LLM-based Control Code Generation using Image Recognition

LLM-based code generation could save significant manual efforts in industrial automation, where control engineers manually produce control logic for sophisticated production processes. Previous attempts in control logic code generation lacked methods to interpret schematic drawings from process engi...

Full description

Saved in:
Bibliographic Details
Published in2024 IEEE/ACM International Workshop on Large Language Models for Code (LLM4Code) pp. 38 - 45
Main Authors Koziolek, Heiko, Koziolek, Anne
Format Conference Proceeding
LanguageEnglish
Published ACM 20.04.2024
Subjects
Automation
ChatGPT
code generation
Codes
DCS
GPT4
IEC 61131-3
Image recognition
industrial automation
industrial case study
Large language models
Logic
Manuals
P&IDs
PLC
Process control
Programming
Software
Source coding
Testing
Online AccessGet full text
DOI10.1145/3643795.3648385

Cover

More Information
Summary:LLM-based code generation could save significant manual efforts in industrial automation, where control engineers manually produce control logic for sophisticated production processes. Previous attempts in control logic code generation lacked methods to interpret schematic drawings from process engineers. Recent LLMs now combine image recognition, trained domain knowledge, and coding skills. We propose a novel LLM-based code generation method that generates IEC 61131-3 Structure Text control logic source code from Piping-and-Instrumentation Diagrams (P&IDs) using image recognition. We have evaluated the method in three case study with industrial P&IDs and provide first evidence on the feasibility of such a code generation besides experiences on image recognition glitches.CCS CONCEPTS* Software and its engineering→Automatic programming; Command and control languages; * Applied computing → Computer-aided design; * Computing methodologies →Natural language processing.
DOI:10.1145/3643795.3648385