Automated Flatwork Feeding via Neural Network Corner Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The automation of industrial laundry processes is hindered by the difficulty in accurately and reliably aligning and feeding flatwork items, such as sheets and towels, into transport conveyors or treating devices, which is typically done manually, being labor-intensive and time-consuming.
Innovation Solution
A method utilizing a neural network to recognize and determine the position and orientation of corners in flatwork items, enabling automated gripping and feeding through the use of guided rollers and grippers to achieve a horizontal orientation, allowing precise alignment and handling of flatwork items.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual alignment and feeding of flatwork items is used, then ease of operation is maintained, but productivity is reduced and labor costs increase
Solution Approach 1:
The patent replaces manual mechanical alignment operations with an automated system comprising imaging devices for detection, neural networks for corner recognition and position determination, and computer-controlled grippers for precise positioning. This substitution enables high-speed automated feeding while maintaining alignment accuracy through digital image processing and automated control algorithms.
2Productivity
If automated feeding system is implemented, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent employs multi-functional integrated components: imaging devices that both capture images and provide positioning information, neural networks that perform both corner recognition and orientation determination, and grippers that combine gripping and positioning functions. This multi-functionality reduces the number of separate components needed, thereby managing system complexity while achieving high automation.
Solution Approach 2:
The system uses the flatwork item itself (specifically its corners and edges) as the reference for alignment and positioning, eliminating the need for external fixtures or pre-marked alignment features. The neural network automatically identifies corners and calculates positions without human intervention, making the system self-sufficient and reducing operational complexity.
3Manufacturing precision
If corner recognition is used for alignment, then manufacturing precision is improved, but measurement precision requirements increase
Solution Approach 1:
The patent performs preliminary capture of images of the flatwork item before the actual feeding operation. The neural network processes these images in advance to determine corner positions and orientations, allowing the system to pre-calculate the required gripper positions and movements. This preliminary processing enables high precision alignment while giving the measurement system adequate time to achieve accurate corner detection without rushing the measurement process.
Data Source
Figure 1
Figure 2
Figure 3a~3b
AI summary
The invention relates to a system and method for feeding a flatwork item to a transport conveyor and/or a flatwork treating device. Therefore first and second corners of a flatwork item are detected and first and second grippers are used to grip a detected first or second corner of the flatwork item which can subsequently be fed to a transport conveyor and/or a flatwork treating device.