CN114088659B - Method for detecting abnormal near infrared spectrum waveform of fabric fiber component - Google Patents
Method for detecting abnormal near infrared spectrum waveform of fabric fiber component Download PDFInfo
- Publication number
- CN114088659B CN114088659B CN202111178115.6A CN202111178115A CN114088659B CN 114088659 B CN114088659 B CN 114088659B CN 202111178115 A CN202111178115 A CN 202111178115A CN 114088659 B CN114088659 B CN 114088659B
- Authority
- CN
- China
- Prior art keywords
- waveform
- near infrared
- information entropy
- smoothness
- fabric fiber
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000000835 fiber Substances 0.000 title claims abstract description 69
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 63
- 239000004744 fabric Substances 0.000 title claims abstract description 60
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000001228 spectrum Methods 0.000 claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000009499 grossing Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000009825 accumulation Methods 0.000 claims description 2
- 238000013479 data entry Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 15
- 238000005286 illumination Methods 0.000 abstract description 5
- 238000004140 cleaning Methods 0.000 abstract description 4
- 230000005672 electromagnetic field Effects 0.000 abstract description 3
- 239000002657 fibrous material Substances 0.000 abstract description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 239000004753 textile Substances 0.000 description 22
- 238000005516 engineering process Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 229920000297 Rayon Polymers 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 239000002964 rayon Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 235000012766 Cannabis sativa ssp. sativa var. sativa Nutrition 0.000 description 1
- 235000012765 Cannabis sativa ssp. sativa var. spontanea Nutrition 0.000 description 1
- 229920000742 Cotton Polymers 0.000 description 1
- 229920000433 Lyocell Polymers 0.000 description 1
- 238000004497 NIR spectroscopy Methods 0.000 description 1
- 239000004677 Nylon Substances 0.000 description 1
- 229920002334 Spandex Polymers 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 235000009120 camo Nutrition 0.000 description 1
- 210000000085 cashmere Anatomy 0.000 description 1
- 235000005607 chanvre indien Nutrition 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000011487 hemp Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000001320 near-infrared absorption spectroscopy Methods 0.000 description 1
- 229920001778 nylon Polymers 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 229920000728 polyester Polymers 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004759 spandex Substances 0.000 description 1
- 230000007847 structural defect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 210000002268 wool Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8444—Fibrous material
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Biochemistry (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Algebra (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a method for detecting abnormal near infrared spectrum waveforms of fabric fiber components, which combines the related principle of one-dimensional signal processing, designs a rapid and effective algorithm for detecting abnormal waveforms, and aims to detect abnormal waveforms generated by interference of factors such as external electromagnetic fields, illumination, manual operation and the like in the process of collecting near infrared spectrum data. The method comprehensively considers the smoothness threshold value and entropy information of the one-dimensional signal, can effectively focus abnormal data, and can solve the problem of non-logic data. The method can be applied to the data acquisition process, and abnormal acquisition information can be found in time; the method can also be applied to the data cleaning process to quickly locate the outlier position and effectively remove noise and distorted spectrum data. The anomaly detection algorithm is mainly aimed at fabric fiber materials, can effectively detect the anomaly waveform of near infrared spectrum data of fabric fiber components, and simultaneously changes parameters.
Description
Technical Field
The invention relates to the technical field of textile component analysis, in particular to a method for detecting abnormal near infrared spectrum waveforms of fabric fiber components.
Background
With the improvement of the living standard of people, more and more people begin to pursue the living quality, and as a part of 'clothing and eating residence', the problem of clothing quality is attracting more and more attention. In order to ensure that the textiles exported in China have higher quality standards and also that the quality of textiles used by people in China is qualified, the improvement of textile technology and related quality detection links are important for the whole textile industry.
The near infrared spectrometry of FZ/T01144-2018 textile fiber quantitative analysis is formally implemented on 1 month 7 in 2019, which marks that the textile component analysis method based on the near infrared spectrum enters an application stage from the research field. The traditional textile fiber component analysis method mainly adopts a chemical method and a physical method in the traditional, and the whole process of the two methods is exposed in the air, so that the two methods are easily affected by various external influences, and are combined with chemical reactions possibly occurring in the interior, so that errors are easily caused, the accuracy of the whole detection result is affected to a certain extent, and the accurate and reliable component analysis work cannot be performed.
