A real-time monitoring method and system for the operating state of yarn transportation

Abstract

The present invention relates to the technical field of yarn running data processing, and in particular to a method and system for real-time monitoring of the running state of yarn transportation. The method includes the steps of: obtaining the speed value and tension value corresponding to each data point in the time series sequence of yarn running data, and presetting the local range of the data points; obtaining the noise index of the data point through the ratio of the absolute value of the difference between the speed value of the data point and the average speed in its local range to the standard deviation of the speed in the local range; recording the normalized value of the ratio of the noise index of the data point to the average value of the perpendicular distances from each data point in its local range to the regression curve as the noise degree of the data point; forming a speed data time series sequence with the speed values of the data points, and denoising the speed data time series sequence using the target mean value of each data point in the MVI algorithm to obtain the yarn running monitoring result, effectively improving the accuracy of the yarn transportation running state monitoring result.

Description

Technical Field

[0001] The present invention relates to the technical field of yarn running data processing, and in particular to a method and system for real-time monitoring of the running state of yarn conveying. Background Art

[0002] Yarn is the basic material in the textile industry. During the textile process, textile machinery weaves the input yarn into various fabrics with complex structures through interlacing, knitting, etc. The conveying and running state of the yarn directly affect the product quality and production efficiency. Therefore, it is necessary to monitor and adjust the running state of the yarn during the textile process.

[0003] In the prior art, the adjustment of the yarn running state is mostly achieved by collecting yarn running data. For example, the patent application document with the publication number CN118348274A discloses an intelligent yarn detection system and method based on charge. This application obtains the time series of the yarn charge quantity signal to obtain the yarn movement speed value. In this way, deep learning algorithms are used to analyze and process the potential time series correlation features regarding the yarn movement state contained in the time series of the yarn charge quantity, and prior information is introduced as an inference clue to comprehensively characterize the yarn movement speed. The yarn movement speed value is estimated by means of decoding regression, so as to realize the monitoring of the yarn running state.

[0004] The above prior art determines the monitoring result through the movement speed value obtained from the yarn charge quantity. However, there may be noise interference when collecting the yarn movement speed during the operation of textile machinery, resulting in low accuracy of the obtained speed data. Based on this, the accuracy of the monitoring result of the yarn running state is also low.

[0005] Based on this, how to accurately obtain the monitoring result of the yarn conveying and running state is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0006] In order to solve the technical problem of how to accurately obtain the monitoring result of the yarn conveying and running state, the present invention provides a method and system for real-time monitoring of the running state of yarn conveying.

[0007] In the first aspect, the present invention provides a method for real-time monitoring of the running state of yarn conveying, adopting the following technical solution:

[0008] A method for real-time monitoring of the running state of yarn conveying includes the steps:

[0009] Obtain the speed value and tension value corresponding to each data point in the time series of yarn running data, and preset the local range of the data points; obtain the absolute value of the difference between the speed value of the data point and the average speed in its local range, and record the ratio of the absolute value of the difference to the standard deviation of the speed in the local range as the noise index of the data point; obtain the regression curve of the local range of the data point, and record the normalized value of the ratio of the noise index of the data point to the average vertical distance from each data point in its local range to the regression curve as the noise level of the data point.

[0010] ;

[0011] is the target mean of the i-th data point, is the average speed of the left and right adjacent data points of the i-th data point, is the speed value of the i-th data point, is the noise level of the i-th data point, is the exponential function with base e; form the speed value of the data point into a speed data time series, and use the target mean of each data point in the MVI algorithm to denoise the speed data time series to obtain the monitoring result of the yarn running state.

