The use of neural networks in ultrasonic flaw detection

F. W. Margrave, K. Rigas, David A. Bradley, P. Barrowcliffe

Research output: Contribution to journalArticle

59 Citations (Scopus)

Abstract

Ultrasound based inspection techniques are used extensively throughout industry for detection of flaws in engineering materials. The range and variety of imperfections encountered is large and critical assessment of location, size, orientation and type is often difficult. In addition, increasing quality requirements of new standards and codes of practice relating to fitness for purpose are placing higher demands on operators. The use of neural networks to support the operator in the initial evaluation and classification process offers advantages in terms of improvement in measurement accuracy and reduction in operator work load. This paper presents an evaluation of various types and configurations of neural networks developed for the purpose of assisting in accurate flaw detection in steel plates. The research presented was conducted using a wide range of samples including non-defective plates, side drilled holes, inclusions and porosity together with smooth and rough cracks. The results obtained indicate that significant benefits may be obtained from the techniques demonstrated.
Original languageEnglish
Pages (from-to)143-154
Number of pages12
JournalMeasurement: Journal of the International Measurement Confederation
Volume25
Issue number2
DOIs
Publication statusPublished - Mar 1999

Fingerprint

ultrasonic flaw detection
Ultrasonics
Neural Networks
Neural networks
operators
Defects
Operator
nondestructive tests
fitness
evaluation
defects
Evaluation
Imperfections
Ultrasound
Porosity
Range of data
Fitness
Rough
Workload
Inspection

Cite this

Margrave, F. W. ; Rigas, K. ; Bradley, David A. ; Barrowcliffe, P. / The use of neural networks in ultrasonic flaw detection. In: Measurement: Journal of the International Measurement Confederation. 1999 ; Vol. 25, No. 2. pp. 143-154.
@article{7d826bfc6b87495fb70a8dc76282e1c0,
title = "The use of neural networks in ultrasonic flaw detection",
abstract = "Ultrasound based inspection techniques are used extensively throughout industry for detection of flaws in engineering materials. The range and variety of imperfections encountered is large and critical assessment of location, size, orientation and type is often difficult. In addition, increasing quality requirements of new standards and codes of practice relating to fitness for purpose are placing higher demands on operators. The use of neural networks to support the operator in the initial evaluation and classification process offers advantages in terms of improvement in measurement accuracy and reduction in operator work load. This paper presents an evaluation of various types and configurations of neural networks developed for the purpose of assisting in accurate flaw detection in steel plates. The research presented was conducted using a wide range of samples including non-defective plates, side drilled holes, inclusions and porosity together with smooth and rough cracks. The results obtained indicate that significant benefits may be obtained from the techniques demonstrated.",
author = "Margrave, {F. W.} and K. Rigas and Bradley, {David A.} and P. Barrowcliffe",
year = "1999",
month = "3",
doi = "10.1016/S0263-2241(98)00075-X",
language = "English",
volume = "25",
pages = "143--154",
journal = "Measurement",
issn = "1536-6367",
publisher = "Elsevier",
number = "2",

}

The use of neural networks in ultrasonic flaw detection. / Margrave, F. W.; Rigas, K.; Bradley, David A.; Barrowcliffe, P.

In: Measurement: Journal of the International Measurement Confederation, Vol. 25, No. 2, 03.1999, p. 143-154.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The use of neural networks in ultrasonic flaw detection

AU - Margrave, F. W.

AU - Rigas, K.

AU - Bradley, David A.

AU - Barrowcliffe, P.

PY - 1999/3

Y1 - 1999/3

N2 - Ultrasound based inspection techniques are used extensively throughout industry for detection of flaws in engineering materials. The range and variety of imperfections encountered is large and critical assessment of location, size, orientation and type is often difficult. In addition, increasing quality requirements of new standards and codes of practice relating to fitness for purpose are placing higher demands on operators. The use of neural networks to support the operator in the initial evaluation and classification process offers advantages in terms of improvement in measurement accuracy and reduction in operator work load. This paper presents an evaluation of various types and configurations of neural networks developed for the purpose of assisting in accurate flaw detection in steel plates. The research presented was conducted using a wide range of samples including non-defective plates, side drilled holes, inclusions and porosity together with smooth and rough cracks. The results obtained indicate that significant benefits may be obtained from the techniques demonstrated.

AB - Ultrasound based inspection techniques are used extensively throughout industry for detection of flaws in engineering materials. The range and variety of imperfections encountered is large and critical assessment of location, size, orientation and type is often difficult. In addition, increasing quality requirements of new standards and codes of practice relating to fitness for purpose are placing higher demands on operators. The use of neural networks to support the operator in the initial evaluation and classification process offers advantages in terms of improvement in measurement accuracy and reduction in operator work load. This paper presents an evaluation of various types and configurations of neural networks developed for the purpose of assisting in accurate flaw detection in steel plates. The research presented was conducted using a wide range of samples including non-defective plates, side drilled holes, inclusions and porosity together with smooth and rough cracks. The results obtained indicate that significant benefits may be obtained from the techniques demonstrated.

U2 - 10.1016/S0263-2241(98)00075-X

DO - 10.1016/S0263-2241(98)00075-X

M3 - Article

VL - 25

SP - 143

EP - 154

JO - Measurement

JF - Measurement

SN - 1536-6367

IS - 2

ER -