Compared with the traditional textile fiber quality inspection mode, the method for analyzing the textile fiber components by using the near infrared spectroscopy has the advantages of being rapid and free of damage, and can realize accurate identification of different types of fibers and perform nondestructive cleaning qualitative and quantitative analysis on the textile fibers by preparing standard samples in the early stage and establishing a detection model. However, in the process of preparing the standard sample in the early stage, due to the influence of electromagnetic waves, illumination influence, personal misoperation and other reasons, abnormal waveforms are easily acquired in a data acquisition process, and the later modeling process is greatly influenced.
Outliers of abnormal near infrared spectral waveforms can be converted into important operational information, so it is important to screen them out. Outliers (outliers) are generally considered as data points that are significantly different from other data points or do not conform to the expected normal pattern of the overall represented phenomenon. The outlier detection technology aims at solving the problem of finding a mode which does not accord with expected behaviors, and the purpose of the patent is to detect outliers and focus abnormal information of near infrared spectrum waveforms in the field of textile fibers and aim at finding abnormal data in the acquisition process.
The patent designs a method for rapidly and effectively detecting abnormal waveforms by combining the related principles of one-dimensional signal processing and combining the detection method for the abnormal near infrared spectrum waveforms of the fabric fiber components, and can rapidly detect the abnormal waveforms generated by the interference of factors such as external electromagnetic fields, illumination, manual operation and the like. The method comprehensively considers the smoothness threshold value and entropy information of the one-dimensional signal, can effectively focus abnormal data, is applied to a data acquisition process, and timely finds abnormal acquisition information; the method can also be applied to the data cleaning process to effectively remove noise and distorted spectrum data. The anomaly detection algorithm is mainly aimed at fabric fiber materials, can effectively detect the anomaly waveform of near infrared spectrum data of fabric fiber components, and can be rapidly popularized to the anomaly waveform detection of one-dimensional near infrared spectrums of other materials by changing parameters. The detection method is nondestructive, clean, efficient, quick and low in cost, and can be used for laboratory analysis, field analysis and the like.
Disclosure of Invention
The invention aims to rapidly detect abnormal waveforms generated by interference of factors such as external electromagnetic fields, illumination, manual operation and the like in a near infrared textile fiber spectrum waveform data acquisition link. Abnormal data refers to sample points where some values in the sample deviate significantly from the remaining values, and so are also referred to as outliers. Anomaly detection is the finding of these outliers because their presence can present significant difficulties for subsequent data analysis and modeling processes. The invention provides a method for detecting abnormal near infrared spectrum waveforms of fabric fiber components by combining smoothness information of one-dimensional signals and an information entropy theory.
The method comprises a near infrared spectrum data acquisition module, a spectrum library module, an information entropy calculation module, a waveform smoothness calculation module, a threshold constraint module and an abnormal detection result output module. The near infrared equipment is used for collecting the spectrum information of the current textile; the data acquisition module is used for acquiring near infrared spectrum characteristics of textile materials, using near infrared spectrum equipment, requiring uniform acquisition environment, avoiding excessive external environment interference such as illumination, randomly selecting characteristic points of each piece of cloth, and recording spectrum data characteristics of each piece of cloth; the spectrum library module is used for storing the collected spectrum data, and the spectrum library has the significance that based on the database, data analysis and modeling are carried out, so that single data, combined data or all data can be conveniently searched and used; the deep information entropy calculation module is based on an information entropy theory and is used for calculating unitary and multi-element spectrum sequence information entropy; the waveform smoothness calculation module is used for calculating smoothness information of unitary and multi-element spectrum sequences; the constraint threshold module is used for judging whether the information entropy and the smoothness of the spectrum sequence to be determined are in a threshold range or not so as to judge whether the spectrum sequence is an abnormal waveform or not; and the abnormal detection result output module is used for acquiring and analyzing the result of the constraint threshold module, outputting a display result at the front end and determining whether the display result is stored in the spectrum database at the rear end.