[0012] When determining the monitoring result of the yarn running state in the present invention, considering that there may be noise data in the yarn speed data, the speed data of the yarn is denoised by the MVI algorithm and then the anomaly monitoring is carried out, which can effectively reduce the influence of the noise data on the monitoring result and improve the accuracy of the running monitoring result. In this process, the present invention considers that when directly identifying the noise data based on the average speed of the left and right adjacent data points of the data point in the MVI algorithm, the abnormal data generated during the yarn running may be identified as the noise data. Based on this, the present invention obtains the possibility that the speed data is noise data by obtaining the data performance of the speed data in its local range and the tension data correlated with the speed data, and adjusts the average speed based on the possibility that the speed data is noise data, reducing the possibility of misidentifying the abnormal data as the noise data, thereby effectively improving the accuracy of the monitoring result of the yarn conveying operation state.

[0013] According to a real-time monitoring method for the yarn conveying operation state provided by the present invention, before obtaining the speed value and tension value corresponding to each data point in the time series of yarn running data, it further includes: forming a point with the speed value and tension value of the yarn obtained at the same acquisition moment as a data point, and obtaining the time series of yarn running data after preprocessing.

[0014] The present invention considers that there may be problems such as data missing in the originally collected speed data and tension data, so the overall quality of the data is improved through preprocessing.

[0015] A real-time monitoring method for the operation state of yarn transportation provided by the present invention, the obtaining method for the local range of the data points includes: presetting the length of the local range, taking the data point as the center, and obtaining other data points on both sides of the data point equally to construct the local range of the data point; wherein the length of the local range is an odd number.

[0016] The present invention constructs the local range of the data point by obtaining other data points on both sides of the data point, fully considering the dispersion degree of the current data point compared with its surrounding data, and thus accurately obtaining the noise index of the data point based on this.

[0017] A real-time monitoring method for the operation state of yarn transportation provided by the present invention, the regression curve for obtaining the local range of the data point includes: taking the speed values of the data points in the local range of the data point as the abscissa and the tension values as the ordinate to obtain an operation data scatter diagram, and using the least squares method to obtain the regression curve of the operation data scatter diagram.

[0018] The present invention constructs the regression curve of the speed data and the tension data, obtains the correlation between the speed value and the tension value in the data point through the vertical distance from each data point to the regression curve, and verifies the noise index of the data point through the correlation.

[0019] A real-time monitoring method for the operation state of yarn transportation provided by the present invention, the denoising of the speed data time series using the target mean of each data point in the MVI algorithm includes: obtaining the absolute value of the difference between the target mean and the speed value of each data point, taking the data points corresponding to the absolute value of the difference greater than the preset threshold as noise points to be removed, and then using the target mean corresponding to the data point for interpolation.

[0020] A real-time monitoring method for the operation state of yarn transportation provided by the present invention, the denoising of the speed data time series using the target mean of each data point in the MVI algorithm to obtain the yarn operation monitoring result includes: if the speed value in the denoised speed data time series is greater than the preset abnormal threshold, obtaining the yarn operation monitoring result as abnormal; otherwise, the yarn operation monitoring result is normal.

[0021] A real-time monitoring method for the operation state of yarn transportation provided by the present invention, after obtaining the yarn operation monitoring result as abnormal, further includes: sending out a warning for the abnormal yarn operation monitoring result.

[0022] The present invention considers that abnormal data in the yarn operation speed data may affect the product quality, so a prompt is sent out in the case of monitoring an abnormal state to facilitate the staff to make timely handling.

[0023] In the second aspect, the present invention provides a real-time monitoring system for the operation state of yarn transportation, adopting the following technical solution:

[0024] A real-time monitoring system for the running state of yarn transportation, comprising: a processor and a memory, where the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned real-time monitoring method for the running state of yarn transportation is implemented.

[0025] By adopting the above technical solution, the above-mentioned real-time monitoring method for the running state of yarn transportation is generated into a computer program and stored in the memory to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, which is convenient to use.

