Before starting, it is important to point out that there are many options and techniques available to gain more insight and make better decisions on the performance of your assets and operation. It all comes down to knowing what the best fit is for your needs and what type of data you are using. 

Machine learning makes complex processes and data easier to comprehend, and it is ideal for industries that are asset and data-rich. A great deal of data from various data sources are required in machine learning, and a data scientist or analyst may be needed to help set up and interpret the results. While it is possible to build your own ML platform, this design takes time, specific skills, and investment in a platform such as Microsoft Azure for a secure, private cloud platform for developers and data scientists. Alternatively, purchasing machine-learning capabilities off the shelf, as part of an asset performance management software solution, or outsourcing to a third party are options, provided you ensure input from in-house skills.

Whatever path is chosen, the benefits machine learning can offer to big data are only just being brought to fruition. Opportunity is rapidly developing with productivity advancements at the heart of the data-rich industry in which you work. Here are some examples leading the way in this fast-moving digital transformation. 

Electric and Power

We are all familiar with the term “smart grid” – the electrical supply network that utilizes digital technology and measures to detect and react to usage issues. In today’s turbulent times, electric utility companies are affected by ageing assets, increasing energy demand, and higher costs; the ability to recognize equipment failure and avoid unplanned downtime, repair costs, and potential environmental damage is critical to success across all areas of the business.

Machine learning is augmenting the smart grid to better leverage and gain insight from the IoT with an enormous number of connected assets spread across a large network. Transformers, pylons, cables, turbines, storage units, and more — the potential for equipment failure is high and not without risk, so predicting failures with data and models is the new answer to keeping the network running smoothly. Another example of how machine learning helps the utilities industry is evidenced through demand forecasting, where predicting usage and consumption from numerous parameters can give a utility the advantage of being able to respond in advance, and balance supply with demand levels Smart meters can also be leveraged more individually so that customer recommendations regarding efficiency can be made. Machine learning also allows thermal images and video to be analyzed without the human eye to spot differences or anomalies in equipment. Additionally, asset health indexing can be leveraged to automate the analysis of extending asset life with machine learning, which is a low cost alternative to capital replacement. 

Oil and Gas 

In the oil and gas industry, the ability to recognize 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. In terms of maintaining reliable production, identifying equipment failures is one of the main areas where machine learning will play an important role. 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 minimize disruption. With the combination of machine learning and maintenance applications leveraging IoT data to deliver more accurate estimates of equipment failure, the range of positive outcomes and reductions in downtime and the associated costs means that it is worth the investment.

As well as predicative maintenance, the oil and gas industry has already started using machine learning capabilities in other areas. These include: reservoir modelling, where advanced analytics are used to make improved estimates on the properties of reservoirs based on historical data and models; video analysis that can be employed to detect patterns associated with anomaly detection; and case-based reasoning, which can help by siphoning out numerous parameters that account for well blow outs and leakages from a large example set of previous cases in order to come up with solutions. The application of machine learning has the potential to transform the oil and gas industry, which is even more crucial during the recent downturn in production and spending. 

Water Utilities

Like the electric utilities mentioned previously, water companies also face the same challenges of an ageing infrastructure, rising costs, tighter regulations, and increasing demand. With that, they also share the same benefits that machine learning offers, such as identifying equipment failure before it happens — not just to predict a failure, but also to identify what type of failure will occur. Other benefits of machine learning in the water industry include meeting supply and demand with predictive forecasting and making smart meters “smarter” to help curb waste, such as during water shortages.

Water distribution is another area that can be optimized with the application of artificial intelligence. Machine learning can be used in this scenario to speed up the decision-making process of how demand can be met by analyzing how much water needs to be supplied from the various locations (reservoirs, desalination plants, and rivers), as well as the pumping considerations and water movement, including associated costs and constraints. Machine learning will help determine the optimal low-cost methods of configuring network transfers, optimizing supply options, enhancing the raw water supply network, and determining the cheapest time to transfer water across the network. 

Flood detection can utilize machine learning by analyzing data from sensors, weather, geospatial location, alarms, and more to provide precise predictions and classifications of when and where floods are likely to occur at any given time; these predictions are based on current and historical data from all sources. This information would help utilities save time and costs, reduce false alarms, and lessen the impact on the environment. 

Manufacturing

Manufacturing has always been the main industry when mentioned alongside machine learning, and for good reason, as the benefits are very real. These benefits include reductions in operating costs, improved reliability, and increased productivity — three goals that relate to the holy trinity of manufacturing. To achieve this, manufacturing also requires a digital platform to capture, store, and analyze data generated by control systems and sensors on equipment connected via the IoT. Preventative maintenance is key in improving uptime and productivity, so greater predictive accuracy of equipment failure is essential with increased demand. Furthermore, by knowing what is about to fail ahead of time, spare parts and inventory can use the data to ensure they align with the prediction. Improving production processes through a robust condition monitoring system can give unprecedented insight into overall equipment effectiveness by monitoring air and oil pressures and temperatures regularly and consistently. Other areas of use include quality control optimization to ensure quality is consistent throughout the manufacturing process. For example, adaptive algorithms can be used to inspect and classify defects in products on the production line with pattern recognition to reject defects, from damaged fruit to deformed packaging.

Digitalization and transformation with machine learning 

Early adopters of machine learning are already reaping the benefits in the speed of information delivery, costs, and usefulness. As the technology advances, each industry is learning from each other, further advancing the use and influence of artificial intelligence. This gives you more information and insight to make smarter decisions. Bentley Systems’ users are combining machine learning with Bentley’s other digitalization technologies to make this process even more beneficial – by making it model-centric and adding visualization dashboards, cloud-based IoT data, analytics, and reality modelling to machine learning, the result is a complete solution for operations, maintenance, and engineering.

Having a machine learning strategy in place will give you unprecedented insight into your operation and will lead to serious benefits in efficiency, safety, optimization, and decision making. The digital transformation for industry is now at a tipping point, with technologies all converging at the same time – a whole range of problems that once took months to address are now being resolved in a matter of minutes, all thanks to machine learning. 

Richard Irwin, Bentley Systems,
richard.Irwin@bentley.com