Closed-loop neural network controlled accelerorneter

E.I. Gaura, R.J. Rider, N. Steele

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The purpose of this paper is to present aspects of an integrated micromachined sensorneural network transducer development. Micromachined sensors exhibit particular problems such as non-linear characteristics, manufacturing tolerances and the need for complex electronic circuitry The novel transducer design described here, based on a mathematical model of the micromachined sensor, is aimed at improving in-service performance and facilitating design and manufacture over conventional transducers. The proposed closed-loop transducer structure incorporates two modular artificial neural networks: a compensating neural network, which performs a static mapping, and a feedback neural network, which both linearizes and demodulates the feedback signal. Simulation results to date show an excellent linearity, wide dynamic range and robustness to shocks for the proposed system. The design was approached from a control engineering perspective due to the closed-loop structure of the transducer. © IMechE 2000.
Original languageEnglish
Pages (from-to)129-138
Number of pages10
JournalProceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering
Volume214
Issue number2
DOIs
Publication statusPublished - 2000

Fingerprint

Transducers
Neural networks
Recurrent neural networks
Sensors
Mathematical models
Feedback

Bibliographical note

cited By 6

Keywords

  • Accelerometers
  • Closed loop control systems
  • Computer simulation
  • Mathematical models
  • Mechatronics
  • Multilayer neural networks
  • Robustness (control systems)
  • Sensors
  • Micromechanical devices
  • Software Package SPICE
  • Micromachined sensor
  • Transducers

Cite this

Closed-loop neural network controlled accelerorneter. / Gaura, E.I.; Rider, R.J.; Steele, N.

In: Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering, Vol. 214, No. 2, 2000, p. 129-138.

Research output: Contribution to journalArticle

@article{14450a866f0c4ae4a880a52db08baf68,
title = "Closed-loop neural network controlled accelerorneter",
abstract = "The purpose of this paper is to present aspects of an integrated micromachined sensorneural network transducer development. Micromachined sensors exhibit particular problems such as non-linear characteristics, manufacturing tolerances and the need for complex electronic circuitry The novel transducer design described here, based on a mathematical model of the micromachined sensor, is aimed at improving in-service performance and facilitating design and manufacture over conventional transducers. The proposed closed-loop transducer structure incorporates two modular artificial neural networks: a compensating neural network, which performs a static mapping, and a feedback neural network, which both linearizes and demodulates the feedback signal. Simulation results to date show an excellent linearity, wide dynamic range and robustness to shocks for the proposed system. The design was approached from a control engineering perspective due to the closed-loop structure of the transducer. {\circledC} IMechE 2000.",
keywords = "Accelerometers, Closed loop control systems, Computer simulation, Mathematical models, Mechatronics, Multilayer neural networks, Robustness (control systems), Sensors, Micromechanical devices, Software Package SPICE, Micromachined sensor, Transducers",
author = "E.I. Gaura and R.J. Rider and N. Steele",
note = "cited By 6",
year = "2000",
doi = "10.1243/0959651001540852",
language = "English",
volume = "214",
pages = "129--138",
journal = "Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering",
number = "2",

}

TY - JOUR

T1 - Closed-loop neural network controlled accelerorneter

AU - Gaura, E.I.

AU - Rider, R.J.

AU - Steele, N.

N1 - cited By 6

PY - 2000

Y1 - 2000

N2 - The purpose of this paper is to present aspects of an integrated micromachined sensorneural network transducer development. Micromachined sensors exhibit particular problems such as non-linear characteristics, manufacturing tolerances and the need for complex electronic circuitry The novel transducer design described here, based on a mathematical model of the micromachined sensor, is aimed at improving in-service performance and facilitating design and manufacture over conventional transducers. The proposed closed-loop transducer structure incorporates two modular artificial neural networks: a compensating neural network, which performs a static mapping, and a feedback neural network, which both linearizes and demodulates the feedback signal. Simulation results to date show an excellent linearity, wide dynamic range and robustness to shocks for the proposed system. The design was approached from a control engineering perspective due to the closed-loop structure of the transducer. © IMechE 2000.

AB - The purpose of this paper is to present aspects of an integrated micromachined sensorneural network transducer development. Micromachined sensors exhibit particular problems such as non-linear characteristics, manufacturing tolerances and the need for complex electronic circuitry The novel transducer design described here, based on a mathematical model of the micromachined sensor, is aimed at improving in-service performance and facilitating design and manufacture over conventional transducers. The proposed closed-loop transducer structure incorporates two modular artificial neural networks: a compensating neural network, which performs a static mapping, and a feedback neural network, which both linearizes and demodulates the feedback signal. Simulation results to date show an excellent linearity, wide dynamic range and robustness to shocks for the proposed system. The design was approached from a control engineering perspective due to the closed-loop structure of the transducer. © IMechE 2000.

KW - Accelerometers

KW - Closed loop control systems

KW - Computer simulation

KW - Mathematical models

KW - Mechatronics

KW - Multilayer neural networks

KW - Robustness (control systems)

KW - Sensors

KW - Micromechanical devices

KW - Software Package SPICE

KW - Micromachined sensor

KW - Transducers

U2 - 10.1243/0959651001540852

DO - 10.1243/0959651001540852

M3 - Article

VL - 214

SP - 129

EP - 138

JO - Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering

JF - Proceedings of the Institution of Mechanical Engineers. Part I: Journal of Systems and Control Engineering

IS - 2

ER -