable speed-sensorless operation of the asynchronous motor drive.



View License

This model demonstrates possibility to use a feedforward neural network (static neural network) to estimate (more precisely to approximate) mechanical speed of the induction motor. The main challenge in such a task is to construct an effective approximation base. Here the 6 heuristic signals described in are used. It should be noted that any estimation method that exploits only fundamental excitation (fundamental model) fails at zero stator flux frequency. The induction motor becomes an unobservable system at zero stator frequency. The proposed solution also has this limitation. If control at zero frequency is required, other techniques have to be implemented. For more hints see e.g. . For some details on the analytical controller tuning in this particular drive, please see .

Comments and Ratings (3)

Dear Gao Xiang,
They are, respectively, the modulus of the stator current and voltage space vectors, the real and imaginary instantaneous powers (please see Akagi et al.), and the real and imaginary part of the instantaneous impedance. More info can be found in our papers. Good luck with your experiments!

gao xiang

gao xiang

GOOD .but who can tell me the' 6 heuristic signs 'means? please tell email



All controllers are now tuned analytically. For more details please see .


All controllers are now tuned analytically. For more details please see .

MATLAB Release
MATLAB 8.1 (R2013a)

MATLAB Online Live Editor Challenge

Win cash prizes and have your live script featured on our website

Learn more

Download apps, toolboxes, and other File Exchange content using Add-On Explorer in MATLAB.

» Watch video