Knowledge‐Based System for Flexible Pavement Structural Evaluation

Abstract

Pavement deflection data are often used to evaluate pavement's structural conditions nondestructively. Pavement layers are characterized by their elastic moduli estimated from surface deflections through backcalculations. Results of various algorithmic backcalculation methods currently available are often dependent upon individual analyst's experience and judgments in supplying input parameters and they often do not agree with each other. Much of the empirical knowledge accumulated through decades of pavement research and practice has yet to be formalized to assist analytical backcalculations. To organize the various knowledge utilized by a human analyst to perform evaluation and to make nondestructive evaluation more accessible, a knowledge‐based system, Pavement Structural Evaluation System (PASELS), is developed. This rule‐based system can help provide rational estimation of pavement layer moduli and is particularly useful when algorithmic backcalculation methods do not give reasonable results. Although it still needs to be supervised by an experienced analyst and its performance is limited by the knowledge available in its knowledge base, such automated deflection analysis systems could greatly improve the efficiency of interpreting nondestructive test results.