Method and apparatus for predetermining yarn dyeing performance, electronic device and computer-readable storage medium

Abstract

To provide a method and apparatus for predetermining yarn dyeing performance, an electronic device and a computer-readable storage medium.SOLUTION: A method includes: defining a yarn normally dyed for a yarn to be determined; performing spectral detection on the yarn normally dyed to obtain first spectral information; calculating a covariance by performing simulation through a Gaussian process kernel; obtaining a plurality of pieces of continuous second spectrum information for the yarn to be determined; and establishing a Gaussian process regression model; obtaining third spectrum information for a yarn to be detected; subtracting a matrix of the third spectral information and a matrix of the second spectral information; and determining yarn dyeing performance according to numerals of the matrix value obtained by the subtraction.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent manufacturing, and particularly to an intelligent detection technology for the dyeing performance of yarns.

Background Art

[0002] In the production of yarns (such as polyester filament yarns) used in spinning and printing and dyeing, the determination of their dyeing performance generally involves winding the yarn onto a winding package, dropping it, and then performing an extraction inspection. The detection method generally involves manually determining using the hosiery dyeing method. Such a method has the defects of being slow and having a large error in manual determination. During the operation period of the production line, products with unqualified dyeing performance cannot be timely found, and the production enterprise cannot timely adjust the production conditions. Moreover, the number of defective products increases, the quality of the products decreases, and the grade related to product sales is affected. In addition, such a manual extraction inspection method has the possibility of inspection omission and determination omission, which causes economic losses to downstream manufacturers.

[0003] Therefore, in the industry, there is a need for a detection method that can accurately, timely, and completely detect the dyeing performance of yarns online.

Summary of the Invention

Means for Solving the Problems

[0004] The present disclosure provides a method and apparatus for pre-determining the dyeing performance of yarns, an electronic device, and a computer-readable storage medium for timely determining the dyeing performance of yarns in a simple and reliable manner.

[0005] According to one aspect of the present disclosure, a method for pre-determining the dyeing performance of yarns is provided. The method includes: determining a normally dyed yarn sample in the same lot for the yarn sample to be determined; Perform spectrum detection on the normally dyed yarn samples in the same lot, and obtain the first spectrum information [x i , y i , where x i is the wavenumber sampling value, y i is the spectrum information intensity, and i is a natural number from 1 to 400; Based on the first spectrum information, perform simulation using the Gaussian process kernel RBF Kernel of the following calculation formula (I) to calculate the covariance,

Equation

[0006] According to a second aspect of the present disclosure, there is provided an apparatus for performing the method to preliminarily determine the dyeing performance of yarn. The apparatus includes a spectrum detection unit, a data preprocessing unit, a preliminary determination unit, and a control unit. Here, the data preprocessing unit calculates the covariance according to the formula of the Gaussian process kernel RBF Kernel based on the continuous spectrum information data obtained from the spectrum detection unit. The preliminary determination unit receives the spectrum information from the spectrum detection unit and constructs a Gaussian process regression model based on the covariance.

[0007] According to a third aspect of the present disclosure, there is provided an electronic device. The electronic device includes at least one processing unit, and a storage unit communicably connected to the at least one processing unit. Here, the storage unit stores instructions executable by the at least one processing unit so that the at least one processing unit can execute the above method.

[0008] According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium storing computer instructions, where the computer instructions are non-transitory and are used to cause the computer to execute the above method.

Advantages of the Invention

[0009] The beneficial effects of the invention provided by this disclosure include at least the following. Only manual weaving and dyeing judgment is performed at the initial stage of production. Based on this manual color judgment, dynamic and complete detection of the yarn production process can be realized by using spectrum detection and data simulation processing. This detection method has simple and convenient steps and can be used for online detection of the production line.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Modes for Carrying Out the Invention

[0011] It should be understood that the content described in the section of the summary of the invention does not limit the key points or important features of the embodiments of this disclosure, nor does it limit the scope of this disclosure. Other features of this disclosure will be easily understood from the following description.

[0012] In the drawings, unless otherwise specified, the same reference numerals in a plurality of drawings indicate the same or similar members or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only show some embodiments of this disclosure and are not considered to limit the scope of this disclosure.

