Assessment of the suitability of degradation models for the planning of CCTV inspections of sewer pipes
This work addresses maintenance planning for sewer infrastructure, which is an incremental improvement by comparing model suitability for inspection efficiency.
The study tackled the problem of planning CCTV inspections for sewer pipe maintenance by evaluating degradation models based on accuracy, long-term degradation curve prediction, and explainability. Results showed that ensemble models had the highest accuracy but could not infer long-term degradation, while Logistic Regression offered slightly lower accuracy but produced consistent degradation curves with high explainability.
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.