Transient Response of Reference Modified Digital PID Control DC-DC Converters with Neural Network Prediction

Hidenori MARUTA; Daiki MITSUTAKE; Masashi MOTOMURA; Fujio KUROKAWA

doi:10.1587/transcom.2016EBP3095

Transient Response of Reference Modified Digital PID Control DC-DC Converters with Neural Network Prediction

Hidenori MARUTA, Daiki MITSUTAKE, Masashi MOTOMURA, Fujio KUROKAWA

Full Text Views

0

Cite this

Summary :

This paper presents a novel control method based on predictions of a neural network in coordination with a conventional PID control to improve transient characteristics of digitally controlled switching dc-dc converters. Power supplies in communication systems require to achieve a superior operation for electronic equipment installed to them. Especially, it is important to improve transient characteristics in any required conditions since they affect to the operation of power supplies. Therefore, dc-dc converters in power supplies need a superior control method which can suppress transient undershoot and overshoot of output voltage. In the presented method, the neural network is trained to predict the output voltage and is adopted to modify the reference value in the PID control to reduce the difference between the output voltage and its desired one in the transient state. The transient characteristics are gradually improved as the training procedure of the neural network is proceeded repetitively. Furthermore, the timing and duration of neural network control are also investigated and devised since the time delay, which is one of the main issue in digital control methods, affects to the improvement of transient characteristics. The repetitive training and duration adjustment of the neural network are performed simultaneously to obtain more improvement of the transient characteristics. From simulated and experimental results, it is confirmed that the presented method realizes superior transient characteristics compared to the conventional PID control.

Publication: IEICE TRANSACTIONS on Communications Vol.E99-B No.11 pp.2340-2350

Publication Date: 2016/11/01

Publicized: 2016/06/17

Online ISSN: 1745-1345

DOI: 10.1587/transcom.2016EBP3095

Type of Manuscript: PAPER

Category: Energy in Electronics Communications

Authors

Hidenori MARUTA
  Nagasaki University
Daiki MITSUTAKE
  Nagasaki University
Masashi MOTOMURA
  Nagasaki University
Fujio KUROKAWA
  Nagasaki University

Keyword

dc-dc converter, neural network, prediction, digital control

Cite this

Copy

Hidenori MARUTA, Daiki MITSUTAKE, Masashi MOTOMURA, Fujio KUROKAWA, "Transient Response of Reference Modified Digital PID Control DC-DC Converters with Neural Network Prediction" in IEICE TRANSACTIONS on Communications, vol. E99-B, no. 11, pp. 2340-2350, November 2016, doi: 10.1587/transcom.2016EBP3095.
Abstract: This paper presents a novel control method based on predictions of a neural network in coordination with a conventional PID control to improve transient characteristics of digitally controlled switching dc-dc converters. Power supplies in communication systems require to achieve a superior operation for electronic equipment installed to them. Especially, it is important to improve transient characteristics in any required conditions since they affect to the operation of power supplies. Therefore, dc-dc converters in power supplies need a superior control method which can suppress transient undershoot and overshoot of output voltage. In the presented method, the neural network is trained to predict the output voltage and is adopted to modify the reference value in the PID control to reduce the difference between the output voltage and its desired one in the transient state. The transient characteristics are gradually improved as the training procedure of the neural network is proceeded repetitively. Furthermore, the timing and duration of neural network control are also investigated and devised since the time delay, which is one of the main issue in digital control methods, affects to the improvement of transient characteristics. The repetitive training and duration adjustment of the neural network are performed simultaneously to obtain more improvement of the transient characteristics. From simulated and experimental results, it is confirmed that the presented method realizes superior transient characteristics compared to the conventional PID control.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2016EBP3095/_p

Copy

@ARTICLE{e99-b_11_2340,
author={Hidenori MARUTA, Daiki MITSUTAKE, Masashi MOTOMURA, Fujio KUROKAWA, },
journal={IEICE TRANSACTIONS on Communications},
title={Transient Response of Reference Modified Digital PID Control DC-DC Converters with Neural Network Prediction},
year={2016},
volume={E99-B},
number={11},
pages={2340-2350},
abstract={This paper presents a novel control method based on predictions of a neural network in coordination with a conventional PID control to improve transient characteristics of digitally controlled switching dc-dc converters. Power supplies in communication systems require to achieve a superior operation for electronic equipment installed to them. Especially, it is important to improve transient characteristics in any required conditions since they affect to the operation of power supplies. Therefore, dc-dc converters in power supplies need a superior control method which can suppress transient undershoot and overshoot of output voltage. In the presented method, the neural network is trained to predict the output voltage and is adopted to modify the reference value in the PID control to reduce the difference between the output voltage and its desired one in the transient state. The transient characteristics are gradually improved as the training procedure of the neural network is proceeded repetitively. Furthermore, the timing and duration of neural network control are also investigated and devised since the time delay, which is one of the main issue in digital control methods, affects to the improvement of transient characteristics. The repetitive training and duration adjustment of the neural network are performed simultaneously to obtain more improvement of the transient characteristics. From simulated and experimental results, it is confirmed that the presented method realizes superior transient characteristics compared to the conventional PID control.},
keywords={},
doi={10.1587/transcom.2016EBP3095},
ISSN={1745-1345},
month={November},}

Copy

TY - JOUR
TI - Transient Response of Reference Modified Digital PID Control DC-DC Converters with Neural Network Prediction
T2 - IEICE TRANSACTIONS on Communications
SP - 2340
EP - 2350
AU - Hidenori MARUTA
AU - Daiki MITSUTAKE
AU - Masashi MOTOMURA
AU - Fujio KUROKAWA
PY - 2016
DO - 10.1587/transcom.2016EBP3095
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E99-B
IS - 11
JA - IEICE TRANSACTIONS on Communications
Y1 - November 2016
AB - This paper presents a novel control method based on predictions of a neural network in coordination with a conventional PID control to improve transient characteristics of digitally controlled switching dc-dc converters. Power supplies in communication systems require to achieve a superior operation for electronic equipment installed to them. Especially, it is important to improve transient characteristics in any required conditions since they affect to the operation of power supplies. Therefore, dc-dc converters in power supplies need a superior control method which can suppress transient undershoot and overshoot of output voltage. In the presented method, the neural network is trained to predict the output voltage and is adopted to modify the reference value in the PID control to reduce the difference between the output voltage and its desired one in the transient state. The transient characteristics are gradually improved as the training procedure of the neural network is proceeded repetitively. Furthermore, the timing and duration of neural network control are also investigated and devised since the time delay, which is one of the main issue in digital control methods, affects to the improvement of transient characteristics. The repetitive training and duration adjustment of the neural network are performed simultaneously to obtain more improvement of the transient characteristics. From simulated and experimental results, it is confirmed that the presented method realizes superior transient characteristics compared to the conventional PID control.
ER -