Real-time control method and system for motion stability of circular knitting machine

Abstract

The invention relates to the technical field of circular knitting machine control, in particular to a real-time control method and system for motion stability of a circular knitting machine. According to the method, the fluctuation feature vectors of the vibration data in the vibration period are extracted, and the similarity between the fluctuation feature vectors is utilized to divide a normal period and an abnormal period; further obtaining a vibration stability coefficient of each monitoring point according to distribution of a normal period and an abnormal period in combination with similar features of the fluctuation feature vector; further according to the fluctuation similarity between the vibration data, the distribution similarity of a normal period and all vibration stability coefficients are combined, and the overall stability coefficient of the needle cylinder is obtained; further according to the fluctuation violent characteristics of the voltage data, combining with the overall stability coefficient to obtain a hardware abnormal factor; finally, the control modes of the circular knitting machine are switched based on the hardware abnormity factors, hardware abnormity is recognized more accurately and comprehensively, control and maintenance are switched in time, and the operation stability and the production quality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of circular knitting machine control, and in particular to a real-time control method and system for the motion stability of a circular knitting machine. Background Art

[0002] The circular knitting machine is a type of knitting equipment for producing weft knitted fabrics. With its efficient production capacity and diverse fabric adaptability, it has become the core equipment in the weft knitting fields such as clothing textiles, home textiles, and industrial textiles.

[0003] During long-term operation, mechanical parts collide with each other and experience abnormal friction due to continuous friction, vibration, and their own wear and aging. This wear and aging is a gradual accumulation process. It is difficult to accurately predict when serious collisions, abnormal friction, and other problems will occur through simple monitoring methods, making prevention difficult. It is difficult to balance the waste of maintenance resources and timeliness of maintenance using fixed maintenance cycles. Hardware wear and aging have a greater impact on the overall structure and motion state, affecting the production stability and quality of circular knitting machines. Summary of the Invention

[0004] In order to solve the technical problem that the hardware wear of large circular knitting machines is difficult to predict and maintain in time, which affects the production stability and production quality of large circular knitting machines, the purpose of the present invention is to provide a method and system for real-time control of the motion stability of large circular knitting machines. The technical solutions adopted are as follows: A real-time control method for motion stability of a circular knitting machine, the method comprising: Obtaining vibration data and voltage data from various monitoring points of the circular knitting machine; obtaining the vibration period of each monitoring point in a current preset historical neighborhood based on the frequency domain distribution of the vibration data; Extracting fluctuation feature vectors of the vibration data within a vibration cycle; for each monitoring point, dividing the vibration cycle into a normal cycle and an abnormal cycle based on the similarity between the fluctuation feature vectors of different vibration cycles; obtaining a current vibration stability coefficient for each monitoring point based on the distribution of the normal cycle and the abnormal cycle and combining similar features of the fluctuation feature vectors between the abnormal cycles; Based on the fluctuation similarity of the vibration data between the monitoring points, combined with the distribution similarity of the normal cycle and all the vibration stability coefficients, the overall stability coefficient of the syringe is obtained; based on the violent fluctuation characteristics of the voltage data in the preset historical neighborhood, combined with the overall stability coefficient, the hardware anomaly factor is obtained; The control mode of the circular knitting machine is switched based on the hardware abnormality factor.

[0005] Furthermore, the method for obtaining the fluctuation characteristic vector includes: The amplitude corresponding to the maximum value of the vibration data in each period and the time interval between the first trough and the first peak constitute a fluctuation characteristic vector.

[0006] Furthermore, the method of dividing the vibration period into a normal period and an abnormal period includes: At the same monitoring point, the average value of the Euclidean distance between the fluctuation feature vector of each vibration cycle and the fluctuation feature vectors of all other vibration cycles is used as the vector difference coefficient of each vibration cycle; the vibration cycle whose vector difference coefficient is less than the preset vector difference threshold is marked as a normal cycle, and the remaining vibration cycles are marked as abnormal cycles.

[0007] Furthermore, the method for obtaining the vibration stability coefficient includes: At the same monitoring point, clustering the fluctuation characteristic vectors of the abnormal period; in each cluster, obtaining the important influencing factors of each cluster according to the distribution of the abnormal period; The vibration stability coefficient of the corresponding monitoring point is obtained according to the number of the normal cycles, the time domain proportion of the maximum continuous duration of the normal cycles, and all the important influencing factors.

[0008] Furthermore, the method for obtaining the important influencing factors includes: In each cluster, the important impact factor of each cluster is obtained according to the minimum time interval of the adjacent abnormal cycles, the maximum time interval of the first and last abnormal cycles in the time domain, and the number of abnormal cycles in the cluster.

