Automatic Monitoring Method and System for the Operating Status of a Water Cloth Winding and Unwinding Machine

Abstract

The present invention relates to the field of water cloth winding and unwinding machines, and more specifically, to a method and system for monitoring the operating state of an automatic water cloth winding and unwinding machine. The method includes: obtaining observation data at a target moment; constructing a window, taking the serial number of the sampling moment in the window as the abscissa and the rotational speed as the ordinate to construct a coordinate system, and calculating the initial noise probability at the target moment according to the position of the sampling moment in the coordinate system; constructing the rotational speed at each sampling moment in the window into a rotational speed sequence, constructing the traction speed at each sampling moment in the window into a traction speed sequence, and calculating a correction factor according to the rotational speed sequence and the traction speed sequence for correcting the initial noise probability to obtain the final noise probability; determining the filtering length of the observation data according to the final noise probability, and filtering the observation data by using Vondrak to complete the state monitoring. Through the technical solution of the present invention, the accuracy of the monitoring result of the operating state of the water cloth winding and unwinding machine can be improved.

Description

Technical Field

[0001] The present invention relates to the field of water cloth winding and unwinding machines. More specifically, the present invention relates to a method and system for monitoring the operating state of an automatic water cloth winding and unwinding machine. Background Art

[0002] A water cloth winding and unwinding machine is a mechanical device used for producing rubber hoses. It is mainly used to wind a special water cloth around the rubber hose before vulcanization to ensure uniform distribution of temperature and pressure during the vulcanization process. In order to ensure the stable operation of the equipment under high load, prevent potential failures, and ensure the smooth progress of the production process, it is crucial to monitor the rotational speed of the water cloth winding and unwinding machine in real time. The rotational speed data is not only a key indicator for evaluating the winding quality but also the basis for adjusting the equipment operating parameters and optimizing the production process. By accurately monitoring the rotational speed, abnormal fluctuations can be detected in a timely manner, and then the equipment rotational speed can be adjusted to ensure the uniformity and stability of the winding process, thereby improving the quality and efficiency of rubber hose production.

[0003] The master's thesis of Central South University titled "Research on Vondrak Filtering Criterion and Its Applications" by Wu Yunyun in 2013 discloses that Vondrak filtering can effectively smooth the observed data without knowing the variation law of the observed data and its fitting function. Its basic idea is to control the degree of data smoothing by selecting different smoothing factors, and to choose a compromise curve between the absolute fitting and absolute smoothing of the observed data, retaining the useful signals and filtering out the noise signals. This method is applicable to both equally spaced and unequally spaced observed data.

[0004] However, the rotational speed data of the water cloth winding and unwinding machine will change due to various factors such as equipment status and working environment. The traditional Vondrak filtering algorithm uses a fixed length of the observed data sequence and cannot accurately reflect the dynamic changes of the data, resulting in a deviation in the filtering effect of the rotational speed data and a reduction in the accuracy of the monitoring results of the operating state of the water cloth winding and unwinding machine. Summary of the Invention

[0005] To solve the problem of reduced accuracy of the monitoring results of the operating state of the water cloth winding and unwinding machine, the present invention proposes a method and system for monitoring the operating state of an automatic water cloth winding and unwinding machine.

[0006] First aspect, the present invention discloses a method for monitoring the operating state of an automatic water cloth winding and unwinding machine, including: obtaining observation data at a target moment, where the observation data includes rotational speed and traction speed, and the target moment is any sampling moment; constructing a window, taking the serial number of the sampling moment in the window as the abscissa and the rotational speed as the ordinate to construct a coordinate system, and calculating the initial noise probability at the target moment according to the position of the sampling moment in the coordinate system; constructing the rotational speed of each sampling moment in the window into a rotational speed sequence, and constructing the traction speed of each sampling moment in the window into a traction speed sequence, and calculating a correction factor according to the rotational speed sequence and the traction speed sequence to correct the initial noise probability and obtain the final noise probability, where the final noise probability satisfies the relationship:

[0007] , represents the final noise probability at the target moment of the target moment, represents the target moment of the initial noise probability, represents the rotational speed sequence, represents the traction speed sequence, represents the similarity, represents the exponential function, represents the normalization function; determining the filtering length of the observation data according to the final noise probability, and filtering the observation data by Vondrak to complete the state monitoring.

