Intelligent control method of carding machine

Abstract

The present invention discloses an intelligent control method for a cotton carding machine, which relates to the technical field of intelligent control and comprises the following steps: obtaining a plurality of groups of cottons of different qualities according to micronaire values, placing the cottons to be tested into a cotton carding machine for combing, and obtaining fiber bundle quality influencing data; constructing a fiber bundle quality evaluation model based on a machine learning algorithm according to the fiber bundle quality influencing data; obtaining the strength of the relationship between the suction negative pressure value, the number of doffers and the fiber bundle quality evaluation coefficient based on Pearson correlation coefficient analysis; adjusting the fiber bundle quality influencing data, the suction negative pressure value and the number of doffers according to the Pearson correlation coefficient; the present application has solved the problem of how to improve the fiber bundle quality, reduce the production cost and realize an efficient and automated cotton carding process by establishing a fiber bundle quality evaluation model while taking into account the relationship between the suction negative pressure value and the number of doffers.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and more specifically, to an intelligent control method for a carding machine. Background Art

[0002] As an important equipment in the textile industry, carding machines are widely used in the pretreatment of cotton. They make cotton fibers more uniform by mechanically combing them to meet the needs of subsequent spinning and weaving processes. As the textile industry continues to increase its requirements for production efficiency, product quality and automation, traditional carding machines have been unable to meet the needs of modern production. To this end, intelligent control technology has emerged, promoting the transformation of carding machines from traditional mechanical operation to highly automated and intelligent ones.

[0003] The application of intelligent control technology in carding machines is mainly reflected in real-time monitoring of the equipment's operating status, fault diagnosis, automatic adjustment, and optimization of the production process. In recent years, with the continuous development of sensor technology, the Internet of Things, artificial intelligence, and big data analysis technology, the intelligence level of carding machines has been significantly improved. First of all, the application of sensor technology enables carding machines to monitor the cotton processing process in real time, including the collection of multiple parameters such as temperature, humidity, pressure, and vibration. These data can be fed back to the control system in real time to ensure the normal operation of the equipment. At the same time, the introduction of visual recognition technology enables the equipment to automatically identify the type and fiber quality of cotton, and adjust the operating parameters according to different raw materials to ensure the consistency of processing quality.

[0004] The combination of data analysis and big data technology enables the carding machine to achieve adaptive adjustment of the production process through machine learning algorithms when processing large amounts of fiber data. For example, when the humidity and temperature of cotton vary greatly, the system can automatically adjust the carding force and speed to ensure the best processing effect. At the same time, the data in the production process can be remotely monitored and analyzed through the cloud platform, realizing unified scheduling and management across regions and equipment.

[0005] The above disclosed technical solutions have at least the following technical problems:

[0006] However, the traditional intelligent control method of the carding machine often finds it difficult to ensure the consistency of the quality of each group of fiber bundles during the carding process, which easily leads to uneven final fiber quality. In addition, the adjustment of the carding machine often relies on manual experience, and the adjustment process is not precise enough, resulting in inefficient operation and waste.

[0007] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0008] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent control method for a carding machine, which solves the problems in the above-mentioned background by establishing a fiber bundle quality evaluation model while taking into account the relationship between the suction negative pressure value and the number of doffers.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] An intelligent control method for a carding machine comprises the following steps: obtaining a plurality of groups of cottons of different qualities according to micronaire values, placing the cottons to be tested into the carding machine for carding, and obtaining fiber bundle quality influencing data; constructing a fiber bundle quality evaluation model based on a machine learning algorithm according to the fiber bundle quality influencing data; obtaining the strength of the relationship between a suction negative pressure value, a doffer number, and a fiber bundle quality evaluation coefficient based on a Pearson correlation coefficient analysis; and adjusting the fiber bundle quality influencing data, the suction negative pressure value, and the doffer number according to the Pearson correlation coefficient.

