Tension control method and system for a high-speed loom

Abstract

The application relates to the field of textile control, in particular to a tension control method and system of a high-speed loom. The method first obtains the tension fluctuation degree of each moment according to the tension data difference of the loom at each moment and the tension data distribution of each moment in the preset time domain of each moment, carries out clustering on all moments to obtain a first clustering cluster, obtains the change state value of each first clustering cluster according to the tension data distribution of each moment in each first clustering cluster and the difference of the tension fluctuation degree of each moment between the first clustering clusters, further carries out clustering on all first clustering clusters to obtain a second clustering cluster, obtains the tension change degree of the loom according to the position distribution of each first clustering cluster in each second clustering cluster, and carries out PID control on the loom according to the deviation of the tension data of the loom at the current moment and the tension change degree. The application can improve the control effect of the yarn tension of the high-speed loom.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of textile control, in particular to a tension control method and system of a high-speed loom. BACKGROUND

[0002] With the rapid development of the textile industry towards intelligence and high efficiency, the high-speed loom puts forward higher requirements for the accurate control of warp tension, and the traditional mechanical tension device has problems such as response lag and insufficient adjustment precision, which is difficult to adapt to the control requirements of instantaneous fluctuation of yarn tension in the modern high-speed weaving process, and is easy to cause quality problems such as broken yarn and fabric defects.

[0003] In related technologies, a PID controller with fixed parameters is usually used to control the tension of the yarn of the loom, but due to the complex nonlinear disturbance caused by factors such as change of yarn material, fluctuation of yarn feeding speed and mechanical vibration in the weaving process of the high-speed loom, at the same time, the tension system of the high-speed loom has time-varying and lagging characteristics, which makes it difficult for the existing PID controller with fixed parameters to achieve accurate and rapid dynamic response, and is easy to cause overshoot or insufficient adjustment of the yarn tension, thereby reducing the control effect of the yarn tension of the high-speed loom. SUMMARY

[0004] In order to solve the technical problem that the existing PID controller with fixed parameters is difficult to achieve accurate and rapid dynamic response, and is easy to cause overshoot or insufficient adjustment of the yarn tension, thereby reducing the control effect of the yarn tension of the high-speed loom, the purpose of the present application is to provide a tension control method and system of a high-speed loom, and the technical solutions adopted are as follows:

[0005] The present application provides a tension control method of a high-speed loom, which comprises:

[0006] Real-time acquisition of the tension data of the yarn of the high-speed loom in the working process;

[0007] According to the difference between the tension data of the loom at each moment and the overall level of the tension data at all moments, and the distribution of the tension data at each moment in the preset time domain of each moment, the tension fluctuation degree of the loom at each moment is obtained; according to the difference of the tension fluctuation degree at each moment, all moments are clustered to obtain a plurality of first clustering clusters; according to the distribution of the tension data at each moment in each first clustering cluster, and the difference of the tension fluctuation degree at each moment between each first clustering cluster, the change state value of each first clustering cluster is obtained;

[0008] According to the overall level of the tension data of all time points in each first clustering cluster and the change state value, all first clustering clusters are clustered to obtain a plurality of second clustering clusters; any one second clustering cluster is taken as a target second clustering cluster, and a tension abnormal value of the target second clustering cluster is obtained according to the position distribution of each first clustering cluster in the target second clustering cluster; and according to the distribution of the tension abnormal values of all second clustering clusters, a tension change degree of the loom is obtained.

[0009] According to the difference between the tension data of the loom at the current time and the overall level of the tension data of all time points and the tension change degree, the loom is PID controlled.

[0010] Further, the obtaining of the tension fluctuation degree of the loom at each time point comprises:

[0011] The average value of the tension data of all time points of the loom is taken as an overall tension value of the loom.

[0012] The absolute value of the difference between the tension data of the loom at each time point and the overall tension value is taken as a tension deviation value of the loom at each time point.

[0013] The dispersion degree of the tension data of all time points in a preset time domain of each time point is analyzed to obtain a local tension dispersion degree of each time point.

[0014] The tension deviation value and the local tension dispersion degree of the loom at each time point are comprehensively processed and normalized to obtain a tension fluctuation degree of the loom at each time point.

