Idea
Natural language interface platform for industrial machines using large language models and OPC UA.
Research Paper
Core Innovation
This paper introduces an agent-based system that leverages large language models combined with OPC UA communication standards to interpret and execute natural language commands on industrial machines. Unlike prior touch-based HMIs, it requires no model fine-tuning or training data, relying solely on machine credentials and parameter dictionaries for universal applicability.
Why It Matters
Industrial operators currently rely on touch-based controls which limit efficiency and flexibility. This natural language interface reduces training time and operational errors by allowing intuitive spoken or typed commands. It scales across any OPC UA-compatible machines, transforming human-machine interaction in manufacturing and automation.
Market Size (TAM)
$10–20B TAM for industrial human-machine interfaces; $2–5B SAM from manufacturing and automation sectors. Driven by Industry 4.0 adoption and demand for intuitive operator interfaces.
Potential Customers & Pain Points
- Manufacturing plants – Complex machine control interfaces
- Industrial automation providers – Need for scalable intuitive HMI solutions
- Machine operators – Reduce training and operational errors
- System integrators – Simplify multi-vendor machine interoperability.
Business Model
Subscription-based SaaS platform with tiered pricing by number of machines and users; enterprise licensing for system integrators and OEMs; professional services for integration and customization.
Competitive Landscape
- Siemens MindSphere
- Rockwell Automation FactoryTalk
- Honeywell Experion
- AVEVA
- PTC ThingWorx
Implementation Challenges
- Integration complexity with legacy systems
- Operator trust and adoption of AI-driven controls
- Data security and machine access credentials management
- Dependence on OPC UA standard adoption across all machines
Validation Strategy
- Pilot deployments in manufacturing plants with Siemens PLCs
- User studies measuring command accuracy and operator satisfaction
- Performance benchmarking against traditional touch-based HMIs
- Iterative improvements based on real-world feedback and error cases
Research Paper Overview
Beyond touch-based HMI: Control your machines in natural language by utilizing large language models and OPC UA
Summary
This paper proposes an agent-based approach toward a more natural interface between humans and machines. Large language models equipped with tools and the communication standard OPC UA are utilized to control machines in natural language. Instead of touch interaction, which is currently the state-of-the-art medium for interaction in operations, the proposed approach enables operators to talk or text with machines. This allows commands such as 'Please decrease the temperature by 20 % in machine 1 and set the motor speed to 5000 rpm in machine 2.' The large language model receives the user input and selects one of three predefined tools that connect to an OPC UA server and either change or read the value of a node. Afterwards, the result of the tool execution is passed back to the language model, which then provides a final response to the user. The approach is universally designed and can therefore be applied to any machine that supports the OPC UA standard. The large language model is neither fine-tuned nor requires training data, only the relevant machine credentials and a parameter dictionary are included within the system prompt. The approach is evaluated on a Siemens S7-1500 programmable logic controller with four machine parameters in a case study of fifty synthetically generated commands on five different models. The results demonstrate high success rate, with proprietary GPT 5 models achieving accuracies between 96.0 % and 98.0 %, and open-weight models reaching up to 90.0 %. The proposed approach of this empirical study contributes to advancing natural interaction in industrial human-machine interfaces.