[0011] In a preferred embodiment, the fiber bundle quality influencing data includes a fiber arrangement coefficient, and the steps for obtaining the fiber arrangement coefficient are as follows: cotton fibers with different micronaire values ​​are put into a carding machine for carding to obtain multiple groups of fiber bundles to be tested, and the angle of each fiber in each group of fiber bundles relative to the main direction of the fiber bundle is recorded; the main direction of the fiber bundle refers to the main stretching direction of the fiber bundle; a fiber arrangement coefficient formula is constructed according to the angle of each fiber relative to the main direction of the fiber bundle and the main direction of the fiber bundle; the sum of squared errors between the predicted value and the actual experimental value is minimized based on the least squares method; by changing the influence constant of the control arrangement angle difference on the arrangement consistency, a parameter combination that minimizes the sum of squared errors is found, and the parameter combination that minimizes the sum of squared errors is the optimal influence constant; the optimal value of the influence constant is obtained more accurately through optimization algorithms including gradient descent method and Newton method; the dimension arrangement coefficient is obtained by calculation according to the dimension arrangement coefficient formula.

[0012] In a preferred embodiment, the fiber bundle quality influencing data includes a fiber uniformity coefficient, and the steps for obtaining the fiber uniformity coefficient are as follows: cotton fibers with different micronaire values ​​are put into a carding machine for carding to obtain multiple groups of fiber bundles to be tested, and the diameter and fiber number of each fiber in each group of fiber bundles are recorded; the average diameter of the fiber is obtained by adding and averaging the diameter of each fiber in each group of fiber bundles and the fiber number; a fiber uniformity coefficient regression model is constructed based on linear regression according to the average diameter of the fiber, the diameter of each fiber and the fiber number; data in the experiment are obtained, including the fiber uniformity coefficient, the average diameter of the fiber, the diameter of each fiber and the fiber number, and fitting is performed based on the least squares method to obtain the optimal value of the coefficient of influence of the control diameter distribution on uniformity; the final dimensional uniformity coefficient formula is obtained according to the optimal value of the coefficient of influence of the control diameter distribution on uniformity and the fiber uniformity coefficient regression model, and the dimensional uniformity coefficient is calculated by the dimensional uniformity coefficient formula.

[0013] In a preferred embodiment, the fiber bundle quality influencing data includes a fiber strength coefficient, and the steps for obtaining the fiber strength coefficient are as follows: cotton fibers with different micronaire values ​​are put into a carding machine for carding to obtain multiple groups of fiber bundles to be tested, and the initial length and initial cross-sectional area of ​​the fiber bundles are recorded; the two ends of the fiber bundle to be tested are clamped in the clamp of the testing machine to ensure that the clamping force is uniform and there is no sliding phenomenon, and the stretching rate is set; the testing machine is started to apply a tensile force, the relationship between the tension and the displacement is recorded, the test is stopped when the fiber breaks, and the maximum load and the deformation of the fiber when the fiber breaks are recorded; the tensile strength of the fiber to be tested is calculated based on a preset tensile strength formula according to the maximum load and the deformation of the fiber when the fiber breaks; the tensile strength is calculated based on the standard deviation formula to obtain the standard deviation of the fiber tensile strength; the experimental data are regressed based on the least squares method to obtain the value of the constant of the experimental fitting, and the experimental data include the standard deviation of the fiber tensile strength, the fiber diameter and the original length of the fiber; the fiber strength coefficient is calculated based on the preset fiber strength coefficient formula according to the experimental data and the value of the experimental fitting constant.

[0014] In a preferred embodiment, the fiber bundle quality influencing data, suction negative pressure value and doffer number are adjusted according to the Pearson correlation coefficient, as follows: if the fiber bundle quality evaluation coefficient is lower than a preset value, the system automatically adjusts the suction negative pressure value and the doffer number; if the suction negative pressure value and the doffer number have reached the preset value after adjustment, the adjustment is stopped; if the highest achievable fiber bundle quality evaluation coefficient has been reached after adjustment of the suction negative pressure value and the doffer number, and the highest fiber bundle quality evaluation coefficient has not reached the preset value, the fiber bundle quality influencing data will be adjusted; if the fiber bundle quality influencing data has not reached the preset value after adjustment, the administrator will be reminded to inspect and replace the equipment.