[0009] Furthermore, the method for obtaining the overall stability coefficient includes: Obtaining the Pearson correlation coefficient of the vibration data of any two monitoring points; The ratio of the normal periods in which the time domains of any two monitoring points overlap is used as the similarity correction coefficient corresponding to the two monitoring points; The Pearson correlation coefficient and the similarity correction coefficient of each monitoring point with all other monitoring points are integrated, and all the vibration stability coefficients are combined to obtain the overall stability coefficient of the syringe.

[0010] Furthermore, the method for obtaining the hardware abnormality factor includes: In a preset neighborhood of each voltage extreme point, a local instability coefficient of each voltage extreme point is obtained based on the difference in voltage amplitudes adjacent to each other in the time domain; and unstable voltage points are screened out based on the local instability coefficient. The number of unstable voltage points and the overall stability coefficient are combined to obtain a hardware abnormality factor.

[0011] Furthermore, the method for obtaining the vibration period includes: Perform Fourier transform on the vibration data of each monitoring point in the current preset historical neighborhood, obtain the frequency with the highest amplitude in the spectrum diagram as the dominant frequency, obtain the period length based on the dominant frequency, divide the preset historical neighborhood according to the period length corresponding to each monitoring point, and obtain the vibration period of each monitoring point.

[0012] Furthermore, the method for switching the control mode of the circular knitting machine based on the hardware abnormality factor includes: When the hardware abnormality factor is greater than a preset abnormality threshold, the circular knitting machine is controlled by switching to fuzzy control.

[0013] The present invention also proposes a real-time control system for the motion stability of a circular knitting machine. The system includes a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, it implements any one of the steps of the real-time control method for the motion stability of a circular knitting machine.

[0014] The present invention has the following beneficial effects: The present invention first obtains vibration data and voltage data and obtains the vibration period of each monitoring point based on the frequency domain characteristics of the vibration data, providing a basis for subsequent analysis; further extracts the fluctuation characteristic vector of the vibration data within the vibration period, and divides the vibration period into normal period and abnormal period based on the similarity between the fluctuation characteristic vectors of different vibration periods, which helps to accurately extract the true vibration characteristics of the circular knitting machine; further, based on the distribution of normal period and abnormal period, combined with the similarity of the fluctuation characteristic vectors between abnormal periods, obtains the current vibration stability coefficient of each monitoring point to characterize the degree of vibration stability, providing a basis for the subsequent calculation of the overall stability coefficient; further, based on the fluctuation similarity of the vibration data between the monitoring points, combined with the distribution similarity of the normal period and all vibration stability coefficients, obtains the overall stability coefficient of the needle cylinder, avoids the excessive influence of the abnormality of a single monitoring point on the overall judgment, and can reveal the degree of damage of the local abnormality to the overall motion stability from a global perspective; further, based on the violent fluctuation characteristics of the voltage data in a preset historical neighborhood, combined with the overall stability coefficient, obtains the hardware abnormality factor, avoids the misjudgment of external voltage mutation as mechanical failure, and enables the hardware abnormality factor to truly reflect the health status of the overall hardware of the circular knitting machine; finally, the control mode of the circular knitting machine is switched based on the hardware abnormality factor. The present invention analyzes the vibration data of each monitoring point to obtain the vibration period, stability coefficient and overall stability coefficient, and combines the voltage fluctuation characteristics to obtain the hardware anomaly factor, so as to more accurately and comprehensively identify hardware anomalies, switch control and maintenance in time, and improve operational stability and production quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A flowchart of a method for real-time control of motion stability of a circular knitting machine provided by one embodiment of the present invention; Figure 2 A flowchart of a method for obtaining a vibration stability coefficient provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a method and system for real-time control of kinematic stability in a circular knitting machine. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The following describes in detail a method and system for real-time control of motion stability of a circular knitting machine provided by the present invention with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a flow chart of a method for real-time control of motion stability of a circular knitting machine provided by one embodiment of the present invention, specifically comprising: Step S1: Obtain vibration data and voltage data of each monitoring point of the circular knitting machine; obtain the vibration period of each monitoring point in the current preset historical neighborhood according to the frequency domain distribution of the vibration data.

[0021] In order to control the motion stability of the circular knitting machine in real time, it is first necessary to determine the vibration data and voltage data of the key parts of the circular knitting machine.

