Deep neural network for simulation of magnetic flux leakage testing
Q1
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
Measurement
2021
|
Subjects: | |
Online Access: | https://www.sciencedirect.com/science/article/abs/pii/S0263224120312306?via%3Dihub#! https://dlib.phenikaa-uni.edu.vn/handle/PNK/1933 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
oai:localhost:PNK-1933 |
---|---|
record_format |
dspace |
spelling |
oai:localhost:PNK-19332022-08-17T05:54:45Z Deep neural network for simulation of magnetic flux leakage testing Minhhuy Le Cong-Thuong Pham Jinyi Lee Deep learning Machine learning MFLT FEM Q1 Magnetic flux leakage testing (MFLT) is an important nondestructive testing method for the detection and evaluation of defects in magnetic materials. Magnetic field distribution in an MFLT system is usually simulated by the finite element method (FEM), which required large memory, high computation, and complication of the meshing process. In this paper, an alternative simulation method will be proposed using a deep neural network (DNN). The DNN method provides an easy way of simulation by feeding only the distribution of supplied current and the physical properties such as magnetic permeability without the need for the meshing process. Defects with arbitrary sizes were simulated under different configurations of the MFLT systems. The DNN was trained on the simulation results of the FEM and provided an accurate prediction of the magnetic field distribution of the unseen data. This study paves the way for designing optimized MFLT systems in a bigdata-driven method. 2021-07-05T08:00:04Z 2021-07-05T08:00:04Z 2021 Article https://www.sciencedirect.com/science/article/abs/pii/S0263224120312306?via%3Dihub#! https://dlib.phenikaa-uni.edu.vn/handle/PNK/1933 10.1016/j.measurement.2020.108726 en application/pdf Measurement |
institution |
Digital Phenikaa |
collection |
Digital Phenikaa |
language |
English |
topic |
Deep learning Machine learning MFLT FEM |
spellingShingle |
Deep learning Machine learning MFLT FEM Minhhuy Le Deep neural network for simulation of magnetic flux leakage testing |
description |
Q1 |
author2 |
Cong-Thuong Pham |
author_facet |
Cong-Thuong Pham Minhhuy Le |
format |
Article |
author |
Minhhuy Le |
author_sort |
Minhhuy Le |
title |
Deep neural network for simulation of magnetic flux leakage testing |
title_short |
Deep neural network for simulation of magnetic flux leakage testing |
title_full |
Deep neural network for simulation of magnetic flux leakage testing |
title_fullStr |
Deep neural network for simulation of magnetic flux leakage testing |
title_full_unstemmed |
Deep neural network for simulation of magnetic flux leakage testing |
title_sort |
deep neural network for simulation of magnetic flux leakage testing |
publisher |
Measurement |
publishDate |
2021 |
url |
https://www.sciencedirect.com/science/article/abs/pii/S0263224120312306?via%3Dihub#! https://dlib.phenikaa-uni.edu.vn/handle/PNK/1933 |
_version_ |
1751856255754829824 |
score |
8.891145 |