Neural State Filtering for Adaptive Induction Motor Speed Estimation

Bharadwaj, Raj; Parlos, Alexander G.

doi:10.1006/mssp.2002.1523

Cited by 12 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a recent study, a comprehensive computational complexity analysis of FMLP and RMLP predictors has been performed, demonstrating that real-time implementation of such predictors is indeed feasible [26]. In addition, recently, such neuro-predictors have been implemented on a fixed-point arithmetic digital signal processor (DSP), and their real-time operation has been experimentally verified at much higher sampling rate requirements than the video source traffic prediction application presented in this study [27].…”

Section: Real-time Implementation Of Neuro-predictorsmentioning

confidence: 99%

Prediction of MPEG-coded video source traffic using recurrent neural networks

Bhattacharya

Parlos

Atiya

2003

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

Predicting traffic generated by multimedia sources is needed for effective dynamic bandwidth allocation and for multimedia quality-of-service (QoS) control strategies implemented at the network edges. The time-series representing frame or visual object plane (VOP) sizes of an MPEG-coded stream is extremely noisy, and it has very long-range time dependencies. This paper provides an approach for developing MPEG-coded real-time video traffic predictors for use in single-step (SS) and multistep (MS) prediction horizons. The designed SS predictor consists of one recurrent network for-VOPs and two feedforward networks forand-VOPs, respectively. These are used for single-frame-ahead prediction. A moving average of the frame or VOP sizes time-series is generated from the individual frame sizes and used for both SS and MS prediction. The resulting MS predictor is based on recurrent networks, and it is used to perform two-step-ahead and four-step-ahead prediction, corresponding to multistep prediction horizons of 1 and 2 s, respectively. All of the predictors are designed using a segment of a single MPEG-4 video stream, and they are tested for accuracy on complete video streams with a variety of quantization levels, coded with both MPEG-1 and MPEG-4. Comparisons with SS prediction results of MPEG-1 coded video traces from the recent literature are presented. No similar results are available for prediction of MPEG-4 coded video traces and for MS prediction. These are considered unique contributions of this research.

show abstract

Section: Real-time Implementation Of Neuro-predictorsmentioning

confidence: 99%

Prediction of MPEG-coded video source traffic using recurrent neural networks

Bhattacharya

Parlos

Atiya

2003

IEEE Trans. Signal Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…They are suitable for wide speed ranges, but unable to achieve high accuracy and fast response simultaneously, because the sample time interval is constant [11][12][13][14][15]. The adaptive methods proposed in [16][17][18][19][20] divide all the speed ranges into several segments, and adopt variable sampling interval to adapt accordingly to the instant angular speed. The adaptive methods have the following significant advantages: (1) being applicable to wide speed ranges; (2) having good accuracy at low speeds; (3) having better response at medium and high speeds; (4) working in parallel with the benefit of using the field programmable gate array (FPGA) and very-large-scale integrated (VLSI) circuit; and (5) being applicable to multi-axial system by expanding modules.…”

Section: Introductionmentioning

confidence: 99%

A high-performance angular speed measurement method based on adaptive hysteresis switching techniques

Huang

Chou

Zhang

2015

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

“…Determination of RSH components and estimation of speed according to RSHs are made by individual approaches. Some studies using artificial neural networks (ANNs) are available in the literature [15][16][17][18][19][20]. However, these studies have methods that are based on a mathematical motor model.…”

Section: Introductionmentioning

confidence: 99%

An artificial neural network approach for sensorless speed estimation via rotor slot harmonics

Arabaci¹

2014

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:In this paper, a sensorless speed estimation method with an artificial neural network for squirrel cage induction motors is presented. Motor current is generally used for sensorless speed estimation. Rotor slot harmonics are available in the frequency spectrum of the current. The frequency components of these determined harmonics are used to estimate the speed of the motor in which the number of rotor slots is given. In the literature, individual algorithms have been used to calculate the speed from the slot harmonics. Unlike the literature, in the proposed method, an artificial neural network is used to extract the speed from the rotor slot harmonic components in the spectrum. This experimental study is carried out to prove the method under steady-state conditions. The experimental results show that the proposed method is suitable for speed estimation and its average error is below 1.5 rpm.

show abstract

Neural State Filtering for Adaptive Induction Motor Speed Estimation

Cited by 12 publications

References 27 publications

Prediction of MPEG-coded video source traffic using recurrent neural networks

Prediction of MPEG-coded video source traffic using recurrent neural networks

A high-performance angular speed measurement method based on adaptive hysteresis switching techniques

An artificial neural network approach for sensorless speed estimation via rotor slot harmonics

Contact Info

Product

Resources

About