Annotated Design Document Parsing for Consistent Control Code

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Industrial automation systems face challenges in efficiently generating control code from text-based design documents, particularly due to laborious manual processes and inconsistencies in coding styles among multiple engineers.

Innovation Solution

A control code collaboration system that imports text-based engineering documents, allows users to annotate control logic, and uses a learning model to automatically generate and update control code, ensuring consistency and reducing manual effort.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual code generation is used by multiple engineers, then flexibility in coding is maintained, but consistency and time consumption worsen

Engineering Contradiction:
Improveflexibility in codingVSAvoidconsistency in coding style
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The system creates a template from the first annotated text-control logic pair and uses this template to automatically generate control logic for similar text patterns throughout the document, ensuring consistent coding style while reducing manual effort

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system learns from user annotations and automatically applies the learned patterns to generate control logic for similar text sections, enabling the system to serve itself in generating consistent code without requiring manual intervention for each section

Inventive Principle:
Principle #25Self-service

2Adaptability or versatility

If manual code generation is used by multiple engineers, then adaptability to different coding scenarios is maintained, but productivity worsens

Engineering Contradiction:
Improveadaptability to different coding scenariosVSAvoidcode generation speed
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The system performs preliminary learning by analyzing the first annotated text-control logic pair to establish a template before automatically generating control logic for all similar text patterns in the document, significantly accelerating the overall code generation process

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses the annotation data from the first text as feedback to train its learning model, which then automatically identifies and generates control logic for similar text patterns, improving both speed and accuracy of code generation

Inventive Principle:
Principle #23Feedback

3Productivity

If automated code generation is implemented, then productivity is improved, but device complexity worsens

Engineering Contradiction:
Improvecode generation speedVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system introduces a learning model as an intermediary between the text-based engineering document and the control logic generation process. This intermediary learns patterns from annotated examples and automatically generates consistent control logic, simplifying the overall system architecture while improving productivity

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS11775263B2Control code generation and collaboration using active machine learning
Publication Date: 2023.10.03 ROCKWELL AUTOMATION TECH INC
  • US11775263B2 patent drawing
  • US11775263B2 patent drawing
  • US11775263B2 patent drawing

AI summary

A control code collaboration system automatically generates control code for an industrial project based on text discovered within the design documents. The system allows a designer to highlight text within a text-based design document representing an interlock definition, step sequence definition, tag name, or other aspects of the design description. The system then allows the user to link annotations to the highlighted text, the annotations representing interlock programming, sequence programming, or controller tag names. The system then searches the document for similarly formatted text, which are assumed to represent descriptions of similar control aspects, and infers suitable control programming from these discovered pieces of text using the previously provided annotations as a guide. In this way, the system uses text pattern recognition generates suggestions as to how to program portions of the design description based on control logic examples provided by the user.