[0022] In one embodiment of the present invention, the needle cylinder is a key component of a circular knitting machine for achieving knitting functions. Its stable operation is crucial for controlling yarn tension, and its vibration directly reflects the stability of the circular knitting machine's mechanical structure. During operation, the vibration of the needle cylinder is affected by multiple mechanical components, such as the fit accuracy between the needle cylinder and the cam, the positional relationship between the needle cylinder and the rollers, and the manufacturing accuracy and installation quality of the needle cylinder itself. If these mechanical components experience wear, looseness, or installation deviations, these will first manifest themselves in the vibration of the needle cylinder. Therefore, the needle cylinder is selected as the primary monitoring component of the circular knitting machine. Sensor selection and installation: Choose a piezoelectric acceleration vibration sensor. This type of sensor has the characteristics of high sensitivity and a wide frequency response range. It can accurately sense small and rapidly changing vibration signals and meet the measurement needs of the complex vibration environment of the circular knitting machine. For example, a piezoelectric acceleration vibration sensor with a measurement range of ±50g, a sensitivity of 100mV / g, and a frequency response range of 0.5Hz-10kHz can be selected to ensure that it can capture the vibration information of key parts of the circular knitting machine under different operating conditions; install the sensor on the outer wall of the needle cylinder in 3-5 evenly selected installation points in the circumferential direction, and use a dedicated magnetic base or strong glue to firmly install the sensor; Select a voltage sensor and install it at the power input of the circular knitting machine to obtain the voltage signal directly supplied to the machine, which truly reflects the actual working voltage of the machine. The sampling frequency can be set to the same frequency as the vibration sensor; Data collection and storage: The vibration data collection interval is set to 10ms to ensure that sufficient and effective vibration data can be obtained; the analog signal output by each vibration sensor is collected in real time, and it is converted into a digital signal and transmitted to the computer together with the voltage signal; the vibration data and voltage data of each monitoring point as well as the vibration curve are obtained.

[0023] It should be noted that the data collected are data during continuous operation. In other embodiments of the present invention, the implementer can adjust the data collection frequency, sensor selection and installation by himself, which will not be repeated here.

[0024] Since the needle cylinder makes circular motion, during the rotation process, each part is evenly stressed. When the operation is smooth, the vibration curve shows a periodic characteristic that is closely related to the rotation period of the needle cylinder. In a complete rotation period, the shape of the vibration curve is relatively fixed and repeats periodically. Therefore, the vibration period of the vibration data is extracted first. Considering that the frequency domain of the vibration data contains the frequency characteristics of the vibration data, in the current preset historical neighborhood, according to the frequency domain distribution of the vibration data, the period identification deviation caused by instantaneous fluctuations or single-point interference is avoided, and the vibration period of each monitoring point is obtained to provide a basis for subsequent analysis.

[0025] Preferably, in one embodiment of the present invention, the preset historical neighborhood is the historical neighborhood 10 minutes before the current moment; Perform Fourier transform on the vibration data of each monitoring point in the current preset historical neighborhood, obtain the frequency with the highest amplitude in the spectrum diagram as the dominant frequency, obtain the period length based on the dominant frequency, divide the preset historical neighborhood according to the period length corresponding to each monitoring point, and obtain the vibration period of each monitoring point.

[0026] Among them, the reciprocal of the dominant frequency is used as the cycle length. Starting from the first moment of the preset historical neighborhood, the preset historical neighborhood of the corresponding monitoring point is divided by the cycle length to obtain the vibration period of each monitoring point; finally, the remaining time domain range that is less than a cycle length is taken as a vibration period alone.

[0027] It should be noted that Fourier transform is already an existing technology. The analysis process of obtaining the hardware abnormality factor and determining the control mode of the circular knitting machine is consistent each time. Only one example is described here; the frequency of determination can be set to once every 10 minutes; in other embodiments of the present invention, the implementer can adjust the length of the preset historical neighborhood and the analysis frequency of the hardware abnormality factor.

[0028] Step S2: Extract the fluctuation feature vector of the vibration data within the vibration cycle; for each monitoring point, divide the vibration cycle into normal cycle and abnormal cycle according to the similarity between the fluctuation feature vectors of different vibration cycles; according to the distribution of normal cycle and abnormal cycle, combined with the similarity characteristics of the fluctuation feature vectors between abnormal cycles, obtain the current vibration stability coefficient of each monitoring point.

[0029] During the operation of the machine, some non-periodic vibrations may be caused by factors such as yarn tension fluctuations and uneven needle wear. Therefore, it is necessary to distinguish all vibration periods in the vibration data. First, the fluctuation feature vectors of the vibration data within the vibration period are extracted to provide a basis for dividing different periods.

[0030] Preferably, in one embodiment of the present invention, considering that the maximum amplitude of the vibration data reflects the peak intensity within the cycle, it can intuitively reflect the maximum impact or energy concentration received by the mechanical component within the cycle; and considering that the time interval between the first trough and the first peak reflects the response speed and frequency characteristics of the vibration signal at the beginning of the cycle, it can sensitively capture the dynamic changes caused by component wear, looseness or external disturbances; Therefore, the amplitude corresponding to the maximum value of the vibration data in each cycle and the time interval between the first trough and the first peak constitute the fluctuation feature vector, which provides a low-dimensional, easy-to-process but informative feature representation for subsequent similarity measurement and stability coefficient calculation.

