|Application of artificial intelligence in structural reinforcement design
|Structural design -- Data processing
Hong Kong Polytechnic University -- Dissertations
|iii, 47,  leaves : ill. ; 30 cm
|In nowadays competitive world, the ability to increase productivity is seen to be the main edge for a company to survive. In this respect, computerization has been the main forms for productivity increase in almost every trade. In the building industry, computerization of the structural design process started some twenty or thirty years ago and it is still continuing. However, while the first part of the structural design process - structural calculation, has been computerized very successfully, the latter part of the process, structural detailing, has not enjoyed such a success. The difficulty to computerize the structural detailing process can be attributed to its nature of design. Conventional computer programming is good at handling numerical analysis but not the process of design. However, the recent rapid development of Artificial Intelligence (AI) techniques gives new opportunity to computerize processes which are not of numerical nature such as the design process. The main objective of this study is to explore the possibility of using AI, in particular the expert system approach, to enable the computerization of the structural detailing process. In this study, a system is developed for the structural detailing process for reinforced concrete beams which aims to meet the requirements of the British Standard 8110 and the Hong Kong building industry environment. The sources of knowledge for the system are extracted from the BS 8110 and also from the author's own structural detailing experience. The system is developed with the frame-based expert system development tool KAPPA-PC, running in a Windows 95 environment on a Pentium-100 IBM-PC compatible computer. The performance of the system is assessed by comparing the detailing results produced by it with those designed by the author. The performance is quite promising both in the aspects of detailing quality and time saving, though further improvement and development are required to enhance its capability in dealing with non-typical beam details and to promote its design standard up to an expert level. Since the performance of the system depends very much on its ability to classify the bending moment and shearing force profiles into different categories for beams, one possible improvement area identified in the study for future development is the incorporation of a neural network module into the system to provide an efficient tool to recognize the bending moment and shearing force profiles.
|All rights reserved
Files in This Item:
|For All Users (off-campus access for PolyU Staff & Students only)
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item: