|
|
|
Title: NEURAL NETWORK INTERPRETATION OF ULTRASONIC RESPONSE FOR CONCRETE CONDITION ASSESSMENT
Accession Number: 00727339
Record Type: Component
Record URL: Availability: Find a library where document is available Abstract: Ultrasonic testing of concrete structures using the pitch-catch method is an effective technique for testing concrete structures that cannot be accessed on two opposing surfaces. However, the ultrasonic signals so measured are extremely noisy and contain a complicated pattern of multiple frequency-coupled reflections that makes interpretation a difficult task. In this investigation, a neural network modeling approach is used to classify ultrasonically tested concrete specimens into one of two classes: defective or nondefective. Different types of neural nets are used, and their performance is evaluated. It was found that correct classification of the individual ultrasonic signals could be achieved with an accuracy of 75% for the test set and 95% for the training set. These recognition rates lead to the correct classification of all the individual test specimens. The study shows that although some neural net architectures may show high performance using a particular training data set, their results might not be consistent. In this paper, the consistency of the network performance was tested by shuffling the training and testing data sets.
Supplemental Notes: This paper appears in Transportation Research Record No. 1532, Advancements in Concrete Materials Technology.
Language: English
Corporate Authors: Transportation Research Board 500 Fifth Street, NW Authors: Shoukry, S NMartinelli, D RPagination: p. 80-86
Publication Date: 1996
Serial: ISBN: 0309059046
Features: Figures
(7)
; References
(12)
; Tables
(4)
TRT Terms: Uncontrolled Terms: Subject Areas: Bridges and other structures; Highways; Materials; I20: Design and Planning of Transport Infrastructure; I32: Concrete
Files: TRIS, TRB
Created Date: Oct 22 1996 12:00AM
More Articles from this Serial Issue:
|