[0026] The present invention has the following technical effects:

[0027] Based on the above technical solution, when determining the monitoring result of the yarn running state, the present invention performs denoising on the speed data of the yarn through the MVI algorithm and then conducts anomaly monitoring, which can effectively reduce the influence of noise data on the monitoring result and improve the accuracy of the running monitoring result. In this process, the present invention obtains the data performance of the speed data itself and the tension data correlated with the speed data, obtains the possibility that the speed data is noise data, and adjusts the speed mean based on the possibility that the speed data is noise data, reducing the possibility of misidentifying abnormal data as noise data, thereby effectively improving the accuracy of the monitoring result of the yarn transportation running state. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] By referring to the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0029] Figure 1 It is a schematic flowchart of a real-time monitoring method for the running state of yarn transportation provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0031] It should be understood that when terms such as "first" and "second" are used in the claims, specification and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "comprising" and "including" used in the specification and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0032] It should be noted that yarn is the basic material in the textile industry. During the textile process, textile machinery weaves the input yarn into various fabrics with complex structures through methods such as interlacing and knitting. The conveying and running states of the yarn directly affect the product quality and production efficiency. Therefore, it is necessary to monitor and adjust the running state of the yarn during the textile process.

[0033] The yarn speed is a key parameter affecting the textile process. If the yarn speed is abnormal, it may cause problems such as uneven thickness and inconsistent density of textiles. By real-time monitoring the speed data of the yarn, early warning prompts can be issued in a timely manner in case of abnormalities to ensure the stability and quality of production. However, there may be noise interference when collecting the yarn movement speed during the operation of textile machinery, resulting in low accuracy of the obtained speed data and unable to accurately obtain the monitoring results of the yarn running state based on this.

[0034] Based on this, the embodiments of the present invention disclose a method for real-time monitoring of the conveying and running state of yarn. By denoising the yarn running data and then performing abnormal monitoring, the accuracy of the obtained abnormal monitoring results can be effectively improved.

[0035] Specifically, please refer to Figure 1 as shown in Figure 1 which is a schematic flowchart of a method for real-time monitoring of the conveying and running state of yarn provided by the embodiments of the present invention. The method specifically includes the following steps.

[0036] S1: Obtain the speed value and tension value corresponding to each data point in the time series of yarn running data, and preset the local range of the data points.

[0037] It should be noted that the Mean-Value Iteration filter (MVI for short) is a filtering and smoothing method based on the movement of a small window. It obtains the mean value of the adjacent data points on the left and right sides of the data point, and identifies the noise data through the difference between the value of this data point and the data mean value. Therefore, it can be used for denoising the yarn speed data.

[0038] However, during the operation of textile machinery, the speed data may fluctuate unstably due to equipment aging and other problems. If it is determined whether the current data point is noise data based on the average values of the adjacent data points on the left and right sides of the data point, normal data fluctuations may be identified as noise data and smoothed, resulting in the loss of data details and affecting the accuracy of subsequent data anomaly monitoring.

[0039] It should be further noted that the normal speed data generated during the operation of the yarn is relatively smooth and concentrated in the local range, while the randomly generated noise data is relatively discrete in the local range.

[0040] Based on this, in the embodiments of the present invention, by obtaining the data dispersion of the speed value of the data point in the local range, the possibility of it being noise data is obtained, and the average values of the speeds on the left and right sides of the data point are adjusted according to the noise possibility of the data point, so as to achieve precise denoising of the speed data.

[0041] Exemplarily, in the embodiments of the present invention, before obtaining the speed values and tension values corresponding to each data point in the time series of the yarn running data, it further includes: forming a point by combining the speed value and the tension value of the yarn obtained at the same acquisition moment as a data point, and obtaining the time series of the yarn running data after preprocessing.

[0042] Among them, the preprocessing can be missing data interpolation, data format conversion, etc., and can be specifically set according to actual needs.

[0043] Specifically, set the acquisition frequencies for the speed sensor and the tension sensor, and acquire a speed value and a tension value at each acquisition moment.

[0044] Among them, the acquisition frequency can be set to 1Hz; the acquisition frequency can be specifically set according to actual needs, and the embodiments of the present invention do not limit this too much here.

