Diversion Detection in Small-Diameter HDPE Pipes Using Guided Waves and Deep Learning
In this paper, we propose a novel technique for the inspection of high-density polyethylene (HDPE) pipes using ultrasonic sensors, signal processing, and deep neural networks (DNNs). Specifically, we propose a technique that detects whether there is a diversion on a pipe or not. The proposed model t...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/24/9586 |
| _version_ | 1797455375003287552 |
|---|---|
| author | Abdullah Zayat Mohanad Obeed Anas Chaaban |
| author_facet | Abdullah Zayat Mohanad Obeed Anas Chaaban |
| author_sort | Abdullah Zayat |
| collection | DOAJ |
| description | In this paper, we propose a novel technique for the inspection of high-density polyethylene (HDPE) pipes using ultrasonic sensors, signal processing, and deep neural networks (DNNs). Specifically, we propose a technique that detects whether there is a diversion on a pipe or not. The proposed model transmits ultrasound signals through a pipe using a custom-designed array of piezoelectric transmitters and receivers. We propose to use the Zadoff–Chu sequence to modulate the input signals, then utilize its correlation properties to estimate the pipe channel response. The processed signal is then fed to a DNN that extracts the features and decides whether there is a diversion or not. The proposed technique demonstrates an average classification accuracy of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90.3</mn><mo>%</mo></mrow></semantics></math></inline-formula> (when one sensor is used) and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99.6</mn><mo>%</mo></mrow></semantics></math></inline-formula> (when two sensors are used) on <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mfrac><mn>3</mn><mn>4</mn></mfrac></semantics></math></inline-formula> inch pipes. The technique can be readily generalized for pipes of different diameters and materials. |
| first_indexed | 2024-03-09T15:53:29Z |
| format | Article |
| id | doaj.art-60a2e710f2314e87be5ceaa8741b7215 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T15:53:29Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-60a2e710f2314e87be5ceaa8741b72152023-11-24T17:52:00ZengMDPI AGSensors1424-82202022-12-012224958610.3390/s22249586Diversion Detection in Small-Diameter HDPE Pipes Using Guided Waves and Deep LearningAbdullah Zayat0Mohanad Obeed1Anas Chaaban2School of Engineering, University of British Columbia, 1137 Alumni Ave, Kelowna, BC V1V 1V7, CanadaSchool of Engineering, University of British Columbia, 1137 Alumni Ave, Kelowna, BC V1V 1V7, CanadaSchool of Engineering, University of British Columbia, 1137 Alumni Ave, Kelowna, BC V1V 1V7, CanadaIn this paper, we propose a novel technique for the inspection of high-density polyethylene (HDPE) pipes using ultrasonic sensors, signal processing, and deep neural networks (DNNs). Specifically, we propose a technique that detects whether there is a diversion on a pipe or not. The proposed model transmits ultrasound signals through a pipe using a custom-designed array of piezoelectric transmitters and receivers. We propose to use the Zadoff–Chu sequence to modulate the input signals, then utilize its correlation properties to estimate the pipe channel response. The processed signal is then fed to a DNN that extracts the features and decides whether there is a diversion or not. The proposed technique demonstrates an average classification accuracy of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90.3</mn><mo>%</mo></mrow></semantics></math></inline-formula> (when one sensor is used) and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>99.6</mn><mo>%</mo></mrow></semantics></math></inline-formula> (when two sensors are used) on <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mfrac><mn>3</mn><mn>4</mn></mfrac></semantics></math></inline-formula> inch pipes. The technique can be readily generalized for pipes of different diameters and materials.https://www.mdpi.com/1424-8220/22/24/9586high-density polyethylene (HDPE)ultrasonic-guided waves (UGWs)Zadoff–Chu sequencedeep neural network (DNN)convolutional neural network (CNN)recurrent neural network (RNN) |
| spellingShingle | Abdullah Zayat Mohanad Obeed Anas Chaaban Diversion Detection in Small-Diameter HDPE Pipes Using Guided Waves and Deep Learning Sensors high-density polyethylene (HDPE) ultrasonic-guided waves (UGWs) Zadoff–Chu sequence deep neural network (DNN) convolutional neural network (CNN) recurrent neural network (RNN) |
| title | Diversion Detection in Small-Diameter HDPE Pipes Using Guided Waves and Deep Learning |
| title_full | Diversion Detection in Small-Diameter HDPE Pipes Using Guided Waves and Deep Learning |
| title_fullStr | Diversion Detection in Small-Diameter HDPE Pipes Using Guided Waves and Deep Learning |
| title_full_unstemmed | Diversion Detection in Small-Diameter HDPE Pipes Using Guided Waves and Deep Learning |
| title_short | Diversion Detection in Small-Diameter HDPE Pipes Using Guided Waves and Deep Learning |
| title_sort | diversion detection in small diameter hdpe pipes using guided waves and deep learning |
| topic | high-density polyethylene (HDPE) ultrasonic-guided waves (UGWs) Zadoff–Chu sequence deep neural network (DNN) convolutional neural network (CNN) recurrent neural network (RNN) |
| url | https://www.mdpi.com/1424-8220/22/24/9586 |
| work_keys_str_mv | AT abdullahzayat diversiondetectioninsmalldiameterhdpepipesusingguidedwavesanddeeplearning AT mohanadobeed diversiondetectioninsmalldiameterhdpepipesusingguidedwavesanddeeplearning AT anaschaaban diversiondetectioninsmalldiameterhdpepipesusingguidedwavesanddeeplearning |