Nonlinear identification of eddy current sensors based on artificial neural networks

Hairong Zou

doi:10.1117/12.819577

31 December 2008 Nonlinear identification of eddy current sensors based on artificial neural networks

Hairong Zou

Proceedings Volume 7130, Fourth International Symposium on Precision Mechanical Measurements; 713013 (2008) https://doi.org/10.1117/12.819577
Event: Fourth International Symposium on Precision Mechanical Measurements, 2008, Anhui, China

Abstract

The nonlinear identification of the input-output characteristic of the eddy current sensor is an important research task in the application of the eddy current sensor. At first, the working principle and the working characteristics of the eddy current sensor were introduced in this paper. Then the nonlinear identification of the eddy current sensor was analyzed in detail. To aim at the error problem of the eddy current sensor with the nonlinear factors, a feasible project of nonlinear identification of the eddy current sensor was researched applied the modeling method of artificial neural networks, and a new artificial neural network is presented to realize the nonlinear identification of the eddy current sensor without linearization processing. Its design, modeling and implement technology based on a new internal recurrent neural networks were advanced, and then the data experiments were processed with MATLAB software, thus the measure precision of the eddy current sensor was enhanced. In the end, the measuring error is no more than 0.1%, and the dynamic responding time is less than 0.5 second. This method can increase the measuring accuracy and be advantageous for the test analysis and the data statistics though the online data processing of the computer.

Citation Download Citation

Hairong Zou "Nonlinear identification of eddy current sensors based on artificial neural networks", Proc. SPIE 7130, Fourth International Symposium on Precision Mechanical Measurements, 713013 (31 December 2008); https://doi.org/10.1117/12.819577

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available