Fixtureless Wheel Mounting on Moving Vehicles Using AI Vision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automating the wheel mounting process in vehicle assembly is challenging due to unique alignment issues and inconsistencies in wheel and hub arrangements, requiring manual adjustments for precise alignment.
Innovation Solution
A system utilizing machine vision components and AI to identify mounting points on partially assembled vehicles in motion, enabling fixtureless wheel mounting through synchronized robot operation and lug nut placement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual wheel mounting is used with visual adjustment, then alignment precision is improved, but productivity decreases and automation extent is reduced
Solution Approach 1:
The patent replaces manual mechanical alignment operations with an automated system comprising machine vision components (cameras) and AI-based image processing. The system captures images of wheel and hub features, automatically identifies mounting points through computer vision algorithms, and guides robotic placement, thereby substituting human visual adjustment with automated optical-mechanical systems that achieve both precision and high productivity
Solution Approach 2:
The system enables self-alignment by automatically detecting wheel and hub geometries, identifying stud positions and hole locations, and calculating optimal mounting parameters without human intervention. The AI-based image processing autonomously adapts to variations in wheel and hub presentations, allowing the system to serve itself in achieving precise alignment across diverse configurations
2Adaptability or versatility
If fixtureless mounting is implemented, then device complexity is reduced and adaptability is improved, but measurement precision requirements increase
Solution Approach 1:
The patent replaces physical fixtures with a vision-based measurement and positioning system. Machine vision components capture high-resolution images of wheel and hub features, and AI-based image processing algorithms precisely identify mounting points, stud locations, and geometric features. This optical substitution eliminates the need for mechanical fixtures while achieving superior adaptability to variations and sufficient measurement precision through advanced image analysis
Solution Approach 2:
The system changes the measurement parameter from physical contact (fixtures) to optical field (camera imaging). By capturing images and processing them through AI algorithms, the system extracts precise geometric parameters including wheel center position, hub stud locations, and hole patterns. This parameter transformation enables fixtureless operation with high measurement precision across varying wheel and hub configurations
Data Source
AI summary
Systems and methods for installing components to other components in motion using machine vision systems and an artificial intelligence derived model are provided. Robots pick up the first component, move it through the work area alongside a conveying subassembly with the second component at matched speed and position, and synchronously place the first component at the second component under the command of a controller based on data received from sensors and machine vision systems regarding speed and position of the second component in the work area and surface feature position information for one or both of the first and second component. At least the machine vision data is processed by an artificial intelligence derived model to calculate offsets between the measured surface feature positions and reference surface feature positions to achieve the synchronous installation.