According to the invention, the near infrared spectrum waveform data of twelve pure materials and mixed materials such as cotton, hemp, rayon (rayon), polyester fiber, nylon, wool, cashmere, spandex, tencel, silk and the like are collected and tested, and the method can be used for carrying out abnormal near infrared spectrum waveform analysis on textile fiber components of the fabric without damage and cleaning. The method is lossless and clean, is conveniently integrated on spectrum acquisition equipment, can be used as a part of an acquisition data module, and can also be used as a single algorithm to play a role in a data analysis stage. The abnormal near infrared spectrum waveform detection process of the method comprises the following steps:
s1: collecting a plurality of near infrared spectrum waveforms of the fabric fibers, and constructing a spectrum library;
s2: randomly selecting a plurality of waveforms of fabric fiber spectra, and calculating average information entropy and average waveform smoothness;
s21: and calculating the average information entropy of the near infrared spectrum waveform of the fabric fiber. The entropy is the result of the discretized addition of the probability function of the random variable throughout the distribution space. Randomly selecting m waveforms of fabric fiber spectra, and calculating the information entropy of the polynary variable, wherein the calculation formula is as follows:
the information entropy value is the result of randomly selecting a plurality of waveforms of the fabric fiber spectrum, so the information entropy value belongs to a relative concept, and is influenced by not only the distribution of variables but also a random distribution mode. And finally calculating average information entropy, wherein the formula is as follows:
s22: the average smoothness of the near infrared spectral waveform of the fabric fiber was calculated. Obtaining a smoothed curve by using a Savitzky-Golay least square smoothing filter algorithm, and then calculating the difference accumulation of the original curve and the smoothed curve by using the Savitzky-Golay least square smoothing filter algorithm to obtain the smoothed values of a plurality of waveforms of the fabric fiber spectrum;
the calculation formula of the Savitzky-Golay least squares smoothing filter algorithm is as follows:
s3: setting an information entropy threshold and a waveform smoothness threshold;
s31: and S2, repeating the step to obtain a plurality of average information entropies and average waveform smoothness. And respectively selecting an average value, a maximum value and a minimum value of the data, and setting an average information entropy threshold value and an average waveform smoothness threshold value.
S4: acquiring a near infrared spectrum waveform of the fabric fiber to be determined, and calculating the information entropy and the waveform smoothness of the fabric fiber to be determined;
s41: and calculating the information entropy of the near infrared spectrum waveform of the fabric fiber to be determined. Because the near infrared spectrum waveform of the fabric fiber to be determined is one-dimensional signal data, the univariate variable information is calculated
The entropy is expressed as follows:
s42: the waveform smoothness of the near infrared spectrum of the fabric fiber to be determined is calculated. And obtaining a smoothed curve by using a Savitzky-Golay least square smoothing filter algorithm, and then calculating the difference value between the original curve and the curve smoothed by the Savitzky-Golay least square smoothing filter algorithm to obtain a smoothed value of the fiber spectrum waveform of the fabric to be determined, wherein the calculation formula is the same as the Savitzky-Golay least square smoothing filter formula in S22.
S5: comparing the information entropy and the waveform smoothness of the fabric fiber to be determined with the average information entropy threshold and the waveform smoothness threshold of the spectrum library determined in the step S3, and eliminating abnormal waveforms when the information entropy and the waveform smoothness threshold are not in the threshold interval;
s51: comparing the smoothness of the undetermined fabric fiber with the average smoothness threshold value of the fabric fiber spectrum library determined in the step S3, and outputting a Boolean value False within the smoothness threshold value; outputting a Boolean value True which is not in the smoothness threshold value interval, and recognizing the Boolean value True as abnormal wave rejection;
s52: comparing the information entropy of the fabric fiber to be determined with the average information entropy threshold value of the spectrum library determined in the step S3, and outputting a Boolean value False within the smoothness threshold value; outputting a Boolean value True which is not in the information entropy threshold interval, and regarding the Boolean value True as an abnormal waveform;
s6: the system notifies whether it is abnormal waveform data, and the database stores normal waveforms.
