Digitalization in the oil and gas industry has led to the formation of digital twins, which are software representations of assets that are used to understand, predict, and optimize performance. Digital twins bring closer the physical and virtual world as data is transmitted seamlessly between real time sensors, databases and models. The strength of the digital twin concept is the interconnectivity of data and models. Any model can use any combination of inputs (e.g. operator owned data sets and sensors, third-party databases such as soil composition or weather data or even results from other models such as flow assurance modeling, threat modeling or risk modeling). Consequently, the results of one model may become the input of another. This strength is also a weakness, as uncertain (or missing) data will lead to a great source of uncertainty, and may lead to incorrect risk results. Worst case scenarios have been used to resolve this issue, however worst case scenarios may lead to undesired outcomes such as a lack of differentiation in risk results. This paper presents a new concept: probabilistic digital twins for pipelines. Probabilistic digital twins use probability density functions instead of deterministic values. Therefore, they do not lose uncertainty as results pass from one model to another, thus providing greater confidence in the results.

First, this publication compares deterministic digital twins versus probabilistic digital twins. Second, data from West Pipeline Company (CNPC) is used to demonstrate how probabilistic digital twins can be implemented in two different scenarios. The methodology is used to predict the evolution of pipeline integrity for the 30 years following installation. Multiple threat models interact with CNPC’s probabilistic data to predict corrosion rates, flaw depth and failure rate. Finally, this publication shows how this methodology could be used for real time risk assessments and real time learning.


Probabilistic Digital Twin for Risk Assessment Transmission Pipelines

Division / Sponsors: 
Pipeline Systems Division

Paper Proceedings: https://asmedigitalcollection.asme.org/IPC/IPC2020/volume/84447

IPC2020 - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.