Accurate neural model identification of measurement devices

Author

Bernieri, Andrea ; Daponte, Pasquale ; Grimaldi, Domenico

Author_Institution

Dipartimento di Ingegneria Ind., Univ. di Cassino, Italy

Volume

2

fYear

1996

fDate

1996

Firstpage

998

Abstract

A neural approach to modeling measurement devices is presented. This approach allows the usual components of a measurement apparatus (transducers, filters, amplifiers, analog-to-digital converters, etc.) to be easily modeled by means of suitably trained Artificial Neural Networks. Two applications regarding analog and mixed analog/digital devices are reported, highlighting the peculiarity of this approach and the accuracy obtainable

Keywords

analogue-digital conversion; backpropagation; digital-analogue conversion; feedforward neural nets; filters; identification; instrumentation amplifiers; instruments; measurement theory; modelling; transducers; transfer functions; accurate neural model identification; amplifiers; analog devices; analog-to-digital converters; error model; feedforward network; filters; learning algorithms; measurement devices modelling; mixed analog/digital devices; node transfer function; nonlinearities; trained ANN; transducers; Analog-digital conversion; Artificial neural networks; Digital filters; IEEE members; Iterative algorithms; Particle measurements; Sensor phenomena and characterization; Sensor systems; Transducers; Transfer functions;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 1996. IMTC-96. Conference Proceedings. Quality Measurements: The Indispensable Bridge between Theory and Reality., IEEE

Conference_Location

Brussels

Print_ISBN

0-7803-3312-8

Type

conf

DOI

10.1109/IMTC.1996.507315

Filename

507315