LLM4SFC: Sequential Function Chart Generation via Large Language Models

TL;DR

This paper introduces LLM4SFC, a novel framework that uses large language models to generate executable Sequential Function Charts from natural language descriptions, effectively bridging graphical and textual PLC programming languages.

Contribution

It presents the first method for converting natural language descriptions into executable SFCs, combining structured representation, fine-tuning, and real-time token pruning for compliance.

Findings

Achieves 75-94% success in generating valid SFCs.

Bridges graphical and textual PLC languages effectively.

Demonstrates applicability on real-world manufacturing data.

Abstract

While Large Language Models (LLMs) are increasingly used for synthesizing textual PLC programming languages like Structured Text (ST) code, other IEC 61131-3 standard graphical languages like Sequential Function Charts (SFCs) remain underexplored. Generating SFCs is challenging due to graphical nature and ST actions embedded within, which are not directly compatible with standard generation techniques, often leading to non-executable code that is incompatible with industrial tool-chains In this work, we introduce LLM4SFC, the first framework to receive natural-language descriptions of industrial workflows and provide executable SFCs. LLM4SFC is based on three components: (i) A reduced structured representation that captures essential topology and in-line ST and reduced textual verbosity; (ii) Fine-tuning and few-shot retrieval-augmented generation (RAG) for alignment with SFC programming conventions; and (iii) A structured generation approach that prunes illegal tokens in real-time to ensure compliance with the textual format of SFCs. We evaluate LLM4SFC on a dataset of real-world SFCs from automated manufacturing projects, using both open-source and proprietary LLMs. The results show that LLM4SFC reliably generates syntactically valid SFC programs effectively bridging graphical and textual PLC languages, achieving a generation generation success of 75% - 94%, paving the way for automated industrial programming.