Instrumentation & Measurement Magazine 25-7 - 53

proposed technique obtained optimal results in terms of all
parameters.
Conclusion
This research proposed a novel technique to develop the MFL
testing system with pattern recognition in non-destructive
principle using deep learning architectures. The MFL signals
were collected as a large data sequence which has to be trained
and validated using neural networks. The detection of MFL
has been done using Faraday's law of electromagnetic (EM) induction
which is induced with Z-filter in EM decomposition.
The collected signal of MFL has been classified using convolutional
neural network (CNN). Proposed damage indexes and
general damage indexes for the MFL approach were used to
quantify discovered MFL signals for every damage type. The
experimental analysis based on NDT shows the accuracy, reliability,
MFL detection rate, and magnitude of MFL.
References
[1] T. K. Patra, T. D. Loeffler, H. Chan, M. J. Cherukara, B.
Narayanan, and S. K. R. S. Sankaranarayanan, " A coarse-grained
deep neural network model for liquid water, " Appl. Phys. Lett.,
vol. 115, 2019.
[2] H. Wang, X. Guo, L. Zhang, H. Wang, and J. Xue, " Deep learning
inter-atomic potential model for accurate irradiation damage
simulations, " Appl. Phys. Lett., vol. 114, 2019.
[3] S. Ye, B. Li, Q. Li, H. P. Zhao, and X. Q. Feng, " Deep neural
network method for predicting the mechanical properties of
composites, " Appl. Phys. Lett., vol. 115, 2019.
[4] D. Moghadas, " One-dimensional deep learning inversion of
electromagnetic induction data using convolutional neural
network, " Geophysical J. Int., vol. 222, no. 1, pp. 247-259, 2020.
[5] K. Noh, D. Yoon, and J. Byun, " Imaging subsurface resistivity
structure from airborne electromagnetic induction data using
deep neural network, " Exploration Geophysics, vol. 51, no. 2, pp.
214-220, 2020.
[6] P. Kinsler, " Faraday's law and induction: cause and effect,
experiment and theory, " Physics, vol. 2, no. 2, pp. 150-163, 2020.
[7] B. Dai and W. Bai, " Denoising ECG by adaptive filter with
empirical mode dDecomposition, " arXiv e-prints, arXiv-2108,
2021.
[8] R. Maoudj, M. Terre, L. Fety, C. Alexandre, and P. Mege, " Spatial
filter decomposition for interference mitigation, " EURASIP J.
Advances in Signal Processing, vol. 2014, no. 1, pp. 1-14, 2014.
[9] B. Ursin and M. J. Porsani, " Signal time-frequency representation
and decomposition using partial fractions, " Geophysical J. Int., vol.
226, no. 1, pp. 617-626, 2021.
[10] Z. Li, X. Huang, O. Elshafiey, S. Mukherjee, and Y. Deng, " FEM of
magnetic flux leakage signal for uncertainty estimation in crack
depth classification using bayesian convolutional neural network
and deep ensemble, " in Proc. 2021 Int. Appl. Computational
Electromagnetics Soc. Symp. (ACES), pp. 1-4, 2021.
[11] S. Lu, J. Feng, H. Zhang, J. Liu, and Z. Wu, " An estimation method
of defect size from MFL image using visual transformation
convolutional neural network, " IEEE Trans. Industrial Informatics,
vol. 15, no. 1, pp. 213-224, 2018.
October 2022
[12] M. Le, C. T. Pham, and J. Lee, " Deep neural network for
simulation of magnetic flux leakage testing, " Meas., vol. 170, 2021.
[13] F. Li, J. Feng, S. Lu, J. Liu, and Y. Yao, " Convolution neural
network for classification of magnetic flux leakage response
segments, " in Proc. 2017 6th Data Driven Control and Learning
Systems (DDCLS), pp. 152-155, 2017.
[14] D. Zhang, E. Zhang, and X. Yan, " Quantitative method for
detecting internal and surface defects in wire rope, " NDT and E
Int., vol. 119, 2021.
[15] M. Zambrano, A. Martinez-de-Guerenu, and F. Arizti, " Magnetic
flux leakage measurement system to detect flaws in small
diameter metallic wire ropes, " in Proc. 11th Eur. Conf. NonDestructive
Testing (ECNDT 2014), pp. 6-10, 2014.
[16] J.-W. Kim and S. Park, " Magnetic flux leakage sensing and
artificial neural network pattern recognition-based automated
damage detection and quantification for wire rope nondestructive
evaluation, " Sensors, vol. 18, no. 1, p. 109, 2018.
[17] X. Zhong and X. Zhang, " Non-destructive testing of steel wire
rope using magnetic flux leakage: principle, sensor design and
signal wavelet analysis, " Int. J. Simulation: Syst., Sci. Technol., vol.
17, no. 26, p. 8, 2016.
[18] H. Wang and G. Chen, " Defect size estimation method for
magnetic flux leakage signals using convolutional neural
networks, " Insight-Non-Destructive Testing and Condition
Monitoring, vol. 62, no. 2, pp. 86-91, 2020.
Nallamilli P. G. Bhavani is an Associate Professor in the
Department of Electronic Instrumentation Systems at the Institute
of Electronics and Communication Engineering, Saveetha
School of Engineering, Saveetha Institute of Medical and Technical
Sciences (SIMATS), Chennai, India. She has 16 years of
teaching experience. Her areas of research are in the fields of
digital image processing, instrumentation, control systems,
smart computing and green energy.
Ganapathy Senthilkumar is a Professor in the Computer Science
and Engineering Department at Panimalar Engineering
College, Chennai, India. His areas of interest include cloud
computing, communication networking and distributed systems.
He obtained his bachelor's degree in mathematics from
Madras University, Chennai, India and his master's degree
in computer application from Bharathiar University, Coimbatore,
India.
Shahnazeer Chembalakkat Kunjumohamad is a Research
Scholar in the Department of Computer Science and Engineering
at Pondicherry University Karaikal Campus, Puducherry,
India. She has nine years of experience as an Assistant Professor
at engineering colleges in Kerala and four years of experience in
industry. Her research interests include machine learning, deep
learning, natural language processing and cloud computing.
Azhagu Jaisudhan Pazhani is an Associate Professor in the
Department of Electronics and Communication Engineering
at Ramco Institute of Technology, Rajapalayam, India. He obtained
his Ph.D. degree in information and communication
IEEE Instrumentation & Measurement Magazine
53
Instrumentation & Measurement Magazine 25-7

Table of Contents for the Digital Edition of Instrumentation & Measurement Magazine 25-7
