Winder Doffing Path Planning Using DSPCNN Road Topology
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In winding workshops, if yarn spindles on full tubes are not doffed in time, the tubes burst, causing the winder to stop working and potentially leading to damage, resulting in reduced production capacity.
Innovation Solution
A method using a Dual Source Pulse Coupled Neural Network (DSPCNN) to plan efficient doffing paths by constructing a road network topology structure of winder nodes, selecting source and target neurons, performing ignition calculations, and determining doffing paths based on pulse signal propagation and backtracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional doffing path planning is used, then the system is simple to implement, but the doffing time is long and production efficiency is reduced
Solution Approach 1:
The patent replaces traditional mechanical/path-based planning with a neural network-based cognitive system. The DSPCNN model uses pulse signal propagation and ignition calculations to intelligently determine optimal doffing paths, substituting complex manual planning with an automated neural computing approach that achieves faster processing and optimization.
Solution Approach 2:
The patent transforms the path planning problem by changing the representation parameters from physical coordinates to a topological graph structure with nodes and edges. This parameter transformation enables the use of neural network algorithms to process and optimize paths more efficiently, improving computational speed and path optimization capabilities.
2Productivity
If doffing is delayed, then the winder can continue working, but the tube will burst causing damage and production loss
Solution Approach 1:
The patent implements preliminary action by proactively planning and executing doffing operations before tube burst occurs. The system continuously monitors yarn spindle status and pre-calculates optimal doffing paths, ensuring that doffing is completed in advance rather than reactively responding to tube burst conditions.
Solution Approach 2:
The system incorporates feedback mechanisms that continuously monitor the status of yarn spindles and tube conditions, adjusting doffing paths and priorities in real-time. This feedback loop ensures that doffing operations are dynamically optimized based on actual production conditions, preventing tube burst while maintaining continuous operation.
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
A method and an apparatus for planning a doffing path, and a storage medium are provided, relating to the field of computer technology and the field of path planning technology. The method includes: constructing (S101) a road network topology structure according to positions of winders to be doffed, the road network topology structure including winder nodes, and one winder node corresponding to one winder; determining (S102) neurons in a DSPCNN according to the winder nodes, one winder node corresponding to one neuron; selecting (S103) a source neuron and a target neuron from the neurons; performing (S104) ignition calculation according to the source neuron and the target neuron to obtain a first path corresponding to the source neuron and a second path corresponding to the target neuron; and determining (S105) a doffing path of a winder node in the road network topology structure according to the first and second paths.