Instrumentation & Measurement Magazine 25-7 - 48
Real-Time Inspection in Detection Magnetic
Flux Leakage by Deep Learning Integrated
with Concentrating Non-Destructive
Principle and Electromagnetic Induction
Nallamilli P. G. Bhavani, Ganapathy Senthilkumar,
Shahnazeer Chembalakkat Kunjumohamad, Azhagu Jaisudhan Pazhani,
Ravi Kumar, Abolfazl Mehbodniya, and Julian L. Webber
O
ne of the most common techniques of pipeline inspection
is magnetic flux leakage (MFL). It is a
non-destructive testing (NDT) method that employs
magnetic sensitive sensors to detect MFL of faults on
pipelines' internal and external surfaces. This research proposed
a novel technique in real-time detection of MFL with
pattern recognition in non-destructive principle using deep
learning architectures. Here, the MFL signal has been collected
as a large data sequence which has to be trained and validated
using neural networks. Initially, the MFL has been detected using
Faraday's law of electromagnetic induction (EMI) which is
induced with Z-filter in electromagnetic (EM) decomposition.
The collected signal of MFL has been classified using convolutional
neural network (CNN), and this classified signal has
been recognized by the patterns based on their threshold of
the signal. By extracting and analyzing magnetic properties
of MFL for a signal, the quantitative MFL has exceeded their
threshold value from detected signals. Damage indices based
on the link between enveloped MFL signal and the threshold
value, as well as a generic damage index for MFL technique,
were used to strengthen the quantitative analysis.
Introduction
Steel wire ropes are utilized extensively in the metallurgical
sector, mining, transportation, construction, cable strayed
bridges, tourism and architecture, among other applications.
However, after a period of use, some faults in steel wire rope
may appear. Steel wire rope deterioration, such as broken
wires, fatigue, corrosion, abrasion or wear, causes the structure
strength of steel wire rope to decline [1]-[3], and they may even
result in disasters. Wire rope safety is becoming increasingly
important in today's world. Acoustic emission, electromagnetic
methods, X-ray, and other inspection methods have been
examined, with the electromagnetic method being the most
practical and robust [4].
As the amount of time spent using the product rises, the
severity of the damage enhances. If rope cannot be fixed or
changed promptly, safe production is jeopardized, putting
people and equipment in danger. Fatigue damage like broken
48
wires, wear and corrosion will occur when employing steel
wire rope [5]-[6]. The design of the MFL testing system is complicated
by the constraints imposed by its portability and some
desired capabilities. Magnetic flux (MF) in specimen stays
uniform when there is no damage. Flux leakage, on the other
hand, happens when local faults cause damage. Because of the
volume constraint, obtaining high defect resolution with a coil
sensor is quite challenging. Hall sensors, on the other hand,
allow for the measurement of MFL's absolute value (B). Because
the Hall sensor dimension is so small, resolution of an
instrument with a Hall sensor might be increased, and novel
concept sensor topologies could be constructed by using an
array of them. Many factors influence the resolution and dependability
of equipment, including detector topology, sensor
technology, defect location and dimension, and signal processing
techniques [6].
The contribution of this research is as follows:
◗ To develop an MFL testing system with pattern recognition
in non-destructive principle using deep learning
architectures.
◗ To collect the MFL signals' large data sequence which has
to be trained and validated using neural networks.
◗ To detect MFL using Faraday's law of electromagnetic
(EM) induction which is induced with Z-filter in EM
decomposition.
◗ To classify collected signals of MFL using convolutional
neural network (CNN).
The paper covers related works, provides an overview of
magnetic flux leakage detection in wire rope, shows CNN
based MFL signal classification, gives a performance analysis
and offers conclusions from the research.
Related Works
The MFL approach has been used in the detection and size
of defects in the past. Authors in [7] analyze the use of multilayer
Perceptrons (MLP) for MFL data pattern recognition in
pipeline weld joints, where machine learning had previously
been employed in this context. For defect-shape construction,
work reported [6] uses inverse modeling methods.