[0045] Exemplarily, in the embodiments of the present invention, the method for obtaining the local range of the data point includes the following two possible implementation methods:

[0046] In one embodiment, the length of the local range can be preset, and with the data point as the center, other data points are equally obtained on both sides of the data point to construct the local range of the data point; among them, the length of the local range is an odd number.

[0047] It can be understood that the length of the local range is the number of data points included in the local range, and the finally obtained local range of the data point includes the data point itself.

[0048] Among them, the length of the local range can be set to 7, and can be specifically set according to actual needs.

[0049] Illustrate the local range by way of example: If the length of the local range of a data point is 7, then with this data point as the center, 3 other data points can be obtained on each of its two sides, and finally the local range of this data point is obtained.

[0050] In another embodiment, the number k of the nearest data points can be preset, the distances between the current data point and other data points are obtained on both sides of the current data point, and the k data points closest to the current data point are used as the data points in the local range of the current data point.

[0051] Among them, the number of the nearest data points can be set to 6, and it can be specifically set according to actual needs. The embodiments of the present invention do not impose too many restrictions here. The distance can be the Euclidean distance, and it can be specifically set according to actual needs.

[0052] After obtaining the local ranges of each data point based on the above steps, the possibility that it is noise data can be obtained based on the degree of dispersion between the data point and its local range, that is, the following steps are continued.

[0053] S2: Obtain the absolute value of the difference between the speed value of the data point and the average speed in its local range, and record the ratio of the absolute value of the difference to the standard deviation of the speed in the local range as the noise index of this data point.

[0054] It should be noted that based on the above steps, the local ranges of each data point can be obtained. Through the degree of dispersion of the speed value of the data point relative to the speed data in its local range, the discreteness of this data point can be obtained. The higher the discreteness of the data point, the higher the possibility that it is noise data.

[0055] Exemplarily, in the embodiments of the present invention, to determine the noise index of a data point, the following relational expression can be specifically referred to:

[0056] ;

[0057] In the formula, is the noise index of the i-th data point, is the speed value of the i-th data point, is the average speed in the local range of the i-th data point, is the standard deviation of the speed in the local range of the i-th data point, is the absolute value symbol.

[0058] In the above formula, represents the absolute value of the difference between the speed value of the i-th data point and the average speed in its local range. The larger this value is, the greater the degree of deviation of the current data point, the greater the possibility that it is noise data, and the corresponding noise index is larger.

[0059] The greater the deviation of the data point speed relative to the standard deviation of the speed in the local range, the greater the difference between the data point and the overall local range, the more prominent its performance, and the greater the possibility of it being noise data.

[0060] Based on the above steps to analyze the speed change of the data point and its local range, the noise index of each data point can be obtained, and the following steps can be continued.

[0061] S3: Obtain the regression curve of the local range of the data point, and normalize the ratio of the noise index of the data point to the average value of the perpendicular distances from each data point in its local range to the regression curve, and record it as the noise degree of the data point.

[0062] It should be noted that the noise index of the data point obtained based on the above steps only considers the speed change of the data point in the local range. However, during the yarn conveying process, the conveying speed may be affected by factors such as yarn quality and equipment failure, resulting in fluctuations in the yarn conveying speed data. Directly calculating the possibility of such speed data being noise data based on the above steps may identify normal changing data points as noise data.

[0063] It should be further noted that during the yarn conveying process, various frictions and resistances will be encountered, resulting in an increase in speed. And the increase in speed will cause an increase in the tension of the yarn. The change in the yarn speed will cause the tension data to change. Therefore, generally, there is a good positive correlation between the yarn conveying speed data and the tension data.

