A neural network based space vector PWM controller for a three-level voltage-fed inverter induction motor drive

Mondal, S.K.; Pinto, J.O.P.; Bose, B.K.

doi:10.1109/ias.2001.955759

Cited by 13 publications

(16 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) In the overmodulation II, during the period when the reference vector is held at the vertex of the hexagon, the on-time calculation is not required. It can thus be concluded from the above discussion that in the proposed method, the on-time calculation for a triangle is not dependent on a set of equations stored in lookup table as compared to traditional approach in Mondal [9]. Rather, the on-times calculation is done using standard two-level equations, which makes the scheme simple and applicable to any level.…”

Section: Inferences Drawn From the Implementation For A 5-level Inmentioning

confidence: 94%

See 1 more Smart Citation

A general space vector PWM algorithm for multilevel inverters, including operation in overmodulation range

Gupta

Khambadkone

2005

IEEE International Conference on Electric Machines and Drives, 2005.

View full text Add to dashboard Cite

Multilevel inverters are being increasingly used in high power industrial drive applications. There are many modulation techniques available for a multilevel inverter but Space Vector PWM is commonly used. When the inverter operates in the sinusoidal mode of Space Vector PWM, the DC link voltage of the inverter is not fully utilized. A suitable overmodulation scheme is required to address this problem. Another problem associated with the Space Vector PWM of multilevel inverters is, when the level of the inverter increases, the implementation of space vector modulation becomes cumbersome due to the difficulty in determining the location of reference vector, calculation of on-times and large number of switching states. This paper proposes a simple space vector PWM algorithm, which (a) can cover sinusoidal mode and overmodulation mode (b) can easily determine the location of reference vector (c) can easily calculate the on-times (d) can be used for any level of inverter. In the proposed scheme, the on-time calculations are based on a standard two-level Space Vector PWM. The proposed scheme is explained for a 5-level cascaded H-bridge inverter with operation in sinusoidal mode, overmodulation mode I, and overmodulation mode II. Experimental results are provided to prove the viability of the scheme. 0-7803-8987-5/05/$20.00 ©2005 IEEE.

show abstract

Section: Inferences Drawn From the Implementation For A 5-level Inmentioning

confidence: 94%

“…The on-time calculation equations do not change with the position of reference vector like the traditional approach in Mondal [9].…”

mentioning

confidence: 99%

A general space vector PWM algorithm for multilevel inverters, including operation in overmodulation range

Gupta

Khambadkone

2005

IEEE International Conference on Electric Machines and Drives, 2005.

View full text Add to dashboard Cite

show abstract

“…DSP processor based implementations have been reported in [16] and [17] for a variety of motor control applications. DSP processors available in the market are typically limited to 1, 2, 4 or 8 MAC cores.…”

Section: Previous Workmentioning

confidence: 99%

FPGA implementation of a multilayer Artificial Neural Network using System-on-Chip design methodology

Biradar

Chatterjee

Mishra

et al. 2015

2015 International Conference on Cognitive Computing and Information Processing(CCIP)

View full text Add to dashboard Cite

Artificial NeuralNetworks (ANNs) find applications in engineering solutions to complex problems. The usefulness of ANNs in real-time embedded applications can be enhanced if feasible architectures for their hardware implementation can be customized to provide an attractive tradeoff between area and performance. In this paper, we present a real-time embedded hardware implementation of a feed-forward neural network which employs backpropagation algorithm for training. Custom modules are designed for the activation functions, the neurons and a finite state machine that co-ordinate activities for training. The proposed ANN is implemented on a Virtex-5 Field Programmable Gate Array. Use of System-on-Chip design methodology enables design reuse while improving the performance metrics.

show abstract

“…In my opinion, the government should maintain a roster of expert researchers in the country and solicit their contributions instead of researchers searching for government funds. Some of my research contributions in the University of Tennessee included a WIllIam mcmurray: thE guru of PoWEr ElEctronIcs William mcmurray ( Figure S1) was a power electronics scientist with GE-crD for 35 years soft-switched inverter for motor drives, HF nonresonant link power conversion for EV drives using a MOS-controlled thyristor [25], fuzzy control of dc and induction motor drives, fuzzy control of wind generation systems, neural network-based drive feedback signal estimation for vector drives, neural control of space vector modulations (SVMs) of two-level and multilevel converters [28], [29], converter faults investigation, automated IM drive control design by expert systems, sensorless vector control of IMs, and high-temperature superconductivity-synchronous motor (SM) ship propulsion with multilevel converters. A number of these projects were government funded.…”

Section: My Experience In Researchmentioning

confidence: 99%

“…■ I pioneered AI (expert system, fuzzy logic, and neural network) applications in the control and estimation of power electronic systems, which is now an emerging technology [1], [15], [27]. These include ANN-based space vector PWM for two- [1] and multilevel converters [28], [29]. ■ I published the first textbook on modern power electronics and ac drives in the English language in 1986 [14], [33].…”

Section: My Experience In Researchmentioning

confidence: 99%

Doing Research In Power Electronics [My View]

Bose¹

2015

EEE Ind. Electron. Mag.

View full text Add to dashboard Cite

A neural network based space vector PWM controller for a three-level voltage-fed inverter induction motor drive

Cited by 13 publications

References 6 publications

A general space vector PWM algorithm for multilevel inverters, including operation in overmodulation range

A general space vector PWM algorithm for multilevel inverters, including operation in overmodulation range

FPGA implementation of a multilayer Artificial Neural Network using System-on-Chip design methodology

Doing Research In Power Electronics [My View]

Contact Info

Product

Resources

About