Liquid retaining structures are more vulnerable to corrosion problem and hence have stringent requirements against serviceability limit state of crack. The design procedures of these structures require significant empirical inputs from specialists. With the recent advent of artificial intelligence technology, a coupled knowledge-based system can handle both the symbolic knowledge processing based on engineering heuristics in the preliminary synthesis stage and the extensive numerical crunching involved in the detailed structural analysis stage.
In this study, a prototype coupled knowledge-based system for the design of liquid retaining structures, LIQSTR, has been developed using the commercial expert system shell VISUAL RULE STUDIO, which acts as an ActiveX Designer under the Microsoft VISUAL BASIC programming environment. The blackboard architecture, which can group all the knowledge together into an integrated system effectively, is employed. By adopting a hybrid knowledge representation approach, production rule system as well as procedural methods under object-oriented programming paradigm are used to express engineering heuristics and standard design knowledge. The basis of design is BS 8007, which is the British Standard on design of concrete structures for retaining aqueous liquid. The present scope of the system covers design of three types of liquid retaining structures, namely, rectangular shape with one compartment, rectangular shape with two compartments and circular shape. Through custom built interactive graphical user interfaces under a user-friendly environment, the user is directed throughout the design process, which includes preliminary design, load specification, model generation, finite element analysis, code compliance checking and member sizing optimization.
The design of typical examples of the design of liquid retaining structure is also illustrated. This system can act as a consultant to offer assistance and advice to novice designers in the design of liquid retaining structures. Advantages of the system include increase in efficiency, improvement, standardization and optimization of design output and automated record keeping. Besides, machine intelligence can be introduced into the knowledge-based system in addition to the knowledge acquired from human experts and the literatures. This prototype model will become the building block for full system implementation.