A. Muthuramalingam's research while affiliated with Pondicherry Engineering College and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (25)
This study presents design and hardware implementation of cascade neural network (NN) based flux estimator using field programmable gate array (FPGA) for speed estimation in induction motor drives. The main focus of this study is the FPGA implementation of cascade NN based flux estimator. The major issues in FPGA implementation are optimisation of...
This paper presents a new neural network based model reference adaptive system (MRAS) to solve low speed problems for estimating rotor resistance in vector control of induction motor (IM). The MRAS using rotor flux as the state variable with a two layer online trained neural network rotor flux estimator as the adaptive model (FLUX-MRAS) for rotor r...
The performance of sensor-less direct vector controlled IM drives to a large extent depends on the accuracy of field angle and resultant flux estimation. This in turn depends on the accuracy of estimated flux. Conventional voltage model used for flux estimation encounters major problems at low speeds/frequencies like integrator drift and stator res...
This paper presents a novel speed estimator using Reactive Power based Model Reference Neural Learning Adaptive System (RP-MRNLAS) for sensorless indirect vector controlled induction motor drives. The Model Reference Adaptive System (MRAS) based speed estimator using simplified reactive power equations is one of the speed estimation method used for...
In this paper, a novel reactive power based model reference neural learning adaptive system (RP-MRNLAS) is proposed. The model reference adaptive system (MRAS) based speed estimation is one of the most popular methods used for sensor-less controlled induction motor drives. In conventional MRAS, the error adaptation is done using a Proportional-inte...
The paper identifies suitable learning algorithm for online flux estimation for sensorless vector controlled Induction Motor (IM) drives. The sensorless vector controlled IM drive requires accurate estimation of flux and speed. The speed estimation depends on the motor flux, which has to be measured or estimated. The flux measurement is difficult a...
The sensor-less vector-controlled induction motor drive requires accurate estimation of speed and flux. The speed estimation depends on the motor flux, which has to be measured or estimated. The flux measurement is difficult and expensive and hence generally estimated. Conventional voltage model equations for flux estimation encounter major drawbac...
This paper identifies the suitable learning algorithm for neural network based on-line speed estimator in sensorless induction motor drives. The performance of sensorless controlled induction motor drives depends on the accuracy of the estimated speed. Conventional estimation techniques being mathematically complex require more execution time resul...
This paper proposes a robust data based flux estimator for sensor-less vector controlled Induction Motor (IM) drives. The performance of sensor-less vector controlled IM drives to a large extent depends on the accuracy of estimated speed. The speed estimation in turn depends on the accuracy of estimated flux. Conventional voltage model equations fo...
Rotor Flux based Model Reference Adaptive System (RF-MRAS) is the most popularly used conventional speed estimation scheme for sensor-less IM drives. In this scheme, the voltage model equations are used for the reference model. This encounters major drawbacks at low frequencies/speed which leads to the poor performance of RF-MRAS. Replacing the ref...
Hardware realization of a Neural Network (NN), to a large extent depends on the efficient implementation of a single neuron. FPGA-based reconfigurable computing architectures are suitable for hardware implementation of neural networks. FPGA realization of ANNs with a large number of neurons is still a challenging task. This paper discusses the issu...
This paper presents a hardware implementation of multilayer feedforward neural networks (NN) using reconfigurable field-programmable gate arrays (FPGAs). Despite improvements in FPGA densities, the numerous multipliers in an NN limit the size of the network that can be implemented using a single FPGA, thus making NN applications not viable commerci...
Multilevel converter technology has recently emerged as a very important alternative in the area of high-power applications. Several modulation methods have been applied to multilevel Inverters. The modulation methods with higher switching frequency reduce filter size but increases switching losses. The Step modulation method operates with low swit...
This paper deals with programmable LPF (low pass filter) based stator flux estimation for speed sensorless induction motor drives. This algorithm is proposed to solve the dc drift problem and errors due to stator resistance variation associated with the ideal integrator and a LPF. This algorithm has pole/gain compensator to estimate stator flux ove...
Harmonic pollution and low power factor in power systems caused by power converters have been a great concern. To overcome these problems several converters and control schemes have been proposed in recent years. This work is proposed to identify the power converters with low cost/small size/high efficiency for single phase and three phase systems....
A high performance motor control system should exhibit good speed tracking and disturbance rejection even under unstructured uncertainty. Usually a lower order and simple controller for IFOC IM exhibits satisfactory nominal tracking performance, but may not provide the required robustness against unstructured uncertainty. A robust compensator can b...
A field programmable gate array (FPGA) based controller is proposed for a dc link series resonant inverter. The basic operation of the zero current switching inverter is briefly described. A strategy of decoupling the control of the dc link current from the load current is identified and referred as decoupled current control (DCC). The use of gate-...
Space Vector Modulation (SVM) is an optimum Pulse Width Modulation (PWM) technique for variable frequency drive applications. It is computationally rigorous and hence limits the switching frequency. Increase in switching frequency can be achieved using Neural Network (NN) based SVM, implemented on application specific chips. This paper proposes a n...