[0013] The present disclosure will be described in more detail below with reference to the drawings. In the drawings, the same reference numerals indicate functionally identical or similar elements. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0014] In addition, in order to better explain the present disclosure, a number of specific details are described in the following specific embodiments. Those skilled in the art should understand that the present disclosure can be implemented similarly without specific details. In some examples, well-known methods, means, members, drugs, etc. are not described in detail so as to emphasize the gist of the present disclosure.

[0015] In the prior art, in order to measure the dyeing performance of polyester filament yarns, a judgment method for sock-like dyeing is usually adopted. The usual judgment method for sock-like dyeing includes steps such as knitting into sock-like objects, preparing a dye solution, dyeing, rinsing, drying, and manual color judgment. This method has many steps, a long usage time, low efficiency, serious delay in color judgment results, a small number of samples extracted and inspected in the production process, easy occurrence of inspection omissions, and moreover, the manual color judgment process is affected by the experience of the detector, the test environment, etc., causing changes in the color judgment results.

[0016] To at least partially solve one or more of the above problems, embodiments of the present disclosure provide a dyeing effect prediction method. By using the technical solution of the embodiments of the present disclosure, the dyeing level of the wound yarn package in each lot can be objectively predicted without dyeing, improving the detection accuracy and detection efficiency.

[0017] The main types of yarns related to the technical solutions of the embodiments of the present disclosure may include one or more of partially oriented yarns (POY), fully drawn yarns (FDY), draw textured yarns (DTY) (or low stretch yarns). For example, the types of yarns may specifically include polyester partially oriented yarns, polyester fully drawn yarns, polyester drawn yarns, polyester draw textured yarns, polyester staple fiber, etc.

[0018] FIG. 1 shows a method for preliminarily determining the dyeing performance of yarns according to an embodiment of the present disclosure. As shown in FIG. 1, the method includes at least the following steps.

[0019] S101: For the yarn sample to be determined, determine a normally dyed yarn sample in the same lot.

[0020] According to one specific embodiment, determining a normally dyed yarn sample in the same lot is manually determined by a sock dyeing method including steps of knitting the yarn sample to be determined into a sock-like object, dyeing, and color determination.

[0021] Specifically, referring to Figure 2, the method of knitting the sock-like object can be carried out according to the method of Standard GB / T 6508-2001. The dyeing step includes the preparation of the dye solution. For example, blue dye, purple dye, or red dye can be used. The amount of dye used can be selected according to the fineness specification of the yarn filament. For example, it may be 0.6% - 1.5% of the weight of the sock-like object, preferably 0.6% - 0.8% of the weight of the sock-like object, or 0.8% - 1.2% of the weight of the sock-like object, or 1.2% - 1.5% of the weight of the sock-like object.

[0022] According to one specific embodiment, the above dyeing step further includes putting the dyed sock-like object into a dye solution at 60°C - 90°C and holding it for a predetermined time, for example, 10 - 20 minutes. Preferably, before putting the sock-like object in, the pH of the dye solution is adjusted to be acidic, for example, the pH value is less than 7, for example, adjusted to a pH of 5. The pH of the dye solution can be adjusted by a buffer system of organic acids and their salts. For example, it can be adjusted by acetic acid - sodium acetate buffer solution, or citric acid - sodium citrate buffer solution. Then, the temperature of the dye solution is raised to the dyeing temperature and kept warm for a certain time. The dyeing temperature may be 100°C. The dyeing step can be carried out in a dyeing apparatus selected from a jet dyeing tank, a rope dyeing tank, and a high-temperature high-pressure dyeing tank.

[0023] After the dyed sock-like object is taken out of the dyeing apparatus, it is preferably washed with water and dehydrated for use in the subsequent color determination step. Specifically, cover the sock-like object with a color determination plate (for example, a black and white two-color plate), select appropriate observation conditions, compare with standard color samples, and determine the dyeing level of the yarn.

