Factors Influencing the Condition of Sewer Pipes: State-of-the-Art Review

Wastewater infrastructure systems deteriorate over time due to a combination of physical and chemical factors. Failure of these critical structures can cause major social, environmental, and economic impacts. To avoid such problems, several researchers attempted to develop infrastructure condition assessment methodologies to maintain sewer pipe networks at desired condition. Sewer condition prediction models are developed to provide a framework to forecast future conditions of pipes and to schedule inspection frequencies. Yet, utility managers and other authorities are often challenged with identifying the optimal timeline for inspection of sewer pipelines. Frequent inspection of sewer networks is not cost-effective due to limited time, expensive assessment technologies, and large inventories of pipes. Therefore, the objective of this state-of-the-art review is to study progress over the years in developing condition prediction models and investigating the potential factors affecting the condition of sewer pipes. Published papers for prediction models from 2001 through 2019 were identified and analyzed. Also, this study conducts a comparative analysis of the most common condition prediction models such as artificial intelligence (AI) and statistical models. The literature review suggests that, out of 20 independent variables studied, pipe age, diameter, and length are the most significant contributors to the deterioration of sewer systems. In addition, it can be concluded that AI models reduce uncertainty in current condition prediction models. Furthermore, the most appropriate prediction models for development are those that are capable of accurately finding nonlinear and complex relationships among variables. This study recommends the use of more environmental and operational factors—e.g., soil type, bedding material, flow rate, and soil corrosivity—and advanced data mining techniques to develop comprehensive and accurate condition prediction models. The findings of this study are intended to guide practitioners in developing customized condition assessment models for their agencies that can save millions of dollars through optimized inspection timelines and fewer incidents.