Premium
Bridge Condition Rating Using an Eigenvector of Priority Settings
Author(s) -
Melhem Hani G.,
Aturaliya Senaka
Publication year - 1996
Publication title -
computer‐aided civil and infrastructure engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.773
H-Index - 82
eISSN - 1467-8667
pISSN - 1093-9687
DOI - 10.1111/j.1467-8667.1996.tb00354.x
Subject(s) - bridge (graph theory) , fuzzy logic , component (thermodynamics) , pairwise comparison , computer science , data mining , artificial intelligence , machine learning , medicine , physics , thermodynamics
To circumvent possible inconsistencies in inspection and rating of highway bridges, two models based on fuzzy logic have been proposed in the literature. These models combine the condition rating of the various elements of the main bridge components to evaluate the overall condition of these components. The first method uses fuzzy weighted average, and the second uses the fuzzy computational technique known as resolution identity of fuzzy sets. A third model proposed by the authors and implemented in a knowledge‐based expert system environment is presented in detail. The fuzzy inference model is based on a priority setting obtained through the solution of an eigenvector problem involving a pairwise comparison matrix of importance. This method and the associated solution technique were developed originally for general use in multiattribute decision making but were never used in a bridge engineering application. The proposed model is superior to other models for bridge rating previously developed because it provides priority settings of the individual elements of a bridge component in addition to the final rating of that component. The computer program was tested using actual bridge inspection data.