[0024] The above observation conditions may include, for example, lighting conditions, the angle of light incidence on the surface of the sock-like object, the observation angle, and the observation distance. Regarding the lighting conditions, for example, referring to the method of FZ / T 01047-1997, the adopted light source may be a D65 standard light source, and the illuminance may be 600 to 1000 lx. Regarding the angle of light incidence on the surface of the sock-like object, for example, the angle between the incident light and the middle part of the surface of the sock-like object may be 45°. Regarding the observation angle, it may be substantially perpendicular to the surface of the sock-like object. Regarding the observation distance, it may be approximately 30 to 40 cm. In addition, when it cannot be clearly observed, the angle of light incidence may be adjusted to 70°, and the observation angle between the observation direction and the surface of the sock-like object may be adjusted to 30°.

[0025] The dyeing level may be determined to be normal, dark, or light based on the standard color swatch.

[0026] S102: Perform spectrum detection on the normally dyed yarn samples in the same lot, and obtain the first spectrum information [x i , y i . However, x i is the wavenumber sampling value, y i is the spectrum information intensity, and i is a natural number from 1 to 400.

[0027] The above spectrum may adopt a Raman spectrum. Among them, in the Raman spectrum analysis method, based on the Raman scattering effect of the filament fiber structure, by analyzing the scattering spectrum with a frequency different from that of the incident light, spectrum information regarding the structure, vibration, and rotation of fiber molecules is obtained, and various qualitative and quantitative analyses are performed. In Raman spectrum analysis, a high-quality high-intensity monochromatic laser beam is irradiated on the surface of the fiber to be analyzed, and its scattered light forms different scattered spectra (i.e., Raman spectra) due to the differences in the microstructure of the fiber to be analyzed, and is used for high-precision qualitative and quantitative analysis of fiber properties.

[0028] For comparison, in the infrared spectrum analysis method, an infrared radiation source is used to excite the sample to be measured, and by measuring the intensity of infrared radiation absorption, scattering, and transmission in the material, the chemical bonds and vibration modes in the molecular structure are recognized, an absorption spectrum (i.e., infrared spectrum) is obtained, and the molecular structure is determined.

[0029] In contrast, the Raman effect exists more widely. Since the excitation source used is a high-purity and high-intensity laser, the signal of Raman spectrum analysis is purer, the signal-to-noise ratio is higher, the system is simpler, the arrangement is more flexible, and the interference from the environment is smaller.

[0030] In the present disclosure, the filament to be measured may be a polyester fiber product with a crystalline structure or a polyester fiber product with an amorphous structure. The polyester fiber product may be a polyester filament yarn obtained through spinning and post-treatment. The crystalline structure refers to the state in which polymers are regularly arranged in the fiber. In the crystalline structure, polymer chains are closely arranged with each other, forming a regular lattice structure. Fibers with a crystalline structure generally have a high degree of crystallinity. Also, due to the regular arrangement of molecules, fibers with a crystalline structure are generally relatively stable and have high strength and hardness. The amorphous structure refers to the state in which polymers exhibit an irregular state in the fiber and do not form a regular lattice structure. In the amorphous structure, polymer chains are relatively relaxed and there is no significant periodic arrangement. The lattice structure generally cannot be colored during dyeing. The difference in the dyeing index of the same kind of fiber mainly results from the differences in the degree of crystallinity (or degree of vitrification), crystal distribution, orientation degree, and end group concentration of the fiber. During the dyeing process, dye molecules can only bind to the end groups of the amorphous part in the fiber. The more dye molecules bind, the darker the dyed color becomes, and conversely, the lighter the dyed color becomes.

[0031] Raman spectrum analysis has a sensitive response to the degree of crystallinity, orientation degree, and component concentration in the fiber sample to be measured. In one specific embodiment, for example, as shown in Figure 3, 500 cm -1 ~3500 cm-1 A plurality of spectral information measured at a plurality of wave numbers in the wave number range may be selected to form a Raman spectrum.

[0032] In an embodiment of the present disclosure, step S102 performs spectrum detection on the wound package determined to be a yarn normally dyed in step S101, obtains a spectrum chart, and continuous spectrum information [x i , y i is obtained. Preferably, the spectral information includes a wave number sampling value x i (corresponding to the horizontal axis of the Raman spectrum chart in FIG. 3) and spectral information intensity y i (corresponding to the vertical axis of the Raman spectrum chart in FIG. 3). However, i is a natural number from 1 to 400, preferably, it may be a natural number from 100 to 300, or may be a natural number from 200 to 400.

