Online implementation of an adaptive calibration technique for displacement measurement using LVDT

K. V. Santhosh, B. K. Roy

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The paper presents the design and validation of an online intelligent displacement measurement technique with Linear Variable Differential Transformer (LVDT) using Artificial Neural Network (ANN). The objectives of the proposed work are to design a calibration technique using an optimised neural network model such that it a) produces an output which is linear for the full scale of input range, b) makes the output independent of the variations in supply frequency, the physical parameters of the LVDT, and ambient temperature. The output of an LVDT is converted to a DC signal by using a rectifier circuit. The rectified output is further amplified using a differential amplifier. This voltage signal is acquired onto a computer for further processing using an ANN. The optimisation of the ANN is carried out to find the minimum number of hidden layers along with the number of neurones in each layer to give least Mean Square Error (MSE) and Regression (R) nearing to one. This optimisation is done considering various schemes of ANN, training algorithms, and the transfer function of neurones. Once the ANN model is designed, it is subjected to test with both simulated data and experimental validation. The results confirm the successful achievement of the objectives of this paper and thus avoiding the need for repeated calibration.

Original languageEnglish
Pages (from-to)19-26
Number of pages8
JournalApplied Soft Computing Journal
Volume53
DOIs
Publication statusPublished - 01-04-2017
Externally publishedYes

Fingerprint

Displacement measurement
Calibration
Neural networks
Neurons
Differential amplifiers
Mean square error
Transfer functions
Networks (circuits)
Electric potential
Processing

All Science Journal Classification (ASJC) codes

  • Software

Cite this

@article{a530e3e86aab4e69971b47b1a5dd6bb0,
title = "Online implementation of an adaptive calibration technique for displacement measurement using LVDT",
abstract = "The paper presents the design and validation of an online intelligent displacement measurement technique with Linear Variable Differential Transformer (LVDT) using Artificial Neural Network (ANN). The objectives of the proposed work are to design a calibration technique using an optimised neural network model such that it a) produces an output which is linear for the full scale of input range, b) makes the output independent of the variations in supply frequency, the physical parameters of the LVDT, and ambient temperature. The output of an LVDT is converted to a DC signal by using a rectifier circuit. The rectified output is further amplified using a differential amplifier. This voltage signal is acquired onto a computer for further processing using an ANN. The optimisation of the ANN is carried out to find the minimum number of hidden layers along with the number of neurones in each layer to give least Mean Square Error (MSE) and Regression (R) nearing to one. This optimisation is done considering various schemes of ANN, training algorithms, and the transfer function of neurones. Once the ANN model is designed, it is subjected to test with both simulated data and experimental validation. The results confirm the successful achievement of the objectives of this paper and thus avoiding the need for repeated calibration.",
author = "Santhosh, {K. V.} and Roy, {B. K.}",
year = "2017",
month = "4",
day = "1",
doi = "10.1016/j.asoc.2016.12.032",
language = "English",
volume = "53",
pages = "19--26",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier BV",

}

Online implementation of an adaptive calibration technique for displacement measurement using LVDT. / Santhosh, K. V.; Roy, B. K.

In: Applied Soft Computing Journal, Vol. 53, 01.04.2017, p. 19-26.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Online implementation of an adaptive calibration technique for displacement measurement using LVDT

AU - Santhosh, K. V.

AU - Roy, B. K.

PY - 2017/4/1

Y1 - 2017/4/1

N2 - The paper presents the design and validation of an online intelligent displacement measurement technique with Linear Variable Differential Transformer (LVDT) using Artificial Neural Network (ANN). The objectives of the proposed work are to design a calibration technique using an optimised neural network model such that it a) produces an output which is linear for the full scale of input range, b) makes the output independent of the variations in supply frequency, the physical parameters of the LVDT, and ambient temperature. The output of an LVDT is converted to a DC signal by using a rectifier circuit. The rectified output is further amplified using a differential amplifier. This voltage signal is acquired onto a computer for further processing using an ANN. The optimisation of the ANN is carried out to find the minimum number of hidden layers along with the number of neurones in each layer to give least Mean Square Error (MSE) and Regression (R) nearing to one. This optimisation is done considering various schemes of ANN, training algorithms, and the transfer function of neurones. Once the ANN model is designed, it is subjected to test with both simulated data and experimental validation. The results confirm the successful achievement of the objectives of this paper and thus avoiding the need for repeated calibration.

AB - The paper presents the design and validation of an online intelligent displacement measurement technique with Linear Variable Differential Transformer (LVDT) using Artificial Neural Network (ANN). The objectives of the proposed work are to design a calibration technique using an optimised neural network model such that it a) produces an output which is linear for the full scale of input range, b) makes the output independent of the variations in supply frequency, the physical parameters of the LVDT, and ambient temperature. The output of an LVDT is converted to a DC signal by using a rectifier circuit. The rectified output is further amplified using a differential amplifier. This voltage signal is acquired onto a computer for further processing using an ANN. The optimisation of the ANN is carried out to find the minimum number of hidden layers along with the number of neurones in each layer to give least Mean Square Error (MSE) and Regression (R) nearing to one. This optimisation is done considering various schemes of ANN, training algorithms, and the transfer function of neurones. Once the ANN model is designed, it is subjected to test with both simulated data and experimental validation. The results confirm the successful achievement of the objectives of this paper and thus avoiding the need for repeated calibration.

UR - http://www.scopus.com/inward/record.url?scp=85008388745&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85008388745&partnerID=8YFLogxK

U2 - 10.1016/j.asoc.2016.12.032

DO - 10.1016/j.asoc.2016.12.032

M3 - Article

VL - 53

SP - 19

EP - 26

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

ER -