Adjustment method of melt quality in fiber production process
A production process and adjustment method technology, applied in the direction of electrical program control, comprehensive factory control, comprehensive factory control, etc., can solve problems such as difficult to accurately predict the quality of polyester fiber melt
Active Publication Date: 2020-11-24
DONGHUA UNIV
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The purpose of the present invention is to provide a method that can accurately predict the melt quality in the polyester fiber production process and adjust the melt quality for the existing technology that is difficult to accurately predict the melt quality in the polyester fiber production process.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0112] A method for adjusting melt quality during fiber production, in which SVR is selected as the X model.
[0113] take as Figure 4 The 400 sets of real input and output temperature data in the melt conveying process shown in this example are respectively predicted by the prediction method, mechanism model prediction method, GRU prediction method and SVR prediction method of this example. The prediction results are shown in the figure Figure 6 As shown in the figure, True is the real value, HYB is the prediction result curve of this method, GRU is the prediction result curve of the GRU algorithm, SVR is the prediction result curve of the SVR algorithm, and ORG is the prediction result curve of the mechanism model;
[0114] The MSEs of each prediction method are as follows: the MSE of the method of the present invention is 5.84 × 10 -4 , the MSE of GRU is 6.25×10 -4 , the MSE of SVR is 1.64×10 -3 , the MSE of the mechanism model is 1.26×10 -3 . compare and observe F...
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
Login to View More Abstract
The invention relates to an adjusting method for melt quality during fiber production. A melt conveying process of fiber production can be divided into multiple sections according to elements that a melt flows through; prediction models can be established section by section; technological parameter data of the starting point of each section can be output to the prediction models; melt quality canbe adjusted according to the technological parameter data of the end and starting points of each section after the technological parameter data of the end point of the section is obtained through prediction; in the adjacent two sections, the output of the front section namely the melt first arrival section prediction model is the input of the rear section namely the melt post-arrival section prediction model; when a technological parameter data acquisition device is installed at some section, the prediction models are the mixing models, and conversely, the prediction models are mechanism models; and the mixing models are formed by the mechanism models and data driving models, the data driving models are formed by GRUs and X models, and the X models are SVR, BR neural networks or ELM. The method is high in prediction accuracy and can adjust the melt quality in real time, so that the stability of the melt quality can be guaranteed.
Description
technical field [0001] The invention belongs to the technical field of polyester fiber production control, and relates to a method for adjusting melt quality in the fiber production process, in particular to a method for segmentally integrating dynamic intelligent prediction of melt quality in the production process of polyester fiber based on a hybrid model and improving the quality of the melt. The method of body quality adjustment. Background technique [0002] Polyester fiber is commonly known as polyester (PET) fiber, which is a synthetic fiber obtained by spinning polyester obtained by polycondensation of organic dibasic acid and dibasic alcohol. Because polyester fiber has the characteristics of high strength, good elastic recovery ability, good wrinkle resistance and good shape retention, it is currently widely used in textile and industrial fields. [0003] With the development of society, people have higher and higher requirements for polyester fiber. Improving t...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G05B19/418
CPCY02P90/02
Inventor 郝矿荣龚龙浩王华平蔡欣陈磊任立红
Owner DONGHUA UNIV