DSP implementation of neural network speed estimator for inverter fed induction motor

Sobczuk, D.L.; Grabowski, Piotr

doi:10.1109/iecon.1998.724227

Cited by 4 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It must be noted here that a similar approach was described in [30] using the VM for the rotor flux estimation. However, as will be described later, many problems are associated with using such model especially at low speed.…”

Section: Nn Stator-current Mras Observermentioning

confidence: 98%

“…However, the main drawback associated with VM implementation is the use of a pure integration which can cause dc drift, sensitivity to machine parameter variation, accurate stator voltage and current acquisition. These problems are not investigated in [30] and no low-speed results were shown especially during regeneration. Hence, the VM is unsuitable for low-speed operation.…”

Section: Rotor Flux Estimation Problemmentioning

confidence: 99%

“…The new weight can be written as

w_{3} false(k false) = w_{3} false(k - 1 false) + normalΔ w_{3} false(k false)

To ensure accelerated convergence, the last weight change is added to the weight update as [3]

w_{3} false(k false) = w_{3} false(k - 1 false) + normalΔ w_{3} false(k false) + α normalΔ w_{3} false(k - 1 false)

where α is a positive constant called the momentum constant. The motor speed can be estimated from the weight w 3 as

{\hat{ω}}_{r} false(k false) = \frac{σ L_{s} L_{r}}{T L_{m}} w_{3} (k)

It must be noted here that a similar approach was described in [30] using the VM for the rotor flux estimation. However, as will be described later, many problems are associated with using such model especially at low speed.…”

Section: Nn Stator‐current Mras Observermentioning

confidence: 99%

“…The VM was used in [30] for rotor flux estimation. However, the main drawback associated with VM implementation is the use of a pure integration which can cause dc drift, sensitivity to machine parameter variation, accurate stator voltage and current acquisition.…”

Section: Rotor Flux Estimation Problemmentioning

confidence: 99%

“…Rotor flux is needed for stator current estimation in the adaptive model and conventionally either a voltage model (VM) [30] or a current model (CM) flux observer [22] has been employed. However, as described in [29,31], the use of a CM gives instability in the regeneration.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Stator current model reference adaptive systems speed estimator for regenerating‐mode low‐speed operation of sensorless induction motor drives

Gadoue¹,

Giaouris

Finch³

2013

IET Electric Power Applications

View full text Add to dashboard Cite

The performance of a stator current-based model reference adaptive systems (MRAS) speed estimator for sensorless induction motor drives is investigated in this study. The measured stator currents are used as a reference model for the MRAS observer to avoid the use of a pure integrator. A two-layer, online-trained neural network stator current observer is used as the adaptive model for the MRAS estimator which requires the rotor flux information. This can be obtained from the voltage or current models, but instability and dc drift can downgrade the overall observer performance. To overcome these problems of rotor flux estimation, an off-line trained multilayer feed-forward neural network is proposed here as a rotor flux observer. Hence, two networks are employed: the first is online trained for stator current estimation and the second is off-line trained for rotor flux estimation. Sensorless operation for the proposed MRAS scheme using current model and neural network rotor flux observers are investigated based on a set of experimental tests in the low-speed region. Using a neural network rotor flux observer to replace the current model is shown to solve the stability problem in the low-speed regenerating mode of operation.

show abstract

Section: Nn Stator-current Mras Observermentioning

confidence: 98%

Section: Rotor Flux Estimation Problemmentioning

confidence: 99%

“…The new weight can be written as