New vs. old: Bridging the 'generation gaps' with digital twins

By Steve Deskevich
Today's industrial businesses operate with a unique blend of technology. Walking into some asset-intensive operations, it’s likely you’ll see ass...

Today's industrial businesses operate with a unique blend of technology. Walking into some asset-intensive operations, it’s likely you’ll see assets of all vintages, from 50-year-old turbines sitting next to brand new ones, retrofitted with the latest sensors and intelligent controls. With this mix of asset vintages and digital technologies, a complex set of failure modes and asset risks come into play, and it quickly becomes challenging for operators to monitor and track asset health.

The additional challenge for facility operators is to monitor failure modes and risks beyond the “traditional” critical set of assets. Business value today is gained by looking at the entire facility, and fleet, which can encompass hundreds or even thousands of assets.  However, the failure modes and risks, along with technology sophistication, will likely differ across older and newer assets. With these challenges in mind, it becomes imperative for companies to develop strategies and processes that enable them to monitor and manage their equipment across the plant and across asset vintages, in an efficient and cost-effective approach.

As industrial organizations continue to meet these challenges, digital twins are helping organizations manage the risks for vintages of equipment and different generations of employees’ experience. Leveraging asset data, a digital twin simulates asset performance in different usage scenarios under varying conditions, based on known failure modes, actual performance and risk factors. Serving as a proxy for physical assets in a digital space, digital twins provide a dynamic digital representation of an industrial asset that enables companies to better understand and predict the performance of their individual machines. Digital twins can be created for varying vintages of equipment, helping to create a common methodology for determining asset performance using modern day asset performance software and platforms.

Digital twins start with asset data and metadata - the sensors’ and actuators’ data, but can also leverage very broad context data or knowledge that is related to the design, building, operation and servicing of the physical asset.  Digital twins in conjunction with asset performance management systems, offer the ability to analyze historical information, monitor current key performance indicators in real time and provide insights about an asset or system, from design and build to operation and maintenance. For instance, an organization can perform analyses to estimate the maximum life of an asset or test what facility production levels would be if a specific piece of equipment were to malfunction. Digital twins help to create a level playing field for asset vintages and enable replication of models across thousands of facility and fleet assets.  

For example, NRG, which has power plants across the US that provide about 48,000 megawatts of generation capacity, was looking to balance maintenance requirements across its units within the NRG fleet in order to maximize power output and meet the needs of the bulk power markets. NRG leveraged the digital twin model to dynamically review the operation of gas turbines across both older and newer assets in order to adjust specific operating conditions and key set points by unit. This optimization in turn allowed customers better manage their power, allowing them to bank megawatt hours during turndown market conditions and use them instead during peak market prices and conditions.

A key feature of the digital twin approach for facility owners that are managing assets of various vintages is the ability to form an “aggregate” of multiple digital twins, whereby an organization can monitor multiple instances of the same type of asset. By bringing all digital twins onto a common platform, plant managers can effectively build a learning system for the fleet as a whole and start to develop a holistic asset performance management strategy. The impact of implementing this kind of system is significant. One energy giant in the US saved 2,000 hours in one year with the ability to track and assess error events. The company was also able to allocate resources more efficiently by saving 700 users from manually updating information.

As digital transformation activities become more and more imperative for industrial organizations to survive, companies will be required to embrace new technology, replacing older assets that they’re accustomed to and turning to newer assets that may perform the same function, but have different types of technology, failure modes and risks. In these years of increased transition, a unifying system of data collection and asset modeling is necessary to effectively monitor asset health and more importantly, its risk of failure. Digital twins are transforming the way operators stay on top of machine health. Digital twins used in today’s asset performance software systems and platforms creates a framework that will bridge the “generation gap” both for asset vintages and the new workforce that is charged with continuing to monitor, predict and prevent costly production downtime.

By Steve Deskevich, Senior Director of Digital Product Management at GE Digital

Share
Share

Featured Articles

Celonis Data Insights Driving BMW's Sustainability Journey

Celonis and the BMW Group have strengthened their partnership to optimise the auto giant’s processes and increase efficiency, productivity & sustainability

How Zoom is Using AI Innovation to Reimagine Teamwork

Zoom has announced Workplace, its new AI-powered collaboration platform, to help reimagine teamwork, facilitate connections and improve productivity

How SAP is Accelerating Deutsche Telekom’s Cloud Journey

Europe’s largest telecommunications provider Deutsche Telekom is using RISE with SAP to accelerate its journey to the cloud

Alibaba Cloud’s Dr Li Feifei: Combining AI & Cloud Computing

Data & Data Analytics

Mustafa Suleyman: DeepMind Cofounder is new Microsoft AI CEO

AI & Machine Learning

Nvidia Blackwell Aims to Continue Powering AI Acceleration

AI & Machine Learning