Revolutionising asset management in the oil and gas industry

The industrial world is awash with data and new information from sensors, applications, equipment and people. But the data is worthless if it is left untouched or not used to its full potential to gain insights and make improved decisions.

To make the most of big data, oil and gas leaders should implement machine learning alongside accurate engineering models linked to the IIoT. This will leverage the digital DNA of the asset to take advantage of the increased insight engineering information can bring to the operation regarding performance and reliability. Using reality-modelling technologies to capture existing asset conditions, applied together and working in tandem with the IIoT and machine learning, companies can reap the rewards of cost savings and improved uptime.

Demystifying machine learning

We have all experienced some form of machine learning, from streaming movie recommendations, to banks that monitor spending patterns to detect fraudulent activity. Now, the industrial arena is moving quickly towards using a type of artificial intelligence to leverage the Industrial Internet of Things.

As a greater variety of data becomes available through advancements in sensor technology to monitor just about anything, machine learning is being applied to efficiently manage increasingly large and fast-moving datasets. Previously, organisations with predictive analytics could use big data (current and historic) to attempt to predict the future — with reasonable results. What machine learning brings is a more accurate prediction using algorithmic models to deliver more insight.

Machine learning can handle large and complex information, from sensors, mobile devices and computer networks, to discover hidden patterns or trends in the data. It can then learn these patterns and apply it to new, real-time data to detect similar patterns in the future. For example, through modelling the performance of a piece of equipment, such as a pipe, in relation to the temperature of its surroundings, machine learning can be taught to see what normal and abnormal behaviour looks like, and by applying the model to current data, can identify events, such as when the pressure within the pipe increases while the temperature remains the same. The system can then predict, from existing knowledge, that something isn’t right and prescribe actions. The more data that is analysed, the more accurate the predictive model.

Machine learning techniques — two paths to choose

Part of the implementation process is understanding how machine learning works and the number of techniques involved. Your software service provider or machine learning expert will recommend which techniques to use and when. The most common techniques are:

• Supervised machine learning: The program is trained on a predefined set of test data comprising historical or similar data to the real thing, which then facilitates its ability to reach an accurate conclusion when given new data.
• Unsupervised machine learning: The program is given a mix of data and must find patterns and relationships therein with no training whatsoever, without any specific target or outcome.
   

So, it comes down to knowing what you want your data to tell you and understanding the data you have available.

Machine learning strategy — questions to consider

When implementing machine learning within an operation, certain considerations must be taken regarding the data, the insights that are sought and how they can be applied within the business. Five questions to ask are:

• Question the data — What isn’t being seeing that it is hoped the data can provide?
• Clean the data — Is the data validated and can it be labelled easily?
• Choose a platform — Has interoperability been considered?
• Hire a data scientist — Does the company have a machine learning engineer, and can they collaborate with a subject matter expert?
• Share the learning — Plan ahead to leverage the technology across the enterprise.

We need machine learning to stay competitive

Unlike business intelligence and predictive analytics methods that require a significant amount of manual labour and time, machine learning automatically produces insights at a consistent and accurate rate. It can then apply the learning to new, real-time data for future predictions and more reliable decision-making.

In the oil and gas industry, the ability to recognise equipment failure, and avoid unplanned downtime, repair costs and potential environmental damage, is critical to success across all areas of the business, from well reservoir identification and drilling strategy, to production and processing. This is even more relevant in today’s turbulent times. With machine learning, there are numerous opportunities to improve the situation. Some forms of predictive analysis machine learning can deliver to the oil and gas industry include:

Predictive maintenance

One of the most applicable areas where machine learning can be applied within the industrial sector is predictive maintenance. Predictive maintenance is the failure inspection strategy that uses data and models to predict when an asset or piece of equipment will fail so that maintenance can be planned well ahead of time to minimise disruption.

Predictive maintenance can cover a large area of topics, from failure prediction, failure diagnosis, to recommending mitigation or maintenance actions after failure. The best maintenance is advanced forms of proactive condition-based maintenance. With the combination of machine learning and maintenance applications leveraging IIoT data to deliver more accurate estimates of equipment failure, the range of positive outcomes and reductions in costs, downtime and risk are worth the investment.

Reservoir modelling

There is some question as to how reliable estimations are, when calculating how a reservoir reacts to fracture treatments. Machine learning makes the process more reliable with decisions made more quickly by providing the reservoir with data that recognises patterns for history matching. The models used will then be robust enough to help improve the accuracy of the predictions of reservoir properties.

