Deep-Learning Parcel Insertion Control for Tipper Angle Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing parcel sorting systems face inefficiencies in parcel insertion and risk of damage due to manual handling and variable parcel weights and materials, necessitating improved automation and control mechanisms.
Innovation Solution
A deep learning-based parcel recognition algorithm integrated with a tipper and insertion line belt system to automatically adjust gradient angles and velocities based on parcel recognition, using multiple sensors to optimize parcel handling and minimize damage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual parcel insertion is used by multiple workers, then parcels can be inserted into the sorter, but insertion efficiency is low and labor costs increase
Solution Approach 1:
The system uses deep learning-based parcel recognition to automatically identify and track parcels, enabling the tipper mechanism to self-adjust its operations without manual intervention. The algorithm processes parcel images in real-time and autonomously controls the gradient angle adjustments, making the system self-sufficient in parcel handling operations.
Solution Approach 2:
The patent replaces manual mechanical insertion operations with an automated system combining computer vision (deep learning algorithms) and controlled mechanical movement (tipper mechanism). The recognition algorithm substitutes human visual inspection, while the automated gradient control replaces manual positioning, achieving higher efficiency and consistency.
2Productivity
If fast parcel insertion is performed to increase throughput, then processing speed increases, but parcel damage risk increases
Solution Approach 1:
The tipper mechanism dynamically adjusts its gradient angle based on real-time parcel recognition results. The system continuously monitors parcel position and characteristics, modifying the insertion angle and speed accordingly to match each parcel's specific properties, thereby preventing damage while maintaining efficient throughput.
Solution Approach 2:
The system changes operational parameters (gradient angle, insertion speed) based on parcel characteristics identified by the deep learning algorithm. By adapting these parameters to each parcel's size, shape, and fragility indicators, the system optimizes the balance between insertion speed and damage prevention.
3Manufacturing precision
If gradient angle of insertion line belt is adjusted to control parcel flow, then parcel handling precision improves, but system complexity increases
Solution Approach 1:
The system implements a closed-loop feedback mechanism where the deep learning algorithm continuously analyzes parcel images, compares actual positions with target positions, and adjusts the tipper gradient angle accordingly. This feedback loop enables precise parcel handling while automating the control complexity, making the sophisticated adjustments transparent to operators.
4Measurement precision
If multiple sensors are used to recognize parcel characteristics, then recognition accuracy improves, but device complexity and cost increase
Solution Approach 1:
The deep learning-based recognition algorithm serves multiple functions simultaneously: it identifies parcel characteristics, determines optimal gradient angles, tracks parcel position, and guides the insertion process. This multi-functional approach consolidates what would otherwise require multiple separate sensor systems into a single integrated software solution, reducing hardware complexity while maintaining high recognition accuracy.
Data Source
AI summary
Disclosed are an insertion automation method and system based on deep-learning parcel recognition. The insertion automation method includes determining an initial gradient change angular velocity of a tipper based on a total weight of parcels in the tipper, recognizing a loading state of the parcels in the tipper by inputting images of the parcels in the tipper to an object recognition model, and redetermining a gradient change angular velocity and gradient angle of the tipper based on the recognized loading state, in which the loading state of the parcels in the tipper includes at least one of a position, size, and packing material of the parcels in the tipper.