3D Plant Layout Generation From 2D Schemas Using Object Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The process of generating 3D digital models of plant layouts from 2D schemas is cumbersome and time-consuming, especially when dealing with diverse CAD tools and formats, requiring manual intervention and limiting efficiency in manufacturing planning.

Innovation Solution

A method using a machine learning algorithm to detect 2D plant objects from input data, associate them with corresponding 3D objects, and generate a 3D model, allowing for automatic conversion without human intervention and supporting various CAD formats.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If manual methods are used to generate 3D plant models from 2D schemas, then layout planners can create accurate 3D models, but the process becomes cumbersome and time-consuming

Engineering Contradiction:

Improveaccuracy of 3D model generationVSAvoidtime required for 3D modeling

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of 3D model creation with an automated computer-based system that uses image processing and machine learning algorithms to detect 2D plant objects in schemas and automatically generate corresponding 3D models, eliminating the need for manual browsing and positioning

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service automation where the software automatically performs object detection, identification, and 3D model generation without requiring manual intervention from layout planners, allowing the process to serve itself through automated workflows

Inventive Principle:

Principle #25Self-service

2Ease of manufacture

If layout planners manually browse plant component libraries to find suitable 3D objects, then they can select appropriate components, but the process becomes time-consuming and reduces productivity

Engineering Contradiction:

Improveease of selecting 3D plant objectsVSAvoidproductivity of layout planners

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The patent replaces the manual browsing and selection process with an automated image processing system that detects plant objects directly from 2D schemas and automatically retrieves corresponding 3D models from component libraries based on detected object characteristics

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system introduces an intermediary automated processing layer between the 2D schema and 3D model library that automatically matches detected 2D plant objects with corresponding 3D models, eliminating the need for manual intervention in the matching process

Inventive Principle:

Principle #24Intermediary (Mediator)

3Stability of the object's composition

If techniques require all data preparation to be done using the same CAD tool, then data consistency can be maintained, but the system becomes less adaptable to diverse CAD formats

Engineering Contradiction:

Improvedata consistencyVSAvoidcompatibility with diverse CAD tools

Core Design Contradiction:

Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The patent creates a universal system that can process 2D plant schemas from multiple different CAD tools and formats by implementing format-agnostic image processing and machine learning algorithms that work with diverse input sources without requiring dedicated tools for each format

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system introduces an intermediary processing layer that converts various CAD formats into a standardized internal representation through automated image processing, allowing data from diverse sources to be processed consistently without requiring the same original CAD tool

Inventive Principle:

Principle #24Intermediary (Mediator)

4Productivity

If automated methods are used to generate 3D models from 2D schemas, then productivity is enhanced, but the complexity of the system increases

Engineering Contradiction:

Improveefficiency of 3D model generationVSAvoidcomplexity of automated system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the automated 3D model generation process into distinct functional modules including image processing for detecting plant objects, machine learning algorithms for identifying object types, and automated retrieval systems for selecting corresponding 3D models, making the complex system manageable through modular design

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20230142309A1Method and system for generating a 3D model of a plant layout cross-reference to related application

Publication Date: 2023.05.11 SIEMENS IND SOFWARE LTD

AI summary

A system and method generating a 3D plant layout model departing from 2D schema of the layout provide access to a plant catalogue of identifiers of 3D plant objects. At least one 3D plant object identifier is associated with a 2D plant object identifier. Data on a given 2D schema of a layout are received as input data. A function trained by machine learning algorithm is applied to the input data for detecting a set of 2D plant objects. A set of identifier and location data on the detected 2D plant object set is provided as output data. A set of 3D plant objects is selected from the plant catalogue with identifiers associated with the set of 2D plant objects identifiers of the output data. A 3D model of the layout is generated by arranging the selected set of 3D plant objects according to location data of the output data.