Automated 3D CAD Model Rebuilding from Laser Scan Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current CAD systems face challenges in efficiently updating and maintaining 3D models of complex facilities like plants and refineries, as minor modifications often render original 3D CAD models obsolete, requiring costly laser scans and manual conversions to revert point clouds into 3D CAD formats.

Innovation Solution

An automated method that uses laser scan data to rebuild 3D CAD models by applying design logic and rules-based analysis to map shape, size, and sequence of facility objects, creating CAD model objects and updating design logic for efficient re-engineering.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If manual conversion methods are used to convert laser scan point clouds to 3D CAD format, then existing 3D model catalogs can be utilized, but the process requires significant labor and time investment

Engineering Contradiction:

Improveease of converting laser scan to CADVSAvoidtime required for manual conversion

Core Design Contradiction:

Ease of manufactureVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical conversion processes with an automated computer vision system that uses machine learning algorithms to directly transform laser scan point cloud data into 3D CAD models, eliminating the need for manual labor while maintaining conversion accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service conversion by automatically processing laser scan data through trained machine learning models that perform the entire conversion workflow without human intervention, from point cloud processing to final CAD model generation

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If manual conversion processes are employed, then flexibility in handling different facility modifications is maintained, but labor costs and processing time increase significantly

Engineering Contradiction:

Improveflexibility in handling facility modificationsVSAvoidconversion speed

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent implements a dynamic machine learning system that can adapt to different facility types and modification scenarios by training on diverse datasets, enabling the automated system to maintain versatility while operating at high speed across various conversion scenarios

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes operational parameters by adjusting machine learning model configurations and processing settings based on the specific characteristics of the input laser scan data, allowing automated adaptation to different facility types without sacrificing conversion speed

Inventive Principle:

Principle #35Parameter changes

3Productivity

If automated analysis with design logic is applied to rebuild 3D CAD models from laser scan data, then labor and time requirements are reduced, but system complexity increases

Engineering Contradiction:

Improverebuild efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary layer of pre-trained machine learning models that bridge the gap between raw laser scan data and CAD model generation, simplifying the overall system architecture by delegating complex pattern recognition tasks to specialized algorithms while maintaining high productivity

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS9916398B2Laser scan re-engineering of 3D CAD models

Publication Date: 2018.03.13 DASSAULT SYSTEMES SA

AI summary

A 3D CAD model of a plant, a factory, refinery, or facility is re-built from laser scan data of the plant, a factory, refinery, or facility. Through a rules-based analysis, CAD model objects are identified in the laser scan data. The rules map laser scan data to CAD model objects based on shape, size and/or sequence of connection of objects in the plant, a factory, refinery, or facility grouping. Design logic of equipment and process facilities are also utilized by the rules.