SHELL STARTS USING MACHINE LEARNING

Reading Time: 2 minutes

Any failures or unplanned downtime can be costly at the vast Pernis refinery in Rotterdam, where Royal Dutch Shell processes 20m tons of crude oil per year. At Europe’s largest refinery, the machinery and operating conditions are tracked using 50,000 sensors that generate 100,000 measurements per minute.

Shell began using machine learning last year to better analyze and process that data. The model was designed to predict control valve failures and enabled workers to perform maintenance or adjust operating conditions as required.

 

The work at Pernis is an example of how oil and gas companies, often months in advance, use artificial intelligence and machine learning to detect problems before they happen. Since then, Shell has extended the program to 19 assets.

“We have stopped two trips with benefits of about $2 m in just the first two weeks since implementing this,” says Alexander Boekhorst, Royal Dutch Shell’s vice president for digitalization and computational research.

Royal Dutch Shell invests heavily in artificial intelligence research and development, which it hopes will address some of its most pressing challenges. From meeting the demands of a transitioning energy market, urgently in need of cleaner and more efficient power, to improving safety on the forecourts of its service stations, AI is at the top of the agenda.

Current programs include implementing reinforcement learning in its system of exploration and mining to reduce the cost of extracting the gas that still drives a significant proportion of its revenue.

During the data strategy development, Daniel Jeavons, Shell’s general manager for data science said “What it means in practice is that we as a data science team are in a great position because we can make our current business more effective, more efficient, more reliable, safer – by applying AI into those settings. But we can also play a role in creating some of the new business models that we want to create, and that’s really exciting because we’re playing our part in taking Shell into the next generation of energy sources, new fuels, and new sources of revenue.”

Shell rolls out AI at its public electric car charging stations elsewhere over its global business to manage the shifting demand for power throughout the day. It also has computer vision-enabled cameras installed at service stations that can detect customers lighting cigarettes–a serious hazard.

Shell will use machine learning to reduce COGS in the short term for predictive maintenance and output optimization. First, Shell can predict when equipment will malfunction then repair it before it fails by gathering sensor data from the equipment in the field. Preventing unplanned downtime of its resources has reduced costs and since implementation has saved around 3.5 million barrels of lost production. Nevertheless, due to the abundance of data, all the above uses of machine learning are valid. Still, the question “Can machine learning be leveraged to eliminate next high risk with less relevant data?” remains unanswered.

 

References:

https://www.ft.com/content/bfbac636-ee8b-11e9-a55a-30afa498db1b?shareType=nongift

https://digital.hbs.edu/platform-rctom/submission/capturing-value-through-machine-learning-shell-adapts-the-era-of-low-oil-prices/

https://www.forbes.com/sites/bernardmarr/2019/01/18/the-incredible-ways-shell-uses-artificial-intelligence-to-help-transform-the-oil-and-gas-giant/#2d5b1cc72701

https://www.ft.com/content/d67962d8-c0d8-11e8-95b1-d36dfef1b89a

https://www.shell.com/energy-and-innovation/overcoming-technology-challenges/digital-innovation.html

https://digital.hbs.edu/platform-rctom/wp-content/uploads/sites/4/2018/11/nynashamnrefinerynight-1100×200.jpg

One thought on “SHELL STARTS USING MACHINE LEARNING

  1. Tan Peng Peng says:

    Amazing to hear Shell is attempting to utilise big data not only for consumers (as with most companies), but to predict supply shortages, elevate safety standards, maintenance updates too!

    Considering that data will be key in the future, I wonder if businesses will turn to data sharing as hospitals do (e.g. sharing of patient data for consolidation and more accurate analyses)! Then, even the small businesses or entrepreneurs could benefit!

Leave a Reply

WordPress › Error

There has been a critical error on this website.

Learn more about debugging in WordPress.