[0008] The correction mechanism effectively suppresses the influence of unnecessary noise by introducing the exponential function and the normalization function, making the noise probability more reasonably reflect the actual operating state of the system. Determining the appropriate filtering length according to the final noise probability and applying the Vondrak filter to process the observation data not only improves the accuracy and reliability of the data, but also can effectively filter out external interference and fluctuations, ensuring the stability and accuracy of the system state monitoring.

[0009] Preferably, the constructing the window includes: taking the target moment as the center and constructing the window in the sampling time order, and the window size is a preset length; taking the sampling moments in the window except the target moment as reference moments, and in response to the unequal number of reference moments on the left side and the right side of the target moment, discarding the data on the side with fewer reference moments.

[0010] When the sampling moment is at the beginning or the end, the winding and unwinding water cloth machine will operate unstably at this time, resulting in errors in the observation data. Discarding the observation data that is prone to anomalies can improve the accuracy of the calculation results.

[0011] Preferably, the initial noise probability includes: respectively calculating the distance between any two adjacent sampling moments in the window, and the distance satisfies the relationship:

[0012] , represents the sampling moment and the sampling moment distance, and respectively represent the sampling moment and the sampling moment rotational speed; Traverse to obtain the distance between any two sampling moments, calculate the average value of all distances in the window, and use the normalized average value as the initial noise probability.

[0013] By traversing all adjacent sampling moments in the window and calculating the distance, and then obtaining the average value, it can reflect the smoothness of the rotational speed change. The normalized average value as the initial noise probability actually quantifies the stability or noise level of the rotational speed signal.

[0014] Preferably, the initial noise probability further includes: respectively calculating the distance between any two adjacent sampling moments in the window, and the distance satisfies the relational expression:

[0015] , represents the sampling moment and the sampling moment distance, and respectively represent the sampling moment and the sampling moment rotational speed, represents the two-norm; Traverse to obtain the distance between any two sampling moments, take the average value of all distances as the first distance, take the sum of the two distances participated in the calculation at the target moment as the second distance, calculate the ratio of the second distance to the first distance, and use the normalized ratio as the initial noise probability.

[0016] The smoothness of the rotational speed signal directly affects the subsequent monitoring and analysis accuracy. Therefore, the accurate identification of these mutation fluctuations is very crucial. By calculating the distance between adjacent sampling moments and normalizing it, the interference degree of noise on the signal can be effectively quantified, especially in the case of irregular fluctuations, and the influence degree of noise can be accurately evaluated. This calculation method further reveals whether the fluctuation at the target moment significantly deviates from the normal rotational speed change law through the calculation of the distance ratio.

[0017] Preferably, the initial noise probability further includes: respectively calculating the distance between any two adjacent sampling moments in the window to construct a distance sequence; respectively obtaining the relative angle of any sampling moment in the window, calculating the sine value of each relative angle to construct a sine sequence; the initial noise probability satisfies the relational expression:

[0018] , represents the target moment The initial noise probability, represents the variance of the distance sequence, represents the variance of the sine sequence, represents the normalization function.

[0019] The variances of these two respectively describe the degree of discreteness and instability of signal changes, and can provide key indicators on whether there are abnormal fluctuations or noise in the signal. By normalizing the variance using the normalization function, the influence degree of noise can be converted into a smooth and quantifiable noise probability, so as to more accurately evaluate the noise risk of the observed data at each sampling moment.

[0020] Preferably, the relative angle includes: taking any sampling moment in the window as the marking moment, and taking the next sampling moment adjacent to the marking moment as the post-marking moment; in the coordinate system, taking the angle between the line connecting the marking moment and the post-marking moment and the horizontal axis as the relative angle of the marking moment, where the counterclockwise direction is the positive direction.

[0021] Preferably, the determining the filtering length of the observed data according to the final noise probability includes: traversing to obtain the final noise probabilities of multiple sampling moments, presetting the initial length of the observed data, and calculating the mean value of the final noise probabilities of the observed data in the initial length; in response to the mean value of the final noise probabilities being greater than the abnormal threshold, iteratively increasing the initial length until the final noise probability is not greater than the abnormal threshold or the initial length reaches the preset maximum value, stopping the iteration, and obtaining the length of the observed data.

[0022] In a second aspect, the present invention discloses an operation state monitoring system for an automatic water cloth winding and unwinding machine, including: a processor; and a memory, where the memory stores computer instructions, and when the computer instructions are run by the processor, the system executes the above-mentioned operation state monitoring method for the automatic water cloth winding and unwinding machine.

