Growing demands are placed on utilities to meet performance and other requirements. Plant operations must be able to quickly and efficiently respond to constantly changing demand while meeting operational limits. Digitalisation offers the potential to improve control beyond the scope of the digital monitoring and control networks used in power plant today.
Digitalisation has become a “trend”, a buzzword cluttering up the pages of magazines and and overused in presentations. There are many names for this approach, but the common thread is digital. There is some irony involved in this discussion, because power generation utilities were in the first wave of companies using sensors, data collection, and control systems to manage and improve their operations. This is why it would appear at first sight that there is nothing new in digitalisation, as its been used in the power industry for years.
There is a huge amount of hype and misunderstanding surrounding digitisation, digitalisation and artificial intelligence. Digitisation is the process of changing from analogue to digital without any different-in-kind changes to the process itself. Power system monitoring and control systems are all digital today are they not ? The IEC 61850 standard is at an advanced stage of development and adoption, and already incorporates the concept of “virtual components” and “virtual systems”. IEC 61850 based systems are in use in many networks. The smart grid is already well on its way to adoption.Digitalisation however goes beyond digitisation and can be described as the use of digital technologies to change a process and enhance efficiency and revenue; it is the process of moving to a digital system. Digitalisation embraces more than just collection and use of data in digital form. Digitalisation can already offer a significant range of immediate operational and financial benefits: sensors, devices and software can enable operators to utilise a wide range of data in real-time and improve decision making; control systems enable improved performance and maintenance of vital infrastructure and equipment either on-site or remotely; advanced analytics enable predictive maintenance and simulation to optimise asset performance; remote monitoring and external support can address key human resource and knowledge retention issues.
There is only one physical power grid, but a typical utility can maintain many diverse grid models, each associated with a different enterprise domain, such as planning, operations, asset management, GIS, outage management, and protection. But keeping this data synchronised is a big challenge. Every system works with its own data format, specific details, and has its own team to maintain the data – creating digital data silos. Inconsistencies during data exchange across those systems – or worse, the lack of data exchange – can lead to dramatic consequences like model inaccuracies, suboptimal system performance, possible regulatory violations, and ultimately system-wide blackouts.
The convergence of IT and OT provides the generation industry with greater system integration in terms of automation and optimisation, as well as better visibility of the supply chain and logistics. What makes it distinct is the intersection of information technology (IT) and operational technology (OT). OT refers to the networking of operational processes and industrial control systems (ICSs), including human machine interfaces (HMIs), supervisory control and data acquisition (SCADA) systems, distributed control systems (DCSs), and programmable logic controllers (PLCs).
Digitalisation makes use of the number of technologies to achieve an integrated system (Fig. 1).
Communication and interlinking:The internet of things (IoT) is another much hyped topic, but a specific application the industrial internet of things (I2ot) is proving to be a game changer in the digitialisation world. I2oT refers to the extension and use of the internet of things (IoT) in industrial sectors and applications. The I2oT has been in existence for years, with a strong focus on machine-to machine (M2M) communication, big data, and machine learning, the I2oT enables industries and enterprises to have better efficiency and reliability in their operations. The I2oT encompasses industrial applications, including robotics, medical devices, and Software-defined processes and opens up a range of applications and potential for optimistion across industries. For electricity, in particular, I2oT applications have been developed to operate and control T&D networks, improve the performance of individual and fleets of power plants, and optimise hybrid microgrid systems.
Deploying intelligent supervisory systems within the existing plant, makes the plant more reliable, more energy efficient more environmental friendly, and a safer place to work. Data can reach every member of staff in the plant for situational awareness. Enhanced situational awareness results in improved up-time and better plant performance.
Advanced analytics
Business applications provide the window of interaction to take action on insights, to manage the power plant and generation fleet functions to a greater level of control and to be able to react to changing market, fuel price and weather conditions in rapid fashion. These business applications are designed to increase asset performance, enhance operations, and improve energy trading decisions to create additional revenue and cost reduction opportunities. The applications fall into the following categories:
The current configuration based on a centralised control room that collects all data from the plant is a complex system already. What can be improved? One possibility is how big data from the remote sites is integrated with the rest of the enterprise to support plant personnel beyond the control room. The speed and accuracy of decision-making is being improved, this leads to actions based on having the right information in the hands of the right expert, no matter where they are. The digital transformation enables companies to exploit technology and expertise better than ever before, but only if the right scalable technology strategy is matched to your business goals.
The digital twin in power generation
The digital twin (DT) is a logical development of the digitalisation process. The DT has also suffered from a high degree of hype, mostly associated with animated 3-D images of the plant or the system. Yes there are systems that provide 3-D images , but the image is not important, what is important is the underlying information and analysis abilities.