[0015] Further, the obtaining of the plurality of first clustering clusters comprises:

[0016] The absolute value of the difference between the tension fluctuation degrees of any two time points is taken as a first distance measure between any two time points.

[0017] Based on the first distance measure, all time points are clustered to obtain a plurality of first clustering clusters.

[0018] Further, the obtaining of the change state value of each first clustering cluster comprises:

[0019] The tension data of all time points in each first clustering cluster is processed by using a PCA principal component analysis algorithm to obtain a principal component direction of each first clustering cluster.

[0020] The average value of the tension fluctuation degrees of all time points in each first clustering cluster is taken as a clustering center value of each first clustering cluster.

[0021] average the tension fluctuation degree of the loom at all times as the overall tension fluctuation value of the loom;

[0022] take the absolute value of the difference between the cluster center value of each first cluster and the overall tension fluctuation value as the tension fluctuation deviation degree of each first cluster;

[0023] take the entropy value of the tension data at all times in each first cluster as the tension confusion degree of each first cluster;

[0024] integrate and normalize the principal component direction, the tension fluctuation deviation degree and the tension confusion degree of each first cluster to obtain the change state value of each first cluster.

[0025] Further, the obtaining a plurality of second clusters comprises:

[0026] take the average value of the tension data at all times in each first cluster as the overall tension level of each first cluster, and take the two-dimensional data composed of the change state value and the overall tension level of each first cluster as the feature array of each first cluster;

[0027] take the Euclidean distance of the feature arrays between any two first clusters as the second distance measure between any two first clusters;

[0028] cluster all first clusters based on the second distance measure to obtain a plurality of second clusters.

[0029] Further, the obtaining a tension abnormal value of a target second cluster comprises:

[0030] take the average value of the second distance measure between all any two first clusters in the target second cluster as the tension abnormal value of the target second cluster.

[0031] Further, the obtaining a tension change degree of the loom comprises:

[0032] take the range of the tension abnormal values of all second clusters as the first tension change coefficient of the loom;

[0033] analyze the dispersion degree of the tension abnormal values of all second clusters to obtain the second tension change coefficient of the loom;

[0034] integrate and normalize the first tension change coefficient and the second tension change coefficient to obtain the tension change degree of the loom.

[0035] Further, the PID control of the loom comprises:

[0036] The tension deviation value of the loom at the current time is obtained by using the calculation method of the tension deviation value of the loom at each time;

[0037] The product value of the tension deviation value of the loom at the current time and the tension change degree of the loom is taken as the adjustment coefficient of the loom at the current time;

[0038] The yarn feeding speed of the loom is controlled in real time based on the adjustment coefficient of the loom at the current time.

[0039] The application further provides a tension control system of a high-speed loom, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor implements the steps of any one of the tension control methods of the high-speed loom when executing the computer program.

[0040] The application has the following beneficial effects:

[0041] The application considers that the existing PID controller with fixed parameters is difficult to realize accurate and rapid dynamic response, and is prone to cause overshoot or insufficient adjustment of the yarn tension, thereby reducing the control effect on the yarn tension of the high-speed loom. Therefore, the yarn tension data of the high-speed loom in the working process is collected in real time. When the yarn tension control of the high-speed loom is insufficient, the yarn tension fluctuation phenomenon occurs. Therefore, the yarn tension fluctuation degree of the loom can be reflected in real time by the obtained yarn tension fluctuation degree. Then, the time points with similar yarn tension fluctuation are divided into the same first clustering cluster, and the change state value is obtained to reflect the change state of the yarn tension data at each time point in each first clustering cluster. In order to accurately describe the yarn tension change of the loom in the whole running process, the application further clusters all the first clustering clusters, divides the similar yarn tension change in the working process of the loom into the same second clustering cluster, and reflects the inconsistency degree of the yarn tension features and the yarn tension change features between the first clustering clusters in the target second clustering cluster by the obtained yarn tension abnormal value. Then, the yarn tension change degree of the high-speed loom in the whole running process is reflected by the yarn tension change degree. Then, the loom is controlled based on the difference between the yarn tension data at the current time and the overall level of the yarn tension data at all time points, and the yarn tension change degree, so as to improve the control effect on the yarn tension of the high-speed loom. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, below will briefly introduce the drawings required by the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative effort.

