Transforming asset management in the energy sector

THERE'S A huge pressure on energy network operators to deliver clean, sustainable, and affordable energy. Maintaining equipment and systems within the energy industry to ensure reliable and proficient operations are the most crucial factor in achieving efficiencies.

Traditional approaches, characterised by reactive maintenance, have proven costly and inefficient, leading to increased downtime, reputational damage, and financial losses. However, the emergence of predictive maintenance strategies, driven by advanced data analytics and technology, is transforming the energy industry's approach to asset management. 

The energy sector has been in the spotlight recently due to rising energy prices. Ofgem has finalised its price control for 2021-26 (RIIO-2) with a major investment programme into England's energy infrastructure. The RIIO-2 stands for Revenues = Incentives + Innovation + Outputs and is the approach Ofgem take to ensure companies that own and operate gas and electricity networks have enough revenue to run an efficient network that delivers customer satisfaction. It works towards improving customer service, a fair price for consumers and, most importantly, reducing the impact of the networks on the environment.

To understand this, we delve into the importance of optimising energy networks through predictive maintenance management and highlight the role of a systems integrator in this transformative journey.

The shift from reactive to predictive maintenance

In the past, the common practice across industries was to wait for equipment failures before acting and this was no different for the energy sector. This reactive approach often resulted in unplanned downtime, decreased productivity, and dissatisfied customers. However, the advent of data-driven maintenance strategies has paved the way for a shift towards predictive maintenance.      

By leveraging advanced analytics and predictive models, energy companies can now anticipate equipment failures and take preventive measures before they occur. This can get complicated because the more you manage, the more you can start looking at things minutely. However, as systems integrators, our training and experience allow us to define the parameters of monitoring operational and internet technologies to maximise the extracted data.     

In UK energy networks, extensive continuous data sets are generated from various operational equipment types. These data sets can be stuck within the Operational Technology (OT) layer, and often not surfaced into the IT layer, where most high-level analytics occur. Surfacing the OT data into the IT layer in a secure manner is the start of the journey. Contextualisation and standardisation across all assets are crucial next steps. Once the data is available in the contextualised format, higher-level analytics layers can utilise the data towards making predictive maintenance possible.

As we start utilising the data sets, maintenance models can predict issues before they occur. In some instances, these predictive results benefit operations by dispatching just-in-time maintenance teams, with up to 80% success rate in finding and fixing issues.

This also allows the team to efficiently plan resolution logistics and execute the replacement of any operational equipment without any downtime.

Harnessing the power of data

At the core of predictive maintenance management lies the effective use of data. As a systems integrator, we understand the significance and the value of the data value chain in optimising energy networks. We work closely with our clients to surface data from the OT layer and contextualise it in a standardised format. This process enables a comprehensive understanding of assets' performance, real-time monitoring, and historical analysis.

To unlock the full potential of predictive maintenance, a system integrator needs to leverage a range of cutting-edge technologies. One example is the AVEVA PI System, a system with an extended capability toolset. It acts as a data historian and facilitates the seamless data flow from the OT to the IT layer in a secure manner. Part of the systems’ capability includes ways to efficiently contextualise data, which then becomes the foundation for further analysis and decision-making.

Additionally, technologies like InfluxDB and the PTC Thingworx platform help us leverage predictive analytical solutions to enhance the capabilities of maintenance management and resolution. InfluxDB provides a robust and scalable data storage solution, while PTC's advanced AI models enable predictive maintenance by identifying patterns, anomalies, and potential failures.

Predictive maintenance management, transforming the energy industry

Implementing predictive maintenance strategies offers numerous benefits to energy companies and their consumers. By adopting a data-driven approach, companies can achieve enhanced situational awareness, improved asset performance and availability, and optimised energy networks. Predictive maintenance reduces downtime, increases asset availability and efficiency, and assists with minimising reputational damage. Moreover, it enables companies to prioritise maintenance efforts based on criticality, ensuring timely interventions and cost savings.

The predictive maintenance approach system integrators advocate represents a significant shift in the energy industry's mindset. It empowers energy companies to transition from reactive practices to a more mature state of condition-based monitoring and, eventually, predictive maintenance. This journey towards optimisation and efficiency requires a holistic approach, integrating data, technology, and expertise.

Optimising energy networks through predictive maintenance management is crucial for energy companies seeking to ensure reliable operations, minimise downtime, and meet customer expectations. By leveraging advanced data analytics, integrated technologies, and the expertise of systems integrators, energy companies can transform their maintenance practices and unlock the full potential of their assets. 

Some of the wins that can be achieved are predictive maintenance techniques in the day-to-day routines. The operations team can compile an asset list and get an initial baseline on the condition of the equipment allowing the prioritisation of work based on the actual state of the equipment. This helps the finance team with budgeting and resource planning. There have also been proven energy savings. 

As the industry embraces predictive maintenance strategies, we can look forward to more efficient, reliable, and sustainable energy networks that power our world seamlessly.

Eduan Smit is solutions architect at Capula 

For more information: 

www.capula.com

Tel: 01785 827000