[0031] Considering that during machine operation, the vibration under ideal conditions presents stable and repetitive periodicity, the fluctuation feature vectors of different periods should have high similarity; therefore, for each monitoring point, based on the similarity between the fluctuation feature vectors of different vibration periods, it is possible to effectively distinguish between the periodic stable state and the non-periodic abnormal state, and divide the vibration period into normal period and abnormal period, which helps to accurately extract the true vibration characteristics of the circular knitting machine and reduce misjudgments and missed judgments.

[0032] Preferably, in one embodiment of the present invention, considering that the Euclidean distance can measure the difference between vectors and reflect the similarity between the fluctuation feature vectors from the side, at the same monitoring point, the average value of the Euclidean distance between the fluctuation feature vector of each vibration cycle and the fluctuation feature vectors of all other vibration cycles is used as the vector difference coefficient of each vibration cycle; the vibration cycle whose vector difference coefficient is less than the preset vector difference threshold is marked as a normal cycle, and the remaining vibration cycles are marked as abnormal cycles.

[0033] As an example, the preset vector difference threshold is 0.7. The larger the vector difference coefficient, the greater the Euclidean distance between a certain vibration period and all other vibration periods. The greater the difference, the more likely it is an abnormal period. Therefore, the vector difference coefficient is linearly normalized in the corresponding data dimension and compared with the preset vector difference threshold to divide normal periods and abnormal periods.

[0034] Among them, in order to prevent the influence of different data magnitudes in the two dimensions, before constructing the fluctuation characteristic vector, the amplitude corresponding to the maximum value of the vibration data in each period and the time interval between the first trough and the first peak can be linearly normalized in their respective data dimensions, and then constructed as the fluctuation characteristic vector.

[0035] It should be noted that the data dimension used for normalization is the data dimension composed of all characteristic parameters of the same type for all monitoring points. For example, when normalizing the vector difference coefficient, the data dimension composed of the vector difference coefficients of all vibration periods of all monitoring points is used. Since linear normalization only requires the maximum value, minimum value and value to be normalized in the data dimension, the required storage and computing resources are relatively small. This method can be used in other normalization methods in the embodiments of the present invention. The specific details are already known technologies and will not be repeated here.

[0036] In another embodiment of the present invention, considering that cosine similarity can also measure the similarity between vectors, cosine similarity can also be used to replace Euclidean distance, and the average value of the cosine similarity between the fluctuation feature vector of each vibration cycle and the fluctuation feature vectors of all other vibration cycles is used as the vector similarity coefficient of each vibration cycle; the vibration cycle with a vector difference coefficient greater than a preset vector similarity threshold is marked as a normal cycle, and the remaining vibration cycles are marked as abnormal cycles.

[0037] The preset vector similarity threshold may be 0.5. In other embodiments of the present invention, implementers may adjust the preset vector similarity threshold and the preset vector difference threshold.

[0038] Considering that the distribution of normal cycles can reflect the stability of the monitoring point during operation, and the distribution of abnormal cycles can reflect the concentration and evolution trend of abnormal cycles, and reflect the potential vibration instability factors, the current vibration stability coefficient of each monitoring point is obtained according to the distribution of normal cycles and abnormal cycles, combined with the similar characteristics of the fluctuation characteristic vectors between abnormal cycles, to characterize the vibration stability, provide accurate and reliable input for the subsequent calculation of the overall stability coefficient, and improve the reliability and accuracy of the real-time control of the circular knitting machine.

[0039] Preferably, in one embodiment of the present invention, see Figure 2 , which shows a flow chart of a method for obtaining a vibration stability coefficient provided by an embodiment of the present invention, specifically comprising: Step S201: clustering the fluctuation characteristic vectors of the abnormal period at the same monitoring point; in each cluster, obtaining the important influencing factors of each cluster according to the distribution of the abnormal period.

[0040] For all abnormal cycles, the causes of their formation are not exactly the same. It may be the sudden loosening of the connecting parts, the sudden knotting of the yarn or the presence of foreign objects, the instantaneous voltage mutation, etc., which will cause abnormal vibration of the needle cylinder. The characteristics of abnormal vibration caused by different types of reasons are also different. Therefore, the fluctuation characteristic vectors of the abnormal cycles are clustered, and the similar characteristics of the fluctuation characteristic vectors between the abnormal cycles are expressed in a clustering manner. The fluctuation characteristic vectors of the abnormal cycles in each cluster are close to the same, and it can be considered that the abnormal vibration in a cluster has the same cause.

