Online Learning Neural Network Control of Buck-Boost Converter

Utomo, Wahyu Mulyo; Bakar, Afarulrazi Abu; Ahmad, M. Z.; Taufik, Taufik; Heriansyah, Rudi

doi:10.1109/itng.2011.216

Cited by 21 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[27], [28], [29], donde a su entrada se tiene un conjunto de señales encargadas de entregar una muestra de corriente o tensión asociada directamente con el circuito [13] o como señales de error, siendo estas la resta entre la señal de referencia y la señal medida, también de tensión o de corriente [26], [27], [28], [29]. La elección de una u otra depende de la aplicación particular y de la facilidad que esté presente al momento de su evaluación y posible implementación.…”

Section: Control Neuronalunclassified

Diseño y simulación de un control neuronal aplicado a un convertidor flyback para la regulación de tensión

2021

View full text Add to dashboard Cite

Este artículo presenta el diseño y simulación de un controlador basado en redes neuronales para regular la tensión de salida de un convertidor flyback. Se usan redes neuronales, ya que estas no requieren de un modelo matemático del convertidor, y, por tanto, se obtiene un mayor rango de operación respecto a métodos de control tradicional. En el entrenamiento se realizan cambios en la base de datos y en la arquitectura para obtener el controlador más apropiado, que garantice la regulación de línea y carga del convertidor. La validación del controlador neuronal funcional se realiza en Simulink con el modelo circuital de un convertidor flyback, sometiéndolo a cambios en la tensión de entrada y en la carga resistiva. Los resultados obtenidos muestran la efectividad del control neuronal para la regulación de línea entre 20 V y 50 V, regulación de carga entre 8 Ω y 12 Ω, y cuya arquitectura está conformada por cuatro neuronas.

show abstract

Section: Control Neuronalunclassified

Diseño y simulación de un control neuronal aplicado a un convertidor flyback para la regulación de tensión

2021

View full text Add to dashboard Cite

show abstract

“…Activation function of the network at ℎ neuron in ℎ layer is defined by [19]: Connection weights (ith input neuron to jth output neuron) and bias parameters at mth layer are expressed in equation (4) & (5) respectively:…”

Section: System Configurationmentioning

confidence: 99%

ANN controlled 4-leg VSC based DSTATCOM for power quality enhancement

Penthia

Panda

Sarangi

et al. 2015

2015 Annual IEEE India Conference (INDICON)

View full text Add to dashboard Cite

In this paper, a novel hybrid control approach has been considered which includes an artificial neural network (ANN), a zig-zag transformer and hysteresis current controllers (HCC) for a distributed static compensator (DSTATCOM). The hybrid controller is used for reduction of line current harmonics and for improvement of power factor in the system. The proposed controller pushes the source current into a sinusoidal one and tries to make it in phase with line voltage. Two main controls are offered for it: estimation of weighting factor of three phase load current and hysteresis switching algorithm for driving the voltage source converter (VSC) of DSTATCOM. The ANN with a suitable learning rate has been used to determine the compensator optimization. A zig-zag transformer is employed for neutral current reduction in the system. Simulation results are obtained for validation of the proposed DSTATCOM in the entire power system using MATLAB/Simulink and Power system tool boxes.Index Terms-Artificial Neural Network (ANN); Distributed static compensator (DSTATCOM); Zig-zag transformer; harmonic filter; hysteresis current controller.

show abstract

“…The connections weight parameter between j th and i th neuron at m th layer is given by w m ij , while bias parameter of this layer at i th neuron is given by b m i . Transfer function of the network at i th neuron in m th layer is defined by [12]:…”

Section: Proposed DC Voltage Controlmentioning

confidence: 99%

Artificial neural network controller for single-phase active power filter

Janggi

Utomo

Yusoh

et al. 2014

2014 IEEE Conference on Energy Conversion (CENCON)

View full text Add to dashboard Cite

This paper shows the conception and simulation of a single-phase shunt active power filter for harmonics and power factor compensation of uncontrolled rectifier with battery load. The objectives of this project are to minimize the harmonic distortion and intensity the power factor of the single-phase system with battery charger load. The design of shunt active power filter is verified using the simulations in Matlab/Simulink. Shunt active harmonic filter was controlled by the neural network method where it applied the proportional and integral method in order to adjust the direct current link voltage and the hysteresis current controller is employed to generate signals for switching the voltage source inverter. The error signal has been compensated using the controllers. The reference filter currents signal is obtained by subtracting the line current with the compensated signal from the controller. This reference current is fed to the hysteresis current controller and compare with the sensed filter currents to obtain the switching signal for active power filter. Simulation results are acquired with the conventional PI controller and ANN controller.

show abstract

Online Learning Neural Network Control of Buck-Boost Converter

Cited by 21 publications

References 10 publications

Diseño y simulación de un control neuronal aplicado a un convertidor flyback para la regulación de tensión

Diseño y simulación de un control neuronal aplicado a un convertidor flyback para la regulación de tensión

ANN controlled 4-leg VSC based DSTATCOM for power quality enhancement

Artificial neural network controller for single-phase active power filter

Contact Info

Product

Resources

About