3D Point Cloud Registration for Real-Time Deviation Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current defect detection systems in manufacturing lack real-time capability and accuracy in comparing as-built models with as-designed models, relying on manual registration and traditional coordinate measuring machines, which are slow and inefficient.

Innovation Solution

A system utilizing multiple sensors to generate and register 3D point clouds using k-d tree and subtree caching techniques, comparing them to a mesh model of the object to identify differences and display deviations graphically, enabling real-time monitoring and defect detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual registration and traditional coordinate measuring machines are used to compare as-built models with as-designed models, then measurement accuracy can be maintained, but the process speed and productivity are severely limited

Engineering Contradiction:
Improvemodel comparison speedVSAvoidtime for manual registration and measurement
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent replaces traditional mechanical coordinate measuring machines with a laser-based scanning system that captures 3D point cloud data of the as-built model. This optical/mechanical substitution enables automated, high-speed data acquisition without manual measurement operations, directly resolving the contradiction between measurement accuracy and process speed.

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

Solution Approach 2:

The patent creates a digital 3D point cloud copy of the as-built model through laser scanning. This digital copy can be automatically registered and compared with the as-designed model's digital representation, eliminating the need for physical manual measurement while maintaining measurement accuracy and enabling rapid processing.

Inventive Principle:
Principle #26Copying

2Extent of automation

If traditional coordinate measuring machines are used for defect detection, then measurement precision can be achieved, but the system cannot operate in real-time and requires manual intervention

Engineering Contradiction:
Improveautomated model comparisonVSAvoiddeviation detection accuracy
Core Design Contradiction:
Extent of automationVSMeasurement precision

Solution Approach 1:

The patent replaces manual mechanical measurement operations with automated laser scanning and digital point cloud processing. The system automatically captures 3D data, performs registration, and compares models without human intervention, achieving both high automation and maintained measurement precision through sophisticated algorithms.

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

Solution Approach 2:

The system performs self-service by automatically registering the as-built point cloud with the as-designed model and conducting the comparison without requiring manual operator intervention. The automated registration and deviation detection processes enable the system to independently complete the entire measurement and analysis workflow.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If detailed 3D point cloud data is collected and processed to identify deviations, then measurement accuracy improves, but data processing time and computational complexity increase

Engineering Contradiction:
Improvedeviation detection accuracyVSAvoiddata processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the complex 3D point cloud data into manageable components during processing. By dividing the large dataset into smaller segments for registration and comparison operations, the system maintains high measurement precision while reducing the computational burden and processing complexity of handling the entire point cloud simultaneously.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3404612B1Monitoring object shape and deviation from design
Publication Date: 2020.11.04 THE BOEING CO
  • EP3404612B1 patent drawingFigure 1
  • EP3404612B1 patent drawingFigure 2
  • EP3404612B1 patent drawingFigure 3

AI summary

A system includes a processor configured to generate a registered first 3D point cloud based on a first 3D point cloud and a second 3D point cloud. The processor is configured to generate a registered second 3D point cloud based on the first 3D point cloud and a third 3D point cloud. The processor is configured to generate a combined 3D point cloud based on the registered first 3D point cloud and the registered second 3D point cloud. The processor is configured to compare the combined 3D point cloud with a mesh model of the object. The processor is configured to generate, based on the comparison, output data indicating differences between the object as represented by the combined 3D point cloud and the object as represented by the 3D model. The system includes a display configured to display a graphical display of the differences.