[0023] Advantages of the present invention:

[0024] By dynamically monitoring key parameters such as the rotation speed and the traction speed, and combining the calculation of the noise probability and the correction factor, the present invention can effectively identify abnormal fluctuations in the operation state of the device.

[0025] By constructing a sampling moment window, calculating the initial noise probability, and correcting it using the rotation speed and traction speed sequences, it can accurately reflect the changes in the state of the water cloth winding and unwinding machine and timely detect potential faults or deviations. In addition, the filtering process in the present invention helps to reduce noise interference and improve the reliability and accuracy of the monitoring results by adjusting the length of the observed data.

[0026] The present invention not only enhances the intelligence level of the monitoring system, but also can provide more efficient and stable operation state monitoring in practical applications, helping to prevent failures, extend the service life of equipment, and improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] By referring to the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understandable. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0028] Figure 1 is a flowchart of the method for monitoring the operation state of the automatic water cloth winding and unwinding machine according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0030] It should be understood that when terms such as "first" and "second" are used in the claims, the description, and the drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "comprising" and "including" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0031] The present invention provides a method for monitoring the operation state of an automatic water cloth winding and unwinding machine. As Figure 1 shown, the method for monitoring the operation state of the automatic water cloth winding and unwinding machine includes steps S1 - S4, which are specifically described below.

[0032] S1, obtaining observation data at a target moment, where the observation data includes rotational speed and traction speed, and the target moment is any sampling moment.

[0033] In one embodiment, the rotational speed sensor is accurately placed at the position of the winding and unwinding water cloth turntable of the winding and unwinding water cloth machine to collect the rotational speed data of this part, while the traction speed sensor is installed at the position of the traction device of the winding and unwinding water cloth machine to obtain the traction speed data of the traction device. The acquisition frequency of these sensors is set to 1 Hz, that is, data is collected once per second, ensuring that the changes in the rotational speed and traction speed of the winding and unwinding water cloth machine at different operating stages can be reflected in real time. Through continuous real-time data monitoring, abnormal situations in the operation of the equipment can be detected in a timely manner and effectively adjusted to ensure the smooth progress of the production process and the stability of the hose quality.

[0034] S2, construct a window. Take the serial number of the sampling moment in the window as the abscissa and the rotational speed as the ordinate to construct a coordinate system, and calculate the initial noise probability of the target moment according to the position of the sampling moment in the coordinate system.

[0035] It should be noted that the winding and unwinding water cloth machine usually works in an environment full of vibration sources, such as the vibration of the workshop floor, the operation of adjacent mechanical equipment, etc. These external factors will interfere with the rotational speed sensor, resulting in unstable and fluctuating rotational speed data collected by the sensor. Due to the nature of the vibration source being usually periodic or random, these vibrations not only affect the accurate measurement of the sensor, but also cause the collected data to no longer present a smooth and continuous curve, but show an obvious fluctuating trend. Specifically, these fluctuations can be manifested as periodic vibration interference or random sudden fluctuations, thereby affecting the accuracy and reliability of the data. In order to evaluate the impact of this interference on the rotational speed data, the noise probability can be calculated by analyzing the volatility and randomness of the data points. The higher the noise probability, the stronger the volatility and randomness in the data, indicating that the impact of the external vibration source on the sensor is greater.

[0036] The reason for constructing the window: The window can often reveal relatively subtle changes, especially when the overall trend of the observed data is relatively stable. By analyzing the fluctuations of the observed data within the window, some potential and minor change trends can be discovered, helping to capture local anomalies or mutations.

[0037] Some abnormal phenomena may be short-lived and instantaneous, making it difficult to detect them globally. However, within the local range of the window, especially the fluctuations of the observed data around the target moment, these sudden events can be captured more sensitively.

[0038] In one embodiment, with the target moment as the center, construct a window in the order of sampling time, and the window size is a preset length; take the sampling moments in the window except the target moment as reference moments, and in response to the unequal number of reference moments on the left side and the right side of the target moment, discard the data on the side with fewer reference moments.

[0039] Exemplarily, the preset length is 11, that is, the window size is 11. There are 5 reference times on the left side of the target time and 5 reference times on the right side of the target time. If the target time is the 4th sampling time and there are only 3 reference times on the left side of the target time, then all the reference data on the left side of the target time are discarded. At this time, the window size is 6.

