|
|
|
Title: CONSTRUCTION CONTRACT QUALITY WARRANTIES: HYBRID QUALITY ASSESSMENT MODEL
Accession Number: 00968534
Record Type: Component
Record URL: Availability: Transportation Research Board Business Office 500 Fifth Street, NW Find a library where document is available Abstract: The term "quality" is defined as the conformance to predetermined requirements or specifications. These requirements may be simple or complex. They may be set in terms of the end result required or as a detailed description of how work should be executed. Recently, there has been increasing interest in quality assurance in the construction industry. Most current techniques used in infrastructure assessment and quality inspection rely merely on subjective criteria. Such inaccurate or subjective assessment techniques have been identified as critical obstacles to effective infrastructure management. An overview of contract quality warranties for steel bridge coatings is presented as a practical example, and a hybrid assessment model that can be used to quantitatively measure quality attributes is proposed. The hybrid model combines image processing and neural networks for defect (specifically, rust) recognition and measurement and uses statistical analysis for quality acceptance or rejection on the basis of the contract warranty clauses. The hybrid model incorporates human experience through the training stage to benefit from experts' knowledge and to correct for other external factors.
Supplemental Notes: This paper appears in Transportation Research Record No. 1861, Construction 2003.
Language: English
Corporate Authors: Transportation Research Board 500 Fifth Street, NW Authors: AbdelRazig, YCHANG, L-MPagination: p. 60-70
Publication Date: 2003
Serial: ISBN: 0309085985
Features: Figures
(8)
; References
(16)
; Tables
(1)
TRT Terms: Subject Areas: Administration and Management; Bridges and other structures; Construction; Data and Information Technology; Highways; I50: Construction and Supervision of Construction
Files: TRIS, TRB, ATRI
Created Date: Jan 9 2004 12:00AM
More Articles from this Serial Issue:
|
