Modeling pipe deterioration using soil properties - an application of fuzzy logic expert system

Several factors may contribute to the structural failure of cast/ductile iron water mains, the most important of which is considered to be corrosion. The ANSI/AWWA C105/A21.5?99 10-point scoring (10-P) method is the most common method used to predict soil corrosivity potential, which is based on soil properties. For a given soil sample, each soil property is evaluated for its contribution towards the corrosivity of soil. The 10-P method uses binary logic to classify the soil, either as corrosive or noncorrosive.Fuzzy logic extends the binary logic in this context as it recognizes the real world phenomena in which each property has certain degree of membership between 0 and 1. The main objective of the present research is to develop a fuzzy logic expert system capable of establishing a criterion (such as corrosion rate or breakage rate) for predicting the deterioration of cast/ductile iron water mains using soil properties. The proposed expert system includes a fuzzy model consisting of a series of IF-THEN rules todetermine soil corrosivity potential (CoP) based on soil properties. The fuzzy model contains the data of linguistic variables (database) characterizing various soil properties, and a rule base that constructs relationships among those properties and CoP. Subsequently, the expert system uses a linear regression model to link CoP to the deterioration rate of metallic pipes. A case study on cast iron pipes is examined to illustrate the application of the proposed expert system.Plusieurs facteurs peuvent contribuer \ue0 la d\ue9faillance structurale des conduites d'eau en fonte grise ou ductile, dont on consid\ue8re que la corrosion est le plus important. La m\ue9thode de notation \ue0 dix points (10-P) de la norme ANSI/AWWA C105/A21.5?99 est la m\ue9thode de pr\ue9diction du potentiel de corrosivit\ue9 du sol, qui est fonction des propri\ue9t\ue9s de ce dernier, dont l'utilisation est la plus r\ue9pandue. Pour un \ue9chantillon de sol donn\ue9, on \ue9value la contribution de chaque propri\ue9t\ue9 du sol \ue0 la corrosivit\ue9 de ce dernier. La m\ue9thode 10-P utilise la logique binaire pour classer le sol, soit comme corrosif, soit comme non corrosif. La logique floue prolonge la logique binaire dans ce contexte, puisqu'elle reconna\ueet les ph\ue9nom\ue8nes du monde r\ue9el, dans lesquels chaque propri\ue9t\ue9 pr\ue9sente un certain degr\ue9 d'appartenance, qui se situe entre 0 et 1. Le principal objectif de la pr\ue9sente recherche consiste \ue0 mettre au point un syst\ue8me expert \ue0 logique floue capable d'\ue9tablir un crit\ue8re (tel que la vitesse de corrosion ou le taux de rupture) servant \ue0 pr\ue9dire la d\ue9t\ue9rioration des conduites d'eau en fonte grise ou ductile \ue0 l'aide des propri\ue9t\ue9s du sol. Le syst\ue8me expert propos\ue9 inclut un mod\ue8le flou qui consiste en une s\ue9rie de r\ue8gles du type SI-ALORS et qui sert \ue0 d\ue9terminer le potentiel de corrosivit\ue9 du sol en fonction des propri\ue9t\ue9s de ce dernier. Le mod\ue8le flou contient les donn\ue9es de variables linguistiques (base de donn\ue9es) qui caract\ue9risent diverses propri\ue9t\ue9s du sol, et une base de r\ue8gles qui construit des relations entre ces propri\ue9t\ue9s et le potentiel de corrosivit\ue9. Subs\ue9quemment, le syst\ue8me expert utilise un mod\ue8le de r\ue9gression lin\ue9aire pour lier le potentiel de corrosivit\ue9 \ue0 la vitesse de d\ue9t\ue9rioration des conduites m\ue9talliques. On examine une \ue9tude de cas relative aux conduites en fonte pour illustrer l'utilisation du syst\ue8me expert propos\ue9.Peer reviewed: YesNRC publication: Ye