[0040] Taking the sequence number of the sampling time in the window as the abscissa and the rotational speed as the ordinate to construct a coordinate system. Exemplarily, since the window size is set to 11, the horizontal axis of the coordinate system is from 1 to 11 and the vertical axis is the value of the rotational speed.

[0041] Calculating the initial noise probability includes: calculating the distances between any two adjacent sampling times in the window respectively, and the distance satisfies the relational expression:

[0042] , representing the distance between sampling time and sampling time , and respectively representing the rotational speeds of sampling time and sampling time .

[0043] Traversing to obtain the distances between any two sampling times, calculating the mean value of all the distances in the window, and taking the normalized mean value as the initial noise probability.

[0044] By traversing all the adjacent sampling times in the window and calculating the distances, and then obtaining the mean value, it can reflect the smoothness of the rotational speed change. Taking the normalized mean value as the initial noise probability actually quantifies the stability of the rotational speed signal or the noise level.

[0045] In one embodiment, calculating the initial noise probability further includes: calculating the distances between any two adjacent sampling times in the window respectively, and the distance satisfies the relational expression:

[0046] , representing the distance between sampling time and sampling time , and respectively representing the rotational speeds of sampling time and sampling time , representing the two-norm.

[0047] Traversing to obtain the distances between any two sampling times, taking the mean value of all the distances as the first distance, taking the sum of the two distances in which the target time participates in the calculation as the second distance, calculating the ratio of the second distance to the first distance, and taking the normalized ratio as the initial noise probability.

[0048] By analyzing the changes in rotational speed between adjacent moments, sudden changes or abnormal fluctuations in rotational speed data can be effectively identified. These fluctuations are usually related to noise, signal interference, or sensor errors in the system. The smoothness of the rotational speed signal directly affects the subsequent monitoring and analysis accuracy. Therefore, accurate identification of these sudden fluctuations is crucial. By calculating the distance between adjacent sampling moments and normalizing it, the degree of interference of noise on the signal can be effectively quantified. Especially in the case of irregular fluctuations, the impact of noise can be accurately evaluated. This calculation method further reveals whether the fluctuations at the target moment significantly deviate from the normal rotational speed change pattern through the calculation of the distance ratio.

[0049] In one embodiment, calculating the initial noise probability further includes: calculating the distances between any two adjacent sampling moments in the window respectively to construct a distance sequence; obtaining the relative angle of any sampling moment in the window respectively, and calculating the sine value of each relative angle to construct a sine sequence.

[0050] The initial noise probability satisfies the relational expression: , represents the initial noise probability at the target moment , represents the variance of the distance sequence, represents the variance of the sine sequence, represents the normalization function.

[0051] Among them, the relative angle includes: taking any sampling moment in the window as the marked moment, and taking the sampling moment adjacent to the marked moment at the back as the post-marked moment; in the coordinate system, taking the included angle between the line connecting the marked moment and the post-marked moment and the horizontal axis as the relative angle of the marked moment, where the counterclockwise direction is the positive direction.

[0052] It should be noted that the distance sequence reflects the amplitude of the rotational speed change between adjacent sampling moments, while the sine sequence reveals the periodic characteristics of the signal through the calculation of the sine values of the relative angle changes. The variances of these two respectively describe the degree of discreteness and instability of the signal change, and can provide key indicators on whether there are abnormal fluctuations or noise in the signal. By normalizing the variance using the normalization function, the impact degree of noise can be converted into a smooth and quantifiable noise probability, so as to more accurately evaluate the noise risk of the observed data at each sampling moment.

[0053] At each marked moment, by calculating the angle between the line connecting with the post - marked moment and the horizontal axis, a quantified relative angle value is obtained. This not only reflects the speed and direction of the rotational speed change but also reveals the dynamic characteristics of the signal in different time periods. The convention that the counter - clockwise direction is the positive direction further clarifies the positive and negative directions of the angle, making the calculation more standardized and consistent. By analyzing these relative angles, it is possible to identify sudden fluctuations or abnormal patterns that may exist during the rotational speed change process. Especially when there are periodic or regular changes, the deviation or unstable state of the signal can be captured more accurately.

[0054] S3. Construct the rotational speed sequence for each sampling moment in the window and construct the traction speed sequence for each sampling moment in the window. Calculate the correction factor based on the rotational speed sequence and the traction speed sequence to correct the initial noise probability and obtain the final noise probability.

