Ultrasonic signal processing methods for detection of defects in concrete pipes

Shivprakash Iyer, Sunil K. Sinha, Bernhard R. Tittmann, Michael K. Pedrick

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Automated inspection systems are important for maintenance and rehabilitation of pipeline systems in North America given their budgetary constraints, demand on providing quality service, and the need for preserving their pipeline infrastructure. Automated ultrasonic signal classification systems are finding increasing use in many applications for the recognition of large volumes of inspection signals. This paper presents an automated signal classification system to process A-scan signals acquired with the Ultrasound transducer from a pipe region of interest (ROI). The overall approach consists of three major steps, preprocessing of the signal, multi-resolution analysis for feature extraction, and neural network classification. Finally, a post processing scheme to interpret the classifier outputs and classify the ROI into an appropriate defect class taking into consideration some a priori knowledge of the problem is developed. The proposed post processing scheme is composed of several steps that combine the statistics from the classification matrix as well as a two-step procedure based on k-nearest neighbor and non-linear regression. The feature extraction, classification and post processing schemes proposed in this paper provide a working proof-of-concept for developing this inspection system into an automated field applicable tool.

Original languageEnglish (US)
Pages (from-to)135-148
Number of pages14
JournalAutomation in Construction
Volume22
DOIs
StatePublished - Mar 1 2012

Fingerprint

Concrete pipe
Signal processing
Ultrasonics
Defects
Inspection
Feature extraction
Processing
Pipelines
Multiresolution analysis
Patient rehabilitation
Transducers
Classifiers
Pipe
Statistics
Neural networks

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Civil and Structural Engineering
  • Building and Construction

Cite this

Iyer, Shivprakash ; Sinha, Sunil K. ; Tittmann, Bernhard R. ; Pedrick, Michael K. / Ultrasonic signal processing methods for detection of defects in concrete pipes. In: Automation in Construction. 2012 ; Vol. 22. pp. 135-148.
@article{6b63c826f01547858c52889399562a2f,
title = "Ultrasonic signal processing methods for detection of defects in concrete pipes",
abstract = "Automated inspection systems are important for maintenance and rehabilitation of pipeline systems in North America given their budgetary constraints, demand on providing quality service, and the need for preserving their pipeline infrastructure. Automated ultrasonic signal classification systems are finding increasing use in many applications for the recognition of large volumes of inspection signals. This paper presents an automated signal classification system to process A-scan signals acquired with the Ultrasound transducer from a pipe region of interest (ROI). The overall approach consists of three major steps, preprocessing of the signal, multi-resolution analysis for feature extraction, and neural network classification. Finally, a post processing scheme to interpret the classifier outputs and classify the ROI into an appropriate defect class taking into consideration some a priori knowledge of the problem is developed. The proposed post processing scheme is composed of several steps that combine the statistics from the classification matrix as well as a two-step procedure based on k-nearest neighbor and non-linear regression. The feature extraction, classification and post processing schemes proposed in this paper provide a working proof-of-concept for developing this inspection system into an automated field applicable tool.",
author = "Shivprakash Iyer and Sinha, {Sunil K.} and Tittmann, {Bernhard R.} and Pedrick, {Michael K.}",
year = "2012",
month = "3",
day = "1",
doi = "10.1016/j.autcon.2011.06.012",
language = "English (US)",
volume = "22",
pages = "135--148",
journal = "Automation in Construction",
issn = "0926-5805",
publisher = "Elsevier",

}

Ultrasonic signal processing methods for detection of defects in concrete pipes. / Iyer, Shivprakash; Sinha, Sunil K.; Tittmann, Bernhard R.; Pedrick, Michael K.

In: Automation in Construction, Vol. 22, 01.03.2012, p. 135-148.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Ultrasonic signal processing methods for detection of defects in concrete pipes

AU - Iyer, Shivprakash

AU - Sinha, Sunil K.

AU - Tittmann, Bernhard R.

AU - Pedrick, Michael K.

PY - 2012/3/1

Y1 - 2012/3/1

N2 - Automated inspection systems are important for maintenance and rehabilitation of pipeline systems in North America given their budgetary constraints, demand on providing quality service, and the need for preserving their pipeline infrastructure. Automated ultrasonic signal classification systems are finding increasing use in many applications for the recognition of large volumes of inspection signals. This paper presents an automated signal classification system to process A-scan signals acquired with the Ultrasound transducer from a pipe region of interest (ROI). The overall approach consists of three major steps, preprocessing of the signal, multi-resolution analysis for feature extraction, and neural network classification. Finally, a post processing scheme to interpret the classifier outputs and classify the ROI into an appropriate defect class taking into consideration some a priori knowledge of the problem is developed. The proposed post processing scheme is composed of several steps that combine the statistics from the classification matrix as well as a two-step procedure based on k-nearest neighbor and non-linear regression. The feature extraction, classification and post processing schemes proposed in this paper provide a working proof-of-concept for developing this inspection system into an automated field applicable tool.

AB - Automated inspection systems are important for maintenance and rehabilitation of pipeline systems in North America given their budgetary constraints, demand on providing quality service, and the need for preserving their pipeline infrastructure. Automated ultrasonic signal classification systems are finding increasing use in many applications for the recognition of large volumes of inspection signals. This paper presents an automated signal classification system to process A-scan signals acquired with the Ultrasound transducer from a pipe region of interest (ROI). The overall approach consists of three major steps, preprocessing of the signal, multi-resolution analysis for feature extraction, and neural network classification. Finally, a post processing scheme to interpret the classifier outputs and classify the ROI into an appropriate defect class taking into consideration some a priori knowledge of the problem is developed. The proposed post processing scheme is composed of several steps that combine the statistics from the classification matrix as well as a two-step procedure based on k-nearest neighbor and non-linear regression. The feature extraction, classification and post processing schemes proposed in this paper provide a working proof-of-concept for developing this inspection system into an automated field applicable tool.

UR - http://www.scopus.com/inward/record.url?scp=84857373117&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857373117&partnerID=8YFLogxK

U2 - 10.1016/j.autcon.2011.06.012

DO - 10.1016/j.autcon.2011.06.012

M3 - Article

AN - SCOPUS:84857373117

VL - 22

SP - 135

EP - 148

JO - Automation in Construction

JF - Automation in Construction

SN - 0926-5805

ER -