S61: respectively obtaining the smoothness analysis and the information entropy analysis results of S51 and S52;
s62: if the output results of the smoothness and the information entropy are False, the detection result is normal, the front end displays normal waveforms, the acquisition can be continued, the rear end stores the acquisition result in a database, and the successful identification of data entry is prompted;
s63: if one of the output results of the smoothness and the information entropy is True, the abnormal waveform is detected, the waveform is displayed at the front end, the waveform is collected again, the result is not recorded in the rear-end database, and log information is stored.
Drawings
The present application is described in further detail below with reference to the drawings and detailed description.
FIG. 1 is a schematic diagram showing the detection effect of the abnormal near infrared spectrum waveform of the present invention.
FIG. 2 is a flowchart of the detection of abnormal near infrared spectrum waveforms according to the present invention.
Fig. 3 is a technical framework of the present invention.
Detailed Description
The following describes in further detail the embodiments of the present invention with reference to the drawings and examples. However, the present invention should be understood not to be limited to such an embodiment described below, and the technical idea of the present invention may be implemented in combination with other known technologies or other technologies having the same functions as those of the known technologies. The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
In the following description of the specific embodiments, for the sake of clarity in explaining the structure and operation of the present invention, description will be given by way of directional terms, but words of front, rear, left, right, outer, inner, outer, inner, axial, radial, etc. are words of convenience and are not to be construed as limiting terms.
The relevant terms are explained as follows:
data cleansing (Data cleansing): the process of re-examining and checking data aims to remove duplicate information, correct errors that exist, and provide data consistency.
Anomaly detection (Anomaly Detection): identification of items, events, or observations that do not conform to the expected patterns or other items in the dataset. Often abnormal items translate into problems of the type of banking fraud, structural defects, medical problems, text errors, etc. Anomalies are also known as outliers, novelty, noise, bias, and exceptions.
Entropy (entropy): in information theory, entropy is the average amount of information contained in each message received, also known as information entropy, source entropy, average self-information amount. Here, "message" represents an event, sample, or feature from a distribution or data stream. Entropy is understood to be a measure of uncertainty, as the more random sources have a greater entropy.
Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
As shown in fig. 1, fig. 1 is a flowchart of the detection of an abnormal near infrared spectrum waveform provided by the present invention, in which the detection of an abnormal near infrared spectrum waveform of a fabric fiber is described in detail. The abnormal near infrared spectrum waveform detection method mainly comprises two parts, wherein the first part is the preparation work of a smoothness threshold value and an information entropy threshold value, and the second part is the detection work of the abnormal near infrared spectrum waveform of the fiber of the fabric to be determined.
The preparation work of the smoothness threshold value and the information entropy threshold value of the method is carried out according to the following steps:
step 1: collecting near infrared spectrum characteristics of textile fiber components, and recording the near infrared spectrum characteristics into a spectrum library;
step 2: randomly selecting part of near infrared spectrum characteristics from a spectrum library and marking the near infrared spectrum characteristics as a group;
step 3: calculating average smoothness information of the random near infrared spectrum characteristic group in the step 2;
step 4: calculating average information entropy information of the random near infrared spectrum characteristic group in the step 2;
step 5: repeating the step 3 and the step 4 to obtain a smoothness threshold value and an information entropy threshold value which are used as normal detection threshold values for detecting abnormal near infrared spectrum waveforms;
the method comprises the steps of collecting near infrared spectrum characteristics of textile fiber components, wherein the step one is that an acquirer is required to ensure the standard of the collection process, the spectrum characteristics recorded in a spectrum library are ensured to be normal as far as possible, and if the condition that the absorptivity or the reflectivity is smaller than 0 or obvious saw tooth condition exists, the recording of the database is stopped, and the near infrared spectrum information of the textile fiber is collected again;