[0055] It should be noted that in order to further improve the accuracy of the noise probability of the rotational speed data points and exclude the interference of external factors or equipment abnormalities on the rotational speed data, the present invention introduces the relationship between the traction speed and the rotational speed of the water - cloth winding and unwinding machine to correct the noise probability of the rotational speed data.

[0056] Specifically, there is a clear positive correlation between the traction speed and the rotational speed of the water - cloth winding and unwinding machine. As the rotational speed of the water - cloth winding and unwinding machine increases, the rotational speed of the winding disc and related rotating components will also increase accordingly, resulting in an increase in the winding speed of the water cloth on the rubber hose. To ensure that the water cloth is wound evenly and tightly on the rubber hose when it passes through the water - cloth winding and unwinding machine, the traction device needs to increase the traction speed so that the rubber hose can pass through the water - cloth winding and unwinding head smoothly and continuously, preventing the phenomenon of water - cloth accumulation or wrinkling. Conversely, when the rotational speed decreases, the winding speed slows down. To avoid water - cloth accumulation or wrinkling, the traction device must reduce the traction speed to ensure that the winding quality is not affected. Based on this positive correlation, the present invention proposes to introduce the traction speed data to correct the calculation of the noise probability of the rotational speed data.

[0057] By analyzing the correlation between the traction speed and the rotational speed data, when the correlation between the two is strong, it indicates that the current rotational speed change is normal and the noise probability should be low; while when the correlation between the two is weak, it may indicate that there are abnormal fluctuations in the rotational speed data, and at this time the noise probability should be high.

[0058] In one embodiment, the final noise probability satisfies the relational expression:

[0059] , represents the final noise probability at the target moment , represents the initial noise probability at the target moment , represents the rotational speed sequence represents the traction speed sequence, represents the similarity, represents the exponential function, represents the normalization function.

[0060] The final noise probability relationship reflects the consistency between the rotational speed change and the traction speed change, thus providing a more reasonable basis for noise probability correction. When the similarity between the rotational speed and the traction speed is high, it means that the operation of the water cloth unwinding and winding machine is relatively normal, and the final noise probability will be correspondingly low. On the contrary, it indicates that there may be abnormal fluctuations and the noise probability increases.

[0061] S4. Determine the filtering length of the observation data according to the final noise probability, and use Vondrak to filter the observation data to complete the state monitoring.

[0062] In one embodiment, traverse to obtain the final noise probabilities at multiple sampling times, preset the initial length of the observation data, and calculate the mean value of the final noise probabilities of the observation data in the initial length; in response to the mean value of the final noise probabilities being greater than the abnormal threshold, iteratively increase the initial length until the final noise probability is not greater than the abnormal threshold or the initial length reaches the preset maximum value, and stop the iteration to obtain the length of the observation data.

[0063] Exemplarily, the initial length is set to 5, and the abnormal threshold is set to 0.4. When the mean value of the final noise probabilities at five sampling times is greater than 0.4, then iteratively add the final noise probability at 1 sampling time in chronological order backward, and recalculate the mean value of the final noise probabilities at 6 sampling times until the mean value of the final noise probabilities is not greater than 0.4 or the number of iterative data is 10. At this time, stop the iteration to obtain the filtering length of the observation data.

[0064] Use the existing Vondrak to filter the observation data. After the filtering is completed, the rotational speed data can more accurately reflect the actual operation of the water cloth unwinding and winding machine. Therefore, the preset rotational speed value can be adjusted in time by real-time monitoring and comparing the deviation between the actual rotational speed and the preset rotational speed value to achieve dynamic correction. When it is found that there is an obvious gap between the actual rotational speed and the preset rotational speed, the preset rotational speed can be appropriately adjusted according to the adjustment strategy, so that the actual rotational speed of the water cloth unwinding and winding machine gradually approaches the ideal rotational speed.

[0065] The embodiment of the present invention also discloses an operation state monitoring system for an automatic water cloth unwinding and winding machine, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the operation state monitoring method for the automatic water cloth unwinding and winding machine according to the present invention is implemented.

[0066] The above system also includes other components well-known to those skilled in the art such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be elaborated here.

[0067] In the present invention, the aforementioned memory may be any tangible medium that contains or stores a program, and the program can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random-access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0068] Although this specification has shown and described multiple embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and concept of the present invention. It should be understood that various alternatives of the embodiments of the present invention described herein may be employed in the practice of the present invention.