DC link series resonance (DCLSR) is a new concept in power conversion and in specific to DC to AC conversion using IGBT. In this work, the operation and control strategies of parallel connected inverters delivering to common/distributed load are investigated. The DC-coupled control of link current from output voltage and load enables the parallel c...
A single-phase high-frequency transformer-isolated Class-D series
parallel (LCC type) resonant power converter (SPRC) with fixed frequency
is presented. The results of AC analysis are used to design the
converter for low harmonic distortion and near unity power factor (PF)
operation. The designed converter is studied through simulation (using
SABER...
A slip power recovery scheme (SPRS) is popular as a variable speed
drive (VSD) for a wound rotor induction motor (WRIM) and as a variable
speed constant frequency doubly fed induction generator (VSCF-DFIG). In
this work an attempt is made to reduce some of the drawbacks of SPRS by
using a DC link series resonant converter (DCLSRC). The implementati...
The present work proposes the DC link series resonant concept for
DC to AC power conversion. The inverter is ZCS-based and operated at 50
kHz and above. A decoupled current control (DCC) strategy of DC link
current from the load current is identified. DCC and the elevated
switching frequency of the inverter enable the application of the pulse
densi...
Space Vector Modulation (SVM) is an optimum Pulse Width Modulation (PWM) technique for an inverter used in a variable frequency drive applications. It is computationally rigorous and hence limits the inverter switching frequency. Increase in switching frequency can be achieved using Neural Network (NN) based SVM, implemented on application specific...
Citations
... A great improvement in the performance of the speed estimator is achieved, particularly at low speeds, both with open-loop and closed-loop conditions [43,44]. The online rotor and stator resistance estimation approaches are proposed, where a fixed learning rate is adopted during the estimation approach [45,46]. The selection of an inappropriate learning rate leads to output errors with slow convergence of the error during network training. ...
... The controller's response time was quicker with a higher frequency, but the motor speed tended to oscillate more and/or overshoot considerably. The usage of an embedded-based fuzzy system has been proposed [42] but doing so would require a significant amount of memory, which might increase project expenses. The computational cost may increase, and real-time performance may decline if real-time hardware is used. ...
... In [13], the NN is used as the adaptive model and not as the reference model. The idea of using two NN in RMAC is employed for rotor resistance estimation [28]. Thus idea of using two neural network models in rotor flux RMAC is not yet exploited for speed estimation as far as the author's knowledge. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/705057972580355-1545110328732_Q64/Himavathi-Srinivasan.jpg)
... Many researchers have been carried on the design of sensorless control of the IM. Most methods are essentially based on the Model Reference Adaptive System (MRAS) or a reactive power based reference model [1][2]. The MRAS algorithm is very simple but its greatest drawback is the sensitivity to uncertainties in the motor parameters. ...
... One is NN based reference model and another is the NN based adaptive model. The idea of using NN based reference model in rotor flux RMAC is inspired from [22,23]. In [22,23] NN is used only as the reference model and not as the adaptive model. ...
... By the use of some new control strategies, like model reference adaptive control (MRAS), estimation and control of the rotor speed are possible [4][5][6]. Various schemes are constituted for realizing this method of speed estimation based on the quantity used to form the error vector that is the input to the adaptation mechanism, for example, rotor flux-based MRAS [7], back EMF-based MRAS [8], reactive powerbased MRAS [9,10], or stator current-based MRAS [11]. Rotor flux-based MRAS method is used in this chapter. ...
... The identification of the parameters, magnetic fluxes and torque of IM is often applied to a specific type of motor control in order to improve drive dynamics, or to eliminate the angular speed sensor. Improving the identification of IM magnetic fluxes based on a neural network, and thus improving the control at DTC (direct torque control), is described in [11]. Accurate identification of the IM parameters and magnetic fluxes for subsequent control by genetic algorithms using a reduced-order robust observer can be found in the [12]. ...
... The ANN application in the area of power electronics is recently growing very fast. Implementation of Space Vector PWM has used ANN in many research works [45][46][47][48][49]. Whereas ANN-SVM controller compute very fast but it has one limitation that it is difficult to train nonlinear modulation technique. ...
... They focus on efficient implementation techniques, particularly for multi-input neurons with linear and nonlinear excitation functions. The paper also proposes a method for handling signed decimal numbers and improving the speed of operation using lookup tables (LUTs) [10]. This paper has delved into the intricate challenges and viable solutions linked to FPGA-based implementations of neural networks, underscoring the need for optimizing computational blocks, judicious resource allocation, and careful consideration of bit precision. ...
... The hidden layer size was determined to be 25, aiming for computational efficiency in the training process of the neural network. The Levenberg-Marquardt backpropagation was applied as a training algorithm since, for a few hundredweights, this algorithm is a good compromise between guaranteed convergence methodologies such as the steepest descent method and the faster convergence methodologies such as the Gauss-Newton algorithm [27]. The choice of training parameters was guided by the surrogate-based evolutionary parameter identification in [25]. ...
