LLM-based and Retrieval-Augmented Control Code Generation

• Published in: 2024 IEEE/ACM International Workshop on Large Language Models for Code (LLM4Code) pp. 22 - 29
• Main Authors: Koziolek, Heiko, Gruner, Sten, Hark, Rhaban, Ashiwal, Virendra, Linsbauer, Sofia, Eskandani, Nafise
• Format: Conference Proceeding
• Language: English
• Published: ACM 20.04.2024
• Subjects: Automation; ChatGPT; code generation; Codes; DCS; GPT-4; IEC 61131-3; IEC Standards; industrial automation; Large language models; Libraries; Logic; PLC; Process control; Programming environments; Testing; Vectors
• DOI: 10.1145/3643795.3648384

Control code is designed and implemented for industrial automation applications that manage power plants, petrochemical processes, or steel production. Popular large language models (LLM) can synthesize low-level control code in the Structured Text programming notation according to the standard IEC 61131-3, but are not aware of proprietary control code function block libraries, which are often used in practice. To automate control logic implementation tasks, we proposed a retrieval-augmented control code generation method that can integrate such function blocks into the generated code. With this method control engineers can benefit from the code generation capabilities of LLMs, re-use proprietary and well-tested function blocks, and speed up typical programming tasks significantly. We have evaluated the method using a prototypical implementation based on GPT-4, LangChain, Open-PLC, and the open-source OSCAT function block library. In several spot sample tests, we successfully generated IEC 61131-3 ST code that integrated the desired function blocks, could be compiled, and validated through simulations.CCS CONCEPTS* Software and its engineering Automatic programming; Command and control languages; * Applied computing → Computer-aided design; * Computing methodologies → Natural language processing.