Video interpretation

As well as the many sensors that are part of the continuous monitoring process of a platform or plant, video technology used in the down-hole drilling environment can benefit from machine learning. Machine learning can be applied to interpret video data through anomaly detection to provide accurate assessment wherever video technology is applied for sensing tasks, therefore improving safety, costs and efficiency.

Case-based reasoning

Frequent operational and reliability problems are still common within the oil and gas process, with well blow-outs, leakages and production issues being some of the serial offenders. The reason they are common is the number of complex parameters that can cause many outcomes.

With case-based reasoning, a current problem or case is compared to historical cases to find similarities that could provide clues to help identify the actions or behaviours to take that could help overcome the current situation. This could include analysing data such as weather conditions, depth, equipment used, costs and more. Case-based reasoning is not a new approach in the oil and gas sector, but the process can be significantly sped up using machine learning.

Other examples

Other examples where machine learning can be used within the oil and gas industry, particularly within down-hole drilling, is optimising the rate of penetration, path and angle correction, to determine the best drilling pattern for the terrain and conditions that will minimise equipment failure.

Accurately forecasting natural gas and oil markets to predict the supply and demand price would also give operators the competitive edge they need to maximise the supply demand price. It would provide them with the information they need to meet customer demand by anticipating future demand or consumption.

Visualisation bridging the gap between real assets and virtual assets

As already seen, machine learning capabilities will help organisations to realise insights from the large amounts of data provided by sensors and the IIoT. Bringing it all together is visualisation through engineering models for structures such as offshore platforms and onshore processing plants.

An engineering model is the computerised 3D version of the physical asset, which maps everything associated to the physical asset using sensors to represent near-real-time status, such as condition, performance and location. Where 3D models do not exist, users can create them with 3D reality modelling software, even utilising drones to capture high-resolution photographs, from which engineers can create digital engineering models for offshore structures, refineries, etc.

Photographs are transformed into detailed, comprehensive 3D models of all infrastructure data — in a less labour-intensive, cheaper and more efficient manner when compared to traditional methods.

IT/OT convergence has become an accepted practice, with operators gaining new insight from known information. But misalignment in corporate strategy still results in silo building across many areas, especially within engineering technologies (ET), where engineering models often remain stranded, inhibiting the ability to leverage this information to optimise operations. They should be included within the existing IT/OT conversation, driven by the IIoT as well as machine learning.

Designing and testing new products, systems and even plants in a virtual environment makes a compelling case, particularly from a cost perspective. Virtual models can tie these domains together over the whole life cycle of an asset using its embedded digital DNA. From an asset management perspective, it’s about predicting a problem before it occurs and enabling maintenance to be performed at optimum rates and costs. This will be accelerated with the application of machine learning to make the decision-making process smarter, faster and, more importantly, in context.

Continually modelling an oil field or installation means that personnel can survey the asset throughout its life cycle, from initial design to current condition, applying the difference in data to maintain up-to-date information on the equipment’s condition along the way. These models become the context within which oil and gas operators can design, build and operate their infrastructure projects. Reality modelling can link engineers in the field directly to the office, sharing information and data collaboratively. With the use of IIoT data provided by the images in the building of 3D models, machine learning algorithms provide even greater context, a predictive capability and deliver more informed business insight to the user, resulting in faster and more reliable decision-making.

Digitalisation and machine learning

While machine learning gives the impression that human involvement is minimal, this is not the case. It gives the user more intelligence, context, and insight to make the decision-making process easier and improve productivity.

For those adding machine learning to their asset management journey, the next logical step is to go model-centric, by adding visualisation dashboards, cloud-based IIoT data, analytics and reality models to machine learning. A machine learning strategy will give companies unprecedented insight into their operations and lead to significant benefits in efficiency, safety and optimisation, as well as the speed in which decisions can be made.

Conclusion

With the arrival of the IIoT, data is growing and becoming more accessible. With the ability to acquire more data, more advanced technologies are required to scrutinise and filter out the important information and the value held within. But, it can only be exploited by identifying what works well and what does not. Machine learning features complex algorithms to sort through large amounts of data, identifying patterns and trends within it, to make predictions.

The use of machine learning in oil and gas doesn’t have to stop at just exploration and production, but can be applied across the whole operation, where algorithms are used to continually improve the overall performance across the whole facility and the equipment within it. By combining these machine learning practices with the IIoT and visual operations, they will bring, as it matures, significant benefits. The IIoT, engineering models and machine learning should no longer be considered just buzzwords. Instead, when combined, they can be an organisation’s number one priority for achieving operational excellence.

Image: ©stock.adobe.com/Kovalenko I