Digital twinning is the mapping of physical assets to a digital platform. For the energy industry, this could be a wind farm, nuclear facility or traditional coal plant. The digital replica uses data from physical assets, for instance, the data acquired from the motor of a wind turbine, to analyse its efficiency, condition and real-time status.
The DT is an organised collection of physics-based methods and advanced analytics used to model the present state of every asset of the plant. The DT is used to execute “what if” scenarios and drive outcomes based on analytic models that mirror and predict the functions of the physical assets. The DT twin uses algorithms, system models and artificial intelligence to predict the future performance of the plant. Using the DT twin models and optimisation techniques and control and forecasting, the applications can accurately predict outcomes in the areas of availability, performance, reliability, wear and tear, flexibility, and maintainability.
The specific details of a digital twin will depend on its scale and purpose, but there are two essential characteristics. A digital twin must:
The digital twin (DT) is finding its way into the operation and maintenance of power plant. The DT has its predecessor in the SCADA, PLC, systems currently used, and the power plant operation and control systems currently used in power plant control rooms. The difference comes with the addition of advanced analysis and simulation abilities, including AI, as well as intercommunication between systems. 3D graphics help to make the system easier to visualise.
The GE digital twin
At its core, the DT consists of sophisticated models or system of models based on deep domain knowledge of specific assets. The DT is relies on having access to a massive amount of design, manufacturing, inspection, repair, online sensor and operational data. It employs a collection of computational physics-based models and advanced analytics to forecast the health and performance of operating assets over their lifetime
Included in the DT models are all necessary aspects of the physical asset or larger system including thermal, mechanical, electrical, chemical, fluid dynamic, material, lifetime economic and statistical. These models also accurately represent the plant or fleet under a large number of variations related to operation including fuel mix, ambient temperature, air quality, moisture, load, weather forecast models, and market pricing. Using these DT models and optimisation techniques , control, and forecasting applications can more accurately predict outcomes in the areas of availability, performance, reliability, wear and tear, flexibility, and maintainability. The models in conjunction with the sensor data give the ability to predict the plant’s performance, evaluate different scenarios, understand trade-offs, and enhance efficiency.
The GE DT employs AI technologies which leverage data from equipment to generate insights and deeper understanding of operating environments. They include:
Some of the areas of optimisation possible are:
ATOM: Digital twin of Siemens gas turbine fleet operations [3]
The agent-based turbine operations and maintenance (ATOM) model is a digital twin simulation model developed by Decision Lab and Siemens. The digital twin emulates the global maintenance repair and overhaul (MRO) operations of Siemens’ aero derivative gas turbine division. Driven by live data already available within the supply chain, the model provides the capability to use sophisticated simulation and data analytics methodologies to optimise the fleet operations of Siemens, enabling better data-driven decision-making to improve productivity and efficiency in customer operations and asset management.
Siemens wanted to visualise the whole production and maintenance process, including the supply-chain logistics, which are critical to the system. With the ability to visualise the results of multiple “what-if” scenarios, in order to communicate the business case for several investment options and enable better decision-making, both inside the company and outside, with clients.To meet the challenges, Decision Lab and Siemens developed the ATOM digital twin which exploits the emergence of digital technologies across Siemens engineering and manufacturing businesses. It uses the vast quantities of data that is available to integrate customers, supply chain, production, and maintenance in order to improve productivity and efficiency in customer operations and asset management.
At its core, ATOM achieves this by modelling the detailed intricacies of customer operations, maintenance facility operations, engine characteristics, and supply-chain logistics across the whole fleet and operational cycle. Representing the entire system, the digital twin provides extensive great analytical capabilities. A core part of the model was made from many independent elements and using agent-based modeling, it was possible to represent the necessary details. To build the model, the developers captured data relating to the following aspects of Siemens gas turbine fleet operations:
This is represented in the agent interaction diagram, which defines the complexity of the digital twin environment. In addition to the agent-based modelling approach, the digital twin incorporated a modular architecture, which allowed the system to be divided virtually into its constituent functional layers and provide a system engineering-based approach to model development.
This approach allows concurrent users to interact with the model in different ways, and to use different data sets, and also enable the development team to adopt a continuous development and deployment approach without disruption – a reinforcement learning element is planned.
Future phases of development could include the following:
References
[1] L Craig: “Beyond the hype: Digitalisation and the future of energy”, DNV GL – Energy, 05/2019.
[2] S Goel: “Digitalization for Smart Power Generation”, Power Info Today, www.powerinfotoday.com/articles/digitalization-for-smart-power-generation
[3] Anylogic: “An Introduction to digital twin development : Case Study: A digital twin of a gas turbine fleet”
[4] GE: “GE Digital Twin: Analytic Engine for the Digital Power Plant”
Send your comments to energize@ee.co.za