APPLICATION OF KNOWLEDGE-BASED EXPERT-SYSTEMS FOR RATING HIGHWAY BRIDGES

This paper presents the establishment of a Bridge Rating Expert System (BRES) by using a knowledge-based computer artificial intelligent exp ert system for analysis and rating of existing short span prestressed concrete highway bridges. The rating methods considered were: Inventor y Rating, Operation Rating, Rating Factor Rating and Sufficiency Ratin g. A strength rating is based on the evaluation of existing prestresse d concrete bridges in accordance with the American Association of Stat e Highway Transportation Officials (AASHTO) specifications, and invent ory rating for all bridges according to the Federal Highway Administra tion (FHWA) guide for the Structure Inventory and Appraisal of the Nat ion's Bridges. The parameters considered were bridge type, dead loads, type of vehicle loading, bridge dimensions and cross-section, materia l properties, reinforcement details, and existing physical condition o f the bridge. The results show that, through its runtime rule controll er, user interface and linkage mechanisms, the BRES is a friendly user system for rating highway bridges. In addition, the EXSYSP shell prov ides an effective tool for other possible applications in civil engine ering practice.