Digital Twin for Pipeline Leak Monitoring

We demonstrate how a visual digital twin system is used to implement a digital twin for pipeline monitoring. A visual digital twin allows for ingestion of data for calibration and creation of models which enable a digital replica of a real-world physical system for decision support and improving situational awareness. A laboratory experimental pipeline system is used to generate data to drive modelling capabilities in this system. We show how machine learning operations (MLOps) principles are applied in the context of digital twins, forming a sub-study area known as Digital Twin ML Ops (DT MLOps). The intended purpose of the system is to both train operators of the leak detection system in its use and provide high situational awareness and operational readiness to users. We demonstrate how multiple sources of monitoring data from an experimental pipeline setup, as well as simulation can be combined in a visual digital twin system and used for pipeline leak detection and leak plume and flow visual prediction. We show how leak detection and visual leak prediction are visualized in the context of a pipeline twin along with confidence and uncertainty and other explainable elements from machine learning models. We demonstrate how models are tracked using the DT MLOps sub system. The overall system demonstrates a novel combination of real experimental data driving models for both leak detection and the prediction of the associated leak plume and pipeline flow visual assessment imagery. This demonstrates a system which can detect leaks and their locations and also provide operators with assessment of the leak. The system provides provenance through its DT MLOps capabilities. This presented virtual pipeline and leak model, which integrates AI with experimental validation, is not widely available in industry.