The cyclical oil and gas industry finally appears to be back on the upswing and poised for growth. Companies that survived the downturn by becoming more efficient are seeking a new competitive edge in production optimization through the use of the Internet of Things (IoT) and cloud technology. These types of technologies are the gateway to a new wave of innovation in the oil field as they consolidate infrastructure, data collection and bandwidth costs while allowing for a greater data collection footprint, control and analytics capabilities.

Using IoT technology and cloud infrastructure benefits the entire life cycle of a well and is easier to integrate and less expensive to implement than one might think. How much of an impact to the bottom line can the use of this technology make? With a secure and timely transit data path to the cloud, companies can reduce production management expenses by up to 15% with downtime reduced by at least 30%. Safety and regulatory compliance also can be improved by at least 30%, driven largely by reduced trips to the field and easy reporting capabilities.

Oilfield data collection

Oilfield data collection, which consists of pressure, temperature, level, flow measurements, equipment parameters and control devices on a well pad, are used to provide valuable insight to deploy capital to ensure the timely delivery of hydrocarbons. The use of an edge-tocloud solution enables real-time data to ensure all assets, including those previously considered stranded, can be monitored at a low cost.

For example, the WellAware Integrated Radio & Controller (WIRC) is an edge computing direct-tocloud device that can be located in Class 1/Division 1 or Class 1/Division 2 locations.

The WIRC is able to sample various data inputs at frequent intervals, even storing those data to forward if the device is offline. It is able to adjust various equipment parameters in the field without requiring someone to visit the site, resulting in faster response times and a more efficient use of labor. Data can be processed on the edge or sent to the cloud for more advanced analytics.

Optimizing production starts with good information, and data need to be collected from remote equipment, the reservoir and the transport infrastructure to ensure the continuous flow of hydrocarbons to the surface.

As data are managed, there is a maturity process moving from descriptive analytics to diagnostic analytics to predictive analytics to prescriptive analytics. The insight gained from these analytics allows better decision-making to manage workflow and keep equipment running at peak performance.

Wellsite data analytics

Data analytics can be subdivided into four categories: descriptive analytics describes what has happened; diagnostic analytics describes why something happened; predictive analytics describes what will happen; and prescriptive analytics describes how to make something happen.

Descriptive and diagnostic analytics have a long history in data acquisition but can be greatly enhanced when visualization is tailored to personas or roles within an organization or combined with additional datasets to provide situational context.

For instance, wellsite descriptive analytics is constantly tracked as readings are sent through a secure, integrated cloud system. The data are then logged, parsed and used to derive additional data that provide valuable insight into what operational activities have happened over time. These data should be visualized on rolebased dashboards that provide logical, easy-to-read outof- the-box reports and trending charts that are available on mobile apps so an engineer, technician or executive can easily access the most relevant information they need to better perform their jobs.

In using diagnostic analytics, historical data can be used to match a real-time dynacard to existing issues like fluid pound, unanchored tubing, gas interference, hole in barrel, incomplete tubing fill, worn pump and more. Armed with this information, the extrapolated numbers and calculations can be used to evaluate low production and either adjust run parameters or determine maintenance needs that can increase production.

Emergence of smart analytics

With the availability of cloud infrastructure, edge computing and advancements in numerical methods, predictive and prescriptive analytics now are able to be implemented in real time on production data, providing new ways to optimize production.

For example, in using predictive analytics, realtime data are collected from artificial lift equipment and then transmitted to the cloud. Numerical and machine learning models are fed the data collected and, after processing, are able to detect patterns and trends that indicate when a failure will occur under the current loading and environmental conditions. In turn, the artificial lift equipment can then have its operational parameters changed from commands sent from the cloud to the artificial lift equipment so as to extend its life and allow for planned downtime to make needed repairs.

Alternatively, prescriptive analytics provides actionable insights that can be computed in the cloud or on the edge. As an example, to ensure that corrosion, paraffin, calcium or hydrate buildup does not begin, chemical concentrations can be altered to maintain a prescribed parts per million concentration to slow these effects. Based on data collected around the well site, the injection pumps then can be told to adjust their output as the production system changes to ensure uptime and maintain flow assurance of the system.

The ability to perform the various wellsite analytics can be even more enhanced by the use of edge computing. When computational power is available right at the point of data collection, data can be processed quickly into information that can then be acted upon, thus allowing new discoveries into equipment efficiencies and workflows.

Enhancing workforce efficiency

Utilizing edge-to-cloud data collection does not eliminate the use of manpower, but it greatly reduces the time and travel of technicians in the field. Data that are collected are used to design new workflows so technicians are assigned routes to the most pressing issues and bypass sites where everything is working properly. Incorporating a mobile device into this workflow allows immediate response to a situation by the technician, easier access to data at the well site and the ability to capture nonsensor data.

When sites do require a visit, inexperienced field personnel gain 20 years of experience when armed with the right information. They no longer have to recall experience or training to troubleshoot a problem—information can be presented on the mobile device that informs them of the correct parts to replace and procedure or safety protocols to follow.

Conclusion

Digital intelligence that will help the industry evolve is found in the edge to cloud-based process of getting data to market. By increasing the footprint and quality of data collection on a well site, companies of any size are able to be more adaptive in their deployment of personnel, inventive in their analytical methods and competitive in their cost to deliver hydrocarbons.

Comments