PMID- 36559955
OWN - NLM
STAT- MEDLINE
DCOM- 20221226
LR  - 20221227
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 22
IP  - 24
DP  - 2022 Dec 7
TI  - Diversion Detection in Small-Diameter HDPE Pipes Using Guided Waves and Deep 
      Learning.
LID - 10.3390/s22249586 [doi]
LID - 9586
AB  - 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 90.3% (when one sensor is 
      used) and 99.6% (when two sensors are used) on 34 inch pipes. The technique can 
      be readily generalized for pipes of different diameters and materials.
FAU - Zayat, Abdullah
AU  - Zayat A
AD  - School of Engineering, University of British Columbia, 1137 Alumni Ave, Kelowna, 
      BC V1V 1V7, Canada.
FAU - Obeed, Mohanad
AU  - Obeed M
AUID- ORCID: 0000-0001-6774-255X
AD  - School of Engineering, University of British Columbia, 1137 Alumni Ave, Kelowna, 
      BC V1V 1V7, Canada.
FAU - Chaaban, Anas
AU  - Chaaban A
AD  - School of Engineering, University of British Columbia, 1137 Alumni Ave, Kelowna, 
      BC V1V 1V7, Canada.
LA  - eng
PT  - Journal Article
DEP - 20221207
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
RN  - 9002-88-4 (Polyethylene)
RN  - 0 (Biological Products)
SB  - IM
MH  - *Deep Learning
MH  - Polyethylene
MH  - *Biological Products
MH  - Culture
MH  - Neural Networks, Computer
PMC - PMC9784724
OTO - NOTNLM
OT  - Zadoff-Chu sequence
OT  - convolutional neural network (CNN)
OT  - deep neural network (DNN)
OT  - high-density polyethylene (HDPE)
OT  - long-short term memory (LSTM)
OT  - piezoelectric
OT  - recurrent neural network (RNN)
OT  - structural health monitoring (SHM)
OT  - ultrasonic-guided waves (UGWs)
COIS- The authors declare no conflict of interest.
EDAT- 2022/12/24 06:00
MHDA- 2022/12/27 06:00
PMCR- 2022/12/07
CRDT- 2022/12/23 02:01
PHST- 2022/10/28 00:00 [received]
PHST- 2022/11/30 00:00 [revised]
PHST- 2022/12/04 00:00 [accepted]
PHST- 2022/12/23 02:01 [entrez]
PHST- 2022/12/24 06:00 [pubmed]
PHST- 2022/12/27 06:00 [medline]
PHST- 2022/12/07 00:00 [pmc-release]
AID - s22249586 [pii]
AID - sensors-22-09586 [pii]
AID - 10.3390/s22249586 [doi]
PST - epublish
SO  - Sensors (Basel). 2022 Dec 7;22(24):9586. doi: 10.3390/s22249586.