Predictive Maintenance Using the Executable Digital Twin xDT

Autor: Maged Ismail, Peter Mas, Wim Hendicx, Kevin Goodheart, Umberto Badiali
Rok vydání: 2021
Předmět:
Zdroj: Day 4 Thu, August 19, 2021.
DOI: 10.4043/30980-ms
Popis: Through the introduction of programmable logic controller (PLCs), Dynamic Process & Controls modeling, integrating with Multiphysics Mechatronics & 3D equipment simulation modeling, companies can work in the online real-time environment. This modeling of equipment or processes builds the foundation for digital transformation of subsea, topside, onshore and plant environments. In the design and operation of field equipment, the physics based Digital Twin is getting more and more traction to develop virtually the equipment because of recent prediction accuracy improvement and faster calculation times. Such digital twins allow to find the optimal operating conditions and predictive maintenance schedules for operation. In this timeslot we will explain, based on few industrial examples, a new set of capabilities that allow companies to get the maximum out of digital twins to be able to use them on their equipment. By applying a structured process using Digital Twins to be able to convert the existing knowledge & data at Companies into solution to be more predictive on their equipment. This will deliver substantial return on investment (ROI) for the Oil and Gas Industry. An AI based methodology to perform Model Order Reduction on the digital twin to be able to get real time response in connection to online unit information An AI based methodology to convert the reduced model into a virtual sensor for online quality predictions or predictive maintenance scheduling as well as to use it for creating an optimal controller of the unit based on the product requirements Fast edge computing hardware that can collect data from sensors and, in real time, run the Executable Digital Twin (xDT) and suggest corrective action to the operator or run in closed loop control
Databáze: OpenAIRE