[0043] Figure 1 A tension control method of a high-speed loom provided by an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined inventive purpose, below, combined with the drawings and preferred embodiments, the specific implementation, structure, features and effects of the high-speed loom tension control method and system according to the present application are described in detail as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0046] Below, the specific scheme of the high-speed loom tension control method and system provided by the present application is specifically described in combination with the drawings.

[0047] Please refer to Figure 1 which shows a flow chart of a high-speed loom tension control method provided by an embodiment of the present application, and the method comprises:

[0048] Step S1: Real-time acquisition of yarn tension data of the high-speed loom in the working process.

[0049] During the operation of the high-speed loom, stable tension can prevent yarn from breaking due to excessive tightness or accumulating due to excessive looseness, thereby reducing the number of stoppages and improving production efficiency. At the same time, reasonable tension control can ensure uniform fabric structure and avoid defects such as wrinkles, weft bars or deformation, ensuring that the appearance and hand feeling of the finished fabric meet the standards. In addition, good tension management can also reduce the wear of mechanical parts, prolong the service life of the equipment, and adapt to the needs of different materials and complex processes, such as the weaving of stretch fabric or high-density fabric.

[0050] The embodiment of the present application first installs a high-precision strain gauge type tension sensor or a piezoelectric sensor on the yarn guide roller or tension roller of the yarn path of the high-speed loom, and uses the sensor to collect the yarn tension data of the high-speed loom in the working process in real time.

[0051] In step S2, the difference between the tension data of the loom at each time and the overall level of the tension data at all times, and the distribution of the tension data at each time within the preset time domain of each time, are obtained to obtain the tension fluctuation degree of the loom at each time. According to the difference between the tension fluctuation degrees at each time, all times are clustered to obtain a plurality of first clustering clusters. According to the distribution of the tension data at each time in each first clustering cluster, and the difference between the tension fluctuation degrees at each time between the first clustering clusters, the change state value of each first clustering cluster is obtained.

[0052] In the tension control of the high-speed loom, the PID control system is widely used due to its simple structure and good regulation performance. The system can quickly respond to tension fluctuations, quickly reduce the deviation through the proportional link, eliminate the steady-state error through the integral link, and suppress the overshoot through the differential link, thereby ensuring the stability of the yarn tension and improving the fabric quality. However, the PID control also has some disadvantages: on the one hand, the traditional PID parameters are usually set by experience, which may not achieve optimal control effect under complex working conditions or high dynamic conditions (such as frequent start-stop, yarn mutation, etc.), on the other hand, the adaptability of PID control to nonlinear and time-varying systems is limited, and when the loom speed is very high or the tension disturbance is large, the regulation may be lagging or oscillating. When the tension control of the yarn on the high-speed loom is insufficient, the tension of the yarn may fluctuate. Therefore, in the embodiment of the present application, the difference between the tension data of the loom at each time and the overall level of the tension data at all times, and the distribution of the tension data at each time within the preset time domain of each time are analyzed. The tension fluctuation degree obtained reflects the degree of tension fluctuation of the yarn on the loom in real time. The length of the preset time domain is usually 10-30, and in the embodiment of the present application, the length of the preset time domain is set to 15, that is, the preset time domain of a certain time includes 14 other times closest to the time and the time itself. The specific length of the preset time domain can also be set by the implementer according to the specific implementation scene, which is not limited here.

[0053] Preferably, in an embodiment of the present application, the method for obtaining the tension fluctuation degree of the loom at each time specifically comprises:

[0054] The average value of the tension data of the loom at all times is taken as the overall tension value of the loom, and the overall tension value reflects the overall level of the yarn tension of the high-speed loom during the entire running process.

[0055] The absolute value of the difference between the tension data of the loom at each moment and the overall tension value is taken as the tension deviation value of the loom at each moment. The larger the tension deviation value at a certain moment, the more the yarn tension deviates from the overall tension level at that moment, and thus the greater the instantaneous fluctuation of the yarn tension at that moment.

[0056] The dispersion of tension data at all times within a preset time domain at each time moment is analyzed to obtain the local tension dispersion at each time moment. The larger the local tension dispersion, the more obvious the tension fluctuation of the yarn in the loom at that time moment in a local short period of time.