[0064] Based on this, the embodiment of the present invention can obtain the yarn tension data that is correlated with the yarn speed data, and verify the noise index of the data point obtained in the above steps through the correlation between the two. If the correlation between the speed data and the tension data of the data point is high, it indicates that the current data point has a high possibility of being generated during the operation of the textile machinery. At this time, the noise index of the data point needs to be adjusted downwards; on the contrary, if the correlation between the speed data and the tension data of the data point is low, it indicates that the current data point has a high possibility of being noise data. At this time, the noise index of the data point needs to be increased.

[0065] Exemplarily, in the embodiment of the present invention, obtaining the regression curve of the local range of the data point includes: taking the speed values of each data point in the local range of the data point as the abscissa and the tension values as the ordinate to obtain an operating data scatter diagram, and using the least squares method to obtain the regression curve of the operating data scatter diagram.

[0066] Among them, the specific steps of obtaining the regression curve of the operating data scatter diagram by the least squares method can be obtained through existing algorithms, and the embodiment of the present invention will not elaborate here.

[0067] Exemplarily, in another embodiment of the present invention, when obtaining the regression curve of the local range of data points, the tension values of each data point in the local range of data points can also be used as the abscissa, and the speed values can be used as the ordinate to obtain a scatter plot of operation data, and the regression curve of the scatter plot of operation data can be obtained by using the least squares method.

[0068] It can be understood that the regression curve can reveal the overall trend between two variables and show the expected relationship. After obtaining the regression curve of the local range of data points based on the above embodiments, the vertical distance from each data point to the regression curve can be obtained as the correlation between the speed data and the tension data in the data point, and the noise index of the data point can be corrected based on the correlation between the speed data and the tension data of the data point to obtain the noise level of the data point.

[0069] Exemplarily, in the embodiment of the present invention, to determine the noise level of a data point, the following relational expression can be specifically referred to:

[0070] ;

[0071] In the formula, is the noise level of the i-th data point, is the noise index of the i-th data point, is the average value of the vertical distances from each data point in the local range of the i-th data point to the regression curve, is the hyperbolic tangent function.

[0072] In the above formula, the hyperbolic tangent function is used to perform normalization processing.

[0073] The larger the average value of the vertical distances from each data point in the local range of the i-th data point to the regression curve, the more the data points in its local range are far from the regression curve, that is, the weaker the positive correlation between the speed data and the tension data of each data point, the greater the possibility that the i-th data point is noise data, and the greater the corresponding noise level.

[0074] Based on the above steps, the noise index of each data point can be corrected to accurately obtain the noise level of each data point. Based on the noise level of the data point, precise denoising of the data point can be achieved, that is, continue to execute the following steps.

[0075] S4: The speed values of the data points are formed into a speed data time series, and the target mean values of each data point are used to denoise the speed data time series in the MVI algorithm to obtain the yarn running monitoring result.

[0076] It should be noted that the MVI algorithm identifies noise data by the difference between the speed value of a data point and the average speed of its adjacent data points on the left and right. After obtaining the possibility of each data point being noise data based on the above steps in the embodiments of the present invention, the average speed of the adjacent data points on the left and right of the data point can be adjusted based on the possibility of the data point being noise data. The greater the degree of noise of a data point, the closer the adjusted target average value is to the initial average value of the data point, so that it can be accurately identified as noise data; for data points with a smaller degree of noise, the difference between the adjusted target average value and the speed value of the data point is smaller, reducing the possibility of the data point being identified as noise data.

[0077] It should be further noted that the relationship between the speed value of the current data point and the average speed of its adjacent data points on the left and right specifically includes the following two possible situations:

[0078] In one possible situation, the speed value of the current data point is greater than or equal to the average speed of its adjacent data points on the left and right; in this case, a noise degree adjustment part can be added to the average speed of the adjacent data points on the left and right.

[0079] In another possible situation, the speed value of the current data point is less than the average speed of its adjacent data points on the left and right; in this case, a noise degree adjustment part can be subtracted from the average speed of the adjacent data points on the left and right.