[0033] According to one specific embodiment, the step size of the wave number sampling in step S102 is 1 to 10 cm -1 , for example, 3 to 7 cm -1 , and preferably 5 cm -1 .

[0034] Specifically, in the method of the present disclosure, spectrum detection is preferably performed downstream of the winding process of the wound package, that is, a spectrometer is installed on the winding machine side or downstream of the yarn production line. For example, by installing the spectrometer on the conveying device of the wound package, spectrum detection can be completed while winding or conveying the wound package. Preferably, the measurement positions can be distributed on the annular side surface of the wound package. For example, by rotating the wound package during measurement, the measurement positions can be distributed at different positions as much as possible to improve the accuracy of measurement.

[0035] On the other hand, in this step, the spectral information obtained does not include a specific structural feature or performance feature, but includes spectral intensity values.

[0036] In the method of the present disclosure, the acquired spectral information includes wavenumber sampling values and spectral intensity values, rather than numerical information of a single physicochemical property. This is because the acquired spectral chart is a comprehensive representation of multiple elements such as the chemical structure, crystal state, orientation degree, glass transition temperature, and spinning finish contained in the fiber, and can more accurately reflect the dyeing properties of the fiber. In addition, since the wavenumber sampling values and spectral intensity values can be directly obtained from the spectral graph, methods and steps related to complex parameter conversion and processing can be avoided.

[0037] S103: Perform simulation using the Gaussian process kernel RBF Kernel of the following calculation formula (I) to calculate the covariance.

Number

[0038] Here, σ is 0.5, l is 1.0, t m and t n represent the notations for dimensions, corresponding to the m-th feature and the n-th feature respectively. However, t m corresponds to the y i value when i = m, and t n corresponds to the y i value when i = n. Also, m and n are natural numbers from 1 to 400 respectively.

[0039] According to the Gaussian process kernel RBF Kernel, the closer two features are adjacent in dimension, the higher the covariance coefficient between them, indicating that these two features are more correlated. On the other hand, the farther two features are apart, the smaller the covariance coefficient, indicating that they are less correlated.

[0040] S104: For the yarn samples in the lot to be determined, obtain a plurality of consecutive second spectral information [x j , y j at a step size of a predetermined wavenumber sampling, and based on the covariance, the second spectral information [xj , y j A Gaussian process regression model is constructed for

[0041] For the plurality of consecutive second spectrum information [x j , y j , it is a 2×N1 matrix. Here, x j is the wavenumber value of the j-th sampling point in the second spectrum chart, and y j is the spectrum intensity of the j-th sampling point in the second spectrum chart. Specifically, j = 1, 2, …, N1, where N1 is the number of samplings of the yarn sample in the lot to be determined, and is a natural number of 200 or more.

[0042] In order to increase the fitting degree of the Gaussian process regression, it is preferable to adopt a high sampling rate, that is, it is preferable to select a large value of N1. According to one embodiment, when the wavenumber step size used for sampling is 10 cm -1 , the number of samplings N is 200. According to another embodiment, when the wavenumber step size used for sampling is 5 cm -1 , the number of samplings N is 400. Also, according to actual needs, other wavenumber step sizes may be selected, and the corresponding number of samplings may be selected accordingly.

[0043] The above sampling process may be performed on one winding package, or may be performed on a plurality of winding packages in the same lot. According to one embodiment, while rotating one winding package, spectrum scanning may be performed so that the sampling points are uniformly distributed on the surface of the side surface in the circumferential direction of the winding package. According to other embodiments, spectrum scanning may be performed on a plurality of winding packages wound in parallel in a winder, and the sampling positions may be evenly distributed.

[0044] S105: For the yarn sample to be detected, third spectrum information [a j , b jObtain []. However, the third spectrum information [a j , b j is a 2×N2 matrix, where N2 is the number of samplings of the winding package sample of the yarn to be detected.

[0045] However, a j is the wave number value of the j-th sampling point in the third spectrum chart, and b j is the spectrum intensity of the j-th sampling point in the third spectrum chart. Specifically, j = 1, 2, …, N1, N2 is the number of samplings of the yarn sample in the lot to be determined, and is a natural number of 200 or more. Preferably, N2 is equal to N1.

