This research focuses on the development and testing of a laser-based multimode optic fiber sensor equipped with machine learning (ML) software that allows for water supply monitoring, including leak detection and quantification, evaluation of transient flows, and alerts for any. This research focuses on the development and testing of a laser-based multimode optic fiber sensor equipped with machine learning (ML) software that allows for water supply monitoring, including leak detection and quantification, evaluation of transient flows, and alerts for any. DNV is a leader in verifying distributed fibre-optic sensing (DFOS) systems for pipeline leak detection. As an independent third party, it can support in advising and verifying these technologies according to international standards and guidelines. By using optical fibers as sensitive sensors, it becomes possible to continuously watch over long stretches of infrastructure for any sign of water ingress. The evidence from field trials and real-world leaks is. DFOS-based pipeline leak detection and location software (DFOS-PLDS) is possibly the most important technological development in pipeline leak detection in recent years. Despite being a relatively new technology, DFOS-PLDS is already applied to an extensive number of pipelines covering a wide. In this study, we explore the development and testing of a multimode optic-fiber-based pipe monitoring and leakage detector based on statistical and machine learning analyses of speckle patterns captured from the fiber's outlet by a defocused camera. The sensor was placed inside or over a PVC pipe.
