Texturing Process Control Network for DTY Yarn Quality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The texturing process for Pre Oriented Yarn (POY) to Draw Textured Yarn (DTY) is complex, with parameter settings significantly impacting the quality of the final yarn spindle, and existing methods fail to optimize these parameters effectively, leading to potential defects in the final product.
Innovation Solution
A control method involving a control network with parameter prediction, index prediction, and data generation models to optimize texturing process parameters by predicting future parameters, selecting target parameters, and adjusting them based on index prediction results to ensure desired quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional control methods are used for the texturing process, then the process is simple to operate, but the manufacturing precision and product quality deteriorate due to inability to optimize parameters effectively
Solution Approach 1:
The system performs preliminary actions by collecting control parameters from multiple past moments and using them to predict future parameters before the actual processing occurs. The parameter prediction model forecasts future control parameters, and the index prediction model predicts quality indicators in advance, allowing operators to adjust parameters proactively to ensure desired yarn quality before defects occur.
Solution Approach 2:
The system implements feedback by using the index prediction model to evaluate predicted future parameters against desired quality standards. When the predicted index does not meet the desired value, the data generation model generates optimized control parameters that are fed back into the control system, creating a closed-loop feedback mechanism that continuously improves manufacturing precision.
2Manufacturing precision
If real-time parameter adjustment is implemented to improve product quality, then the manufacturing precision improves, but the loss of time increases due to complex data processing and model predictions
Solution Approach 1:
The system performs predictions in advance using historical data from multiple moments to forecast future parameters before the actual processing moment arrives. By collecting parameters from moments t-n to t-1 and predicting moment t, the system prepares optimized parameters proactively, reducing the need for time-consuming real-time adjustments during critical processing phases.
Solution Approach 2:
The system collects control parameters from multiple moments (t-n, t-n+1, ..., t-1) rather than just the immediate past, using an excessive amount of historical data to improve prediction accuracy. This partial action approach processes more data points than strictly necessary but ensures higher precision in parameter optimization, thereby improving yarn quality while managing time loss through efficient model processing.
3Manufacturing precision
If multiple control parameters from multiple moments are collected and processed, then the manufacturing precision improves through better parameter optimization, but the device complexity increases due to multiple models and data processing steps
Solution Approach 1:
The control system is segmented into three distinct functional modules: the parameter prediction model that forecasts future control parameters, the index prediction model that evaluates quality indicators, and the data generation model that optimizes parameters when needed. This segmentation allows each model to specialize in its specific function, improving overall manufacturing precision while organizing complexity into manageable, independent components that can be developed and maintained separately.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided is a control method for a texturing process, a training method for a control network and related apparatuses. The control method includes: sequentially collecting preset control parameters of a plurality of moments in the texturing process to obtain a first sequence (S201); inputting the first sequence into a parameter prediction model to predict prediction parameters of a plurality of future moments (S202); selecting a target parameter of a target moment from the prediction parameters (S203); building a second sequence containing the target parameter based on the control parameters before and after the target moment (S204); processing the second sequence based on an index prediction model to obtain an index prediction result (S205); and inputting the result into a data generation model in a case where the result does not meet a desired value, to obtain a desired control parameter for the target moment (S206).