|
Title: NEURAL NETWORKS FOR RAPID REDUCTION INTERPRETATION OF SPECTRAL ANALYSIS OF SURFACE WAVES RESULTS
Accession Number: 00978567
Record Type: Component
Record URL: Availability: Transportation Research Board Business Office 500 Fifth Street, NW Find a library where document is available Abstract: Nondestructive testing (NDT) of pavements has made substantial progress during the past two decades. Most algorithms currently used to determine the remaining life of pavements rely on stiffness parameters determined from NDT devices. One major area of continual improvement is the reliable extraction of stiffness parameters from nondestructive field data. The spectral analysis of surface waves (SASW) method is one of the more frequently used NDT methods because of its capabilities in characterizing the near-surface layers effectively. In this method, time records obtained with vibration sensors are used to obtain an experimental dispersion curve, which, through an inversion procedure, provides an estimate of the elastic modulus profile of the pavement. The inversion process requires a significant computational effort or frequent operator intervention. To improve the user-friendliness of the inversion process, an algorithm for the rapid reduction of the SASW data was developed. Thickness and modulus of each pavement layer are estimated in real time using artificial neural network models. These models serve a dual purpose: (a) the results from the neural network models can be used to approximate the layer properties of a given pavement section and (b) it can be used as a first approximation to the traditional inversion process. The reduction algorithm appears to be robust and to yield consistent results in almost real time.
Supplemental Notes: This paper appears in Transportation Research Record No. 1868, Soil Mechanics 2004.
Monograph Title: Monograph Accession #: 00978551
Language: English
Corporate Authors: Transportation Research Board 500 Fifth Street, NW Authors: Nazarian, SAbdallah, I NYuan, DPagination: p. 150-155
Publication Date: 2004
Serial: ISBN: 0309094623
Features: Figures
(6)
; References
(13)
; Tables
(2)
TRT Terms: Candidate Terms: Subject Areas: Geotechnology; Highways; I42: Soil Mechanics
Files: TRIS, TRB, ATRI
Created Date: Sep 27 2004 12:00AM
More Articles from this Serial Issue:
|