The excitement around generative AI (GenAI) has been undeniable, promising wide-ranging changes across industries. However, for those of us in the world of industrial control and automation, the realities of implementing these powerful technologies are a little more nuanced.
While large language models (LLMs) demonstrate impressive text generation and knowledge synthesis capabilities, their inherent probabilistic nature often falls short of the levels of certainty required for critical industrial processes. The issue of hallucinations, where an LLM confidently produces an incorrect output, underscores the need for caution. It still requires an experienced professional to interpret the result. In short, a technology based on likely outcomes often lacks the robustness required for automation and control applications.
For many potential industrial use cases, simple prompt-based interactions with GenAI models are not always useful. The ‘prompt-engineering’ paradigm (for example where you ask ChatGPT for an answer) will soon reach a point of diminishing returns. So, is the current hype cycle around GenAI fading and are we approaching the trough of disillusionment? The answer probably lies not in discarding the technology, but in finding ways to adapt it to more specialised industrial needs. AI agents will soon have an important role to play in this transformation.
The rise of industrial AI agents
AI agents are more than just enhanced LLMs. They can leverage the power of LLMs, but are designed with specific tasks and objectives in mind. Unlike a typical LLM like Gemini, Grok or ChatGPT that responds to a wide range of general questions, an agent is designed to execute pre-defined tasks autonomously, given some initial parameters. Agents represent a more practical way to leverage AI for specific industrial purposes.
An AI agent therefore narrows the focus of the LLM to well-defined tasks, and can incorporate logic to deliver more targeted and predictable outcomes. But to perform well, an agent needs good quality context, and this is obtained from a ‘knowledge graph’.
The importance of context: knowledge graphs
The core limitation of relying solely on LLMs for industrial applications is that they lack the deep, contextual information about plant-specific or site-specific processes. A generic LLM has no idea how specific equipment is configured in your specific plant or site. This is why context is important.
A knowledge graph is a structured way of organising information and the relationships between it. It’s like a map of your plant’s knowledge, going beyond simple databases by connecting information in a way that makes it meaningful to the agent. Knowledge graphs can represent not only the equipment in a facility and its relationships, but also plant specific rules, procedures and the historical performance data associated with the plant.
For instance, a knowledge graph might show that a specific pump (node) is connected to a particular line (edge) which is part of a specific process, and that the pump was previously repaired a couple of months ago, and that its current operating pressure is outside a defined threshold according to the manufacturers data sheet.
Rather than searching through isolated data points and guessing, the AI agent can follow the web of connections within the knowledge graph. This allows it to draw more accurate conclusions and to make the right decisions within a very specific context.
Standardising knowledge for interoperability
Creating this context as a knowledge graph on a typical plant is obviously no small task. In the same way that industrial communications are standardised via protocols such as Modbus or Profibus to facilitate the exchange of data, the same concept needs to apply to higher level information involving AI.
Think about what occurred in the 1990’s with the introduction of electronic data interchange (EDI). Back then, every large business was struggling with inconsistent business practices, particularly for invoicing, payments, orders, etc. With EDI the format of each business document was standardised and codified, using a universal and ubiquitous system. This solved a huge problem because companies could then exchange business-critical documents with one another and be confident that the content would be understood. This same concept is now being applied to industrial information and data. Standard ways of representing data allow highly specialised AI agents to be independently developed and readily deployed to your factory.
There are many different industrial information model standards that could be used to define different aspects of industrial information. Examples include:
• ISA-95: Defines a hierarchical model for enterprises to control system integration.
• ISO 15926: A standard for representing data about engineering projects, with a particular focus on process plants.
• OPC UA: While primarily a communication standard, OPC UA also has an information modelling component.
• IEC 61131-3: Standardises programming languages for PLC and related automation.
• Asset Administration Shell (AAS): Developed for Industry 4.0, providing a digital representation of an asset and all its relevant data.
These data models can be stored in a graph database and therefore provide a common basis for the storage and exchange of information with AI agents.
How AI agents work: beyond simple prompts
An industrial AI agent is more than a model responding to a prompt. Instead, it’s a process involving specific stages:
• Task specification: The agent is configured with a specific, well-defined task within a narrow scope. For example, an agent might be set up to monitor for a specific type of equipment fault or to generate a preventative maintenance report.
• Contextualisation: The agent accesses relevant contextual data from the knowledge graph to inform its task.
• LLM execution: The agent uses an appropriate AI model to perform the core task, but with this additional context.
• Output formatting and validation: An agent can allow you to specify the format and type of output allowed from the language model. It has specific rules on how the LLM results can be used and has a validation mechanism to further reduce uncertainty.
• Learning and feedback loop: Crucially, agents can incorporate historical interaction data to refine their operation further. In theory, with each successful interaction the agent’s effectiveness improves, creating a continuous self-learning feedback loop.
Specialisation
The real power of agents comes from their specialisation. In an industrial setting, you might have dedicated agents for safety compliance, quality control, predictive maintenance, inventory management, energy optimisation and more. Instead of one general-purpose AI trying to manage all facets of a plant, many specialised agents can work together, each responsible for a defined area of expertise.
Provided the knowledge graph follows industry standards, these specialised agents could be provided by third parties. Companies, for example specialising in energy optimisation, could develop and provide their proprietary agents for your plant.
The path forward
Like much of the AI world, agent technology is still maturing, and there is much we need to learn. There is limited real-world experience with industrial AI agents so far, but the potential for reliability, scalability and true automation is undeniable.
Agents provide a viable path for moving beyond the limitations of simple prompting, enabling us to scale generative AI to real industrial use cases. The complexity of industrial environments requires robust and reliable solutions, and AI agents are an important piece of that puzzle. The development of platforms that can configure, manage and orchestrate multiple AI agents are all evolving. Together with a knowledge graph capability, these AI Agent platforms might just be the catalyst that will make industrial AI a practical and widespread reality.
Conclusion
The next 12 months will be critical in shaping how AI will be deployed in the industrial space. The initial enthusiasm for GenAI has given way to a more pragmatic understanding of what’s required for industrial applications. The focus will soon shift away from general purpose LLM’s like ChatGPT and towards the development of task-specific AI agents. The combination of these agents, working in concert with a knowledge graph could finally make industrial AI a viable reality. As automation specialists, our role is to foresee and understand these developments and steer our company’s adoption of this technology in the right direction.
About Gavin Halse
Gavin Halse, an experienced chemical process engineer, has been an integral part of the manufacturing industry since the 1980s. In 1999, he embarked on a new journey as an entrepreneur, establishing a software business that still caters to a global clientele in the mining, energy, oil and gas, and process manufacturing sectors. Gavin’s passion lies in harnessing the power of IT to drive performance in industrial settings. As an independent consultant, he offers his expertise to manufacturing and software companies, guiding them in leveraging IT to achieve their business objectives. His specialised expertise has made contributions to various industries around the world, reflecting his commitment to innovation and excellence in the field of manufacturing IT.
© Technews Publishing (Pty) Ltd | All Rights Reserved
printer friendly version