Siemens Plant Simulation is one of the world’s leading solutions for digital factory and production simulation. In the automotive industry, this simulation platform is particularly used in early planning phases for designing new production lines and optimizing existing facilities. The Automotive Library is typically used as a modeling library to create simulation models more quickly and in a standardized way. As part of the integration of an AI copilot, this modeling library was utilized to connect to generative AI systems. inpro supported Siemens in the semantic structuring of the content, thereby laying the foundation for a powerful AI integration.

The Starting Point

Plant Simulation is based on modular building blocks that can be flexibly extended using the proprietary scripting language SimTalk and—more recently—also Python. However, the system’s high performance comes with a corresponding level of complexity.

In practice, simulation models are therefore often developed by specialized service providers. Due to the division of labor between plant operators, OEM specialists, and external engineering service providers, consistent standardization of modeling components is essential.

The Automotive Library establishes a binding industry standard in this regard. It provides preconfigured modeling components for key types of equipment in the automotive industry, including conveyor systems, machining production lines, body shop cells, and paint shop systems.

The goal of the copilot integration was to make this structured knowledge available more quickly, contextually, and in a user-oriented manner.

The Challenge

The greatest effort in simulation projects does not lie in the actual modeling, but in understanding the system, analyzing data, and interpreting complex documentation.

Simulation specialists often work under high cognitive load: in addition to modeling, they handle coordination, organizational tasks, and detailed technical analyses. Interruptions and task switching make continuous in-depth work more difficult. At the same time, the software offers virtually unlimited possibilities—far more than any single expert can fully master.

An LLM-based copilot offers significant potential here—provided that the underlying data is structured in a way that makes it machine-interpretable and semantically consistent.

The Implementation

The Automotive Library includes heterogeneous data sources such as training materials, guidelines, source code, and documentation in various formats (PDF, PowerPoint, HTML). To make this content usable for a large language model, systematic data modeling was required.

The focus was on introducing a consistent hierarchical heading structure and semantically segmenting the content. The objective was to explicitly represent logical relationships and enable context-aware querying by the copilot.

The Result

Today, the copilot supports users in getting up to speed with Plant Simulation more quickly. It facilitates re-onboarding after project breaks and accelerates operational modeling—especially when working with SimTalk.

At the same time, the next stage of development is becoming clear: while the copilot effectively supports users in operation and functional understanding, the conceptual structuring of complex simulation models still remains with the user. The cognitive translation of source data into a consistent model continues to be a domain-specific expert task.

Outlook

Looking ahead, software-agnostic copilots are conceivable—systems that do not primarily support the use of a specific application, but instead draw on domain-specific expertise. Such systems would need a deep understanding of production systems, simulation methodologies, and experimental design in order to go beyond pure functional assistance and deliver real substantive value.

“The semantic enrichment of the data, along with the associated testing using various LLMs, has laid the foundation for a production-ready solution that will support us in our work.”

Felix Bräsemann, Volkswagen AG | Factory Security & Simulation

Would you like to learn more about our expertise with Siemens Plant Simulation?

Kostenfreies Beratungsgespräch

Duration: 30min

Take the opportunity to discuss your use cases with us. We’ll be happy to show you live demos and relevant technology building blocks.

Dr. Andreas Geiger
Management Consulting

Learn more

Data Modeling for the First Siemens Plant Simulation Copilot

datamodelling, Success Story - öffentlich, Success Story - öffentlich, Success Story - privat

Data Modeling for the First Siemens Plant Simulation Copilot

Siemens Plant Simulation is one of the world’s leading solutions for digital factory and production simulation. As part of integrating an AI copilot for the automotive industry, the “Automotive Library” model library was specifically leveraged to enable connectivity with generative AI systems.

Previous 12