[0057] In an embodiment of the present invention, the standard deviation or variance of the tension data at all times within a preset time domain at each time can be used as the local tension dispersion at each time, thereby realizing the analysis of the dispersion of the tension data at all times within a preset time domain at each time. This is not limited here, and the same method can be used in subsequent steps to realize the analysis of the dispersion of the data.

[0058] Then, the tension deviation and local tension dispersion of the loom at each moment are combined and normalized to limit the calculation results to within a certain range. Within a certain range, the degree of tension fluctuation of the loom at each moment can be obtained.

[0059] In embodiments of the present invention, the sum or product of the tension deviation and local tension dispersion of the loom at each moment can be calculated to achieve the integration of the two, which is not limited here. Furthermore, the same method can be used to integrate two or more data in subsequent steps.

[0060] In one embodiment of the present invention, the normalization process can be specifically, for example, maximum and minimum value normalization. Furthermore, the normalization in subsequent steps can all adopt maximum and minimum value normalization. In other embodiments of the present invention, other normalization methods can be selected according to the specific range of values, or activation functions and hyperbolic tangent functions can be used to implement the normalization process. These will not be elaborated or limited further.

[0061] As an example, in one embodiment of the present invention, the expression for the degree of tension fluctuation of the loom at each moment can be specifically as follows:

[0062]

[0063] in, Indicates the loom in the first The degree of tension fluctuation at any given moment; Indicates the loom in the first Tension data at each moment; This indicates the overall tension value of the loom; represents a tension deviation value of the loom at the first time point; represents a tension deviation value of the loom at the first time point; represents a standard deviation of tension data of all time points in a preset time domain at the first time point, that is, a local tension dispersion degree at the first time point; represents a normalization function for normalization processing. In the entire running process of the high-speed loom, there are time points with similar tension fluctuation conditions, so the embodiment of the present application clusters all time points according to the differences in tension fluctuation degrees of the time points to obtain a plurality of first clustering clusters, thereby realizing the division of time points with similar tension fluctuations into the same clustering cluster, and subsequent analysis of the tension data and tension fluctuation degrees of the time points in each first clustering cluster, so as to accurately analyze the change conditions of the tension data of the time points in each first clustering cluster.

[0064] Preferably, in an embodiment of the present application, the method for obtaining the plurality of first clustering clusters specifically includes:

[0065] The absolute value of the difference in tension fluctuation degrees of any two time points is taken as the first distance measurement between any two time points, and all time points are clustered based on the first distance measurement to obtain a plurality of first clustering clusters, wherein in an embodiment of the present application, the existing K-meams clustering algorithm can be used to realize the clustering operation, and the number of clustering clusters can be determined using the existing elbow method, and in other embodiments of the present application, the hierarchical clustering algorithm or other clustering algorithms can also be used to realize the clustering operation, which is not limited here.

[0066] In the process of spinning of the high-speed loom, various factors can cause the tension of the yarn to change, for example, uneven braking of the warp beam, response lag of the servo motor or mechanical wear, etc., which can cause the yarn feeding speed to fluctuate, thereby directly causing the yarn tension to change, and the change conditions of the tension data of the time points in different first clustering clusters are different, so it is necessary to analyze each first clustering cluster, and the embodiment of the present application analyzes the distribution of the tension data of the time points in each first clustering cluster and the differences in tension fluctuation degrees of the time points between the first clustering clusters, thereby obtaining a change state value of each first clustering cluster, and the change state value reflects the tension change conditions of the time points in each first clustering cluster.

[0067] Preferably, in an embodiment of the present application, the method for obtaining the change state value of each first clustering cluster specifically includes:

[0068] Preferably, in an embodiment of the present application, the method for obtaining the change state value of each first clustering cluster specifically includes:

[0069] ​First, the PCA principal component analysis algorithm is used to process the tension data at all times in each first cluster to obtain the principal component direction of each first cluster. The larger the principal component direction of a first cluster, the greater the trend of tension data change at each time in that first cluster. The PCA principal component analysis algorithm is a well-known technique in the art and will not be described in detail here.

[0070] The average tension fluctuation at all times in each first cluster is taken as the cluster center value of each first cluster. The average tension fluctuation of the loom at all times is taken as the overall tension fluctuation value of the loom. The absolute value of the difference between the cluster center value of each first cluster and the overall tension fluctuation value is taken as the tension fluctuation deviation of each first cluster. The larger the tension fluctuation deviation of a certain first cluster, the more the tension fluctuation characteristics at each time in the first cluster deviate from the overall tension fluctuation level of the loom during the entire operation process.

