Pipe Leak Detection System using Wireless Acoustic Sensor Module and Deep Auto-Encoder (무선 음향 센서 모듈과 딥 오토인코더를 이용한 배관 누출 탐지 시스템)

Doyeob Yeo (여도엽); Giyoung Lee (이기영); Jae Cheol Lee (이재철)

doi:10.9708/jksci.2020.25.02.059

Pipe Leak Detection System using Wireless Acoustic Sensor Module and Deep Auto-Encoder

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2020, 25(2), pp.59-66
DOI : 10.9708/jksci.2020.25.02.059
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science
Received : December 13, 2019
Accepted : January 17, 2020
Published : February 28, 2020

Doyeob Yeo ¹, Giyoung Lee ¹, Jae Cheol Lee ²

¹한국전자통신연구원
²한국원자력연구원

Accredited

ABSTRACT

In this paper, we propose a pipe leak detection system through data collection using low-power wireless acoustic sensor modules and data analysis using deep auto-encoder. Based on the Fourier transform, we propose a low-power wireless acoustic sensor module that reduces data traffic by reducing the amount of acoustic sensor data to about 1/800, and we design the system that is robust to noise generated in the audible frequency band using only 20kHz~100kHz frequency signals. In addition, the proposed system is designed using a deep auto-encoder to accurately detect pipe leaks even with a reduced amount of data. Numerical experiments show that the proposed pipe leak detection system has a high accuracy of 99.94% and Type-II error of 0% even in the environment where high frequency band noise is mixed.

KEYWORDS

Wireless, Ultrasonic wave, Low-power, Deep auto-encoder, Pipe leak detection

Citation status

* References for papers published after 2023 are currently being built.

[confproc] D. -B. Yoon / 2016 / A Study on Acoustic Signal Processing Method for Detecting Small Leak of Piping System / Proceedings of the Domestic conference on the Korean Society for Noise and Vibration Engineering : 139~139

[confproc] J. -H. Bae / 2018 / Deep-Learning-Based Pipe Leak Detection Using Image-Based Leak Features / Proceedings of the IEEE International Conference on Image Processing (ICIP) : 2361~2365

[journal] 여도엽 / 2019 / Unsupervised Learning-Based Pipe Leak Detection using Deep Auto-Encoder / 한국컴퓨터정보학회논문지 / 한국컴퓨터정보학회 24(9) : 21~27

[journal] G. Cybenko / 1989 / Approximation by superpositions of a sigmoidal function / Mathematics of Control, Signals, and Systems / Springer Science and Business Media LLC 2(4) : 303~314

[confproc] C. Szegedy / 2015 / Going Deeper with Convolutions / Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) : 1~9

[confproc] K. Simonyan / 2015 / Very Deep Convolutional Networks for Large-scale Image Recognition / Proceedings of 5th International Conference on Learning Representations (ICLR) : 1~14

[confproc] K. He / 2016 / Deep Residual Learning for Image Recognition / Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) : 1~12

[confproc] G. Huang / 2017 / Densely Connected Convolutional Networks / Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) : 2261~2269

[journal] Sepp Hochreiter / 1997 / Long Short-Term Memory / Neural Computation / MIT Press - Journals 9(8) : 1735~1780

[other] V. Mnih / 2013 / Playing atari with deep reinforcement learning / arXiv preprint arXiv:1312.5602

[other] V. Mnih / 2016 / Asynchronous Methods for Deep Reinforcement Learning / arXiv preprint arXiv:1602.01783

[other] R. Chalapathy / 2019 / Deep Learning for Anomaly Detection : A survey / arXiv preprint arXiv:1901:03407

[confproc] A. Borghesi / 2019 / Anomaly detection using autoencoders in high performance computing systems / Proceedings of the AAAI Conference on Artificial Intelligence 33(01) : 9428~9433

[confproc] T. Luo / 2018 / Distributed Anomaly Detection Using Autoencoder Neural Networks in WSN for IoT / Proceedings of 2018 IEEE International Conference on Communications (ICC) : 1~6

[confproc] J. Pereira / 2018 / Unsupervised Anomaly Detection in Energy Time Series Data using Variational Recurrent Autoencoders with Attention / Proceedings of 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) : 1275~1282

[web] / 2018 / ASTM E1002-11(2018), Standard Practice for Leaks Using Ultrasonics / American Society for Testing and Materials (ASTM) International / www.astm.org.

[other] / NDIS 3420-2000: Methods for Leak Test using Ultrasonics / Non-Destructive Inspection Society

[confproc] Y. Pei / 2015 / The gas leak locating detection based on the improved ultrasonic transducer array group / Proceedings of the International Conference on Machinery, Materials Science and Engineering Application (MMSE) : 251~255

This paper was written with support from the National Research Foundation of Korea.

KJCKorea
Journal Central

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Pipe Leak Detection System using Wireless Acoustic Sensor Module and Deep Auto-Encoder

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Pipe Leak Detection System using Wireless Acoustic Sensor Module and Deep Auto-Encoder

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (1)

REFERENCES (18) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.