Computer Vision Sealant Dispensing for Adaptive Robotic Sealing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for sealing large manufactured objects, such as aircraft wings, are labor-intensive and prone to inconsistencies due to the manual application of viscous sealing compounds, which can lead to leakage and contamination issues, as robots have not been effectively integrated to perform precise and reliable sealing operations.

Innovation Solution

A computer vision-guided dispensing system using a robotic arm with a dispensing nozzle, where real-time visual images are processed to determine the precise positioning and amount of viscous fluid to be applied, allowing for instant quality inspection and control of the sealing process, ensuring accurate deposition and shape of the sealant.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual application of sealing compound is used, then flexibility and adaptability to complex geometries are maintained, but labor intensity increases and consistency/reliability decreases

Engineering Contradiction:
Improvesealing reliabilityVSAvoidautomation level
Core Design Contradiction:
ReliabilityVSExtent of automation

Solution Approach 1:

The patent replaces manual mechanical application with an automated robotic dispensing system that uses computer vision guidance. The robotic arm with dispensing nozzle automatically applies sealant based on visual feedback from cameras, eliminating manual labor while maintaining precision through image processing and automated control algorithms.

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

Solution Approach 2:

The system incorporates real-time visual inspection capabilities that allow the dispensing process to self-correct and self-verify. The computer vision system continuously monitors the dispensing operation, automatically detects defects or inconsistencies, and adjusts the process parameters to maintain sealing quality without human intervention.

Inventive Principle:
Principle #25Self-service

2Productivity

If automated robotic dispensing is implemented, then labor intensity decreases and consistency improves, but system complexity increases

Engineering Contradiction:
Improvedispensing efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The robotic system is designed with multi-functionality, combining dispensing, positioning, and inspection capabilities in a single integrated platform. The same robotic arm that dispenses sealant can also position the nozzle and the computer vision system that monitors the process can serve multiple inspection purposes, reducing the need for separate dedicated devices.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The computer vision system acts as an intermediary between the robotic dispenser and the workpiece. Instead of requiring complex direct control mechanisms, the vision system captures images, processes them to extract feature information, and translates this into dispensing commands, simplifying the overall control architecture while enabling precise automation.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If pre-programmed trajectories are used, then automation is achieved, but adaptability to variations in feature location and geometry is lost

Engineering Contradiction:
Improveadaptability to feature variationsVSAvoidtime for quality inspection
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by capturing images of the workpiece before dispensing begins. The computer vision system processes these images to identify feature locations, geometries, and characteristics in advance, allowing the robotic dispenser to adapt its trajectory and dispensing parameters dynamically without requiring time-consuming inspections during or after the process.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements real-time feedback through the computer vision system that continuously monitors the dispensing process. The captured images are processed to provide feedback on the actual dispensing outcome, allowing the system to detect and correct deviations from the desired seal quality immediately, ensuring adaptability while maintaining efficiency.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS20220080454A1System and method for automated artificial vision guided dispensing viscous fluids for caulking and sealing operations
Publication Date: 2022.03.17 MACDONALD DETTWILER & ASSOC INC
  • US20220080454A1 patent drawing
  • US20220080454A1 patent drawing
  • US20220080454A1 patent drawing

AI summary

The present disclosure provides a method and system by which a precise amount of a viscous fluid sealing compound can be dispensed at required locations through computer vision-based observation of the fluid deposited, its rate and amount of deposition and location; and that the dispensed fluid may be accurately shaped through robotic or other special purpose mechanism motion. The invention enables instant quality inspection of the dispensing process in terms of the locations, amounts and shapes of newly created seals.