[0071] The entropy value of the tension data at all times in each first cluster is used as the tension disorder of each first cluster. The greater the tension disorder, the more inconsistent the tension data at each time in the first cluster. The calculation of the entropy value of the data is a well-known technique in the art and will not be described in detail here.

[0072] Then, the principal component orientation, tension fluctuation deviation, and tension disorder of each first cluster are synthesized and normalized to limit the calculation results to... Within the range, the change state value of each first cluster is obtained.

[0073] As an example, in one embodiment of the present invention, the expression for the changed state value of each first cluster can be specifically as follows:

[0074]

[0075] in, Indicates the first The changing state values ​​of the first cluster; Indicates the first The principal component direction of the first cluster; Indicates the first The cluster center value of the first cluster; This indicates the overall tension fluctuation value of the loom; Indicates the first The tension fluctuation deviation of the first cluster; Indicates the first Tension disorder of the first cluster; This represents the normalization function, used for normalization processing.

[0076] At this point, the analysis of the change state of the tension data at each time in each first clustering cluster is completed.

[0077] Step S3: clustering all first clustering clusters according to the overall level and change state value of the tension data at all times in each first clustering cluster, obtaining a plurality of second clustering clusters; taking any one second clustering cluster as a target second clustering cluster, obtaining a tension abnormal value of the target second clustering cluster according to the position distribution of each first clustering cluster in the target second clustering cluster; and obtaining the tension change degree of the loom according to the distribution of the tension abnormal values of all second clustering clusters.

[0078] Since different first clustering clusters represent the yarn tension change mode of the high-speed loom during operation, in order to describe the yarn tension change of the high-speed loom during operation, the first clustering clusters need to be further classified to determine the adjustment degree of the high-speed loom running speed and improve the control effect of the yarn tension of the high-speed loom. In the embodiment of the application, first, all first clustering clusters are clustered according to the overall level and change state value of the tension data at all times in each first clustering cluster, and a plurality of second clustering clusters are obtained. The first clustering clusters in the same second clustering cluster have similar tension change characteristics and similar tension characteristics.

[0079] Preferably, in an embodiment of the application, the method for obtaining a plurality of second clustering clusters specifically comprises:

[0080] The average value of the tension data at all times in each first clustering cluster is taken as the overall tension level of each first clustering cluster, and the two-dimensional data composed of the change state value and the overall tension level of each first clustering cluster is taken as the feature array of each first clustering cluster. At this time, each first clustering cluster can be considered as a data point, and each data point is distributed in a two-dimensional plane composed of the change state value and the overall tension level.

[0081] The Euclidean distance of the feature arrays between any two first clustering clusters is taken as the second distance measurement between any two first clustering clusters, and all first clustering clusters are clustered based on the second distance measurement to obtain a plurality of second clustering clusters. In an embodiment of the application, the existing DBSCAN clustering algorithm or other clustering algorithm can be selected for clustering processing, which is not limited or described herein.

[0082] Then, any one of the second clustering clusters is analyzed, and any one of the second clustering clusters is taken as a target second clustering cluster. If each first clustering cluster in the target second clustering cluster is regarded as a data point, the more concentrated the position distribution of each first clustering cluster in the target second clustering cluster is, the more similar the tension change characteristics and tension characteristics between each first clustering cluster in the target second clustering cluster are. Conversely, the more dispersed the position distribution of each first clustering cluster in the target second clustering cluster is, the greater the difference between the tension change characteristics and tension characteristics of each first clustering cluster in the target second clustering cluster is, and thus the more obvious the abnormality of the yarn tension represented by the target second clustering cluster is. Therefore, the tension abnormal value of the target second clustering cluster can be obtained according to the position distribution of each first clustering cluster in the target second clustering cluster. Subsequently, the degree of tension change of the high-speed loom during the entire running process can be analyzed by combining the tension abnormal values of each second clustering cluster, thereby improving the effect of yarn tension control.

