Modelling sewer failure by evolutionary computing

The sewer system is a service that is expected to function without interruptions. Contin-uous assessment, maintenance and rehabilitation are the key to maintain a required level of service at an acceptable cost. An appropriate and cost effective prioritisation scheme for periodical surveys could be built based on failure data collected by sewerage compa-nies over time. Such a scheme could be achieved using data-driven modelling techniques jointly with engineering knowledge of the failure mechanisms. This paper presents a descriptive analysis performed on a real database containing collapse and blockage incident records for a large sewer system in the United Kingdom. Starting from a sta-tistical study of both failure types, the most important variables are identified and a classification scheme is suggested. Then, using a hybrid modelling technique, Evolu-tionary Polynomial Regression, two different formulas for blockage events and collapse failures are obtained and their engineering interpretation is offered.