During the last decades, the problem of detecting leaks in pipes with the help of software has been much discussed. Timely leak detection prevents water loss and helps prevent economic and environmental catastrophes. It is evident that companies choose to have good leak control policies, detection systems in Control Centers and teams of operators who locate leaks directly on the ground. However, these strategies do not allow for real-time leak detection. This project implements techniques based on machine learning that, through the introduction of process data from the studied pipes, systematically determine the presence of leaks. With this project, it is hoped to improve the speed and accuracy of leak detection, using only process data, system knowledge and intelligent software.