Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/85877
Title: Knowledge-based understanding and interpretation of construction engineering drawings
Authors: Cao, Yang
Degree: Ph.D.
Issue Date: 2004
Abstract: In the construction industry, many aspects from structural analysis to drawing production have already been computerized, except quantity surveying which includes the measurement of steel reinforcement used in reinforced concrete, still involves large amount of manual processes. Taking off is a very time consuming process. For example, at the tender preparation stage, it normally takes 4 to 5 man-months of an experienced Quantity Surveyor to complete the measurement work of a reasonable size, high-rise construction project. In order to solve this problem, this thesis presents a computer-aided quantity survey system, named as VHSTATION, to automatically recognize and interpret CAD structural engineering drawings, and to take off the amount of steel reinforcement indicated in the drawings. The methodologies integrated in the VHSTATION system include methods for automatic version control to guarantee the most update version to be analyzed; weighting symbols by the statistics of similar instances in candidate drawings under different recognition thresholds in order to adjust symbol recognition order; detecting walls in an architectural plan based on door symbol recognition; automatically extracting geometric features of architectural objects and converting the features into recognition rules, and utilizing Virtual Reality (VR) enabled 3D reconstruction and collision detection techniques to automatically identify and minimize design errors. The integration of these methods not only makes a useful contribution to the task of developing intelligent computer systems to automate the task of quantity surveying, but also provides interesting insight into the research domain of engineering drawings recognition.
Subjects: Hong Kong Polytechnic University -- Dissertations
Computer-aided design
Structural design -- Data processing
Engineering drawings -- Data processing
Pages: xii, 155 leaves : ill. ; 30 cm
Appears in Collections:Thesis

Show full item record

Page views

9
Citations as of May 15, 2022

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.