[0041] Considering that the smaller the minimum time interval between adjacent abnormal cycles in a cluster, the more continuous and concentrated the abnormal cycles are. The larger the maximum time interval between the first and last abnormal cycles in the time domain, the longer the occurrence time is. At the same time, the greater the number of abnormal cycles in a cluster, the more important the cause of such abnormality is. Based on this, in each cluster, the important influencing factors of each cluster are obtained according to the minimum time interval of adjacent abnormal cycles in time sequence, the maximum time interval between the first and last abnormal cycles in time domain, and the number of abnormal cycles in the cluster.

[0042] As an example, in each cluster, the abnormal cycles are sorted in chronological order. For two adjacent abnormal cycles, the time interval between the time domain end of the abnormal cycle with the smallest time sequence and the time domain beginning of the abnormal cycle with the largest time sequence is used as the minimum time interval; the time interval between the time domain beginning of the abnormal cycle with the smallest time sequence and the time domain end of the abnormal cycle with the largest time sequence within the cluster is used as the maximum time interval. The product of the reciprocal of the average value of the minimum time interval of all adjacent abnormal cycles in each cluster, the maximum time interval and the number of abnormal cycles in the cluster is taken as the important influencing factor of each cluster.

[0043] Among them, the two-dimensional fluctuation characteristic vector is used as the two-dimensional coordinate of the abnormal period, and the elbow method and K-means clustering algorithm are used to cluster the fluctuation characteristic vector of the abnormal period; the distribution of the abnormal period is shown by the inverse of the average value of the minimum time interval and the maximum time interval.

[0044] It should be noted that the elbow method and K-means clustering algorithm are already existing technologies. In other embodiments of the present invention, implementers can also use other existing clustering algorithms such as DBSCAN, which will not be described in detail.

[0045] Step S202: Obtain the vibration stability coefficient of the corresponding monitoring point based on the number of normal cycles, the time domain proportion of the maximum continuous duration of the normal cycles, and all important influencing factors.

[0046] Taking into account the preset historical neighborhood of the monitoring point, the greater the number of normal cycles, the longer the overall duration of normal vibration and the more stable the vibration; at the same time, the greater the time domain proportion of the maximum continuous duration of the normal cycle, the longer the maximum duration of normal vibration and the more stable the vibration; and the smaller the important influencing factor, the smaller the impact of the abnormal cycle and the more stable the vibration, so these three are integrated to obtain the vibration stability coefficient of the monitoring point.

[0047] As an example, when there is no abnormal cycle between two adjacent normal cycles, the two adjacent normal cycles are considered to be continuous, thereby determining the maximum continuous length of all normal cycles, and determining the maximum continuous duration of the normal cycle with the maximum continuous length. Based on the preset historical neighborhood, the ratio of the maximum continuous duration to the preset historical neighborhood is used as the time domain ratio of the maximum continuous duration of the normal cycle; For each monitoring point, the product of the number of normal cycles and the time domain proportion of the maximum continuous duration of the normal cycle is used as the numerator, the average value of the important influencing factors of all clusters is used as the denominator, and the fractional ratio is used as the vibration stability coefficient of the corresponding monitoring point.

[0048] Among them, the distribution of normal cycles is shown by the number of normal cycles and the time domain proportion of the maximum continuous duration of normal cycles.

[0049] Step S3: Based on the fluctuation similarity of the vibration data between the monitoring points, combined with the distribution similarity of the normal cycle and all vibration stability coefficients, the overall stability coefficient of the syringe is obtained; based on the violent fluctuation characteristics of the voltage data in the preset historical neighborhood, combined with the overall stability coefficient, the hardware anomaly factor is obtained.

[0050] Multiple vibration sensors are evenly distributed around the outer wall of the needle cylinder. The needle cylinder performs circular motion as a whole, with each part rotating synchronously around the central axis. The driving forces and constraints are similar. When the circular knitting machine is operating normally, the vibration patterns at different positions on the needle cylinder are generally consistent. However, when the circular knitting machine is unstable, the vibration patterns at different points on the needle cylinder will be different, and the interference of mechanical components will be aggravated. For example, the relative positions of various components are more prone to change. Scratches can occur where clearances are too small, causing a sharp change in the force applied to the needle cylinder. This can lead to abnormal vibration at that point, which is completely different from the vibration pattern at other points, thus affecting the movement stability of the entire machine. Alternatively, the needle cylinder and surrounding components (such as sinkers and yarn guides) may shift position due to unstable machine movement, making intermittent collisions more likely. The impact force generated by each collision on a specific point on the needle cylinder can cause a sudden change in vibration at that point.

