CONDITION PREDICTION OF SANITARY SEWERAGE PIPELINE SYSTEMS USING MULTINOMIAL LOGISTIC REGRESSION

Abstract

It is important for the sanitary sewerage pipeline system to be in a good condition for providing safe conveyance of the wastewater from households, businesses, and industries to the wastewater treatment plants. Water utilities inspect sewer pipelines to decide which segments of the sanitary sewer pipes need renewal or replacement. This process of inspecting the sewer pipes is described as condition assessment. The objective of this paper is to develop Multinomial Logistic Regression (MLR) to predict the condition rating of sanitary sewerage pipelines using inspection and condition assessment data. MLR model was developed from the City of Dallas's data. The MLR model was built using 80% of randomly selected data and validated using the remaining 20% of data. The significant physical factors influencing sanitary pipes condition rating included diameter, age, pipe material, and length. Soil type was the environmental factor that influenced sanitary sewer pipes condition rating. The accuracy of the performance of the MLR was found to be 75%. This developed model will help the policymakers and sanitary sewer utility managers to predict sanitary sewer pipes condition rating that enables to prioritize the sanitary sewer pipes to be rehabilitated and/or replaced.