From Repsol: "Refineries are among the largest and most complex industrial facilities. A refinery is made up of multiple divisions, including the unit that distils crude into various components to be processed into fuels such as gasoline and diesel and the entity that converts heavy residual oils into lighter, more valuable products. Managing a refinery involves around 400 variables, which demands a high level of computational capacity and a vast amount of data control". The FT notes that "Energy companies are increasingly looking to use the type of analytics often employed by companies such as Google and Amazon for consumer data across their operations, from boosting the performance of drilling rigs to helping to deliver greater returns from refineries".
According to FT: "Repsol will use Cloud ML, Google’s machine learning tool, to optimise the performance of its 120,000 barrel-a-day Tarragona oil refinery on the east coast of Spain, near Barcelona. Google’s technology will be used to analyse hundreds of variables that measure pressure, temperature, flows and processing rates among other functions for each unit. The project has the potential to add 30 cents on the dollar to Repsol’s refined barrel margin, which could translate to 20 million dollars annually for the Tarragona refinery, with significant upward growth if all optimization objectives are achieved. María Victoria Zingoni, Repsol’s executive managing director of downstream, said AI has only been applied to about 30 variables in a refinery but this will be increased to 400".
Repsol: "Google Cloud will provide its computing power, experience with big data and machine learning expertise".
Refinery variables including pressure, temperature, flows and processing rates.
Planned; results not yet available