[0051] Therefore, based on the fluctuation similarity of the vibration data between monitoring points, combined with the distribution similarity of normal cycles and all vibration stability coefficients, the overall stability coefficient of the syringe is obtained to avoid the excessive influence of the abnormality of a single monitoring point on the overall judgment. It can reveal the degree of damage to the overall motion stability caused by local abnormalities from a global perspective, laying the foundation for the subsequent acquisition of hardware abnormality factors and switching control modes.

[0052] Preferably, in one embodiment of the present invention, considering that the Pearson correlation coefficient can measure the fluctuation similarity of vibration data between different monitoring points, the closer the Pearson correlation coefficient is to 1, the greater the fluctuation similarity of the vibration data, so the Pearson correlation coefficient of the vibration data of any two monitoring points is obtained; at the same time, in order to prevent the Pearson correlation coefficient caused by extreme cases from negatively affecting subsequent logical relationships, the Pearson correlation coefficient is used as an independent variable and mapped by the ReLU (x) function, ReLU (x) = Max (0, x); Considering that the more normal periods that overlap in the time domain between monitoring points, the more similar the vibration characteristics of the two are, the proportion of normal periods that overlap in the time domain between any two monitoring points is used as the similarity correction coefficient corresponding to the two monitoring points to characterize the distribution similarity of the normal periods; Furthermore, the Pearson correlation coefficient and similarity correction coefficient of each monitoring point with all other monitoring points are integrated, and all vibration stability coefficients are combined to obtain the overall stability coefficient of the syringe.

[0053] As an example, the average value of the product of the Pearson correlation coefficient of each monitoring point and all other monitoring points and the similarity correction coefficient is used as the vibration similarity coefficient of each monitoring point and other monitoring points; The product of the average value of the vibration similarity coefficient and the average value of the vibration stability coefficient at each detection point is taken as the overall stability coefficient of the syringe.

[0054] In other embodiments of the present invention, the implementer may also adopt the weighted summation of the mean, median and mode to replace the average value, for example, fusing the vibration similarity coefficients of all monitoring points with weights of 0.5, 0.2 and 0.3 to obtain the first stability factor; fusing the vibration stability coefficients of all monitoring points with weights of 0.5, 0.2 and 0.3 to obtain the second stability factor; and taking the product of the first stability factor and the second stability factor as the overall stability coefficient of the syringe.

[0055] It should be noted that the Pearson correlation coefficient and the ReLU(x) function are both existing technologies. In other embodiments of the present invention, the DTW algorithm can also be used to obtain the DTW similarity of the vibration data curves of different monitoring points, replacing the Pearson correlation coefficient. The DTW algorithm is already a well-known technology and will not be described in detail.

[0056] When the needle cylinder is unstable during the movement of the circular knitting machine, it may be caused by collision and friction between mechanical parts due to the unstable movement of the circular knitting machine, which may cause the instability of the needle cylinder. It may also be caused by unstable voltage in the workshop. Unstable voltage will cause the motor speed to fluctuate, and then make the rotation speed of the needle cylinder unstable. For example, a sudden drop or rise in voltage will cause the rotation speed of the needle cylinder to change in a short time. Different points will respond differently, and the vibration characteristics will also change accordingly. However, voltage mutations are usually caused by failures or abnormal operations of the external power supply system. Such emergencies are rare, and there are devices with stable voltage, such as distribution cabinets, for timely regulation. In contrast, during long-term operation, mechanical parts collide with each other and rub abnormally due to continuous friction, vibration, and their own wear and aging. This wear and aging is a gradual accumulation process, and it is difficult to use simple monitoring methods to completely and accurately predict when serious collisions and friction problems will occur. Prevention is difficult and can easily affect the production stability and quality of large circular knitting machines.

[0057] Therefore, based on the dramatic fluctuation characteristics of voltage data in the preset historical neighborhood and combined with the overall stability coefficient, the hardware anomaly factor is obtained to avoid misjudging external voltage mutations as mechanical failures. The hardware anomaly factor can truly reflect the health status of the overall hardware of the circular knitting machine and provide a reliable basis for the dynamic switching of the control mode.

[0058] Preferably, in one embodiment of the present invention, voltage fluctuations are generally manifested as violent fluctuations near extreme points. Therefore, observing the difference between adjacent amplitudes within a preset neighborhood of each voltage extreme point can effectively capture local voltage instability characteristics. Therefore, within the preset neighborhood of each voltage extreme point, the local instability coefficient of each voltage extreme point is obtained based on the difference between adjacent voltage amplitudes in the time domain. Unstable voltage points are screened out based on the local instability coefficient. Furthermore, considering that the fewer the number of unstable voltage points, the smaller the overall stability coefficient, the more likely the instability of the circular knitting machine is caused by hardware abnormalities, and the larger the hardware abnormality factor, the number of unstable voltage points and the overall stability coefficient are integrated to obtain the hardware abnormality factor, which also reflects the coupling between the external power supply fluctuation and the mechanical vibration state, thereby obtaining a more comprehensive and objective hardware abnormality factor.