and step three, calculating the average smoothness information, and calculating the smoothness characteristics of the one-dimensional spectrum data by using a segmentation Savitzky-Golay smoothing algorithm of the signals. The segmented Savitzky-Golay algorithm of the signal is a polynomial smoothing algorithm based on the least squares principle, also known as convolutional smoothing. The principle is that 5 points with equal wavelength intervals in a section of a spectrum are marked as an X set, polynomial smoothing is to replace m points by using polynomial fitting values of data of which the wavelength points are m points left two, m points left one, m points right one and m points right two, and then the polynomial fitting values are sequentially moved until the spectrum signal is traversed. The curve smoothness of each signal data of the group is calculated and its average is calculated as the average smoothness value of the group. The calculation formula is as follows:
the average information entropy calculation of the one-dimensional spectrum data in the fourth step uses the information entropy theory content. The information entropy (entropy) herein is an average amount of information contained in the received near infrared spectrum waveform data, and is also referred to as source entropy, average self-information amount. "message" here represents a sample or feature from a distribution or data stream. Information entropy can be a measure of uncertainty because the more random sources have greater entropy. Randomly selecting m waveforms of fabric fiber spectrums, and calculating multi-variable information entropy, wherein the calculation formula is as follows:
the information entropy value is the result of randomly selecting a plurality of waveforms of the fabric fiber spectrum, so the information entropy value belongs to a relative concept, and is influenced by not only the distribution of variables but also a random grouping mode. And finally calculating average information entropy, wherein the formula is as follows:
the detection work of the fabric fiber abnormal near infrared spectrum waveform is carried out according to the following steps:
step 1: collecting near infrared spectrum characteristics of textile fiber components;
step 2: calculating the smoothness of the near infrared spectrum waveform to be measured;
step 3: comparing the smoothness value obtained in the step (2) with an average smoothness threshold value, and if the smoothness value is within a threshold value interval, calculating the information entropy of the next step; if the data is not within the threshold value, screening out abnormal data, and prompting to re-acquire at the front end;
step 4: calculating the information entropy of the near infrared spectrum waveform to be measured;
step 5: comparing the smoothness value obtained in the step 4 with an average smoothness threshold value, and if the smoothness value is within the threshold value interval, storing the smoothness value into a spectrum database to prompt that the data acquisition is successful; if the data is not within the threshold value, the abnormal data is screened out, and the front end prompts to re-acquire.
Fig. 2 is a graph showing the detection effect of the abnormal near infrared spectrum waveform of the present invention. Near infrared spectral characteristics of the fabric fibers in the 900 to 1700 nanometer band are acquired. Noise or erroneous data exist in the textile near infrared spectrum database, namely abnormal waveforms of the near infrared spectrum data need to be detected, and according to the near infrared spectrum characteristics of the textile, automatic check is performed on the basis of indexes such as one-dimensional signal smoothness, one-dimensional signal information entropy and the like, and further check can be performed during manual acquisition. Fig. 2 shows the partial anomaly data that is being examined.
Fig. 3 shows a frame diagram of an abnormal near infrared spectrum waveform detection method for fabric fiber components provided by the invention. The method comprises the steps of generating an average smoothness threshold value of a spectrum library, generating an average information entropy threshold value, and detecting abnormal near infrared spectrum waveforms in a real-time user acquisition process.
The foregoing is merely a preferred embodiment of the present application, and it should be noted that modifications and substitutions can be made by those skilled in the art without departing from the technical principles of the present application, and these modifications and substitutions should also be considered as being within the scope of the present application.
