Comprehensive Feature Analysis for Sewer Deterioration Modeling

Abstract

Timely maintenance of sewers is essential to preventing reduced functionality and breakdown of the systems. Due to the high costs associated with inspecting a sewer system, substantial research has focused on sewer deterioration modeling and identification of the most useful features. However, there is a lack of consensus in the findings. This study investigates how the feature importance depends on the definition of bad pipes and how the feature importance changes between utilities with similar data bases. A dataset containing 318,457 pipes from 35 utilities with a condition state (CS) ranging from one to four was used. The dataset was cleaned, and a backward step analysis (BSA) was applied to two ways of binarizing the CS. Additionally, a BSA was applied for each utility with ≥100 pipes in CS four. The results showed that a selective definition of bad pipes reduced the performance and changed the order of which features contributed the most. In each case, either year of construction, age, groundwater, year of rehabilitation, or dimension was the most important feature. On average 6.5 features contributed to the utility-specific models. The feature analysis was sensitive to the inspection strategy, the size of the dataset, and interdependency between the features.

Towards a decentralized solution for sewer leakage detection – a review

“…A wide variety of deterioration models has been developed and proposed to predict the deterioration process based on existing data and real-observed sewer conditions. Hansen et al (2021) studied a database containing 318,457 pipes from 35 utilities which are implementing deterioration models and found that the age, groundwater, and pipe shape are the most common deterioration factors used by these models. Based on Kley & Caradot (2013), these models can be categorized into three main non-exclusive groups, i.e., (i) deterministic models, (ii) statistical models, and (iii) artificial intelligence (AI) models.…”

Assessment of Human Stability in Sewer Systems during Dry Weather Conditions

“…The inspection of the collectors is mainly done by closed circuit television video (CCTV) [4], but when the sewer is big enough to allow the access of people, this inspection is done in person [2]. Inspectors can directly observe pipeline problems, perform repairs, define maintenance works, etc.…”

Dramatic voids and how to find them: In-pipe condition assessment of sewer pipes

“…We chose this approach because there is no comprehensive reference in the literature, and it allows us to consider failures that have the most significant impact on the asset users and lives of the residents. Imaging the underground world and understanding its condition using visual inspections and integrating this condition data in the maintenance decisions is a very popular global trend in asset management literature and practice [74,[208][209][210][211]. Despite the efforts to assess conditions of the sewer through these methods, failures caused by sinkholes seem to often catch asset managers by surprise.…”