Fabric air permeability analysis method based on SVM (support vector machine)
An analysis method and air permeability technology, applied in the direction of analysis materials, instruments, etc., can solve the problem of low data accuracy and so on
Inactive Publication Date: 2014-07-02
NINGBO INST OF TECH ZHEJIANG UNIV ZHEJIANG
View PDF1 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The main purpose of the present invention is to solve the defect that the accuracy of air flow and pressure difference data between nozzles is not high through power function modeling analysis in the existing fabric air flow measurement and analysis process, and proposes the modeling of fabric air flow based on SVM to improve Fitting Accuracy and Prediction Accuracy
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 Construction
[0017] The present invention proposes the fabric air flow analysis method based on SVM, and it comprises the following steps: (1) measure the air flow of different nozzles at different pressure differences, set up the pressure difference-air flow data sets of different nozzles; (2) collect the Preprocessing the pressure difference-air flow data; data preprocessing includes eliminating the singular data of pressure difference-air flow, and normalizing the pressure difference-air flow data, the expression of data normalization is X represents the data before processing; X* represents the normalized data; Xmin represents the minimum value of the data to be normalized; Xmax represents the maximum value of the normalized data; (3) Select the radial basis RBF kernel function , use the genetic algorithm to optimize the penalty parameter C and kernel parameter g of the SVM air flow model of different nozzles; specifically, first establish the initial SVM regression prediction model, i...
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 discloses a fabric air permeability analysis method based on an SVM (support vector machine). The fabric air permeability analysis method comprises the following steps of (1) measuring the air permeability of different nozzles under different pressure differences to establish pressure difference-air permeability data sets of different nozzles; (2) preprocessing acquired pressure difference-air permeability data; (3) selecting a RBF (radial basis function) kernel function, and performing optimal selection on a penalty parameter C and a kernel parmeter g of an SVM air permeability model of different nozzles by a genetic algorithm; (4) constructing SVM forecasting models corresponding to pressure difference-air permeability under a condition of different nozzles according to optimal parameters obtained in the third step and data obtained in the second step; and (5) performing air permeability analysis on pressure difference parameters, acquired in real time, at two ends of the nozzles through the model obtained in the fourth step, and performing reverse normalization processing on analysis data to obtain the air permeability of a fabric. According to the technical scheme disclosed by the invention, the method for analyzing and calculating the air permeability of the fabric based on the SVM model is creatively provided; the shortcomings that the air permeability, calculated according to conventional pressure difference data, of the fabric is low, and the model is inaccurate are overcome.
Description
technical field [0001] The invention belongs to the field of automatic detection of textiles, in particular to a method for analyzing the air permeability of fabrics using the SVM principle and method. Background technique [0002] Fabric air permeability refers to the performance of air passing through the pores of the fabric when there is a pressure difference on both sides of the fabric. The air permeability of the fabric is usually expressed by air permeability. Air permeability refers to the volume of air passing through a unit area of the fabric per unit time under a specified pressure difference on both sides of the fabric. There are two ways for air to pass through the fabric: (1) the gap between the yarns of the fabric; (2) the gap between the fibers in the yarn, generally the gap between the yarns is the main way. The size of air permeability is directly related to the quality of fabric comfort. Therefore, the size of the air permeability is an important index ...
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 Applications(China)
IPC IPC(8): G01N7/10
Inventor 吴飞青俞恩军张科峰
Owner NINGBO INST OF TECH ZHEJIANG UNIV ZHEJIANG