[0015] The technical effects and advantages of the intelligent control method of a carding machine of the present invention are as follows:

[0016] 1. The present invention can adjust relevant parameters (such as suction negative pressure value and doffer number) in real time during the carding process by accurately controlling the data affecting the quality of the fiber bundle (such as fiber arrangement coefficient, uniformity coefficient and strength coefficient), thereby effectively improving the quality of the fiber bundle, reducing the defect rate, and ensuring the consistency and high quality of each batch of cotton.

[0017] 2. The present invention realizes the automatic adjustment function of the carding machine through machine learning algorithm and Pearson correlation coefficient analysis. The system can automatically adjust parameters according to the relationship between the fiber bundle quality evaluation coefficient and related influencing factors (such as suction negative pressure and doffer number), optimize the carding effect, avoid manual operation errors, and improve production efficiency.

[0018] 3. The present invention can accurately find out the key parameters that affect the quality of cotton fibers through the least square method and regression analysis, and adjust the machine settings according to these parameters to achieve the best operating effect. In particular, by adjusting the fiber arrangement angle and diameter distribution factors, it can reduce energy consumption and equipment wear while ensuring product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The present invention is a schematic structural diagram of an intelligent control method for a carding machine. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Embodiment 1, Figure 1 The present invention provides an intelligent control method for a carding machine, comprising the following steps:

[0022] S1, obtaining multiple groups of cotton with different qualities according to the micronaire value, placing the cotton to be tested in a carding machine for carding, and obtaining fiber bundle quality impact data.

[0023] In this embodiment, multiple groups of cotton with different qualities are obtained according to the micronaire value, and the cotton to be tested is put into a carding machine for carding to obtain fiber bundle quality influence data, which is specifically as follows:

[0024] The micronaire value is a comprehensive reflection of the fineness and maturity of cotton fibers, and is also a comprehensive indicator for evaluating the intrinsic quality of cotton fibers. It directly affects the color, strength, fineness, naturalness, elasticity, moisture absorption, and dyeing properties of the fibers, and a micronaire value that is too high or too low is not conducive to the spinning and weaving of cotton.

[0025] The fiber bundle quality influencing data include fiber arrangement coefficient, fiber uniformity coefficient and fiber strength coefficient, which are as follows:

[0026] Fiber alignment coefficient is an important indicator to measure the consistency of fiber alignment direction in a fiber bundle. It takes into account the deviation between each fiber and the ideal alignment angle (usually the main direction of the fiber bundle). When the fiber alignment is closer to the ideal angle, the fiber alignment coefficient value is higher, indicating that the fiber bundle has better alignment consistency, which may have higher tensile strength and other mechanical properties. Therefore, the fiber alignment coefficient is one of the important parameters for evaluating the quality of fiber bundles.

[0027] The steps for obtaining the fiber arrangement coefficient are specifically as follows:

[0028] Cotton fibers with different micronaire values ​​are fed into a carding machine for carding to obtain multiple groups of fiber bundles to be tested, and the angle of each fiber in each group of fiber bundles relative to the main direction of the fiber bundle is recorded;

[0029] The main direction of the fiber bundle refers to the main stretching direction of the fiber bundle;

[0030] Constructing a fiber arrangement coefficient formula according to the angle of each fiber relative to the main direction of the fiber bundle and the main direction of the fiber bundle;

[0031] Based on the least squares method, the sum of squared errors between the predicted value and the actual experimental value is minimized;

[0032] By changing the influence constant of the control arrangement angle difference on the arrangement consistency, find the parameter combination that minimizes the sum of square errors. The parameter combination that minimizes the sum of square errors is the optimal influence constant.

