How to leverage data in the energy industry

The piecemeal approach taken by midstream oil and gas operators to leveraging their data is often challenged in providing scalability and value beyond its initial purpose.

On my last trip to Abu Dhabi, I came across a great description of the technology challenges facing the overall oil and gas sector: “The digital transformation of oil and gas companies has been largely piecemeal and focused on improving efficiencies for very specific applications.”

For those involved in midstream – where the storage, processing, and transportation of petroleum products takes place – there may be some value-creation opportunities with this approach, but it is very hard to scale.

This approach is often taken in a variety of very specific applications – scheduling, blend management and custody transfers to name a few – that are purpose-built for managing the storage and transportation of petrochemicals.

On the other end of the spectrum, a large number of field assets in the midstream storage, transport and financial settlement process are managed through manual processes.

Which is where the two principle challenges facing these midstream operators arise.

1. While purpose-built applications work, these solutions often function as stand-alone applications generating data that is specific and isolated to one application.

Purpose-built solutions will always have a key role in supporting midstream operations, but they also need world-class application API and integration capabilities that allows them to access any data pool and provides them with the ability to move the data where it can best be used in a timely fashion by production engineers, data scientist and plant managers.

For example, one of the state-owned oil companies of the region is one of the few who is ahead of the digitalization curve. API and integration capabilities benefited the company through data synchronization – connecting the dots between applications across all partners and operating companies via a unified layer of common framework and standards.

As key business objective was to integrate for internal and external purposes, which increased the effectiveness and efficiency of services delivered by the firm and its companies, providing the firm a distinctive competitive advantage. It further has the option to scale it up horizontally and vertically.

With this truly cloud-enabled platform, the organization is able to adapt cloud technologies and move gradually to cloud without jeopardizing the security or quality of services.

2. For the field assets that are not enabled to log and record data, there is no data generation. Without access to quality data, it is very difficult to optimize production decisions through advanced analytical capabilities such as AI/ML.

My favorite example of the importance of this capability is in the field of self-service industrial analytics. Anyone who has worked or supported storage and pipeline operations knows that they are in an incredibly complicated process environment. Within this environment, there are a multitude of assets from different vendors generating millions of data tags. These tags are captured in either historian or data lake environments.

For production and reliability engineers to make full use of this data, self-service industrial analytics technology platforms that can perform advanced pattern recognition analytics are critical for two reasons.

1. To find and record root-cause anomalies that are negatively impacting reliability across the end-to-end production process.
2. Once an anomaly is recorded and diagnosed, it can be cataloged and utilized as a predictive tool to inform engineers that the potential for a production disruption is high when that pattern repeats itself.

In the case of the regional oil firm highlighted above, integration across siloed applications, assets and services enabled the firm to combine existing functions and its underlying data to increase agility and improve efficiency.

Manual management of field assets

Field assets in the midstream sector are largely managed through manual processes. One of the better examples is the storage and blending of petroleum stocks. For a number of storage operators, tank levels are often measured by work crews going out to individual tanks. While this process works, it is often associated with recording inaccuracies and delayed decision making associated with the time it takes crews to visit, record and post their findings.

Compare this against a storage environment where all tank levels are monitored with IoT tank-level sensors and technology across terminal and blended storage tanks. At any given time, plant managers can make real-time decisions to support storage requests based on a real-time view of storage capacity. Additionally, they can run advanced IoT analytics on transferred volumes in relation to tank storage levels, also in real time, to identify asset integrity (leakage) events.

And, by using a self-service industrial analytics platform, they could run advanced pattern analytics to enable predictive maintenance capabilities across the field assets (pumps, compressors, etc.) supporting the storage and transport transfer process.

In summary, while the majority of professionals who have supported this industry over the years are intimately aware of its challenges, it is time for optimism. Modern technology applications have the capacity and the integration, IoT connected devices and industrial analytics capabilities to not only enhance the legacy technologies that have been deployed in the past, but just as importantly, support the midstream oil and gas sector in their business transformation efforts going forward.

Learn more about what Software AG can do to help you on your own business transformation journey by clicking below.