Digital Twins and Augmented Observability: An Architecture Model for Experimental Oil & Gas Separator Vessel Digitization
Name: RAPHAEL ALMEIDA GUIMARÃES DOS SANTOS
Publication date: 22/07/2021
Advisor:
Name |
Role |
|---|---|
| ARNALDO GOMES LEAL JÚNIOR | Co-advisor * |
| MOISÉS RENATO NUNES RIBEIRO | Advisor * |
Examining board:
| Name |
Role |
|---|---|
| ARNALDO GOMES LEAL JÚNIOR | Co advisor * |
| CELSO JOSE MUNARO | Internal Examiner * |
| MOISÉS RENATO NUNES RIBEIRO | Advisor * |
Summary: Digital industrial transformation has leveraged the concept of Digital Twins (DTs) and Cyber-Physical Systems (CPSs) in the Industry 4.0 context. While CPS are multididimensional and complex systems that integrate computation, communication and control of dynamic physical systems, DTs are related to high-fidelity models of physical elements in a virtual space. Its goal is to simulate the physical world and provide near real-time feedbacks to "what if" scenarios in order to assist operational decision-making. Separator vessels are key elements in water-oil separation process in oil & gas industry. Basically,
they are pressurized vessels that can be subjected to structural failures like fatigue if not adequately monitored, maintained and operated. Conventional sensing alone cannot match the diverse needs of DTs, and computer vision and machine learning come in hand to provide a modern way to estimate multiple parameters. Thus, this work aims at proposing an architectural model to an experimental separator vessel DT encompassing modern sensing and data processing techniques. The experimental separator vessel is a multi-material
prototype built with carbon steel and polycarbonate monitored by a sensing technique for density profiling the multiphase crude oil based on a new computer vision technique that is proposed for non-contact density measurement. This information is consumed by the DTs structural digital models, which are custom built for this experimental separator vessel. This way, digital models enable an improved sensing, i.e., extrapolating data from
few sensors, to compose a rich information set to be provided to operators. This unleashes "what if" scenarios to be quickly tested and maintenance indicators to be inferred. In order to illustrate these functionalities, a pressurized scenario is considered for this experimental separator vessel originally designed for 1 atm operation. The work contributions are presented
through a simple structural failure prediction approach under static and dynamic loads as well as through critical points traceability. Also, it is proposed a new method for estimate level interfaces in multiphase liquids by using clustering techniques. Thus, it is concluded that, at operation time, DTs has the potential of aggregating to separator vessel process control new dimensions of observability.
Key-words: Digital Twins; Cyber-Physical Systems; Industry 4.0; separator vessels; clustering; computer vision; observability.
