Assessment of the suitability of degradation models for the planning of CCTV inspections of sewer pipes

TL;DR

This paper evaluates different degradation models for sewer pipe inspections, emphasizing accuracy, long-term prediction, and explainability to improve maintenance planning.

Contribution

It introduces a methodology to assess degradation models based on accuracy, long-term prediction, and explainability, guiding better inspection planning.

Findings

Ensemble models have the highest accuracy but lack long-term degradation inference.

Logistic Regression provides a good balance with explainability and consistent degradation curves.

Model-based planning outperforms current inspection strategies in efficiency.

Abstract

The degradation of sewer pipes poses significant economical, environmental and health concerns. The maintenance of such assets requires structured plans to perform inspections, which are more efficient when structural and environmental features are considered along with the results of previous inspection reports. The development of such plans requires degradation models that can be based on statistical and machine learning methods. This work proposes a methodology to assess their suitability to plan inspections considering three dimensions: accuracy metrics, ability to produce long-term degradation curves and explainability. Results suggest that although ensemble models yield the highest accuracy, they are unable to infer the long-term degradation of the pipes, whereas the Logistic Regression offers a slightly less accurate model that is able to produce consistent degradation curves with a high explainability. A use case is presented to demonstrate this methodology and the efficiency of model-based planning compared to the current inspection plan.