[0080] Exemplarily, in the embodiments of the present invention, to determine the target average value of a data point, the following relational expression can be specifically referred to:

[0081] ;

[0082] is the target average value of the i-th data point, is the average speed of the adjacent data points on the left and right of the i-th data point, is the speed value of the i-th data point, is the noise degree of the i-th data point, is the exponential function with base e, is the absolute value symbol.

[0083] In the above formula, represents the adjustment factor. The higher the noise degree of the i-th data point, the greater the possibility that the data point is noise data, and the smaller the corresponding adjustment factor.

[0084] After adjusting the average speed of the adjacent data points on the left and right of each data point based on the above steps, accurate denoising of speed data can be achieved based on the adjusted target average value.

[0085] Exemplarily, in the embodiments of the present invention, when denoising the time series of speed data using the target mean of each data point in the MVI algorithm, it includes: obtaining the absolute value of the difference between the target mean of each data point and the speed value, removing the data points corresponding to the absolute value of the difference greater than a preset threshold as noise points, and then using the target mean corresponding to this data point for interpolation.

[0086] Among them, the preset threshold can be set to 0.63; the preset threshold can be specifically set according to actual needs, and the embodiments of the present invention do not impose too many restrictions here.

[0087] It can be understood that if the absolute value of the difference between the target mean of a data point and its speed value is not greater than the preset threshold, it indicates that this data point is the speed data generated during the yarn conveying process.

[0088] After denoising the time series of yarn speed data based on the above steps, the yarn running monitoring result can be accurately obtained based on the denoised time series of speed data.

[0089] Exemplarily, in the embodiments of the present invention, when denoising the time series of speed data using the target mean of each data point in the MVI algorithm to obtain the yarn running monitoring result, it includes: if the speed value in the denoised time series of speed data is greater than the preset abnormal threshold, the obtained yarn running monitoring result is abnormal; otherwise, the yarn running monitoring result is normal.

[0090] Among them, the preset abnormal threshold can be set to revolutions per minute; the preset abnormal threshold can be specifically set according to actual needs, and the embodiments of the present invention do not impose too many restrictions here.

[0091] After determining the yarn running monitoring result in the above manner, the embodiments of the present invention also consider that if the yarn running monitoring result is abnormal, there may be potential safety hazards or affect the product quality. Based on this, after obtaining the abnormal monitoring result, the embodiments of the present invention can also send out a prompt externally to facilitate the staff to handle it in time.

[0092] Exemplarily, in the embodiments of the present invention, after obtaining the yarn running monitoring result as abnormal, it further includes: sending out a warning about the abnormal yarn running monitoring result externally.

[0093] Among them, the warning method can be a sound warning, a signal lamp warning, etc., which can be specifically set according to actual needs, and the embodiments of the present invention do not impose too many restrictions here.

[0094] It can be seen that in the embodiment of the present invention, when determining the monitoring result of the yarn conveying operation state, the speed value and the tension value corresponding to each data point in the time series sequence of the yarn operation data can be obtained, and the local range of the preset data point can be obtained; the absolute value of the difference between the speed value of the data point and the average speed value in its local range can be obtained, and the ratio of the absolute value of the difference to the standard deviation of the speed in the local range is denoted as the noise index of the data point; the regression curve of the local range of the data point can be obtained, and the normalized value of the ratio of the noise index of the data point to the average value of the perpendicular distances from each data point in its local range to the regression curve is denoted as the noise level of the data point; the speed values of the data points are composed into a time series sequence of speed data, and the target mean value of each data point is used to denoise the time series sequence of speed data in the MVI algorithm to obtain the yarn operation monitoring result.

