IoT and the Digitalization of Oil and Gas Production

Posted on

Dave McCarthy, senior director of products, Bsquare Corporation

The oil and gas industry faces key challenges in both production and business environments. Capital expenditures across the industry are decreasing by roughly 20 percent annually while at the same time the amount of data coming from the oil field can exceed 1.5 terabytes a day and threatens to overwhelm IT departments. However, through more efficient use of device data, advanced cloud-based data analytics, and automated application of corrective measures, the normal production decline of approximately 10-15 percent annually could be slowed to as little as 5 percent. Additionally, facility capital costs can be reduced by up to 3 percent and operating costs lowered by nearly 25 percent.

Digitalization of the oilfield represents both a challenge and an opportunity for the industry. However, oil and gas companies can address their production and operational challenges by deploying Internet of Things (IoT) solutions without getting bogged down in the crush of data or driving up their IT budgets. IoT extracts data from critical devices in order to provide actionable insights that can drive positive business outcomes.

Challenges Facing the Oil and Gas Industry

The oil and gas industry is undergoing one of the most transformative and challenging business periods in its history. Companies are tasked with improving the efficiency of their operations while reducing their environmental footprints and finding support structures for new developments. Each company in the industry is tasked with these challenges in the face of capital spending reductions of nearly 20 percent in the past year alone.

Oil and gas companies will need to depend on the data analytics capabilities that  are inherent in IoT in order to compete in an industry where the need to make rapid decisions across enormous data sets is paramount. In order to combat the industry’s growing challenges, companies are in the process of automating and digitizing their operations. Many petroleum operations have already embedded sensor technology enabling the collection of operating data from a range of critical points within their operating environments. However, many of these companies are currently only focusing on individual asset-level operational technologies such as robots and sensors and not on integrated strategic technology deployments. Both automation and digitalization solutions produce streams of data to be collected and analyzed.

Further, most companies lack a holistic approach to the problem and come away with most of the data unanalyzed. According to a 2015 Deloitte study, only one percent of the information from the nearly 30,000 data points being collected is currently available to oil and gas decision makers.

Benefits of IoT and Digitalization in the Oilfield

The use of IoT technology, which incorporates advanced data analytics and predictive reasoning, in the petroleum industry enables companies to harness, analyze, and act on large data sets from the physical assets employed in the field. Advanced data analytics can unlock and aggregate the many sensors used in the oil and gas industry to automate the response of certain systems without overloading IT and operations staffs.

These benefits can be applied to three different types of operations in oil and gas: unconventionals, conventionals and midstream operations.

Unconventionals: Use large numbers of quickly deployed wells where the timely collection and analysis of data is critical to understanding the oil field characteristics with less trial and error. This holds particularly true in using analytics to optimize well spacing and drilling parameters.

Conventionals: Using far fewer wells than unconventionals, data analytics and predictive tools are able to identify anomalous trends sooner so that issues can be addressed before production is impacted or failures occur.

Midstream: With up to 70 percent of pipeline leaks only identified by a visual inspection, use of sensors and analytics can help spot compressor, valve and pipeline maintenance issues before problems become catastrophic. Scheduling preventive maintenance for these issues helps to avoid environmental damage and the resulting fines.

IoT also supports the shift in oil-field organizations from a functional IT focus to a business IT focus. In many companies IT’s role is primarily to digitize back office functions. Aligning IT with business operations, driven by data analytics, can have a direct and positive impact on business outcomes:

Research firms estimate that using data analytics could help improve oil and gas production by between 6 percent and 8 percent. Making localized data actionable and providing trend analysis over an extended period of time results in increased efficiency and improved business outcomes by lowering operating costs between 5-25 percent and reducing facility capital costs by 1-3 percent.

Companies can now leverage data to identify patterns indicative of a potential mechanical failure or safety hazard via predictive analytics, and then automatically employ proactive measures (preventative maintenance, initiate supply chain, early warning system, etc.) to alleviate costly unplanned downtime before a negative situation ever occurs. The need to improve financial performance while also maintaining critical uptime and safety performance presents a prime opportunity to use IoT data analytics combined with real-time automation as a means to improve business outcomes.

The benefits of IoT technology to the oil and gas industry directly impact the bottom line. Whether used in exploration, production, transmission, or refining, IoT delivers specific business benefits in three critical areas across the petroleum ecosystem:

Increased Uptime

Production downtime resulting from equipment failure can have significant adverse impact on revenue. In a 2015 study, Deloitte University Press found that single pump failure can cost companies $100,000 to $300,000 a day in lost production. Clearly, if this can be avoided the benefits will be immediate and substantial.

One of the most fundamental use cases for IoT is the harnessing of real-time and historical data from large populations of equipment spread over multiple sites in order to construct (using machine learning) highly accurate digital models of physical assets. IoT then leverages data analytics so that potential equipment failures can be predicted with a high degree of probability (typically greater than 90 percent). This allows equipment remediation to be scheduled during planned maintenance windows thereby contributing to smoother operations and reducing, or even eliminating, unplanned downtime.

