The paper discusses the design and DSP implementation of artificial-intelligence-based (AIB) speed estimators for control applications in electromechanical drives. The design and performance of AIB estimators based on feedforward and recursive artificial neural networks (ANNs), associative memory networks (AMNs) and neuro-fuzzy networks (NFNs) are compared and discussed. Emphasis is placed on the development of minimal configuration estimators with a view to reducing DSP requirements. It is shown that it is an advantage of the AIB approach to estimator design that neither a conventional drive model nor a knowledge of any drive parameters are required and that an estimate of rotor speed can be obtained using only measurements of supply voltages and/or currents. The DSP system used is based on the Texas Instruments TMS320C31 mounted in a host PC. Results are presented for the real-time application to the speed control of a small DC drive and the estimators are shown to provide a sufficiently accurate speed estimate resulting in stable, robust, speed control. The DSP requirements and performances of each of the estimator forms are presented and compared and it is shown that the overheads imposed by implementation of these estimators is small.
References
-
-
1)
-
B. Hassibi ,
D.G. Stork
.
(1993)
Second order derivatives for network pruning: optimal brain surgeon, Advances in neural information processing systems.
-
2)
-
L. Ljung
.
Asymptotic behaviour of the extended Kalman filter as a parameter estimatorfor linear system.
IEEE Trans. Automatic Control
,
36 -
50
-
3)
-
Hansen, L.K., Pedersen, M.W.: `Controlled growth of cascade correlation nets', Proceedings of ICANN '94, 1994, Italy, p. 797–800.
-
4)
-
Rao, D.H., Gupta, M.M.: `A neural processor for coordinating multiple systems with dynamic uncertainties', Proceedings of international symposium on Uncertainty andmanagement, 1993, Maryland, p. 633–640.
-
5)
-
Hennenberger, H., Otto, B.: `Sensorless operation of DC machines using neural networks', SPEEDAM, 1994, p. 77–82.
-
6)
-
P. Vas
.
(1992)
Electrical machines and drives: a space-vector theory approach.
-
7)
-
Bossley, K.M.: `Neurofuzzy modelling approaches in system identification', 1997, PhD, University of Southampton, Department of Electronics and Computer Science.
-
8)
-
L. Ljung
.
(1987)
System identification - theory for the user.
-
9)
-
Damiano, A., Vas, P., Marongiu, I., Stronach, A.F.: `Comparison of speed sensorless DTC induction motor drives', PCIM 97, 1997, Nurnberg, p. 1–12.
-
10)
-
L.-X. Wang
.
(1994)
Adaptive fuzzy systems and control,.
-
11)
-
P. Vas
.
(1993)
Parameter estimation, diagnosis and condition monitoring of electricalmachines.
-
12)
-
P. Vas
.
(1990)
Vector control of AC machines.
-
13)
-
D.R. Hush ,
W.G. Horne
.
Progress in supervised neural networks.
IEEE Signal Process. Mag.
,
8 -
39
-
14)
-
A.F. Stronach ,
P. Vas ,
M. Neuroth
.
Implementation of intelligent self-organising controllers in DSP-controlledelectromechanical drives.
IEE Proc. Control Theory Appl.
,
4 ,
324 -
330
-
15)
-
K. Fukunaga
.
(1991)
Introduction to statistical pattern recognition.
-
16)
-
A. Waibel ,
G. Hanazawa ,
K. Hinton ,
K. Shikano ,
K.J. Lang
.
Phoneme recognition using time delayneural networks.
IEEE Trans. Acoust., Speech Signal Process.
,
3 ,
328 -
339
-
17)
-
Roberts, J.M., Mills, D.J., Charnley, D., Harris, C.J.: `Improved Kalman filter initialisation using neurofuzzy estimation', Proceedings of 4th international conference on Artificialneural networks, 1995, IEE, Cambridge, p. 329–334.
-
18)
-
Beierke, S., Vas, P., Simor, B., Stronach, A.F.: `DSP-controlled sensorless ac drives using the extendedKalman filter', PCIM 97, 1997, Nurnberg, p. 31–41.
-
19)
-
K. Warwick ,
G.W. Irwin ,
K.J. Hunt
.
(1992)
Neural networks for control and systems.
-
20)
-
K.J. Hunt ,
G.W. Irwin ,
K.J. Warwick
.
(1995)
Neural network engineering in dynamical control systems.
-
21)
-
Norgaard, M.: `Neural network based system identification toolbox', 95E–773, Tech. Report, 1995.
-
22)
-
J.S. Albus
.
A new approach to manipulator control: the cerebellar model articulationcontroller (CMAC).
Trans. ASME J. Dyn. Syst. Meas. Control
,
3 ,
220 -
227
-
23)
-
J. Moody ,
C. Darken
.
Fast learning networks of locally-tuned processing units.
Neural Comput.
,
281 -
294
-
24)
-
F. Rosenblatt
.
The perceptron: a probabilistic model for information storage and organisationin the brain.
Psychol. Rev.
,
386 -
408
-
25)
-
M. Brown ,
C. Harris
.
(1994)
Neurofuzzy adaptive modelling and control.
-
26)
-
M. Shirsavar ,
M.D. McCulloch
.
Speed sensorless vector control of induction motors with parameter estimation.
IEE, PEVD
,
267 -
272
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-cta_19981894
Related content
content/journals/10.1049/ip-cta_19981894
pub_keyword,iet_inspecKeyword,pub_concept
6
6