[0083] Preferably, in an embodiment of the present application, the method for obtaining the tension abnormal value of the target second clustering cluster specifically comprises:

[0084] The average value of the second distance metric between any two first clustering clusters in the target second clustering cluster is taken as the tension abnormal value of the target second clustering cluster.

[0085] The tension abnormal value of each second clustering cluster can be obtained by the same method as described above. The greater the dispersion degree of the distribution of the tension abnormal values of each second clustering cluster is, the greater the degree of yarn tension change of the high-speed loom during the running process is. Therefore, the distribution characteristics of the tension abnormal values of all second clustering clusters can be analyzed, the degree of tension change is obtained to reflect the degree of yarn tension change of the high-speed loom during the entire running process, and subsequently the thread feeding speed of the loom can be controlled based on the degree of tension change, thereby ensuring the stability of the yarn tension and improving the control effect of the yarn tension.

[0086] Preferably, in an embodiment of the present application, the method for obtaining the degree of tension change of the loom specifically comprises:

[0087] The range of the tension abnormal values of all second clustering clusters is taken as a first tension change coefficient of the loom. The dispersion degree of the tension abnormal values of all second clustering clusters is analyzed to obtain a second tension change coefficient of the loom. The greater the first tension change coefficient and the second tension coefficient are, the greater the degree of tension change of the loom during the entire running process is.

[0088] The first tension change coefficient and the second tension change coefficient are then integrated and normalized, and the calculation result is limited to a range, thereby obtaining the tension variation degree of the loom.

[0089] As an example, in an embodiment of the present application, the expression of the tension variation degree of the loom can be specifically, for example:

[0090]

[0091] wherein, represents the tension variation degree of the loom; represents the maximum value of the tension abnormal value of all the second clustering clusters; represents the minimum value of the tension abnormal value of all the second clustering clusters; represents the range of the tension abnormal value of all the second clustering clusters, that is, the first tension variation coefficient of the loom; represents the standard deviation of the tension abnormal value of all the second clustering clusters, that is, the second tension variation coefficient of the loom; represents the hyperbolic tangent function, which is used for normalization processing.

[0092] Step S4: PID control of the loom according to the difference between the tension data of the loom at the current moment and the overall level of the tension data at all moments, and the tension variation degree.

[0093] The thread feeding speed of the high-speed loom is a key factor affecting the yarn tension. When the thread feeding speed of the high-speed loom is unstable during operation, the yarn tension will appear instantaneous fluctuation. Therefore, in order to realize more accurate real-time adjustment of the yarn tension of the high-speed loom, the embodiment of the present application combines the difference between the tension data of the loom at the current moment and the overall level of the tension data at all moments, and the tension variation degree of the loom, to perform more accurate PID control on the thread feeding speed of the loom, thereby improving the control effect on the yarn tension.

[0094] Preferably, in an embodiment of the present application, the method of PID control on the thread feeding speed of the loom specifically comprises:

[0095] The tension deviation value of the loom at the current moment is obtained by using the calculation method of the tension deviation value of the loom at each moment, and the specific calculation method is: taking the absolute value of the difference between the tension data of the loom at the current moment and the overall tension value as the tension deviation value of the loom at the current moment.

[0096] The product value of the tension deviation value of the loom at the current moment and the tension variation degree of the loom is taken as the adjustment coefficient of the loom at the current moment, and the thread feeding speed of the loom is controlled in real time based on the adjustment coefficient of the loom at the current moment.

[0097] Preferably, in one embodiment of the present application, the method of PID control of the incoming speed of the loom further comprises:

[0098] One embodiment of the present application provides a tension control system of a high-speed loom, which comprises a memory, a processor and a computer program, wherein the memory is used to store the corresponding computer program, the processor is used to run the corresponding computer program, and the computer program can realize the method described in steps S1-S4 when running in the processor.

[0099] It should be noted that the above-mentioned embodiment sequence of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0100] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments.

