Virtual Industrial Space Segmentation for Equipment Modeling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Digital modeling of industrial spaces with multiple machines and equipment is challenging due to the lack of digital definitions for machines and buildings, leading to time-consuming and costly manual drawing, and existing methods like three-dimensional scanning fail to distinguish between equipment and the environment, limiting the ability to reorganize production lines effectively.

Innovation Solution

A method involving three-dimensional digitization of the industrial space followed by real-time segmentation in a virtual environment using a bounding box to define virtual objects, allowing users to accurately model equipment and buildings without external assistance, using photogrammetry or lasergrammetry for digitization and scalar product calculations for segmentation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If three-dimensional scanning is used to obtain a point cloud representing the production space, then the complete space including building and equipment is captured, but the point cloud does not distinguish the building from machines and pieces of equipment

Engineering Contradiction:

Improvecompleteness of space captureVSAvoiddistinction between building and equipment

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The patent applies segmentation by dividing the captured point cloud into distinct virtual objects representing individual machines and equipment. The system automatically segments the monolithic point cloud data into separable components, enabling differentiation between building structures and movable equipment while maintaining complete spatial information.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent extracts meaningful information from the point cloud by identifying and separating equipment objects from the building environment. Virtual objects are extracted representing individual machines, allowing them to be independently manipulated while the building remains as the contextual framework.

Inventive Principle:

Principle #2Taking out (Extraction)

2Manufacturing precision

If each machine is computationally drawn in detail, then accurate digital definition is achieved, but the process is time consuming and costly

Engineering Contradiction:

Improveaccuracy of machine representationVSAvoidmodeling time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent uses photogrammetry to create accurate visual copies of machines and equipment from photographic images. Instead of manually modeling each machine in detail, the system captures real-world visual information and generates corresponding virtual objects that accurately represent the appearance and dimensions of actual equipment.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces manual computational drawing with automated photogrammetric processing. The mechanical process of detailed digital modeling is substituted with an automated system that captures images and algorithmically generates accurate 3D representations, dramatically reducing time and cost while maintaining precision.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If each machine is drawn in a rough way as blocks, then modeling time is reduced, but it is not possible for the user to immediately distinguish one machine from another

Engineering Contradiction:

Improvemodeling speedVSAvoidmachine distinguishability

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The patent uses photogrammetric copying to generate visually distinctive virtual objects that retain the unique appearance characteristics of each machine. This approach maintains high modeling speed while ensuring each equipment piece is immediately recognizable and distinguishable from others through its accurate visual representation.

Inventive Principle:

Principle #26Copying

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables users to efficiently and accurately model industrial spaces by allowing self-segmentation of equipment and buildings, reducing costs and time, and providing a realistic representation for reorganizing production lines without the need for detailed redrawing of each machine.

Implementation Method 1

using photogrammetry or lasergrammetry for digitization

Methodology Applied

Scientific EffectPhotogrammetry: Photogrammetry

Implementation Method 2

using photogrammetry or lasergrammetry for digitization

Methodology Applied

Scientific EffectLIDAR: LIDAR

Implementation Method 3

using scalar product calculations for segmentation

Methodology Applied

Scientific EffectScalar product calculation:

Data Source

PatentUS11430183B2Method and system for digitally modeling an industrial space in virtual reality

Publication Date: 2022.08.30 ATOS FRANCE

AI summary

A method for digitally modeling an industrial space, the industrial space including a plurality of pieces of equipment (E3) disposed in an industrial building (B), the modeling method including a step of three-dimensionally digitizing the industrial space so as to obtain a web (NAP) defining meshes representing the outer envelope of the industrial space with all of its pieces of equipment (E3), a step of real-time segmenting the web (NAP) in a virtual environment by a user during which:a bounding box (F) is positioned to bound at least one piece of equipment to be segmented (E3), andthe points of the web (NAP), belonging to the volume of the bounding box (F), are associated so as to form a virtual object (OBJ).