Beckhoff has developed the TwinCAT Chat Client for the TwinCAT XAE engineering environment. This makes it possible to use Large Language Models (LLMs), such as ChatGPT from OpenAI, conveniently in the development of a TwinCAT project for increased productivity in control programming.
Large Language Models are created based on a neural network and trained with a large number of texts. LLMs have become widely used in recent years and are used for a whole host of tasks, including as the basis for chatbots or language translation tools.
The TwinCAT Chat Client enables AI-supported engineering to automate tasks such as the creation or addition of function block code, and even code optimization, documentation, and restructuring (refacturing). Implemented in TwinCAT XAE, this client connects to the host cloud of the respective LLM (e.g., Microsoft AzureTM in the case of ChatGPT), provides a user interface, and provides communication to the PLC development environment via the Automation Interface. This is available via a corresponding chat window in Visual Studio, whereby the LLM functionality has been optimized especially for TwinCAT 3 users – i.e., extensively supplemented with TwinCAT-specific content.
Product Manager Sven Goldstein explains how Beckhoff is taking advantage of the new chatbot possibilities for control engineering: