A learning feed-forward current controller for linear reciprocating vapor compressors

Zhengyu Lin, Jiabin Wang, David Howe

Research output: Contribution to journalArticle

Abstract

Direct-drive linear reciprocating compressors offer numerous advantages over conventional counterparts which are usually driven by a rotary induction motor via a crank shaft. However, to ensure efficient and reliable operation under all conditions, it is essential that motor current of a linear compressor follows a sinusoidal current command with a frequency which matches the system resonant frequency. The design of a high-performance current controller for linear compressor drive presents a challenge since the system is highly nonlinear, and an effective solution must be low cost. In this paper, a learning feed-forward current controller for the linear compressors is proposed. It comprises a conventional feedback proportional-integral controller and a feed-forward B-spline neural network (BSNN). The feed-forward BSNN is trained online and in real time in order to minimize the current tracking error. Extensive simulation and experiment results with a prototype linear compressor show that the proposed current controller exhibits high steady state and transient performance.
Original languageEnglish
Pages (from-to)3383-3390
Number of pages8
JournalIEEE Transactions on Industrial Electronics
Volume58
Issue number8
Early online date28 Oct 2010
DOIs
Publication statusPublished - Aug 2011

Fingerprint

Compressors
Vapors
Controllers
Splines
Neural networks
Reciprocating compressors
Induction motors
Natural frequencies
Feedback
Costs
Experiments

Keywords

  • compressors
  • current control
  • learning control systems
  • linear motors
  • neural networks

Cite this

Lin, Zhengyu ; Wang, Jiabin ; Howe, David. / A learning feed-forward current controller for linear reciprocating vapor compressors. In: IEEE Transactions on Industrial Electronics. 2011 ; Vol. 58, No. 8. pp. 3383-3390.
@article{bb880868a72e4bda837437baed0cf36f,
title = "A learning feed-forward current controller for linear reciprocating vapor compressors",
abstract = "Direct-drive linear reciprocating compressors offer numerous advantages over conventional counterparts which are usually driven by a rotary induction motor via a crank shaft. However, to ensure efficient and reliable operation under all conditions, it is essential that motor current of a linear compressor follows a sinusoidal current command with a frequency which matches the system resonant frequency. The design of a high-performance current controller for linear compressor drive presents a challenge since the system is highly nonlinear, and an effective solution must be low cost. In this paper, a learning feed-forward current controller for the linear compressors is proposed. It comprises a conventional feedback proportional-integral controller and a feed-forward B-spline neural network (BSNN). The feed-forward BSNN is trained online and in real time in order to minimize the current tracking error. Extensive simulation and experiment results with a prototype linear compressor show that the proposed current controller exhibits high steady state and transient performance.",
keywords = "compressors, current control, learning control systems, linear motors, neural networks",
author = "Zhengyu Lin and Jiabin Wang and David Howe",
year = "2011",
month = "8",
doi = "10.1109/TIE.2010.2089948",
language = "English",
volume = "58",
pages = "3383--3390",
journal = "IEEE Transactions on Industrial Electronics",
issn = "0278-0046",
publisher = "IEEE",
number = "8",

}

A learning feed-forward current controller for linear reciprocating vapor compressors. / Lin, Zhengyu; Wang, Jiabin; Howe, David.

In: IEEE Transactions on Industrial Electronics, Vol. 58, No. 8, 08.2011, p. 3383-3390.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A learning feed-forward current controller for linear reciprocating vapor compressors

AU - Lin, Zhengyu

AU - Wang, Jiabin

AU - Howe, David

PY - 2011/8

Y1 - 2011/8

N2 - Direct-drive linear reciprocating compressors offer numerous advantages over conventional counterparts which are usually driven by a rotary induction motor via a crank shaft. However, to ensure efficient and reliable operation under all conditions, it is essential that motor current of a linear compressor follows a sinusoidal current command with a frequency which matches the system resonant frequency. The design of a high-performance current controller for linear compressor drive presents a challenge since the system is highly nonlinear, and an effective solution must be low cost. In this paper, a learning feed-forward current controller for the linear compressors is proposed. It comprises a conventional feedback proportional-integral controller and a feed-forward B-spline neural network (BSNN). The feed-forward BSNN is trained online and in real time in order to minimize the current tracking error. Extensive simulation and experiment results with a prototype linear compressor show that the proposed current controller exhibits high steady state and transient performance.

AB - Direct-drive linear reciprocating compressors offer numerous advantages over conventional counterparts which are usually driven by a rotary induction motor via a crank shaft. However, to ensure efficient and reliable operation under all conditions, it is essential that motor current of a linear compressor follows a sinusoidal current command with a frequency which matches the system resonant frequency. The design of a high-performance current controller for linear compressor drive presents a challenge since the system is highly nonlinear, and an effective solution must be low cost. In this paper, a learning feed-forward current controller for the linear compressors is proposed. It comprises a conventional feedback proportional-integral controller and a feed-forward B-spline neural network (BSNN). The feed-forward BSNN is trained online and in real time in order to minimize the current tracking error. Extensive simulation and experiment results with a prototype linear compressor show that the proposed current controller exhibits high steady state and transient performance.

KW - compressors

KW - current control

KW - learning control systems

KW - linear motors

KW - neural networks

UR - http://www.scopus.com/inward/record.url?scp=79960349306&partnerID=8YFLogxK

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5613180

U2 - 10.1109/TIE.2010.2089948

DO - 10.1109/TIE.2010.2089948

M3 - Article

AN - SCOPUS:79960349306

VL - 58

SP - 3383

EP - 3390

JO - IEEE Transactions on Industrial Electronics

JF - IEEE Transactions on Industrial Electronics

SN - 0278-0046

IS - 8

ER -