Opinions expressed by contributors are their own.
The oil and gas industry is in the midst of a titanic period of disruption.
It’s troubling—but not surprising—that 40% of new capital projects within the industry fail in terms of budgets and schedules, according to a study published by Booz Allen Hamilton.
At the root of these issues is the fact that oil and gas companies are overwhelmed with floods of data coming from expansive well sites, lengthy pipelines, high-tech equipment and sensitive gas-gathering systems. The quality of this data is not the problem; the problem is that it tends to flow directly into silos that are linked to outdated legacy systems. As a result, organizations experience an overwhelming lack of operational insights.
When you consider that the average offshore production platform has 40,000 data tags, it’s clear that the data flood is not going anywhere soon. Therefore, it’s crucial for oil and gas companies to learn how and why to use data to their advantage.
Creating, Leveraging Digital
A great competitive advantage lies in creating digital oil fields that are capable of producing and analyzing vast amounts of data in real time. Through a combination of connected technology and cognitive data science, companies can easily develop this capacity without making a significant investment in high-priced, hard-to-find human capital.
The positive impact of this data-driven approach cannot be overstated, especially when companies concurrently adopt a methodology known as cognitive predictive maintenance.
Maintenance on everything, including trucks and tanks, is a major cost and a major source of uncertainty for oil and gas companies. Even as organizations invest millions of dollars in upkeep and repairs, the risk of a spill or breach—along with the resulting fallout—looms large.
Cognitive predictive maintenance is a way to leverage real-time data to take a smarter, safer approach to service and repairs. By analyzing data streams coming out of digital oil fields, it’s possible to predict when service is actually necessary rather than presumably necessary. This specific but substantial capability has the potential to slash costs, eliminate inefficiencies and boost safety throughout the industry.
Saving Money, Lives
Even as oil and gas exploration have become more high-tech, the industry still relies on massive machines operating in extreme conditions. Predictive maintenance is a strategy that is uniquely suited to address the challenges this volatile, mission-critical equipment faces on a daily basis, helping companies optimize the following realms:
•Equipment Health: Capturing and analyzing data from performance sensors reveals exactly how well something like a drill or a pipeline is performing. With a holistic view of the health of this equipment, it’s relatively easy to spot weaknesses before they translate into failures. For instance, an underperforming drill can automatically have its speed reduced so it continues to operate but does not destruct. The long-term value of all equipment is maximized.
•Operational Efficiency: Any site that is contending with equipment failure is losing money by the minute. Cognitive predictive maintenance reduces instances of failure while accelerating the time necessary to perform mandatory repairs. As a result, delays and downtime are largely eliminated. In fact, the U.S. Department of Energy estimates that integrating connected technology more broadly into oil and gas could lead to a 45% reduction in downtime.
• Worker Safety: Workplace accidents are disruptive and costly. Many of these accidents occur while workers are conducting routine inspections and improvements. Cognitive predictive maintenance promises to slash the number of incidents by eliminating the need for many in-person inspections and indicating when human presence is too dangerous. If and when there is a high probability of an accident, it’s apparent before anyone arrives on site.
Oil and gas companies are constantly trying to juggle safety, productivity and cost-effectiveness. Fortunately for them, cognitive predictive maintenance is a rare approach that improves each priority without calling for compromises.
Ultimately, a smarter approach to maintenance is good for not only business leaders, but also everyone who works in the industry or consumes its products. That is the definition of a win-win situation.
Sundeep Sanghavi co-founded DataRPM to tackle the business problem of maintenance inefficiencies in industrial IoT. Sanghavi also founded Razorsight, a provider of cloud-based analytics solutions that has since been acquired by Synchronos.