SYSTEM THAT LEARNS TO DESIGN CABLE-STAYED BRIDGES

The critical design decisions in bridge design are made at the prelimi nary design stage. They depend on the expertise of the designer, built up from extensive experience. Experience is difficult to acquire, and may be entirely lacking when new technology is introduced. As a resul t, there is little shareable and transferable collective design knowle dge within the profession. This paper explores how preliminary design knowledge may be generated, updated, and used, employing techniques of machine learning from the field of artificial intelligence. A model o f the preliminary design process is first presented as a sequence of f ive tasks and then specialized to the design of cable-stayed bridges. A computer tool serving as a design support system is described, whose design follows the model of the preliminary design process, and a des ign example using the tool is presented. The key property of the syste m is its adaptive nature: it acquires knowledge from information on ex isting bridges as well as from designs generated with the system, ther eby continuously improving its performance. Future enhancements to the tool breadth and depth are offered.