[0046] In steps S104 and S105, spectrum information matrices of the same size are obtained. That is, preferably, the sampling method for the winding package to be detected is made to coincide with the sampling method of the Gaussian process regression model so that the data processing in the subsequent steps becomes easy.

[0047] S106: Subtract the 2×N2 matrix of the third spectrum information [a j , b j from the 2×N1 matrix of the above second spectrum information [x j , y i after constructing the Gaussian process regression model to obtain a 2×N3 matrix [u j , v j . However, N3 is equal to N1 and N2.

[0048] The spectrum information measured for the yarn sample to be detected (for example, the winding package to be detected) is compared with the spectrum information processed by the Gaussian process regression model to obtain the variation range of the spectrum characteristics of the yarn sample to be detected, and further, it is used to evaluate the dyeing performance of the yarn sample.

[0049] S107: Determine the dyeing performance of the yarn sample to be detected based on the value of v j .

[0050] Based on the characteristics of the adopted spectrum detection method and the characteristics of the detected yarn, when the change range of the spectrum intensity is within 0.01, it is recognized that the dyeing performance of the yarn is within the normal range.

[0051] Referring to FIG. 3, according to one specific embodiment, when the value of v j is within the interval [-0.01, 0.01], it is determined that the yarn sample to be detected is normally dyed, that is, as shown in the S region in FIG. 3.

[0052] According to another specific embodiment, when the value of v j is greater than 0.01, it is determined that the dyeing of the yarn sample to be detected is dark, that is, as shown in the D region in FIG. 3. Preferably, when the number of v j with a value greater than 0.01 exceeds 3, it is determined that the dyeing of the yarn sample to be detected is dark.

[0053] According to still another specific embodiment, when the value of v j is less than -0.01, it is determined that the dyeing performance of the yarn sample to be detected is light, that is, as shown in the L region in FIG. 3. Preferably, when the number of v j with a value less than -0.01 exceeds 3, it is determined that the dyeing of the yarn sample to be detected is light.

[0054] As can be seen from the above, compared with the normal infrared spectrum detection method with generally 5 to 10 sampling numbers, the sampling number of the method of the present disclosure is significantly larger (200 or more), so the detection result becomes more accurate, and it further contributes to preventing the occurrence of detection omission situations. In addition, by processing the detection data using the Gaussian process regression model, the spectrum intensity value can be directly corresponded to the dyeing characteristics of the yarn, the process of data conversion can be saved, and the phenomenon that deviation is likely to occur when evaluating the dyeing performance of the yarn using the data of a single performance characteristic can be avoided, so the determination result becomes more accurate, the detection process is simplified, the detection efficiency is higher, and it is more suitable for on-line immediate detection of the production line.

[0055] Referring to FIG. 4, according to the second aspect of the present disclosure, there is provided an apparatus 300 for preliminarily determining the dyeing performance of yarns, including a spectrum detection unit 310, a data preprocessing unit 320, a preliminary determination unit 330, and a control unit 340.

[0056] The spectrum detection unit 310 is used to perform spectrum scanning on the yarn samples to be detected in the same lot determined to be color qualified based on the set scanning parameters (such as wavenumber step size, number and distribution of scanning positions, etc.), obtain a spectrum chart, and transmit continuous spectrum information data to the data preprocessing unit 320.

[0057] The data preprocessing unit 320 obtains continuous wavenumber and spectrum intensity data from the spectrum information data, and calculates the covariance according to the formula of the Gaussian process kernel RBF kernel. The method of calculating the covariance using the formula of the Gaussian process kernel RBF kernel is as described above.

[0058] The pre - determination unit 330 obtains the spectral information of a plurality of yarn samples to be determined from the spectrum detection unit 310, constructs a Gaussian process regression model based on the above covariance, obtains the spectral information of the yarn sample to be detected from the spectrum detection unit 310, subtracts it from the spectral information matrix of the Gaussian process regression model, and is used to determine the dyeing performance of the yarn sample to be detected based on the obtained subtracted data. Further, the pre - determination unit 330 transmits the determination result of the dyeing performance to the control unit 340.

