A FRAMEWORK FOR DEVELOPING AN EXPERT ANALYSIS AND FORECASTING SYSTEM FOR CONSTRUCTION PROJECTS

Analyzing construction project performance is a diagnostic process, an d forecasting project performance is a cognitive process. Both process es require the exercise of expert judgment and intelligence. Artificia l Intelligence programming techniques such as expert systems and neura l networks provide assistance to construction project managing personn el in capturing construction knowledge needed for analyzing and foreca sting construction projects. This paper describes the development of a framework titled PAFEX (Performance Analysis and Forecasting Expert S ystem). The framework has two main modules. The first module is a diag nostic expert system that has the objective of analyzing construction project performance and adopts causal diagnostic reasoning as a strate gy and object-oriented programming technology as a knowledge represent ation scheme. The second module has the objective of forecasting the c onstruction performance and applies artificial neural networks as a mo deling strategy. The advantages and limitations of these two modeling processes are discussed. Issues regarding integrating the proposed app roach with existing project management systems are also discussed. (C) 1998 Published by Elsevier Science Ltd. All rights reserved.