Closed-loop, neural network controlled accelerometer design

E.I. Gaura; N. Ferreira; R.J. Rider; N. Steele

Closed-loop, neural network controlled accelerometer design

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

College of Engineering, Environment & Science

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

3 Citations (Scopus)

Abstract

In this paper, a closed-loop, smart transducer design is proposed, based on artificial neural network (ANN) techniques. The design aims to improve the performance of open-loop, off-the-shelf capacitive acceleration sensors and increase their robustness to manufacturing tolerances. A "model reference" control strategy was adopted for the design of the smart transducer. Multilayer perceptron (MLP) type networks were chosen for implementing the control strategy. While a static MLP was used for the feedback arrangement, a tap delayed lines MLP was necessary for implementing the controller due to the dynamic nonlinear behaviour exhibited by the sensing device. A dynamic version of the back-error propagation algorithm was used for training the networks. The resulting closed-loop transducer had a dynamic range of ±10g and a stable behaviour for input stimuli up to ±100g.

Original language	English
Title of host publication	2000 International Conference on Modeling and Simulation of Microsystems
Publisher	NSTI
Pages	513-516
Number of pages	4
Publication status	Published - 2000
Event	International Conference on Modeling and Simulation of Microsystems - San Diego, United States Duration: 27 Mar 2000 → 29 Mar 2000 http://www.nsti.org/Nanotech2000/MSM2000/

Conference

Conference	International Conference on Modeling and Simulation of Microsystems
Abbreviated title	MSM
Country/Territory	United States
City	San Diego
Period	27/03/00 → 29/03/00
Internet address	http://www.nsti.org/Nanotech2000/MSM2000/

Keywords

Accelerometers
Closed loop control systems
Electrostatic actuators
Feedback control
Machine design
Microelectromechanical devices
Micromachining
Nonlinear systems
Robustness (control systems)
Transducers, Electrostatic actuation
Micromachined accelerometers
Model reference control
Multilayer perceptron (MLP) neural networks, Neural networks

Cite this

@inproceedings{35de309827cf46909e30457fed7e5af1,

title = "Closed-loop, neural network controlled accelerometer design",

abstract = "In this paper, a closed-loop, smart transducer design is proposed, based on artificial neural network (ANN) techniques. The design aims to improve the performance of open-loop, off-the-shelf capacitive acceleration sensors and increase their robustness to manufacturing tolerances. A {"}model reference{"} control strategy was adopted for the design of the smart transducer. Multilayer perceptron (MLP) type networks were chosen for implementing the control strategy. While a static MLP was used for the feedback arrangement, a tap delayed lines MLP was necessary for implementing the controller due to the dynamic nonlinear behaviour exhibited by the sensing device. A dynamic version of the back-error propagation algorithm was used for training the networks. The resulting closed-loop transducer had a dynamic range of ±10g and a stable behaviour for input stimuli up to ±100g.",

keywords = "Accelerometers, Closed loop control systems, Electrostatic actuators, Feedback control, Machine design, Microelectromechanical devices, Micromachining, Nonlinear systems, Robustness (control systems), Transducers, Electrostatic actuation, Micromachined accelerometers, Model reference control, Multilayer perceptron (MLP) neural networks, Neural networks",

author = "E.I. Gaura and N. Ferreira and R.J. Rider and N. Steele",

year = "2000",

language = "English",

pages = "513--516",

booktitle = "2000 International Conference on Modeling and Simulation of Microsystems",

publisher = "NSTI",

address = "United States",

note = "International Conference on Modeling and Simulation of Microsystems, MSM ; Conference date: 27-03-2000 Through 29-03-2000",

url = "http://www.nsti.org/Nanotech2000/MSM2000/",

}

TY - GEN

T1 - Closed-loop, neural network controlled accelerometer design

AU - Gaura, E.I.

AU - Ferreira, N.

AU - Rider, R.J.

AU - Steele, N.

PY - 2000

Y1 - 2000

N2 - In this paper, a closed-loop, smart transducer design is proposed, based on artificial neural network (ANN) techniques. The design aims to improve the performance of open-loop, off-the-shelf capacitive acceleration sensors and increase their robustness to manufacturing tolerances. A "model reference" control strategy was adopted for the design of the smart transducer. Multilayer perceptron (MLP) type networks were chosen for implementing the control strategy. While a static MLP was used for the feedback arrangement, a tap delayed lines MLP was necessary for implementing the controller due to the dynamic nonlinear behaviour exhibited by the sensing device. A dynamic version of the back-error propagation algorithm was used for training the networks. The resulting closed-loop transducer had a dynamic range of ±10g and a stable behaviour for input stimuli up to ±100g.

AB - In this paper, a closed-loop, smart transducer design is proposed, based on artificial neural network (ANN) techniques. The design aims to improve the performance of open-loop, off-the-shelf capacitive acceleration sensors and increase their robustness to manufacturing tolerances. A "model reference" control strategy was adopted for the design of the smart transducer. Multilayer perceptron (MLP) type networks were chosen for implementing the control strategy. While a static MLP was used for the feedback arrangement, a tap delayed lines MLP was necessary for implementing the controller due to the dynamic nonlinear behaviour exhibited by the sensing device. A dynamic version of the back-error propagation algorithm was used for training the networks. The resulting closed-loop transducer had a dynamic range of ±10g and a stable behaviour for input stimuli up to ±100g.

KW - Accelerometers

KW - Closed loop control systems

KW - Electrostatic actuators

KW - Feedback control

KW - Machine design

KW - Microelectromechanical devices

KW - Micromachining

KW - Nonlinear systems

KW - Robustness (control systems)

KW - Transducers, Electrostatic actuation

KW - Micromachined accelerometers

KW - Model reference control

KW - Multilayer perceptron (MLP) neural networks, Neural networks

M3 - Conference proceeding

SP - 513

EP - 516

BT - 2000 International Conference on Modeling and Simulation of Microsystems

PB - NSTI

T2 - International Conference on Modeling and Simulation of Microsystems

Y2 - 27 March 2000 through 29 March 2000

ER -

Closed-loop, neural network controlled accelerometer design

Abstract

Conference

Keywords

Fingerprint

Cite this