[0033] The optimal value of the influence constant is obtained more accurately through optimization algorithms including gradient descent method and Newton method;

[0034] The dimension arrangement coefficient is calculated according to the dimension arrangement coefficient formula to obtain the dimension arrangement coefficient.

[0035] The calculation formula of the fiber arrangement coefficient is as follows:

[0036]

[0037] In the formula, K 1 is the fiber arrangement coefficient, N is the total number of fibers, θ i is the arrangement angle of the i-th fiber, θ0 is the ideal arrangement angle, i.e. the main direction of the fiber bundle, and η and ξ are constants that control the influence of arrangement angle differences on arrangement consistency.

[0038] Fiber uniformity coefficient, fiber uniformity refers to the consistency and stability of the distribution of fiber diameters in a fiber bundle, and is one of the important indicators for evaluating fiber quality. It not only focuses on the degree of deviation of the diameter of each fiber from the average diameter, that is, the average value of the sum of squares of diameter variations, but also comprehensively considers the impact of fiber diameter distribution on overall uniformity by introducing experimental constants. When the fiber diameter distribution is more concentrated, that is, when the diameter of each fiber is close to the average value, the uniformity of the fiber diameter is better. In addition, this definition also implies the potential impact of fiber mass distribution on uniformity, thereby more comprehensively evaluating the uniformity performance of the fiber bundle.

[0039] The steps for obtaining the fiber uniformity coefficient are specifically as follows:

[0040] Cotton fibers with different micronaire values ​​are fed into a carding machine for carding to obtain multiple groups of fiber bundles to be tested, and the diameter and number of each fiber in each group of fiber bundles are recorded;

[0041] The average diameter of the fibers is calculated by adding and averaging the diameter of each fiber in each group of fiber bundles and the number of fibers;

[0042] Constructing a fiber uniformity coefficient regression model based on linear regression according to the average diameter of the fibers, the diameter of each fiber and the number of fibers;

[0043] The experimental data, including the fiber uniformity coefficient, the average fiber diameter, the diameter of each fiber and the number of fibers, are obtained, and fitting is performed based on the least square method to obtain the optimal value of the coefficient of influence of the control diameter distribution on uniformity;

[0044] The final dimensional uniformity coefficient formula is obtained according to the optimal value of the coefficient of influence of the control diameter distribution on uniformity and the fiber uniformity coefficient regression model, and the dimensional uniformity coefficient is calculated by the dimensional uniformity coefficient formula.

[0045] The calculation formula of the fiber uniformity coefficient is as follows:

[0046]

[0047] In the formula, K 2 is the fiber uniformity coefficient, γ and δ are the coefficients that control the influence of diameter distribution on uniformity, N is the total number of fibers, and d i is the diameter of the ith fiber, and d is the average diameter of the fibers in the fiber bundle.

[0048] Fiber strength coefficient is a correction parameter used to characterize the tensile strength of fibers. It depends not only on the fiber material itself, but also on factors such as microstructure, impurities, surface defects, and geometric properties. The fiber strength coefficient combines the randomness of strength with the geometric properties of the fiber to more comprehensively describe the tensile strength of the fiber under different conditions. The fiber strength coefficient can more accurately predict the performance of the fiber in practical applications, especially in the case of material defects or geometric inhomogeneities.

[0049] The steps for obtaining the fiber strength coefficient are specifically as follows:

[0050] Cotton fibers with different micronaire values ​​are fed into a carding machine for carding to obtain multiple groups of fiber bundles to be tested, and the initial length and initial cross-sectional area of ​​the fiber bundles are recorded;

[0051] Clamp both ends of the fiber bundle to be tested in the fixture of the testing machine, ensure that the clamping force is uniform and there is no slippage, and set the stretching rate;

[0052] Start the testing machine to apply tensile force, record the relationship between tensile force and displacement, stop the test when the fiber breaks, and record the maximum load and fiber deformation when the fiber breaks;

[0053] The tensile strength of the fiber to be tested is obtained by calculating the maximum load when the fiber breaks and the deformation of the fiber based on a preset tensile strength formula;

[0054] The standard deviation of the tensile strength of the fiber is calculated based on the standard deviation formula;

[0055] Performing regression analysis on the experimental data based on the least square method to obtain the value of the constant of the experimental fitting, wherein the experimental data includes the standard deviation of the tensile strength of the fiber, the diameter of the fiber and the original length of the fiber;

[0056] The fiber strength coefficient is calculated based on the experimental data and the value of the experimental fitting constant based on a preset fiber strength coefficient formula to obtain the fiber strength coefficient.

