ChatGPT for PLC/DCS Control Logic Generation

TL;DR

This paper explores how GPT-4 can generate control logic code for PLCs and DCS from natural language prompts, demonstrating promising syntactic correctness and reasoning skills that could aid control engineers.

Contribution

It presents an exploratory study with a prompt collection and analysis of GPT-4's ability to generate control logic code, forming a basis for a new benchmark.

Findings

GPT-4 generates syntactically correct IEC 61131-3 Structured Text code

Demonstrates useful reasoning skills for control logic tasks

Prompt collection enables future benchmarking of LLMs in control engineering

Abstract

Large language models (LLMs) providing generative AI have become popular to support software engineers in creating, summarizing, optimizing, and documenting source code. It is still unknown how LLMs can support control engineers using typical control programming languages in programming tasks. Researchers have explored GitHub CoPilot or DeepMind AlphaCode for source code generation but did not yet tackle control logic programming. The contribution of this paper is an exploratory study, for which we created 100 LLM prompts in 10 representative categories to analyze control logic generation for of PLCs and DCS from natural language. We tested the prompts by generating answers with ChatGPT using the GPT-4 LLM. It generated syntactically correct IEC 61131-3 Structured Text code in many cases and demonstrated useful reasoning skills that could boost control engineer productivity. Our prompt collection is the basis for a more formal LLM benchmark to test and compare such models for control logic generation.