Claims (1)
1. The method for detecting the abnormal near infrared spectrum waveform of the fabric fiber component is characterized by comprising the following steps of:
s1: collecting a plurality of near infrared spectrum waveforms of the fabric fibers, and constructing a spectrum library;
s2: randomly selecting a plurality of waveforms of fabric fiber spectra, and calculating average information entropy and average waveform smoothness;
s3: repeating the step S2, and setting an information entropy threshold and a waveform smoothness threshold;
s4: acquiring a near infrared spectrum waveform of the fabric fiber to be determined, and calculating the information entropy and the waveform smoothness of the fabric fiber to be determined;
s5: comparing the information entropy and the waveform smoothness of the fabric fiber to be determined with the average information entropy threshold and the waveform smoothness threshold of the spectrum library determined in the step S3, and eliminating abnormal waveforms when the information entropy and the waveform smoothness threshold are not in the threshold interval;
s6: the system notifies whether it is abnormal waveform data, the database stores normal waveforms,
step S2 in the method for detecting abnormal near infrared spectrum waveform of fabric fiber component further comprises:
s21: calculating the average information entropy of the fabric fiber near infrared spectrum waveform, wherein the information entropy is the result of discretization summation of probability functions of random variables in the whole distribution space, randomly selecting m waveforms of the fabric fiber spectrum, and calculating the multi-variable information entropy, wherein the calculation formula is as follows:
the information entropy value is the result of randomly selecting a plurality of waveforms of fabric fiber spectrum, so the information entropy value belongs to a relative concept, is influenced by the distribution of variables, is influenced by a random distribution mode, and finally calculates the average information entropy, and has the following formula:
s22: calculating the average smoothness of the near infrared spectrum waveform of the fabric fiber, obtaining a smoothed curve by using a Savitzky-Golay least squares smoothing filter algorithm, and then calculating the difference accumulation of the original curve and the curve smoothed by the Savitzky-Golay least squares smoothing filter algorithm to obtain the smoothed values of a plurality of waveforms of the fabric fiber spectrum;
the calculation formula of the Savitzky-Golay least squares smoothing filter algorithm is as follows:
step S3 in the method for detecting abnormal near infrared spectrum waveform of fabric fiber component further comprises:
s31: repeating step S2 to obtain multiple average information entropy and average waveform smoothness, respectively selecting average value, maximum value and minimum value, setting average information entropy threshold and average waveform smoothness threshold as the standard of abnormal waveform screening in the subsequent step,
step S4 in the method for detecting abnormal near infrared spectrum waveform of fabric fiber component further comprises:
s41: the near infrared spectrum waveform information entropy of the fabric fiber to be determined is calculated, and because the near infrared spectrum waveform of the fabric fiber to be determined is one-dimensional signal data, the unitary variable information entropy is calculated according to the following formula:
s42: calculating the waveform smoothness of the near infrared spectrum of the fiber of the fabric to be determined, obtaining a smoothed curve by using a Sayitzky-Golay least square smoothing filter algorithm, then calculating the difference between the original curve and the curve smoothed by the Sayitzky-Golay least square smoothing filter algorithm to obtain a smoothed value of the fiber spectrum waveform of the fabric to be determined, wherein the calculation formula is the same as the Savitzky-Golay least square smoothing filter formula in S22,
step S5 in the method for detecting abnormal near infrared spectrum waveform of fabric fiber component further comprises:
s51: comparing the smoothness of the undetermined fabric fiber with the average smoothness threshold value of the fabric fiber spectrum library determined in the step S3, and outputting a Boolean value False within the smoothness threshold value; outputting a Boolean value True which is not in the smoothness threshold value interval, and recognizing the Boolean value True as abnormal wave rejection;
s52: comparing the information entropy of the fabric fiber to be determined with the average information entropy threshold value of the spectrum library determined in the step S3, and outputting a Boolean value False within the smoothness threshold value; the boolean value True is output, which is not within the information entropy threshold interval, as an abnormal waveform,
step S6 in the method for detecting abnormal near infrared spectrum waveform of fabric fiber component further comprises:
s61: respectively obtaining an analysis result of the smoothness of S51 and an analysis result of the information entropy of S52;
s62: if the output results of the smoothness and the information entropy are False, the detection result is normal, the front end displays normal waveforms, the acquisition can be continued, the rear end stores the acquisition result in a database, and the successful identification of data entry is prompted;
