The conceptual phase of structural design involves selecting preliminary materials, selecting the overall structural form of the building, producing a rough dimensional layout, and considering technological possibilities. Decisions are made on the basis of such information as height of the building, building use, typical live load, wind velocity, earthquake loading, design fundamental period, design acceleration, maximum lateral deflection, spans, story height, and other client requirements. This design process is an information processing activity. More detailed information about the task itself; about the constraints, about possible solutions principles, and about known solutions for similar problems is extremely useful in the process of defining the problem and finding a solution to the design problem. This paper presents the M-RAM (Multi-Reasoning Artificial Mind) model that aim to assist engineers in this conceptual phase of the structural design of tall buildings by providing him/her with adapted past design solutions with the help of a distributed multi-reasoning mechanism. The M-RAM objective is to provide the adapted past design solutions in an organized and reliable way creating a support system to enhance creativity, engineering knowledge and experience of designers. To test the feasibility of the proposed model a prototype of a distributed artificial intelligence system was developed where the Internet was used as a communication backbone among the different systems that implemented the reasoning mechanisms employed. Each different reasoning mechanism was considered as an autonomous module acting as an intelligent agent supporting the design process. To ensure a coherent outcome a manager program was developed to integrate the partial solutions provided by the different reasoning mechanisms.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £66 +P&P)