Construction method of a friction acoustic wave discriminator for textile fabrics
A technology of textile fabrics and construction methods, which is applied to the use of sound waves/ultrasonic waves/infrasonic waves to analyze solids, instruments, and analytical materials, etc., and can solve problems such as complexity, subjectivity and error-prone hand-feeling visual inspection methods, and destructive testing operations.
Inactive Publication Date: 2020-09-29
ZHEJIANG SCI-TECH UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The visual inspection method is highly subjective and error-prone, the combustion method and the chemical reagent method are destructive detection and the operation is complicated, and the spectral analysis method is expensive
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
[0029] The present invention will be further described below in conjunction with the accompanying drawings of the description.
[0030] exist figure 1 In , typical examples of fabric friction acoustic signals are given, and the fabric components are wool, cotton, silk, and polyester in sequence. Eight samples were collected for each fabric friction sound wave, a total of 4 groups of 32 samples. To construct a friction acoustic wave discriminator for wool fabric, the friction acoustic wave signal of wool fabric is used as positive samples, and the rest are negative samples, namely 8 positive samples and 24 negative samples. The sampling rate is 8KHz, each sample contains 8000 data.
[0031] exist figure 2 In , the calculated feature space of each sample is given. The feature space of the series of samples includes 8000×8000=64,000,000 feature points, and a discriminator is constructed for each feature point. Taking the discriminator D(1,1) as an example, the value of each...
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 construction method of a textile fabric friction sound wave discriminator. The present invention calculates the Haar feature space for the acoustic wave signal, builds a discriminator on each feature point in the feature space, and determines the threshold value of the discriminator according to the principle of "passing all positive samples and minimizing negative sample misjudgments"; for each discriminator The discriminator is scored, and the one with the highest score is picked to build a discriminator queue. By continuously adjusting the weight of the misjudged negative samples, the picking process is biased, thereby forming an efficient progressive discriminator queue. The method provided by the invention can be used to classify textile fabrics according to friction sound waves, as a supplement to the current textile fabric classification methods.
Description
technical field [0001] The invention belongs to the technical field of textile engineering, and in particular relates to a construction method of a textile fabric friction sound wave discriminator. Background technique [0002] Existing fabric detection and classification methods include visual inspection, combustion, chemical reagents and spectral analysis. The visual inspection method is highly subjective and error-prone, the combustion method and the chemical reagent method are destructive detection and the operation is complicated, and the spectral analysis method is expensive. Textile fabrics have different frictional acoustic signal characteristics due to different materials, and the classification of fabrics by frictional acoustic waves can be used as a supplement to the existing methods. The premise and key of fabric classification by friction acoustic wave is the construction of friction acoustic wave discriminator. Contents of the invention [0003] As a supple...
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): G06K9/62G01N29/04
CPCG01N29/04G01N2291/023G06F18/24
Inventor 陶晨周赳
Owner ZHEJIANG SCI-TECH UNIV