INTELLIGENT MODEL MANAGEMENT AND VISUALIZATION FOR SMART OILFIELDS

Simulation models that represent a variety of what‑if scenarios are commonly used as an aid to decision making for oilfield development and operations. Engineers create multitude models to explore a design space that represents uncertainty of information and alternate operational strategies. As the composition of asset teams changes over the lifetime of asseta and new modeling requirements emerge, it becomes important for asset teams to be able to quickly "mine" the legacy model set to understand the distribution of the models in the design space, and also to know if a particular scenario was already modeled in the past or if a new model needs to be created. Further, it is important for asset teams to understand the impact of changes between deferent models for the best operational strategy to be chosen. We describe a technique to analyze arbitrarily large set of simulation models, identify similarities and differences between model parameters, and automatically cluster the models based on similarity in an n‑dimensional design space. The objective is twofold: to create a smart browse, search and visualization capability over a legacy model catalog in a non legacy manner and to try to reverse engineer the original intent of the modeler by detecting which models can be represented as variations of same underlying templates. We demonstrate the application of our algorithm to a set of IPM models. However, our use of a standard, non‑proprietary network model abstraction as an intermediate representation means that our analysis technique can be applied to asset models created using a variety of modeling and simulation tools. The broader significance of this work is in the context of knowledge management for smart oilfields, specifically focused on extracting meaningful information from legacy simulation models, and making this information available and useful to the asset team.