[0057] The calculation formula of the fiber strength coefficient is as follows:

[0058]

[0059] The calculation formula of the tensile strength is as follows:

[0060]

[0061] In the formula, K 3 is the fiber strength coefficient, σ is the standard deviation of the fiber tensile strength, α and β are constants of experimental fitting, D is the fiber diameter, L is the original length of the fiber, σ tsis the tensile strength, F max is the maximum load when the fiber breaks, A is the original cross-sectional area of ​​the fiber, k is a constant representing the influence coefficient of strain on tensile strength, and ΔL is the deformation of the fiber.

[0062] S2, constructing a fiber bundle quality assessment model based on the fiber bundle quality influencing data and a machine learning algorithm.

[0063] In this embodiment, a fiber bundle quality assessment model is constructed based on the fiber bundle quality influencing data and a machine learning algorithm.

[0064] The calculation formula of the fiber bundle quality evaluation model is as follows:

[0065] Q=K1×K2×K3

[0066] Where Q is the fiber bundle quality assessment coefficient, K 1 is the fiber alignment coefficient, K 2 is the fiber uniformity coefficient, K 3 is the fiber strength coefficient.

[0067] It should be noted that the higher the fiber bundle quality evaluation coefficient is, the better the fiber bundle quality is; conversely, the lower the fiber bundle quality evaluation coefficient is, the worse the fiber bundle quality is.

[0068] S3, based on the Pearson correlation coefficient analysis, the strength of the relationship between the suction negative pressure value, the number of doffers and the fiber bundle quality evaluation coefficient was obtained.

[0069] In this embodiment, the strength of the relationship between the suction negative pressure value, the doffer number and the fiber bundle quality evaluation coefficient is obtained based on the Pearson correlation coefficient analysis;

[0070] The calculation formula of the Pearson correlation coefficient is as follows:

[0071]

[0072] The calculation formula for the relationship between the suction negative pressure value, the number of doffers and the fiber bundle quality evaluation coefficient is as follows:

[0073]

[0074] In the formula, r is the Pearson correlation coefficient, X i is the i-th suction negative pressure value, is the mean value of the suction negative pressure, Y i is the number of the i-th doffer, is the mean of the number of doffers, Z i is the quality assessment coefficient of the ith fiber bundle, is the mean value of the fiber bundle quality assessment coefficient, Z is the fiber bundle quality assessment coefficient, X is the suction negative pressure value, Y is the doffer number, β 0 is the intercept, β 1 and β 2 is the regression coefficient, is the error term.

[0075] It should be noted that the Pearson correlation coefficient is usually used to measure the linear relationship between two variables. The value ranges from -1 to 1. The closer the value is to 1, the stronger the relationship between the variables, and the closer it is to 0, the weaker the correlation.

[0076] S4, adjusting the fiber bundle quality impact data, the suction negative pressure value and the doffer number value according to the Pearson correlation coefficient.

[0077] In this embodiment, the fiber bundle quality influence data, suction negative pressure value and doffer quantity value are adjusted according to the Pearson correlation coefficient, as follows:

[0078] If the fiber bundle quality evaluation coefficient is lower than the preset value, the system automatically adjusts the suction negative pressure value and the number of doffers;

[0079] If the suction negative pressure value and the number of doffers have reached the preset value after adjustment, stop adjusting;

[0080] If the highest fiber bundle quality evaluation coefficient that can be achieved has been reached after adjusting the suction negative pressure value and the number of doffers, and the highest fiber bundle quality evaluation coefficient has not yet reached the preset value, the fiber bundle quality impact data will be adjusted;

[0081] If the fiber bundle quality impact data still does not reach the preset value after adjustment, the administrator is reminded to inspect and replace the equipment.

