How industrial AI can transform energy
Artificial intelligence (AI) has a lot of potential in the energy industry. As energy organizations navigate market volatility, net zero goals, and rising energy demands, much of the industry is turning toward digitalization, including AI to better manage such trends, all the while increasing sustainability, efficiency, and growth. However, the amount of hype and speculation currently surrounding AI can obfuscate how to start applying it correctly for energy organizations seeking its adoption.
Such is the focus of a webinar done in association between Siemens and Energy Connects. The webinar is headed by Thiago Ribeiro, Global Head of Energy, Chemicals, and Infrastructure for Siemens, and Hermias Hendrikse, Global Technologist for Energy, Chemicals, and Infrastructure for Siemens. Together, they explore the current state of AI in the energy industry, what kinds of benefits it can bring, and use cases that show how the industry can apply AI in an industrial capacity and successfully reap its rewards.
The current state of AI and energy
According to Thiago and Hermias, there is a lot AI has to offer for energy. Its ability to manage increasingly large and complex datasets can help improve operational efficiency and throughout; mitigate risks in supply chains, cybersecurity, energy usage, and costs; and enhance customer engagement and experiences. The applications are numerous and wide-reaching.
That said, much of the energy industry is struggling with the adoption of AI. In their presentation, Hermias outlines how 40 percent of the industry views AI as untrustworthy, while 92 percent lack AI-skilled experts. As a result, only around 16 percent of energy organizations pursuing AI adoption are achieving their AI-related goals.
Much of this, Hermias states, can be attributed to not knowing how to properly apply AI in industrial processes. While the technology has been around for years, AI has been rapidly evolving recently, with new models and terminology being thrown into the conversation with each passing month. Some confusion as to what it is and what it can do among those seeking to adopt it is not unlikely.
Applying AI in an industrial capacity
One of the first steps toward gaining a better understanding to apply AI in the energy industry is to differentiate between generative AI and industrial AI. Generative AI is perhaps the form of AI most commonly used by the wider public, leveraging public data modalities to generate text, images, code, etc. However, industrial data modalities are far more complex, incorporating mechanical designs, electrical designs, simulations, manufacturing, and more that are contained from the public. Generative AI typically falls short in managing such data.
Industrial AI, meanwhile, is more than capable of operating in industrial and engineering environments. This can come in multiple forms, such as agentic AI that uses retrieval augmented generation (RAG) to access large language models (LLMs) trained on data from their organization’s industrial data. Hermias explains how engineers can use these agents as assistants in their work, asking engineering-related questions to generate insights that would otherwise be acquired with larger teams of engineers over longer periods of time. AI, uncover these insights in record time, accelerating, but not replacing, engineers’ work processes.
In another example, Thiago highlights a use case involving the high-fidelity modeling of a sustainable ship powered by hydrogen and ammonia. Utilizing data from the digital twin of the ship, AI was able to assist in true physics rendering to accurately model the ship and its more than seven million discrete parts, as well as generate realistic 3D objects and environments to simulate it in different scenarios.
This demonstrates how industrial AI can help organizations interactively visualize large-scale industrial datasets and projects to uncover errors and optimize designs. The same principles can be used in energy-specific projects, whether they are midstream, downstream, or even renewable projects.
These examples are just the tip of the iceberg. Other use cases Thiago and Hermias explore in the webinar showcase how the data interoperability and deep domain knowledge afforded by AI can accelerate supply chains, optimize the manufacturing of parts, and enable new processes such as predictive maintenance that can significantly increase project lifespans. The applications of AI in the energy industry are numerous, and any organization, no matter its size, can find ways to use it and unleash their full potential.
Be sure to register for the webinar to find more examples of how industrial AI can transform the energy industry.
Siemens Digital Industries Software helps organizations of all sizes digitally transform using software, hardware and services from the Siemens Xcelerator business platform. Siemens’ software and the comprehensive digital twin enable companies to optimize their design, engineering and manufacturing processes to turn today’s ideas into the sustainable products of the future. From chips to entire systems, from product to process, across all industries. Siemens Digital Industries Software – Accelerating transformation.
