The deployment of digital oilfield solutions has taken an enormous step. While organizations historically have had to rely exclusively on field professionals to interpret and act on the physical characteristics of their environment, they are finding today’s new wave of digital oilfield solutions helpful in both capturing this data and using it to build complex, actionable models.

The amount of data being generated is almost beyond comprehension as the number of connected devices continues to grow. The industry also is moving rapidly from big data dimensions (gigabytes, terabytes, and petabytes) to “Big Analog Data” scales (exabytes, zettabytes, and yottabytes). This means decision-makers across operations, quality management, maintenance, training, safety, geoscience, and even IT now have both unprecedented opportunities and unprecedented challenges.

“For my job at National Instruments, I travel the world and see firsthand how engineers and scientists are acquiring vast amounts of data at very high speeds and in a variety of forms,” said Tom Bradicich, R&D fellow and corporate officer at National Instruments and the “father” of Big Analog Data. “I’ve seen how tens of terabytes can be created in just a few seconds of physics experiments – and similar amounts can be created in hours by taking measurements of jet engines or testing a turbine used for electric power generation. Immediately after this data acquisition, a big data – or Big Analog Data – problem exists.

“From my background in the IT industry, it’s clear to me that advanced tools and techniques are required for data transfer, management, and analytics as well as systems management for the many data acquisition and automated test systems nodes.”

All of these analog data points are being generated – along with hundreds of thousands more – every second or tenth of a second or hundredth of a second. Companies are asking, “How do we harness all of the information and begin to unlock the value in the data? Is there a business case for investing in the effort?”

The promise

One global oilfield services company recently claimed it was retaining about 5% of the data being generated by its equipment and only using the data for post-event diagnostics. While the company is deriving value through component-level, post-mortem diagnostics – and feeding that information into R&D for future product development improvements – it is falling short of what can be achieved in this new arena of digitized analog data. This approach results in a muted impact to the multibillion dollar maintenance and warranty budget and only takes into account the “archived” data, missing out on a large value opportunity for the organization.

The streams of data being generated today can be considered in three categories of use or value: real-time (in equipment monitoring), near-time (immediate adjustment of complex systems), and archival.

“While the ability to capture data from sensors and equipment in the field is maturing rapidly and being used for monitoring and alerts, the untapped value is in the prescriptive analytics using near-time response, which will increase production and efficiency,” said Aron Bowman, portfolio management leader for Dell’s Product and Process Innovation group.

The analysis of archival data, normally within a purpose-built data repository, is fairly mature although still very expensive to license and operate.

Safety

Safety is paramount across every aspect of the energy industry. The post-event feedback loop is a critical component of making incremental improvements in safety by design, but companies need to know how it can make quantum improvements. The answers may lie in the evaluation of complex systems of physical attributes all being considered in relationship to one another in the moment of operation.

Operational

Through big data or Big Analog Data, companies now have the ability to examine a wider variety of physical characteristics in the environments where they work, which gives them an opportunity to do predictive and prescriptive maintenance. They can see the earliest stages of wear and then issue maintenance tickets or recommendations against the manufacturers’ recommended cycles. This is perhaps the biggest opportunity that awaits the industry. If problems are germinating, they can be discovered earlier and managed according to safety, operational, and financial priorities. Reduction of unplanned downtime is only one obvious result.

Efficiency

The post-event analysis also is fairly mature and allows organizations to draw a relational link between physical environmental aspects and the results that were achieved. Companies are able to look for the same characteristics in their next action and apply the lessons they’ve learned to get a slightly better result. In the near-time model of analytics, it will be possible to monitor these production indicators and make suggestions about adjustments that will impact the current result rather than having to wait for the next appearance of this type of environment.

Training

Training is not an area that most people relate to digital oilfield discussions, but consider a case in which normal monitoring of a drill site shows an unusual pattern for pressure at a set of pumps. The increased pressure starts to impact the projected life cycle of the seals and bearings of the system, but the pressure is not something that can relate directly to other elements in the physical data, such as a drop in temperature or changes in gas composition. It’s only when the staffing schedules from the HR management platform are added that it becomes apparent that a specific operator, or group of operators, is overtaxing the machinery in order to hit the shift’s goals. That information can trigger retraining requests as well as alerts to the appropriate supervisors in the field, allowing the future monitoring of indicators to ensure compliance.

The potential

The future of digital oilfield technologies may lie in a new domain that Ron Pecunia, global director of end-to-end solutions at Dell Business Innovation Services, has coined as “engineering intelligence and analytics.”

“With advances in big data know-how we can bring in vast amounts of rich engineering information along with robust analog data to exploit possibilities enabled via advanced analytics,” Pecunia said. “The resulting new business processes will reshape the energy industry over time.”

The digital oil field has the potential to change all aspects of business in the oil and gas industry. To be successful in this next evolution, companies will need to unite engineering and data science and keep in mind that the models will need to continuously evolve to improve and adapt to changes in technology and environments. This will require companies to partner with firms that understand and excel in the four dimensions of the digital oil field: engineering, data science, business, and operations. These areas correlate to the acquisition of data, analysis of the data, action taken from the data, and the assessment of impact to the business. If any of these components is underrepresented, companies run the risk of being less safe, less efficient, or less profitable than they could be.