Claims

1. A tension control method of a high-speed loom characterized by comprising: The method comprises: Real-time acquisition of yarn tension data of the high-speed loom during operation; According to the difference between the tension data of the loom at each time and the overall level of the tension data at all times, and the distribution of the tension data at each time within the preset time domain at each time, the tension fluctuation degree of the loom at each time is obtained; according to the difference between the tension fluctuation degrees at each time, all times are clustered to obtain a plurality of first clustering clusters; according to the distribution of the tension data at each time in each first clustering cluster and the difference between the tension fluctuation degrees at each time between the first clustering clusters, a change state value of each first clustering cluster is obtained; According to the overall level of the tension data at all times in each first clustering cluster and the change state value, all first clustering clusters are clustered to obtain a plurality of second clustering clusters; any one second clustering cluster is taken as a target second clustering cluster, and a tension abnormal value of the target second clustering cluster is obtained according to the position distribution of each first clustering cluster in the target second clustering cluster; according to the distribution of the tension abnormal values of all second clustering clusters, the tension change degree of the loom is obtained; According to the difference between the tension data of the loom at the current time and the overall level of the tension data at all times, and the tension change degree, PID control is performed on the loom; The method comprises: The average value of the tension data of the loom at all times is taken as the overall tension value of the loom; The absolute value of the difference between the tension data of the loom at each time and the overall tension value is taken as the tension deviation value of the loom at each time; The dispersion degree of the tension data at all times within the preset time domain at each time is analyzed to obtain the local tension dispersion degree at each time; The tension deviation value and the local tension dispersion degree of the loom at each time are integrated and normalized to obtain the tension fluctuation degree of the loom at each time; The method comprises: The calculation method of the tension deviation value of the loom at each time is used to obtain the tension deviation value of the loom at the current time; The product value of the tension deviation value of the loom at the current time and the tension change degree of the loom is taken as the adjustment coefficient of the loom at the current time; Based on the adjustment coefficient of the loom at the current time, real-time PID control is performed on the thread feeding speed of the loom.

2. The tension control method of a high-speed loom according to claim 1, characterized in that, The method comprises: The absolute value of the difference between the tension fluctuation degrees at any two times is taken as the first distance measure between any two times; Based on the first distance measure, all times are clustered to obtain a plurality of first clustering clusters.

3. The tension control method of a high-speed loom according to claim 1, characterized in that, The method comprises: The PCA principal component analysis algorithm is used to process the tension data at all times in each first clustering cluster to obtain the principal component direction of each first clustering cluster; The average value of the tension fluctuation degrees at all times in each first clustering cluster is taken as the clustering center value of each first clustering cluster. The average of the tension fluctuation degree of the loom at all times is taken as the overall tension fluctuation value of the loom; The absolute value of the difference between the cluster center value of each first clustering cluster and the overall tension fluctuation value is taken as the tension fluctuation deviation degree of each first clustering cluster; The entropy value of the tension data at all times in each first clustering cluster is taken as the tension confusion degree of each first clustering cluster; The principal component direction, the tension fluctuation deviation degree and the tension confusion degree of each first clustering cluster are integrated and normalized to obtain the change state value of each first clustering cluster.

4. The tension control method of a high-speed loom according to claim 1, characterized in that, The obtaining of the plurality of second clustering clusters comprises: The average of the tension data at all times in each first clustering cluster is taken as the overall tension level of each first clustering cluster, and the two-dimensional data composed of the change state value and the overall tension level of each first clustering cluster is taken as the feature array of each first clustering cluster; The Euclidean distance of the feature arrays between any two first clustering clusters is taken as the second distance measure between any two first clustering clusters; Based on the second distance measure, all first clustering clusters are clustered to obtain a plurality of second clustering clusters.

5. The tension control method of a high-speed loom according to claim 4, characterized in that, The obtaining of the tension abnormal value of the target second clustering cluster comprises: The average of the second distance measure between all arbitrary two first clustering clusters in the target second clustering cluster is taken as the tension abnormal value of the target second clustering cluster.

6. The tension control method of a high-speed loom according to claim 1, characterized in that, The obtaining of the tension change degree of the loom comprises: The range of the tension abnormal values of all second clustering clusters is taken as the first tension change coefficient of the loom; The dispersion degree of the tension abnormal values of all second clustering clusters is analyzed to obtain the second tension change coefficient of the loom, wherein the standard deviation of the tension abnormal values of all second clustering clusters is taken as the second tension change coefficient; The first tension change coefficient and the second tension change coefficient are integrated and normalized to obtain the tension change degree of the loom.

7. A tension control system for a high speed loom, said system comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that, The processor implements the steps of the method of any one of claims 1-6 when executing the computer program.

Images