AI PLC Code Generation from Natural Language Requirements

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The conventional approach to configuring and programming industrial devices for manufacturing processes requires specialized knowledge, limiting the development of industrial control projects to experienced engineers and extending the time required for solution development.

Innovation Solution

An industrial integrated development environment (IDE) system using generative artificial intelligence (AI) techniques to generate industrial control code based on natural language inputs, reducing the need for manual programming and expertise.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional manual programming approach is used, then programming accuracy and reliability are maintained, but development time increases and accessibility is limited to expert engineers

Engineering Contradiction:
Improvedevelopment timeVSAvoidaccessibility to non-experts
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The patent replaces manual mechanical programming processes with an AI-based automated system. The generative AI model automatically translates natural language requirements into PLC code, eliminating the need for engineers to manually write programming code while maintaining code quality and functionality.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an AI intermediary layer between the user's natural language requirements and the final PLC code. This intermediary (the generative AI model) translates and transforms the requirements into executable code, acting as a bridge that enables non-experts to achieve programming results without direct manual coding.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If specialized knowledge requirements are maintained, then code quality and reliability are ensured, but device complexity increases

Engineering Contradiction:
Improvecode accuracyVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The AI system performs self-service by automatically generating, validating, and optimizing the PLC code without requiring user intervention in the complex programming processes. The system self-manages the translation from natural language to code, handling complexity internally while presenting a simple interface to users.

Inventive Principle:
Principle #25Self-service

3Productivity

If manual programming by experts is used, then programming precision is maintained, but productivity decreases

Engineering Contradiction:
Improvedevelopment speedVSAvoidskill requirement
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The patent substitutes the manual mechanical process of expert programming with an automated AI system that generates code at higher speed. The generative AI model processes requirements and outputs optimized PLC code instantly, dramatically increasing development speed compared to manual expert programming.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250147736A1PLC program generator/copilot using generative ai
Publication Date: 2025.05.08 ROCKWELL AUTOMATION TECH INC
  • US20250147736A1 patent drawing
  • US20250147736A1 patent drawing
  • US20250147736A1 patent drawing

AI summary

An integrated development environment (IDE) for uses a generative artificial intelligence (AI) model to generate industrial control code in accordance with functional requirements provided to the industrial IDE system as natural language prompts. The system's generative AI model leverages both a code repository storing sample control code and a document repository that stores device or software manuals, program instruction manuals, functional specification documents, or other technical documents. These repositories are synchronized by digitizing selected portions of document text from the document repository into control code for storage in the code repository, as well as contextualizing control code from the code repository into text-based documentation for storage in the document repository.