[0059] The control unit 340 receives the determination result from the pre - determination unit 330, and based on the determination result, transmits the transport direction and label of the yarn sample to be detected, that is, the good product warehouse or the defective product warehouse, to the production line.

[0060] According to the third aspect of the present disclosure, an electronic device including at least one processing unit and a storage unit communicably connected to the at least one processing unit is provided. Instructions (i.e., a computer program) executable by the processing unit are stored in the storage unit. When the electronic device executes the computer program, the processing unit can be made to execute the above method.

[0061] The electronic device may further include a communication interface for communicating with an external device so as to perform data exchange and transmission.

[0062] The above - mentioned processing unit may be selected from a central processor, other general - purpose processors, digital signal processors or application - specific integrated circuits, etc. The general - purpose processor may be a microprocessor or any conventional processor, etc.

[0063] The above - mentioned storage unit may include one or more of read - only memory, random - access memory, and non - volatile random - access memory. The memory may be volatile memory, non - volatile memory, or may include both volatile memory and non - volatile memory.

[0064] According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium storing computer instructions. Here, the computer instructions are non-transitory and are used to cause the computer to execute the above method.

[0065] In the above embodiments, all or part of them may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of them can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer loads and executes the computer instructions, all or part of the flows or functions described in the embodiments of the present disclosure are generated. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wire (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (such as infrared, Bluetooth (registered trademark), microwave, etc.). The computer-readable storage medium may be any available medium accessible by a computer, or may be a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (such as a floppy (registered trademark) disk, a hard disk, or a magnetic tape), an optical medium (such as a Digital Versatile Disc (DVD)), a semiconductor medium (such as a Solid State Disk (SSD)), etc. It should be noted that the computer-readable storage medium according to the present disclosure may be a non-volatile storage medium, that is to say, a non-temporary storage medium.

[0066] For the specific functions and exemplary descriptions of each module and sub-module of the device in the embodiments of the present disclosure, reference may be made to the relevant descriptions of the corresponding steps in the above method embodiments, and the descriptions are omitted here.

[0067] A person skilled in the art would understand that all or part of the steps for implementing the above embodiments may be completed by hardware, or may be completed by instructing the relevant hardware by a program, and the program may be stored in a computer-readable storage medium, and the above storage medium may be a read-only memory, a magnetic disk, an optical disk, etc.

[0068] In the description of the embodiments of the present disclosure, the descriptions of the terms "one embodiment", "some embodiments", "exemplification", "specific exemplification", or "some exemplifications" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or exemplification are included in at least one embodiment or exemplification of the present disclosure. Also, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or exemplifications in an appropriate manner. Also, unless they are mutually contradictory, a person skilled in the art can combine the different embodiments or exemplifications described in this specification and the features in different embodiments or exemplifications.

[0069] In the description of the embodiments of the present disclosure, unless otherwise specified, " / " means "or", for example, "A / B" can represent "A" or "B". The "and / or" in this specification is only a relationship describing the relevant object and means that there are three possible relationships. For example, "A and / or B" can indicate three situations where "A" exists alone, "A" and "B" exist simultaneously, and "B" exists alone.

[0070] In the description of the embodiments of the present disclosure, the terms "first", "second", etc. are for description only and should not be understood as indicating or implying relative importance or implying the number of the indicated components. Thus, the features limited by "first", "second" can include one or more of such features explicitly or implicitly. In the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "a plurality" is two or more.

[0071] The above are only exemplary embodiments of the present disclosure and do not limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made in accordance with the spirit and principles of the present disclosure should all be included within the scope of the claims of the present disclosure.