s63: if the arbitrary value of the output results of the smoothness and the information entropy is True, the abnormal waveform is detected, the waveform is displayed at the front end, the waveform is collected again, the result is not recorded in the rear-end database, and log information is stored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111178115.6A CN114088659B (en) | 2021-10-09 | 2021-10-09 | Method for detecting abnormal near infrared spectrum waveform of fabric fiber component |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111178115.6A CN114088659B (en) | 2021-10-09 | 2021-10-09 | Method for detecting abnormal near infrared spectrum waveform of fabric fiber component |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114088659A CN114088659A (en) | 2022-02-25 |
| CN114088659B true CN114088659B (en) | 2024-04-16 |
Family
ID=80296656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111178115.6A Active CN114088659B (en) | 2021-10-09 | 2021-10-09 | Method for detecting abnormal near infrared spectrum waveform of fabric fiber component |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114088659B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110987866A (en) * | 2019-12-19 | 2020-04-10 | 汉谷云智(武汉)科技有限公司 | Gasoline property evaluation method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103823980A (en) * | 2014-02-26 | 2014-05-28 | 浙江水利水电学院 | Method for detecting abnormal dam monitoring data based on entropy theory |
| WO2018010352A1 (en) * | 2016-07-11 | 2018-01-18 | 上海创和亿电子科技发展有限公司 | Qualitative and quantitative combined method for constructing near infrared quantitative model |
| KR101872240B1 (en) * | 2017-01-26 | 2018-06-29 | 서울대학교산학협력단 | Imaging measurement method using hyperspectral imaging measurement apparatus |
| CN113340822A (en) * | 2021-06-23 | 2021-09-03 | 浙江启真信息科技有限公司 | Automatic calibration spectrum acquisition method, device and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11175589B2 (en) * | 2013-06-03 | 2021-11-16 | Kla Corporation | Automatic wavelength or angle pruning for optical metrology |
-
2021
- 2021-10-09 CN CN202111178115.6A patent/CN114088659B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103823980A (en) * | 2014-02-26 | 2014-05-28 | 浙江水利水电学院 | Method for detecting abnormal dam monitoring data based on entropy theory |
| WO2018010352A1 (en) * | 2016-07-11 | 2018-01-18 | 上海创和亿电子科技发展有限公司 | Qualitative and quantitative combined method for constructing near infrared quantitative model |
| KR101872240B1 (en) * | 2017-01-26 | 2018-06-29 | 서울대학교산학협력단 | Imaging measurement method using hyperspectral imaging measurement apparatus |
| CN113340822A (en) * | 2021-06-23 | 2021-09-03 | 浙江启真信息科技有限公司 | Automatic calibration spectrum acquisition method, device and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114088659A (en) | 2022-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU745828B2 (en) | System for surveillance of spectral signals | |
| Mäkelä et al. | Machine vision estimates the polyester content in recyclable waste textiles | |
| TWI691914B (en) | Method for automated classification, and apparatus, system and computer-readable medium thereof | |
| JP4394286B2 (en) | Multidimensional method and system for statistical process management | |
| CN107478598A (en) | A kind of near-infrared spectral analytical method based on one-dimensional convolutional neural networks | |
| CN108267414B (en) | Near infrared spectrum analysis method for textile fiber content | |
| US7127372B2 (en) | Retro-regression residual remediation for spectral/signal identification | |
| US20210247367A1 (en) | Workflow-based model optimization method for vibrational spectral analysis | |
| CN114088659B (en) | Method for detecting abnormal near infrared spectrum waveform of fabric fiber component | |
| CN107247033B (en) | Identify the method for Huanghua Pear maturity based on rapid decay formula life cycle algorithm and PLSDA | |
| US20180067048A1 (en) | Unknown Sample Determining Method, Unknown Sample Determining Instrument, and Unknown Sample Determining Program | |
| CN112834481B (en) | Raman spectrum enhancement measurement system and measurement method | |
| CN114112982A (en) | Fabric fiber component qualitative method based on k-Shape | |
| CN113686804A (en) | Textile fiber component nondestructive cleaning analysis method based on deep regression network | |
| JP4315975B2 (en) | Noise component removal method | |
| Sun et al. | Variables selection for quantitative determination of cotton content in textile blends by near infrared spectroscopy | |
| CN116985183A (en) | Quality monitoring and management method and system for near infrared spectrum analyzer | |
| CN115406852A (en) | Fabric fiber component qualitative method based on multi-label convolutional neural network | |
| CN116026808A (en) | Raman spectrum discrimination method and system | |
| CN113435115B (en) | Fluorescence spectrum characteristic wavelength screening method, fluorescence spectrum characteristic wavelength screening device, computer equipment and readable storage medium | |
| CN112104340B (en) | HMM model and Kalman filtering technology-based switching value input module BIT false alarm reduction method | |
| CN114324294A (en) | Multi-probe gas Raman spectrum system and mixed gas quantitative analysis method | |
| CN113791062A (en) | Method for judging fixed substance type based on Raman spectrum | |
| CN114264626A (en) | Fabric nondestructive quantitative analysis method based on time series residual error network | |
| CN112666094A (en) | Common toxin recognition system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |