TY - JOUR
T1 - Coupling Analytical Models and Machine Learning Methods for Fast and Reliable Resolution of Effects in Multifrequency Eddy-Current Sensors
AU - Kucheryavskiy, Sergey
AU - Egorov, Alexander
AU - Polyakov, Victor
PY - 2021
Y1 - 2021
N2 - Eddy current (EC) measurements, widely used for diagnostics of conductive materials, are highly dependent on physical properties and geometry of a sample as well as on a design of an EC-sensor. For a sensor of a given design, the conductivity and thickness of a sample as well as the gap between the sample and the sensor (lift-off) are the most influencing parameters. Estimation of these parameters, based on signals acquired from the sensor, is quite complicated in case when all three parameters are unknown and may vary. In this paper, we propose a machine learning based approach for solving this problem. The approach makes it possible to avoid time and resource- consuming computations and does not require experimental data for training of the prediction models. The approach was tested using independent sets of measurements from both simulated and real experimental data.
AB - Eddy current (EC) measurements, widely used for diagnostics of conductive materials, are highly dependent on physical properties and geometry of a sample as well as on a design of an EC-sensor. For a sensor of a given design, the conductivity and thickness of a sample as well as the gap between the sample and the sensor (lift-off) are the most influencing parameters. Estimation of these parameters, based on signals acquired from the sensor, is quite complicated in case when all three parameters are unknown and may vary. In this paper, we propose a machine learning based approach for solving this problem. The approach makes it possible to avoid time and resource- consuming computations and does not require experimental data for training of the prediction models. The approach was tested using independent sets of measurements from both simulated and real experimental data.
KW - Convolutional neural networks
KW - Data driven approach
KW - Deep learning
KW - Eddy current sensors
KW - Machine learning
KW - Multifrequency eddy currents
KW - Partial least squares regression
KW - Support vector machines
UR - http://www.scopus.com/inward/record.url?scp=85099497743&partnerID=8YFLogxK
U2 - 10.3390/s21020618
DO - 10.3390/s21020618
M3 - Journal article
SN - 1424-8220
VL - 21
SP - 1
EP - 16
JO - Sensors
JF - Sensors
IS - 2
M1 - 618
ER -