Control Sensor Linearization Using Artificial Neural Networks

Authors:
G. L. Dempsey;J. S. Alig;N. L. Alt;B. A. Olson;D. E. Redfield
Affiliations:
Department of Electrical and Computer Engineering, Bradley University, Peoria, Illinois 61625;Department of Electrical and Computer Engineering, Bradley University, Peoria, Illinois 61625;Department of Electrical and Computer Engineering, Bradley University, Peoria, Illinois 61625;Department of Electrical and Computer Engineering, Bradley University, Peoria, Illinois 61625;Department of Electrical and Computer Engineering, Bradley University, Peoria, Illinois 61625
Venue:
Analog Integrated Circuits and Signal Processing
Year:
1997

Citing 1
Cited 2

Fuzzy logic for digital phase-locked loop filter design

IEEE Transactions on Fuzzy Systems

A Thermocouple Model Based on Neural Networks

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II
Nonlinear calibration for n thermocouple sensor

ICSI'12 Proceedings of the Third international conference on Advances in Swarm Intelligence - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Traditionally, the issues of cost, size, and weightof artificial neural network implementations have not been theprimary concern of researchers. These issues are important inmany applications such as those required in space travel, high-volumecommercial products, or products with size limitations. In thispaper, we discuss methods to improve the characteristics of controlsensors using compact and low-cost circuitry. Our objective isto extend the linear region of operation of a nonlinear sensorusing artificial neural networks. An analog circuit approachwas investigated for high-speed applications and a microcontrollerapproach for low-speed applications. The methods are appliedto the design of a discrete-component phase-locked loop. Bothapproaches resulted in doubling the sensor‘s linear range.