[0095] In this way, in the embodiment of the present invention, the speed data of the yarn is denoised by the MVI algorithm and then abnormal monitoring is carried out, which can effectively reduce the influence of noise data on the monitoring result and improve the accuracy of the operation monitoring result. In this process, the embodiment of the present invention takes into account that when directly identifying noise data based on the average speed values of the data points adjacent to the left and right of the data point in the MVI algorithm, the abnormal data generated by the yarn itself may be identified as noise data. Based on this, the embodiment of the present invention obtains the possibility that the speed data is noise data by obtaining the data performance of the speed data itself and the tension data correlated with the speed data, and adjusts the average speed value based on the possibility that the speed data is noise data, reducing the possibility of misidentifying abnormal data as noise data, thereby effectively improving the accuracy of the monitoring result of the yarn conveying operation state.

[0096] The embodiment of the present invention also discloses a real-time monitoring system for the yarn conveying operation state, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a real-time monitoring method for the yarn conveying operation state provided by the present invention is implemented.

[0097] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be elaborated here.

[0098] In the present invention, the aforementioned memory may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as, resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high bandwidth memory (HBM), hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0099] Although this specification has shown and described multiple embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and scope of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

[0100] The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention shall be covered within the protection scope of the present invention.

Claims

1. A method for real-time monitoring of yarn conveying operation status, characterized in that: include: Obtain the speed value and tension value corresponding to each data point in the yarn running data time series, and preset the local range of the data point; Methods for obtaining the local range of data points include: The length of the local range is preset, with the data point as the center, and other data points are equally obtained on both sides of the data point to construct the local range of the data point; the length of the local range is an odd number; Obtain the absolute value of the difference between the speed value of the data point and the speed mean in its local range, and record the ratio of the absolute value of the difference to the speed standard deviation in the local range as the noise index of the data point; Obtain the regression curve of the local range of the data point, and record the normalized value of the ratio of the noise index of the data point to the average of the vertical distances of each data point in its local range to the regression curve as the noise level of the data point; ； is the target mean of the ith data point, is the mean velocity of the left and right adjacent data points of the i-th data point, is the velocity value of the ith data point, is the noise level of the ith data point, is an exponential function with base e, is the absolute value symbol; The speed values ​​of the data points are combined into a speed data time series sequence. The target mean of each data point is used in the MVI algorithm to denoise the speed data time series sequence to obtain the yarn running monitoring results.

2. A method for real-time monitoring of yarn conveying operation status according to claim 1, characterized in that: The method of obtaining the speed value and tension value corresponding to each data point in the yarn running data time series also includes: The speed value and tension value of the yarn obtained at the same acquisition time are combined into one point as a data point, and the yarn running data time series sequence is obtained after preprocessing.

3. A method for real-time monitoring of yarn conveying operation status according to claim 1, characterized in that: The step of obtaining a regression curve of a local range of data points includes: The speed value of each data point in the local range of the data point is used as the horizontal coordinate and the tension value is used as the vertical coordinate to obtain the operation data scatter plot, and the regression curve of the operation data scatter plot is obtained by using the least squares method.

4. A method for real-time monitoring of yarn conveying operation status according to claim 1, characterized in that: The method of using the target mean value of each data point in the MVI algorithm to denoise the speed data time series includes: The absolute value of the difference between the target mean and the speed value of each data point is obtained, and the data points corresponding to the absolute value of the difference greater than the preset threshold are removed as noise points, and the target mean corresponding to the data point is used for interpolation.

5. A method for real-time monitoring of yarn conveying operation status according to claim 1, characterized in that: The method of using the target mean value of each data point in the MVI algorithm to denoise the speed data time series to obtain the yarn running monitoring result includes: If the speed value in the speed data time series after denoising is greater than the preset abnormal threshold, the yarn running monitoring result is abnormal; otherwise, the yarn running monitoring result is normal.

6. A method for real-time monitoring of yarn conveying operation status according to claim 5, characterized in that: The yarn operation monitoring result is abnormal, and then further includes: Abnormal yarn operation monitoring results will be issued as an early warning.

7. A real-time monitoring system for yarn conveying operation status, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for real-time monitoring of the yarn conveying operation status according to any one of claims 1 to 6 is implemented.

Images