[0059] As an example, the preset neighborhood is the time domain range corresponding to the voltage extreme point and three seconds before and after it. Within the preset neighborhood of each voltage extreme point, the average of the absolute values ​​of the differences in the voltage amplitudes of adjacent time domains is used as the local instability coefficient of the corresponding voltage extreme point. The absolute values ​​of the differences are used to express the differences in the voltage amplitudes of adjacent time domains, and the average values ​​are used to express the violent fluctuation characteristics of the overall voltage data within the preset neighborhood. The larger the local instability coefficient, the more unstable the voltage. Therefore, the local instability coefficient is linearly normalized in the corresponding data dimension, and a preset instability threshold of 0.7 is set. When the normalized local instability coefficient is greater than the preset instability threshold, the corresponding voltage extreme point is marked as an unstable voltage point.

[0060] The product of the number of unstable voltage points and the overall stability coefficient is added to the inverse of the sum after the preset positive division parameter 0.01 is linearly normalized in the corresponding data dimension and used as the hardware anomaly factor.

[0061] The logical relationship is adjusted by taking the inverse, and the denominator is prevented from being zero by presetting a positive division by zero parameter. In other embodiments of the present invention, the implementer can adjust the preset instability threshold on his own.

[0062] Step S4: Switching the control mode of the circular knitting machine based on the hardware abnormality factor.

[0063] The hardware anomaly factor provides a basis for determining hardware anomalies of the circular knitting machine, and ultimately switches the control mode of the circular knitting machine based on the hardware anomaly factor.

[0064] Preferably, when the hardware abnormality factor is greater than a preset abnormality threshold, the circular knitting machine is controlled by switching to fuzzy control; otherwise, the original control mode is maintained unchanged.

[0065] As an example, the preset abnormality threshold is 0.8. Fuzzy control is an existing technology and is not the focus of this solution. It is briefly described here. The machine's spindle speed, the vibration amplitude of different points on the needle cylinder, the weight of the needle cylinder vibration data, the yarn tension, the voltage, etc. are used as input data. The output is the execution parameters for adjusting stability, such as the spindle speed adjustment amount and the yarn feed speed adjustment amount. Control the equipment's actuators to change their unstable state; keep the machine stable during operation, reduce vibrations caused by mechanical component collisions, friction, and voltage mutations, and ensure that the vibration stability and vibration similarity of each point on the needle cylinder meet normal operating requirements, thereby ensuring that the circular knitting machine produces high-quality fabrics.

[0066] When the hardware anomaly factor is greater than the preset anomaly threshold, residual material production is carried out, that is, feeding is stopped, and maintenance is stopped after the residual material is produced.

[0067] In another embodiment of the present invention, the implementer may also issue a warning signal when the hardware abnormality factor is greater than a preset abnormality threshold, and relevant personnel may take over the control of the circular knitting machine and perform emergency production stoppage or surplus material production control.

[0068] In other embodiments of the present invention, implementers can adjust the preset abnormality threshold by themselves.

[0069] One embodiment of the present invention also provides a real-time control system for the motion stability of a circular knitting machine, the system comprising 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 when the computer program runs in the processor, it can implement a real-time control method for the motion stability of a circular knitting machine described in steps S1-S4.

[0070] In summary, to address the technical issues of hardware wear and tear on circular knitting machines, which are difficult to predict and maintain in a timely manner and affect their production stability and quality, the present invention proposes a real-time control method and system for the motion stability of circular knitting machines. The method extracts the fluctuation feature vectors of vibration data within a vibration cycle and, by using the similarity between the fluctuation feature vectors, divides the vibration cycle into normal and abnormal cycles. Furthermore, based on the distribution of normal and abnormal cycles and the similarity of the fluctuation feature vectors between abnormal cycles, the vibration stability coefficient of each monitoring point is obtained. Furthermore, based on the fluctuation similarity of vibration data between monitoring points, the distribution similarity of normal cycles, and all vibration stability coefficients, the overall stability coefficient of the needle cylinder is obtained. Furthermore, based on the fluctuation intensity of voltage data within a preset historical neighborhood and the overall stability coefficient, a hardware anomaly factor is obtained. Finally, the control mode of the circular knitting machine is switched based on the hardware anomaly factor. The method analyzes the vibration data of each monitoring point to obtain the vibration cycle, stability coefficient, and overall stability coefficient. Combining the voltage fluctuation characteristics to obtain the hardware anomaly factor, the method more accurately and comprehensively identifies hardware anomalies, enabling timely control and maintenance switching, thereby improving operational stability and production quality.