Reduced Service and Maintenance Costs

Upstream production facilities are complex, multifaceted operations. Keeping these facilities running smoothly requires periodic maintenance of equipment used in these operations. However, this maintenance is almost always based on either elapsed time or hour of use. These are both simply best guesses as to the optimal maintenance frequency and, as a result, equipment is almost always under- or over-serviced. Under-serviced equipment can lead to premature failures resulting in unplanned downtime. Over-serviced equipment increases service costs and reduces equipment longevity.

IoT can be used to maintain equipment based on actual conditions rather than arbitrary time or usage intervals. In addition to reducing equipment servicing costs, this contributes to equipment longevity and further improves production uptime.

Device Optimization

In almost any industrial setting, and especially in petroleum production environments, actual performance of critical equipment can vary across sites. This means that production sites which might otherwise be quite similar can exhibit substantial variance in production efficiency and overall output.

IoT, further using digital models of physical equipment along with advanced data analytics, can characterize the behavior of optimally performing equipment in the field. This characterization, among other things, includes equipment settings, calibration, service intervals, and configurations that can then be applied to underperforming equipment. This device optimization process, which is actually a continuous, on-going aspect of IoT, results in steadily improving production efficiency.

A Distributed Approach to Oil and Gas Industry Challenges

Bsquare DataV makes sense out of the vast amounts of data generated by digitalization of the oilfield by splitting the data collection and processing between local and cloud-based systems. Currently most petroleum companies access and process as little as two percent of their sensor data due to high transmission costs and the sheer volume of data generated. With DataV’s unique approach, companies can expect event monitoring and automation to happen in real-time. Using this approach reduces workflow bottlenecks and creates automated solutions that lead to quality results. DataV utilizes 100 percent of available data for on-board processing and automation, while still sending vital data to the cloud for processing. When utilizing this local data, operators can expect real-time rule creation like operational alerts to appropriate staff, orchestration across disparate enterprise systems, and remote asset rule modification when appropriate.

This automation of local functions provides for immediate response to changing conditions without waiting on human intervention while at the same time collecting necessary data for real-time processing and dashboard display. Digitizing exploration, drilling, transmission, and production systems takes advantage of IoT’s ability to expand the monitoring and the remote use of functions that reduce operational cost. Automating specific high cost functions such as drilling substantially benefit from near-zero unplanned downtime and running oilfield equipment closer to optimal specifications. To make this happen five IoT functions must be addressed and implemented: connect, monitor, predict, automate and optimize.

IoT Functions

Connect physical assets for:

  • Data collection and transmission to the network, cloud-based databases and applications
  • Filtering, prioritization and pre-processing of data
  • Local business rules and actions of assets

Monitor asset data to:

  • Apply logic to real-time data streams from physical assets both locally and remotely
  • Run complex event detection in real-time
  • Establish a distributed rules engine for anomalous condition

Predict conditions to:

  • Best identify conditions that frequently precede failures and orchestrate complex actions
  • Integrate into enterprise systems to prevent predictable failures
  • Schedule preventative maintenance at optimal interval so that costly unplanned downtime is eliminated

Automate operations with:

  • Machine learning that optimizes equipment efficiency and lower the cost of failures
  • Predictive modeling that plans for anomalous conditions detected by the monitor function
  • Auto-generation of rules that can do things like reduce drill bit torque or RPM to prevent overheating

Optimize equipment performance through:

  • Digital asset modeling that can benchmark operational parameters of high performing equipment
  • Performance optimization that applies the parameters used for the best performing equipment
  • Prescriptive remediation that can improve abilities of less than optimal assets

The Bottom Line for Oil & Gas Operations

The emergence of IoT technology in industrial applications is transforming operational efficiency, bottom line productivity, and safety around the world. Current petroleum production statistics show a normal decline of approximately 10-15 percent annually; this could be slowed to 3-5 percent with targeted reinvestment in fields like data analytics.

Bsquare helps make IoT data actionable and can result in increased efficiency and improved business outcomes. Benefits of oilfield digitalization according to IHS Energy include:

  • Increasing oil and gas production by 2-8 percent
  • Reducing facility capital costs by 1-3 percent
  • Lowering operating costs by 5-25 percent

Through the establishment of comprehensive, data-driven predictive insights, oil and gas companies can employ sophisticated rules and machine learning to constantly adapt and tune expensive assets in real-time and using trend analysis. The enhanced visibility into operational and geospatial data offers companies a more transparent view of a region’s productive potential to better inform subleasing and commitments to extraction activities. Visibility into operational and geospatial data offers companies a more transparent view of a region’s productive potential to better inform sub-leasing and commitments to extraction activities.

Dave McCarthy is a leading authority on industrial IoT. As senior director of products at Bsquare Corporation, he advises Fortune 1000 customers on how to integrate device and sensor data with their enterprise systems to improve business outcomes. Dave regularly speaks at technology conferences around the globe and recently delivered the keynote presentation at Internet of Things North America. Dave earned an MBA with honors from Northeastern University.

 

Find articles with similar topics
, ,