Unlock instant, AI-driven research and patent intelligence for your innovation.

Polyamide fiber production process based on brain-like memory gru

A polyamide fiber and production process technology, applied in the field of polyamide fiber production process based on brain-like memory GRU, can solve problems such as gaps

Active Publication Date: 2020-01-17
DONGHUA UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there is a big gap between the performance of polyamide fiber precursors that can be realized and the performance that can be achieved in theory, and there are still arduous tasks for the research on the production process and control system of polyamide fibers

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Polyamide fiber production process based on brain-like memory gru
  • Polyamide fiber production process based on brain-like memory gru
  • Polyamide fiber production process based on brain-like memory gru

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0087] In this embodiment, a public time series data set is used, and four other different prediction methods are used to conduct comparative experiments with the method of the present invention. Simulation results such as Figure 7 , where the abscissa represents the number of experiments, and the ordinate represents the mean square error between the predicted result and the actual result. The smaller the value, the better the prediction effect of the model. Model 1 refers to the GRU network, model 2 refers to the dual-stream parallel GRU network, model 3 refers to the dual-stream parallel SwishGRU network, model 4 refers to the dual-stream parallel MSwishGRU model, and model 5 refers to the brain-like memory-based GRU neural network model of the present invention.

[0088] Among them, SwishGRU refers to changing the activation function of the GRU model from the tanh function to the Swish function; the specific calculation formula of MSwishGRU is as follows:

[0089] z t =σ...

Embodiment 2

[0094] In this embodiment, the four process parameter data sets of spinning temperature and speed and blowing temperature and speed of the polyamide fiber spinning process are used for simulation. The simulation results are as follows: Figure 8 shown. The abscissa indicates the number of experiments, and the ordinate indicates the mean square error between the predicted result and the actual result. The smaller the value, the better the prediction effect of the model. Model 1 in the figure refers to the initial GRU neural network model, and model 5 refers to the brain-like memory-based GRU neural network model of the present invention. from Figure 8 It can be seen from the figure that the prediction method of the present invention has higher prediction accuracy and better effect.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a polyamide fiber production technology based on a brain-inspired memory GRU. The polyamide fiber production technology comprises the steps that (1) a GRU neural network model based on the brain-inspired memory is established; (2) the polyamide fiber spinning process parameters of the historical moments are compiled into samples according to the time order to act as the input value of the model, the value of the (k+1)th moment is predicted by using the values of the previous k moments, the output value of the model is compared with the actual value of the (k+1)th moment,and model training is ended if the error of the mean square of the two values is within 0.001, or the hyper-parameter of the model is adjusted until the error of the mean square is within 0.001; (3)the process parameter of the current moment is inputted to the prediction model, and the obtained prediction result is the polyamide fiber spinning process parameter of the next moment; and (4) the polyamide fiber spinning process is adjusted according to the prediction result. The model has the nonlinearity and the dual-flow parallelism of the memory content and meets the brain memory characteristics so as to better guide production and have high application prospect.

Description

technical field [0001] The invention belongs to the field of polyamide fiber production, in particular to a polyamide fiber production process based on brain-like memory GRU. Background technique [0002] Polyamide fiber is the earliest industrialized synthetic fiber variety in the world. It has excellent strength, wear resistance, elastic recovery rate, and hygroscopicity. fiber. There are many kinds of polyamide fibers, the main varieties are polyamide 6 (PA6) fiber and polyamide 66 (PA66) fiber, accounting for about 98% of the total. [0003] Polyamide fiber adopts the melt spinning method, and its production process is complicated and has many links, so it is relatively difficult to predict the process parameters of the production process. The production process of polyamide fiber mainly includes three parts: polymerization, spinning, and post-processing. After analyzing many factors that restrict the development of polyamide fiber, relevant researchers agree that the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 郝矿荣谢锐敏陈磊丁永生
Owner DONGHUA UNIV