[0071] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0072] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A real-time control method for the motion stability of a circular knitting machine, characterized in that: The method comprises: Obtaining vibration data and voltage data from various monitoring points of the circular knitting machine; obtaining the vibration period of each monitoring point in a current preset historical neighborhood based on the frequency domain distribution of the vibration data; Extracting fluctuation feature vectors of the vibration data within a vibration cycle; for each monitoring point, dividing the vibration cycle into a normal cycle and an abnormal cycle based on the similarity between the fluctuation feature vectors of different vibration cycles; obtaining a current vibration stability coefficient for each monitoring point based on the distribution of the normal cycle and the abnormal cycle and combining similar features of the fluctuation feature vectors between the abnormal cycles; Based on the fluctuation similarity of the vibration data between the monitoring points, combined with the distribution similarity of the normal cycle and all the vibration stability coefficients, the overall stability coefficient of the syringe is obtained; based on the violent fluctuation characteristics of the voltage data in the preset historical neighborhood, combined with the overall stability coefficient, the hardware anomaly factor is obtained; The control mode of the circular knitting machine is switched based on the hardware abnormality factor.

2. The method for real-time control of motion stability of a circular knitting machine according to claim 1, characterized in that: The method for obtaining the fluctuation characteristic vector includes: The amplitude corresponding to the maximum value of the vibration data in each period and the time interval between the first trough and the first peak constitute a fluctuation characteristic vector.

3. The method for real-time control of motion stability of a circular knitting machine according to claim 2, characterized in that: The method for dividing the vibration period into normal periods and abnormal periods includes: At the same monitoring point, the average value of the Euclidean distance between the fluctuation feature vector of each vibration cycle and the fluctuation feature vectors of all other vibration cycles is used as the vector difference coefficient of each vibration cycle; the vibration cycle whose vector difference coefficient is less than the preset vector difference threshold is marked as a normal cycle, and the remaining vibration cycles are marked as abnormal cycles.

4. The method for real-time control of motion stability of a circular knitting machine according to claim 1, characterized in that: The method for obtaining the vibration stability coefficient includes: At the same monitoring point, clustering the fluctuation characteristic vectors of the abnormal period; in each cluster, obtaining the important influencing factors of each cluster according to the distribution of the abnormal period; The vibration stability coefficient of the corresponding monitoring point is obtained according to the number of the normal cycles, the time domain proportion of the maximum continuous duration of the normal cycles, and all the important influencing factors.

5. The method for real-time control of motion stability of a circular knitting machine according to claim 4, characterized in that: The method for obtaining the important influencing factors includes: In each cluster, the important impact factor of each cluster is obtained according to the minimum time interval of the adjacent abnormal cycles, the maximum time interval of the first and last abnormal cycles in the time domain, and the number of abnormal cycles in the cluster.

6. The method for real-time control of motion stability of a circular knitting machine according to claim 1, characterized in that: The method for obtaining the overall stability coefficient includes: Obtaining the Pearson correlation coefficient of the vibration data of any two monitoring points; The ratio of the normal periods in which the time domains of any two monitoring points overlap is used as the similarity correction coefficient corresponding to the two monitoring points; The Pearson correlation coefficient and the similarity correction coefficient of each monitoring point with all other monitoring points are integrated, and all the vibration stability coefficients are combined to obtain the overall stability coefficient of the syringe.

7. The method for real-time control of motion stability of a circular knitting machine according to claim 1, characterized in that: The method for obtaining the hardware abnormality factor includes: In a preset neighborhood of each voltage extreme point, a local instability coefficient of each voltage extreme point is obtained based on the difference in voltage amplitudes adjacent to each other in the time domain; and unstable voltage points are screened out based on the local instability coefficient. The number of unstable voltage points and the overall stability coefficient are combined to obtain a hardware abnormality factor.

8. The method for real-time control of motion stability of a circular knitting machine according to claim 1, characterized in that: The method for obtaining the vibration period includes: Perform Fourier transform on the vibration data of each monitoring point in the current preset historical neighborhood, obtain the frequency with the highest amplitude in the spectrum diagram as the dominant frequency, obtain the period length based on the dominant frequency, divide the preset historical neighborhood according to the period length corresponding to each monitoring point, and obtain the vibration period of each monitoring point.

9. The method for real-time control of motion stability of a circular knitting machine according to claim 1, characterized in that: The method for switching the control mode of the circular knitting machine based on the hardware abnormality factor includes: When the hardware abnormality factor is greater than a preset abnormality threshold, the circular knitting machine is controlled by switching to fuzzy control.

10. A real-time control system for the motion stability of a circular knitting machine, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the real-time control method for motion stability of a circular knitting machine as described in any one of claims 1 to 9 are implemented.

Images