You are Home   »   News   »   View Article

How to use analytics to improve production

Friday, December 18, 2015

Digital Energy Journal's Aberdeen conference on Sept 29 2015 explored how man and machine (or woman and machine) can work together to achieve the best results in production.

In the world of chess computing, 'every chess player will agree that the combination of a human plus a chess computer program are absolutely unbeatable,' said Sergio Sama Rubio, Industry Solutions Advisor with Halliburton, speaking at the Digital Energy Journal conference in Aberdeen on Sept 29, 'Using Analytics to Improve Production'.

It should be similar in the world of oil and gas production. If you can combine the human's strengths (strategy, designs and choices, objectives and decisions) with the computer's strengths (repetitive tasks, running models, optimising and training) you can work out the best way to get the most production and maximum safety with your resources available.

Dr Duncan Irving of analytics data platform company Teradata said that oil company staff will typically hand one data file onto the next person in the chain with no-one keeping track of the algorithms or models used to create it.

By the time the data is used to make a decision, sometimes the only version of the data is on a PowerPoint slide. 'This is not the same of pretty much any other industry Teradata works in,' he said.

Steve Harrison of Scottish Enterprise said he had been speaking to a senior leader from an oil and gas maintenance company, who pointed out that he gets paid in terms of man hours from sending staff offshore to fix things. It might be better for the client if he could do predictive analytics and only fix things which need fixing, but not better for his company.

The conference was not all negative. Tom Fox, a former field development engineer with Shell, explained how to bring together commercial, production and maintenance staff together to work on a production forecast, all putting their respective expertise into developing and accessing a model which they can access through a web browser.

Duncan Hart of Data Lab offered the resources of Scotland's academic community to assist with any data problem the industry has, with funding from the Scottish government to pay for it.

Oludare Elebiju of Enginsoft explained how companies can set up a central data repository for all reservoir data, using technology originally developed for a very large Brazilian oil and gas company.

Halliburton's Sergio Rubio explained how setting up well structured 'workflow' systems is a great way that oil companies can harness the expertise of retiring staff members. Jonathan Guthrie explained how you can start small with an analytics problem to prove it works, and Duncan Irving explained how the goal is to achieve a far more 'sentient' organisation - one which has a much better understanding of what is going on.

It isn't an easy time to be selling technology or services - energy consultant Jonathan Guthrie told a story of how he identified an opportunity for an oil company to accelerate and deliver a potential £15m of business value. The initial analysis was made from the oil company's own data. To validate and complete the analysis would require a short-term commitment of £15k from the operator. But was then told to cut his consultancy fees by 10 per cent because 'that was company policy'. He walked away from the business.

But the current oil price environment means that many companies have more time to evaluate better data technologies and pressure to see if they can deliver results. But can they get past the senior management who prefer to 'just do the same rubbish we've been doing because it feels safe'?

Scottish Enterprise - understanding big data

Scottish Enterprise has been looking into 'big data' since spring 2014 to find out what value it can actually add, said Steve Harrison, project manager with Scottish Enterprise.

It wants to help oil companies separate hype from reality with analytics. If all the hype was true, "we'd find oil in a second, we'd be able to maximise production and turn it into dollars," he said.

Senior management are asking for more 'evidence'. "We've been working with leadership to understand what evidence they need," he said.

Another challenge Scottish Enterprise is looking at is improving the goal alignment between operators and suppliers. For example, the incentives for predictive analytics are not as great as you might think. A senior leader of a maintenance company once told him, 'I get paid for the man hours for people who go out and fix kit. No-one will pay me for telling them when it's going to break.' Mr Harrison said.

Scottish Enterprise wants to help operators and service chain companies to help make the UKCS more competitive, and help the companies develop into international dominant players, he said. But also consider that the main objective of government, which pays Scottish Enterprise's bills, is often jobs, not competitiveness.

Associated Companies
» Digital Energy Journal
comments powered by Disqus


To attend our free events, receive our newsletter, and receive the free colour Digital Energy Journal.


Latest Edition Sept-Oct 18
Sep 2018

Download latest and back issues


Learn more about supporting Digital Energy Journal