Claims

1. A method for pre-determining the dyeing performance of yarns, comprising: determining a normally dyed yarn sample in the same lot for the yarn sample to be determined; Detect the spectrum for the normally dyed yarn samples in the same lot, and obtain first spectrum information [x ｉ , y ｉ (where x ｉ is the wavenumber sampling value, y ｉ is the spectrum information intensity, and i is a natural number from 1 to 400), and Based on the first spectrum information, perform a simulation using the Gaussian process kernel RBF Kernel of the following calculation formula (I) to calculate the covariance (where σ is 0.5, l is 1.0, and t ｍ corresponds to the y value when i = m, and t ｉ corresponds to the y value when i = n, and m and n are natural numbers from 1 to 400 respectively), and ｎ ｉ ​​ 【Number 1】 With a step size of a predetermined wave number sampling, a plurality of consecutive second spectrum information [x ｊ , y ｊ is obtained for the yarn sample in the lot to be judged, and a Gaussian process regression model is constructed for the second spectrum information [x ｊ , y ｊ based on the covariance (however, the plurality of consecutive second spectrum information [x ｊ , y ｊ is a 2×N １ matrix, j = 1, 2, …, N １ , N １ is the number of samplings of the yarn sample in the lot to be judged, and is a natural number of 200 or more), and Obtain third spectrum information [a ｊ , b ｊ for the yarn sample to be detected (where the third spectrum information [a ｊ , b ｊ is a 2×N ２ matrix, N ２ is the number of samplings of the yarn sample to be detected, and N ２ is equal to N １ ), and the third spectral information [a ｊ , b ｊ of 2×N ２ matrix, and the second spectral information [x ｊ , y ｊ of 2×N １ matrix after constructing the Gaussian process regression model are subtracted to obtain a 2×N ３ matrix [u ｊ , v ｊ (where N ３ is equal to N １ and N ２ ), and v ｊ A method for preliminarily determining the dyeing performance of a yarn, including determining the dyeing performance of the yarn sample to be detected based on the numerical value of

2. Based on the value of the aforesaid v ｊ determining the dyeing performance of the yarn sample to be detected v ｊ When the value of v is within the interval of [-0.01, 0.01], it is determined that the yarn sample to be detected is normally dyed, and v ｊ When the value of v is greater than 0.01, it is determined that the dyeing of the yarn sample to be detected is dark, or when v ｊ When the value of v is less than -0.01, it is determined that the dyeing of the yarn sample to be detected is light, the method according to claim 1, comprising.

3. The method according to claim 1, wherein the spectrum adopts a Raman spectrum.

4. In the step of constructing the Gaussian process regression model, the wavenumber step size used for sampling is 2 to 10 cm -１ The method according to claim 1, wherein the sampling number is 200 to 400 and the wavenumber step size used for sampling is 2 to 10 cm

5. When the wave number step size used for sampling is 10 cm -１ the number of samplings N is 200, or when the wave number step size used for sampling is 5 cm -１ the number of samplings N is 400, the method according to claim 4.

6. The method according to claim 1, wherein determining a normally dyed yarn sample in the same lot means manually determining the yarn sample to be determined by knitting it into a sock-like object and using a sock-like object dyeing method including steps of dyeing and color determination.

7. The method according to any one of claims 1 to 6, wherein the yarn is selected from pre-oriented yarn, fully drawn yarn, and drawn textured yarn.

8. An apparatus for pre-determining the dyeing performance of yarns, used for implementing the method according to any one of claims 1 to 6, comprising: a spectrum detection unit, a data pre-processing unit, a pre-determination unit, and a control unit; the data pre-processing unit calculates a covariance according to the formula of a Gaussian process kernel RBF Kernel based on the continuous spectrum information data obtained from the spectrum detection unit; the pre-determination unit receives the spectrum information from the spectrum detection unit and constructs a Gaussian process regression model based on the covariance, for pre-determining the dyeing performance of yarns.

9. The apparatus according to claim 8, wherein the spectrum detection unit is a Raman spectrometer.

10. The apparatus according to claim 8, wherein the spectrum detection unit is a spectrometer installed downstream of a winding machine, and is used to detect the spectrum of the wound yarn package to be measured produced by the winding machine to obtain spectrum information.

11. The apparatus according to claim 8, wherein the control unit receives the determination result from the pre-determination unit and issues a control command.

12. An electronic device, comprising: at least one processing unit; and a storage unit communicably connected to the at least one processing unit, wherein the storage unit stores instructions executable by the at least one processing unit so that the at least one processing unit can execute the method according to any one of claims 1 to 6.

13. A computer-readable storage medium storing computer instructions, The computer instructions are non-transitory and are used to cause a computer to execute the method according to any one of claims 1 to 6, a computer-readable storage medium.

Images