I will be working this summer on a paper about applying AI algorithms in control theory, i think induction motor control is a very interesting topic and i have found some papers about applying indirect field oriented control using neural networks but they are quite old (late nineties)

The question is :

1-Is there any need to have a better method to control IM rather than FOC? Or simply what are the problems in controlling an induction motor?

2-another topic i found interesting, Is it important to have a POSITION control for an induction motor? I mean like we need to have large expensive steppers or servos to have accurate position control...Would it be better if IM can serve in such a field?

and thanks :)


closed as unclear what you're asking by brhans, Eugene Sh., Olin Lathrop, Voltage Spike, Lior Bilia May 15 '18 at 17:31

Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • 1
    \$\begingroup\$ Welcome to EE.SE. Please fix your question title. \$\endgroup\$ – Transistor May 9 '18 at 20:46
  • \$\begingroup\$ Yes, FOC is not easy. How is it related to neural networks - is a complete mystery to me. \$\endgroup\$ – Eugene Sh. May 9 '18 at 20:50
  • \$\begingroup\$ The "field oriented control" I know about has to do with motors. I don't know how that's supposed to be relevant to neural networks though. If the title and question hadn't been written so sloppily, I might have tried to work with you to understand the question. But, due to the disrespect of the volunteers here, I'm just going to vote to close for the nearest handy reason, downvote, and move on. \$\endgroup\$ – Olin Lathrop May 9 '18 at 21:41
  • \$\begingroup\$ first of all, i apologize for this vague question i should have said more details...second, i dont know where is the disrespect part that made you so angry.....whatever...... thats my fault, i should have added the paper link. \$\endgroup\$ – Mark Naeem May 9 '18 at 23:29
  • \$\begingroup\$ Carelessly written questions are not well received. Those who write such questions are not taken as seriously as those who take more care. The harder working volunteers like Olin Lathrop can get quite impatient with carelessness. \$\endgroup\$ – Charles Cowie May 9 '18 at 23:49

AC motor speed and torque control can be quite complex. Field oriented control offers the highest level of control and is probably more complex than other methods, but sensorless control methods that seek to approach the highest level of performance can also be quite complex. I don't believe that AC motor controls on the market use neural networks.

There is a large market for induction motor speed and torque control. There is probably a small part of that market that requires position control.

There are recent papers about neural networks used in AC motor control, not necessarily field oriented control.

  • \$\begingroup\$ Thanks Eng. Charles, I was Asking this question because i will be working on a research paper this summer and I'm planning to use things i know about AI in control theory, i wanted to know if field-oriented control is just enough and no need to any simplification. \$\endgroup\$ – Mark Naeem May 10 '18 at 8:40

Not the answer you're looking for? Browse other questions tagged or ask your own question.