This work kick-started AI (artificial intelligence) for pipe management among Swedish water utilities.
Focus was on proactive pipe network management and discussions about risk analysis in the field. A previously developed ANN model was used to estimate probability of leakage in water pipes. The model had been trained on leaks that have occurred over a ten-year period, and a comparison with leaks reported after the studied period shows that the ANN model succeeded in identifying groups of pipes with a higher leakage frequency. By combining the ANN model with a model for impact assessment, the most prioritised pipes, from a risk perspective, can be identified.