A fuzzy expert system for design performance prediction and evaluation

This paper describes a fuzzy expert system for design project performance e valuation and prediction. It presents a comprehensive framework of factors that impact design performance and factors used to measure performance. A n ew approach to generating membership functions based on objective data is p resented. This approach provides for membership functions that are widely a pplicable in a given context and can be calibrated to suit different contex ts. A method of generating expert rules to relate factors impacting design performance is presented. A survey was conducted to collect data to develop and test the proposed methods. These methods were used in developing the f uzzy expert system. Based on validation of the system, the fuzzy expert sys tem provides accurate linguistic predictions of design performance paramete rs. The methods presented in this paper are useful and realistic in modelin g design performance and in capturing the inherent subjectivity involved.