IEEE Instrumentation & Measurement Magazine
1094-6969/22/$25.00©2022IEEE
October 2022
Instrumentation & Measurement Magazine 25-7
Table of Contents for the Digital Edition of Instrumentation & Measurement Magazine 25-7
Instrumentation & Measurement Magazine 25-7 - Cover1
Instrumentation & Measurement Magazine 25-7 - Cover2
Instrumentation & Measurement Magazine 25-7 - 1
Instrumentation & Measurement Magazine 25-7 - 2
Instrumentation & Measurement Magazine 25-7 - 3
Instrumentation & Measurement Magazine 25-7 - 4
Instrumentation & Measurement Magazine 25-7 - 5
Instrumentation & Measurement Magazine 25-7 - 6
Instrumentation & Measurement Magazine 25-7 - 7
Instrumentation & Measurement Magazine 25-7 - 8
Instrumentation & Measurement Magazine 25-7 - 9
Instrumentation & Measurement Magazine 25-7 - 10
Instrumentation & Measurement Magazine 25-7 - 11
Instrumentation & Measurement Magazine 25-7 - 12
Instrumentation & Measurement Magazine 25-7 - 13
Instrumentation & Measurement Magazine 25-7 - 14
Instrumentation & Measurement Magazine 25-7 - 15
Instrumentation & Measurement Magazine 25-7 - 16
Instrumentation & Measurement Magazine 25-7 - 17
Instrumentation & Measurement Magazine 25-7 - 18
Instrumentation & Measurement Magazine 25-7 - 19
Instrumentation & Measurement Magazine 25-7 - 20
Instrumentation & Measurement Magazine 25-7 - 21
Instrumentation & Measurement Magazine 25-7 - 22
Instrumentation & Measurement Magazine 25-7 - 23
Instrumentation & Measurement Magazine 25-7 - 24
Instrumentation & Measurement Magazine 25-7 - 25
Instrumentation & Measurement Magazine 25-7 - 26
Instrumentation & Measurement Magazine 25-7 - 27
Instrumentation & Measurement Magazine 25-7 - 28
Instrumentation & Measurement Magazine 25-7 - 29
Instrumentation & Measurement Magazine 25-7 - 30
Instrumentation & Measurement Magazine 25-7 - 31
Instrumentation & Measurement Magazine 25-7 - 32
Instrumentation & Measurement Magazine 25-7 - 33
Instrumentation & Measurement Magazine 25-7 - 34
Instrumentation & Measurement Magazine 25-7 - 35
Instrumentation & Measurement Magazine 25-7 - 36
Instrumentation & Measurement Magazine 25-7 - 37
Instrumentation & Measurement Magazine 25-7 - 38
Instrumentation & Measurement Magazine 25-7 - 39
Instrumentation & Measurement Magazine 25-7 - 40
Instrumentation & Measurement Magazine 25-7 - 41
Instrumentation & Measurement Magazine 25-7 - 42
Instrumentation & Measurement Magazine 25-7 - 43
Instrumentation & Measurement Magazine 25-7 - 44
Instrumentation & Measurement Magazine 25-7 - 45
Instrumentation & Measurement Magazine 25-7 - 46
Instrumentation & Measurement Magazine 25-7 - 47
Instrumentation & Measurement Magazine 25-7 - 48
Instrumentation & Measurement Magazine 25-7 - 49
Instrumentation & Measurement Magazine 25-7 - 50
Instrumentation & Measurement Magazine 25-7 - 51
Instrumentation & Measurement Magazine 25-7 - 52
Instrumentation & Measurement Magazine 25-7 - 53
Instrumentation & Measurement Magazine 25-7 - 54
Instrumentation & Measurement Magazine 25-7 - 55
Instrumentation & Measurement Magazine 25-7 - 56
Instrumentation & Measurement Magazine 25-7 - 57
Instrumentation & Measurement Magazine 25-7 - 58
Instrumentation & Measurement Magazine 25-7 - 59
Instrumentation & Measurement Magazine 25-7 - 60
Instrumentation & Measurement Magazine 25-7 - 61
Instrumentation & Measurement Magazine 25-7 - Cover3
https://www.nxtbook.com/allen/iamm/26-6
https://www.nxtbook.com/allen/iamm/26-5
https://www.nxtbook.com/allen/iamm/26-4
https://www.nxtbook.com/allen/iamm/26-3
https://www.nxtbook.com/allen/iamm/26-2
https://www.nxtbook.com/allen/iamm/26-1
https://www.nxtbook.com/allen/iamm/25-9
https://www.nxtbook.com/allen/iamm/25-8
https://www.nxtbook.com/allen/iamm/25-7
https://www.nxtbook.com/allen/iamm/25-6
https://www.nxtbook.com/allen/iamm/25-5
https://www.nxtbook.com/allen/iamm/25-4
https://www.nxtbook.com/allen/iamm/25-3
https://www.nxtbook.com/allen/iamm/instrumentation-measurement-magazine-25-2
https://www.nxtbook.com/allen/iamm/25-1
https://www.nxtbook.com/allen/iamm/24-9
https://www.nxtbook.com/allen/iamm/24-7
https://www.nxtbook.com/allen/iamm/24-8
https://www.nxtbook.com/allen/iamm/24-6
https://www.nxtbook.com/allen/iamm/24-5
https://www.nxtbook.com/allen/iamm/24-4
https://www.nxtbook.com/allen/iamm/24-3
https://www.nxtbook.com/allen/iamm/24-2
https://www.nxtbook.com/allen/iamm/24-1
https://www.nxtbook.com/allen/iamm/23-9
https://www.nxtbook.com/allen/iamm/23-8
https://www.nxtbook.com/allen/iamm/23-6
https://www.nxtbook.com/allen/iamm/23-5
https://www.nxtbook.com/allen/iamm/23-2
https://www.nxtbook.com/allen/iamm/23-3
https://www.nxtbook.com/allen/iamm/23-4
https://www.nxtbookmedia.com