[0069] The above are all the preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention shall be covered within the protection scope of the present invention.

Claims

1. A method for monitoring the operating status of an automatic water cloth untangling machine, characterized in that: include: Obtain observation data at a target time, the observation data including rotation speed and traction speed, and the target time is any sampling time; Construct a window, use the sequence number of the sampling moment in the window as the horizontal coordinate and the rotation speed as the vertical coordinate to construct a coordinate system, and calculate the initial noise probability at the target moment according to the position of the sampling moment in the coordinate system; The speed at each sampling moment in the window is constructed as a speed sequence, and the traction speed at each sampling moment in the window is constructed as a traction speed sequence. The correction factor is calculated according to the speed sequence and the traction speed sequence to correct the initial noise probability and obtain the final noise probability. The final noise probability satisfies the relationship: , Indicates the target time The final noise probability is Indicates the target time The initial noise probability is represents the speed sequence, represents the traction speed sequence, Indicates similarity, represents the exponential function, represents the normalization function; The final noise probability of multiple sampling moments is obtained by traversing, the initial length of the observation data is preset, and the final noise probability mean of the observation data in the initial length is calculated; In response to the final noise probability mean being greater than the abnormal threshold, iteratively increasing the initial length until the final noise probability is not greater than the abnormal threshold or the initial length reaches a preset maximum value, stopping the iteration, and obtaining the length of the observed data; Vondrak is used to filter the observed data, and the deviation between the actual speed and the preset speed value is monitored and compared in real time, and the preset speed value is adjusted in time to achieve dynamic correction, so as to complete the state monitoring.

2. The method for monitoring the operating status of the automatic water cloth untangling machine according to claim 1 is characterized in that: The build window includes: Centered on the target time, a window is constructed in the order of sampling time, and the window size is the preset length; The sampling moments except the target moment in the window are taken as reference moments. In response to the unequal number of reference moments on the left side of the target moment and the unequal number of reference moments on the right side of the target moment, the data on the side with fewer reference moments are discarded.

3. The method for monitoring the operating status of the automatic water cloth untangling machine according to claim 1 is characterized in that: The initial noise probability includes: Calculate the distance between any two adjacent sampling moments in the window respectively, and the distance satisfies the relationship: , Indicates the sampling time and sampling time The distance and Respectively represent the sampling time and sampling time Speed; Traverse to obtain the distance between any two sampling moments, calculate the mean of all distances in the window, and use the normalized mean as the initial noise probability.

4. The method for monitoring the operating status of the automatic water cloth untangling machine according to claim 1 is characterized in that: The initial noise probability also includes: Calculate the distance between any two adjacent sampling moments in the window respectively, and the distance satisfies the relationship: , Indicates the sampling time and sampling time The distance and Respectively represent the sampling time and sampling time The rotation speed, represents the two-norm; Traverse to obtain the distance between any two sampling moments, take the mean of all distances as the first distance, take the sum of the two distances involved in the calculation at the target moment as the second distance, calculate the ratio of the second distance to the first distance, and take the normalized ratio as the initial noise probability.

5. The method for monitoring the operating status of the automatic water cloth untangling machine according to claim 1 is characterized in that: The initial noise probability also includes: Calculate the distance between any two adjacent sampling moments in the window to construct a distance sequence; Get the relative angle at any sampling moment in the window respectively, calculate the sine value of each relative angle to construct a sine sequence; The initial noise probability satisfies the relationship: , Indicates the target time The initial noise probability is represents the variance of the distance series, represents the variance of the sine sequence, Represents the normalization function.

6. The method for monitoring the operating status of the automatic water cloth untangling machine according to claim 5 is characterized in that: The relative angles include: Take any sampling time in the window as the marking time, and take the next sampling time adjacent to the marking time as the post-marking time; In the coordinate system, the angle between the line connecting the marking time and the post-marking time and the horizontal axis is taken as the relative angle of the marking time, wherein the counterclockwise direction is taken as the positive direction.

7. Automatic water cloth untangling machine operation status monitoring system, characterized in that: include: Processor; and A memory storing computer instructions, wherein when the computer instructions are executed by the processor, the system executes the method for monitoring the operating status of the automatic water-cloth untangling machine according to any one of claims 1 to 6.

Images