[0082] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0083] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0084] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0085] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0086] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0087] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent control method for a carding machine, characterized in that: The steps include: According to the micronaire value, multiple groups of cotton with different qualities are obtained, and the cotton to be tested is put into a carding machine for carding to obtain the fiber bundle quality impact data; Constructing a fiber bundle quality assessment model based on the fiber bundle quality influencing data and a machine learning algorithm; The strength of the relationship between the suction negative pressure value, the number of doffers and the fiber bundle quality evaluation coefficient was obtained based on the Pearson correlation coefficient analysis; The fiber bundle quality influence data, the suction negative pressure value and the value of the doffer number are adjusted according to the Pearson correlation coefficient.

2. The intelligent control method of a carding machine according to claim 1, characterized in that: The fiber bundle quality influencing data includes a fiber arrangement coefficient, and the steps for obtaining the fiber arrangement coefficient are specifically as follows: Cotton fibers with different micronaire values ​​are fed into a carding machine for carding to obtain multiple groups of fiber bundles to be tested, and the angle of each fiber in each group of fiber bundles relative to the main direction of the fiber bundle is recorded; The main direction of the fiber bundle refers to the main stretching direction of the fiber bundle; Constructing a fiber arrangement coefficient formula according to the angle of each fiber relative to the main direction of the fiber bundle and the main direction of the fiber bundle; Based on the least squares method, the sum of squared errors between the predicted value and the actual experimental value is minimized; By changing the influence constant of the control arrangement angle difference on the arrangement consistency, find the parameter combination that minimizes the sum of square errors. The parameter combination that minimizes the sum of square errors is the optimal influence constant. The optimal value of the influence constant is obtained more accurately through optimization algorithms including gradient descent method and Newton method; The dimension arrangement coefficient is calculated according to the dimension arrangement coefficient formula to obtain the dimension arrangement coefficient.

3. The intelligent control method of a carding machine according to claim 2, characterized in that: The fiber bundle quality influencing data includes a fiber uniformity coefficient, and the steps for obtaining the fiber uniformity coefficient are specifically as follows: Cotton fibers with different micronaire values ​​are fed into a carding machine for carding to obtain multiple groups of fiber bundles to be tested, and the diameter and number of each fiber in each group of fiber bundles are recorded; The average diameter of the fibers is calculated by adding and averaging the diameter of each fiber in each group of fiber bundles and the number of fibers; Constructing a fiber uniformity coefficient regression model based on linear regression according to the average diameter of the fibers, the diameter of each fiber and the number of fibers; The experimental data, including the fiber uniformity coefficient, the average fiber diameter, the diameter of each fiber and the number of fibers, are obtained, and fitting is performed based on the least square method to obtain the optimal value of the coefficient of influence of the control diameter distribution on uniformity; The final dimensional uniformity coefficient formula is obtained according to the optimal value of the coefficient of influence of the control diameter distribution on uniformity and the fiber uniformity coefficient regression model, and the dimensional uniformity coefficient is calculated by the dimensional uniformity coefficient formula.

4. The intelligent control method of a carding machine according to claim 3, characterized in that: The fiber bundle quality influencing data includes a fiber strength coefficient, and the steps for obtaining the fiber strength coefficient are as follows: Cotton fibers with different micronaire values ​​are fed into a carding machine for carding to obtain multiple groups of fiber bundles to be tested, and the initial length and initial cross-sectional area of ​​the fiber bundles are recorded; Clamp both ends of the fiber bundle to be tested in the fixture of the testing machine, ensure that the clamping force is uniform and there is no slippage, and set the stretching rate; Start the testing machine to apply tensile force, record the relationship between tensile force and displacement, stop the test when the fiber breaks, and record the maximum load and fiber deformation when the fiber breaks; The tensile strength of the fiber to be tested is obtained by calculating the maximum load when the fiber breaks and the deformation of the fiber based on a preset tensile strength formula; The standard deviation of the tensile strength of the fiber is calculated based on the standard deviation formula; Performing regression analysis on the experimental data based on the least square method to obtain the value of the constant of the experimental fitting, wherein the experimental data includes the standard deviation of the tensile strength of the fiber, the diameter of the fiber and the original length of the fiber; The fiber strength coefficient is calculated based on the experimental data and the value of the experimental fitting constant based on a preset fiber strength coefficient formula to obtain the fiber strength coefficient.

