The global energy company, based in Spain, has teamed up with Google to launch a project that will use Big Data and Artificial Intelligence to optimise its Tarragona refinery’s efficiency, boosting margins and cutting costs.
Google will provide Repsol with data and analytics products, experienced consultants and its Machine Learning managed service, Google Cloud ML. The pair said this will help developers to build and bring Machine Learning models to production in the refinery environment.
Google’s technology will be used to analyse hundreds of variables in the refinery, which demands a high level of computer capacity and a large amount of data control. Previously, the highest number of functions that could be integrated digitally in an industrial plant was around 30 variables – the project aims to increase this number by more than 10 times.
Maria Zingoni, executive managing director of downstream at Repsol, said “This initiative belongs to a more comprehensive plan to take advantage of the possibilities afforded us by the latest in technology and improve industrial processes. We are not afraid of aiming for the stars, even if some projects will fail. This is about learning as fast as possible and that machines help people in their work.”
At more than 1,000 acres, Tarragona is Repsol’s third-largest unit and has the capacity to distil 186,000 barrels of oil a day. The current margin figure is US$6.6 dollars per barrel and through the project it has the potential to add 30 cents on the dollar. This could translate to US$20m annually for the refinery if all optimisation objectives are achieved.
This project is part of Repsol’s ongoing digitalisation in all of its business units to improve its competitiveness and efficiency. For example, Siclos with which Repsol’s refinery control panel operators learn, in real time, the economic implications of operating decisions; or Nepxus, which increases planning, analysis and agility in decision-making in the control rooms of these industrial installations.
Fuencisla Clemares, Google’s Country Manager for Spain and Portugal, said that “This project demonstrates the commitment from Spanish companies to digital transformation and the application of machine learning in industrial processes, of which Repsol is a pioneer.”
Other companies using Google Cloud ML includes RealMassive, a cloud-based source for real-time commercial real estate information, which uses the technology to deliver digital real estate listings faster. Another company is Buildertrend which develops cloud-based software and mobile apps for construction professionals, with tools for managing pre-sales, projects, customers, and financials. They switched to the platform after experiencing frequent frustration over slow performance using a shared cloud infrastructure.
Google is making further movements in the energy industry. The tech giant has released an online tool called Project Sunroof which estimates the solar potential of a house by examining the property’s features and local weather data. The project is a partnership with energy supplier Eon and German software firm Tetraeder.