Real-time Automatic Thickness Recognition Using Pulse Eddy Current with Deep Learning

Tian Meng; Lei Xiong; Xinnan Zheng; Zihan Xia; Xiaofei Liu; Yang Tao; Wuqiang Yang; Wuliang Yin

doi:10.1109/i2mtc53148.2023.10175900

Real-time Automatic Thickness Recognition Using Pulse Eddy Current with Deep Learning

Tian Meng, Lei Xiong, Xinnan Zheng, Zihan Xia, Xiaofei Liu, Yang Tao, Wuqiang Yang, Wuliang Yin

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

Pulse eddy current (PEC) is one of the key eddy current testing (ECT) techniques and it is widely used in metal industry. Being able to automatically recognize thickness with PEC can make the manufacturing process more efficient and convenient. In this paper, the main contribution is three-fold. Firstly, a novel portable pulse eddy current device is designed, and a new PEC dataset is constructed with a wide variety of features using our device. Secondly, 1-D convolutional-based deep learning models are utilised to achieve automatic thickness recognition with high accuracy. In addition, models are moderately immune to lift-off and edge effects. Lastly, a compact and lightweight 1-D convolutional neural network is deployed on the STM32 microcontroller in our device, and it achieves real-time, accurate and low-latency automatic thickness recognition.

Original language	English
Title of host publication	2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781665453837
ISBN (Print)	9781665453844
DOIs	https://doi.org/10.1109/i2mtc53148.2023.10175900
Publication status	Published - 13 Jul 2023
Event	2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) - Kuala Lumpur, Malaysia Duration: 22 May 2023 → 25 May 2023

Conference

Conference	2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)
Period	22/05/23 → 25/05/23

Keywords

pulse eddy current
deep learning
embedded system
real-time recognition

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/i2mtc53148.2023.10175900

Cite this

@inproceedings{efb4fc421dd649d19bf99a634f9c4088,

title = "Real-time Automatic Thickness Recognition Using Pulse Eddy Current with Deep Learning",

abstract = "Pulse eddy current (PEC) is one of the key eddy current testing (ECT) techniques and it is widely used in metal industry. Being able to automatically recognize thickness with PEC can make the manufacturing process more efficient and convenient. In this paper, the main contribution is three-fold. Firstly, a novel portable pulse eddy current device is designed, and a new PEC dataset is constructed with a wide variety of features using our device. Secondly, 1-D convolutional-based deep learning models are utilised to achieve automatic thickness recognition with high accuracy. In addition, models are moderately immune to lift-off and edge effects. Lastly, a compact and lightweight 1-D convolutional neural network is deployed on the STM32 microcontroller in our device, and it achieves real-time, accurate and low-latency automatic thickness recognition.",

keywords = "pulse eddy current, deep learning, embedded system, real-time recognition",

author = "Tian Meng and Lei Xiong and Xinnan Zheng and Zihan Xia and Xiaofei Liu and Yang Tao and Wuqiang Yang and Wuliang Yin",

year = "2023",

month = jul,

day = "13",

doi = "10.1109/i2mtc53148.2023.10175900",

language = "English",

isbn = "9781665453844",

pages = "1--6",

booktitle = "2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)",

publisher = "IEEE",

address = "United States",

note = "2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) ; Conference date: 22-05-2023 Through 25-05-2023",

}

Meng, T, Xiong, L, Zheng, X, Xia, Z, Liu, X, Tao, Y, Yang, W & Yin, W 2023, Real-time Automatic Thickness Recognition Using Pulse Eddy Current with Deep Learning. in 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). IEEE, Piscataway, NJ, pp. 1-6, 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 22/05/23. https://doi.org/10.1109/i2mtc53148.2023.10175900

TY - GEN

T1 - Real-time Automatic Thickness Recognition Using Pulse Eddy Current with Deep Learning

AU - Meng, Tian

AU - Xiong, Lei

AU - Zheng, Xinnan

AU - Xia, Zihan

AU - Liu, Xiaofei

AU - Tao, Yang

AU - Yang, Wuqiang

AU - Yin, Wuliang

PY - 2023/7/13

Y1 - 2023/7/13

N2 - Pulse eddy current (PEC) is one of the key eddy current testing (ECT) techniques and it is widely used in metal industry. Being able to automatically recognize thickness with PEC can make the manufacturing process more efficient and convenient. In this paper, the main contribution is three-fold. Firstly, a novel portable pulse eddy current device is designed, and a new PEC dataset is constructed with a wide variety of features using our device. Secondly, 1-D convolutional-based deep learning models are utilised to achieve automatic thickness recognition with high accuracy. In addition, models are moderately immune to lift-off and edge effects. Lastly, a compact and lightweight 1-D convolutional neural network is deployed on the STM32 microcontroller in our device, and it achieves real-time, accurate and low-latency automatic thickness recognition.

AB - Pulse eddy current (PEC) is one of the key eddy current testing (ECT) techniques and it is widely used in metal industry. Being able to automatically recognize thickness with PEC can make the manufacturing process more efficient and convenient. In this paper, the main contribution is three-fold. Firstly, a novel portable pulse eddy current device is designed, and a new PEC dataset is constructed with a wide variety of features using our device. Secondly, 1-D convolutional-based deep learning models are utilised to achieve automatic thickness recognition with high accuracy. In addition, models are moderately immune to lift-off and edge effects. Lastly, a compact and lightweight 1-D convolutional neural network is deployed on the STM32 microcontroller in our device, and it achieves real-time, accurate and low-latency automatic thickness recognition.

KW - pulse eddy current

KW - deep learning

KW - embedded system

KW - real-time recognition

U2 - 10.1109/i2mtc53148.2023.10175900

DO - 10.1109/i2mtc53148.2023.10175900

M3 - Conference contribution

SN - 9781665453844

SP - 1

EP - 6

BT - 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)

PB - IEEE

CY - Piscataway, NJ

T2 - 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)

Y2 - 22 May 2023 through 25 May 2023

ER -

Real-time Automatic Thickness Recognition Using Pulse Eddy Current with Deep Learning

Abstract

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this