5. The intelligent control method of a carding machine according to claim 4, characterized in that: The fiber bundle quality influence data, suction negative pressure value and doffer quantity value are adjusted according to the Pearson correlation coefficient, specifically as follows: If the fiber bundle quality evaluation coefficient is lower than the preset value, the system automatically adjusts the suction negative pressure value and the number of doffers; If the suction negative pressure value and the number of doffers have reached the preset value after adjustment, stop adjusting; If the highest fiber bundle quality evaluation coefficient that can be achieved has been reached after adjusting the suction negative pressure value and the number of doffers, and the highest fiber bundle quality evaluation coefficient has not yet reached the preset value, the fiber bundle quality impact data will be adjusted; If the fiber bundle quality impact data still does not reach the preset value after adjustment, the administrator is reminded to inspect and replace the equipment.

6. The intelligent control method of a carding machine according to claim 5, characterized in that: The calculation formula of the fiber arrangement coefficient is as follows: Where K1 is the fiber arrangement coefficient, N is the total number of fibers, θ i is the arrangement angle of the i-th fiber, θ0 is the ideal arrangement angle, i.e. the main direction of the fiber bundle, and η and ξ are constants that control the influence of the arrangement angle difference on the arrangement consistency.

7. The intelligent control method of a carding machine according to claim 6, characterized in that: The calculation formula of the fiber uniformity coefficient is as follows: Where K2 is the fiber uniformity coefficient, γ and δ are the coefficients that control the influence of diameter distribution on uniformity, N is the total number of fibers, and d i is the diameter of the ith fiber, and d is the average diameter of the fibers in the fiber bundle.

8. The intelligent control method of a carding machine according to claim 7, characterized in that: The calculation formula of the fiber strength coefficient is as follows: The calculation formula of the tensile strength is as follows: Where K3 is the fiber strength coefficient, σ is the standard deviation of the fiber tensile strength, α and β are constants of experimental fitting, D is the fiber diameter, L is the original length of the fiber, and σ ts is the tensile strength, F max is the maximum load when the fiber breaks, A is the original cross-sectional area of ​​the fiber, k is a constant representing the influence coefficient of strain on tensile strength, and ΔL is the deformation of the fiber.

9. The intelligent control method of a carding machine according to claim 8, characterized in that: The calculation formula of the fiber bundle quality evaluation model is as follows: Q=K1×K2×K3 Where Q is the fiber bundle quality evaluation coefficient, K1 is the fiber arrangement coefficient, K2 is the fiber uniformity coefficient, and K3 is the fiber strength coefficient.

10. The intelligent control method of a carding machine according to claim 9, characterized in that: The calculation formula of the Pearson correlation coefficient is as follows: The calculation formula for the relationship between the suction negative pressure value, the number of doffers and the fiber bundle quality evaluation coefficient is as follows: In the formula, r is the Pearson correlation coefficient, X i is the i-th suction negative pressure value, is the mean value of the suction negative pressure, Y i is the number of the i-th doffer, is the mean of the number of doffers, Z i is the quality assessment coefficient of the ith fiber bundle, is the mean value of the fiber bundle quality evaluation coefficient, Z is the fiber bundle quality evaluation coefficient, X is the suction negative pressure value, Y is the doffer number, β0 is the intercept, β1 and β2 are regression coefficients, is the error term.

Images