A real-time monitoring method and system for overflow dyeing equipment data

Abstract

The present invention relates to the field of overflow dyeing equipment, and more specifically, the present invention relates to a real-time monitoring method and system for overflow dyeing equipment data. The method comprises: obtaining multidimensional operation data; calculating the local density and preference degree of a target point in different neighborhood ranges, taking the neighborhood range with a preference degree greater than a preset preference threshold as the preferred range, and taking the local density mean of all preferred ranges as the optimal local density of the target point; traversing to obtain the optimal local density of each multidimensional operation data to calculate the cluster center possibility of the target point; taking the target point with a cluster center possibility greater than a preset threshold as a candidate center point, screening the candidate center points to complete clustering, obtaining cluster clusters, and completing the monitoring of the overflow dyeing equipment according to the cluster clusters. Through the technical solution of the present invention, the accuracy of the overflow dyeing equipment data monitoring results can be improved.

Description

Technical Field

[0001] The present invention relates to the field of overflow dyeing equipment, and more specifically, to a real-time monitoring method and system for overflow dyeing equipment data. Background Art

[0002] With the rapid development of industrial automation technology, the dyeing industry is constantly pursuing higher efficiency, more precise control and lower resource waste in the production process. In the dyeing process, overflow dyeing is a common and efficient dyeing method, which is widely used in textile, printing and dyeing and other liquid dyeing processes. The core principle of overflow dyeing equipment is to achieve uniform dyeing by circulating the dye liquid continuously and fully contacting the liquid with the material.

[0003] During the overflow dyeing process, the equipment may malfunction or performance fluctuate due to various reasons, resulting in unstable dyeing quality. For example, too high or too low dyeing liquid flow, inaccurate temperature control, too high overflow liquid concentration, etc., may directly lead to fluctuations in dyeing quality. If not discovered and adjusted in time, it may eventually lead to dyeing failure of the production batch or even equipment damage. Therefore, how to monitor the operating status of dyeing equipment in real time, discover potential problems in time, and issue early warnings has become the key to improving dyeing quality and production efficiency.

[0004] The existing Chinese patent application document with publication number CN116756597A discloses a real-time monitoring method for harmonic data of wind turbines based on artificial intelligence, wherein a cutoff distance is calculated according to a harmonic anomaly density index, and the harmonic data is clustered based on a density peak clustering algorithm and the cutoff distance to obtain a clustering result of the harmonic data.

[0005] However, different clusters have different densities, and a cluster with a smaller density may be misjudged as part of a cluster with a higher density, resulting in inaccurate clustering results when using density peak clustering to monitor data. Summary of the invention

[0006] In order to solve the problem of inaccurate clustering results, the present invention proposes a real-time monitoring method and system for overflow dyeing equipment data.

[0007] In a first aspect, the present invention discloses a real-time monitoring method for overflow dyeing equipment data, comprising: obtaining multidimensional operation data of the overflow dyeing equipment after preprocessing; taking any multidimensional operation data as a target point, taking the multidimensional operation data in the neighborhood range of the target point as a reference point, presetting neighborhood ranges of different sizes for the target point, calculating the local density and the degree of preference of the target point in different neighborhood ranges, taking the neighborhood range with a degree of preference greater than a preset preferred threshold as the preferred range, and taking the local density mean of all preferred ranges as the optimal local density of the target point, and the neighborhood range corresponding to the optimal local density is the maximum neighborhood range; traversing to obtain the optimal local density of each multidimensional operation data to calculate the cluster center possibility of the target point, and the cluster center possibility satisfies the relationship:

[0008] , represents the cluster center possibility, represents the optimal local density, represents the total number of reference points in the maximum neighborhood range, Indicates reference point In Dimension The value of Indicates that the target point is in dimension The value of Represents the total number of dimensions, represents the exponential function, represents a normalization function; the target point whose cluster center possibility is greater than a preset threshold is taken as a candidate center point, the candidate center point is screened to complete clustering, and cluster clusters are obtained, and the overflow dyeing equipment is monitored according to the cluster clusters.

[0009] The local density analysis of the multi-dimensional operation data of the overflow dyeing equipment is carried out, and combined with the optimization selection of the neighborhood range, the optimal local density and cluster center possibility of the target point are effectively identified, so as to accurately locate the operation status and cluster structure of the equipment. By calculating the density in different neighborhood ranges, the local characteristics of the equipment under different operating conditions can be reflected, avoiding the wrong clustering caused by uneven data distribution or noise. At the same time, screening the multi-dimensional operation data with a higher probability of cluster center as the clustering core helps to accurately identify the abnormal mode or operation trend of the equipment, and improves the accuracy and real-time performance of overflow dyeing equipment monitoring.

[0010] Preferably, the local density includes: for a neighborhood range of any size, calculating the average Euclidean distance between the target point and each reference point, and taking the reciprocal of the average Euclidean distance as the local density.

[0011] By calculating the average Euclidean distance between the target point and the reference point and taking its reciprocal as the local density, we can reflect the distribution density of the data points in the local neighborhood. The closer the distance, the greater the local density, indicating that the target points are more concentrated in the area, which helps to identify the intrinsic structure and abnormal patterns of the data.

[0012] Preferably, the local density further includes: for a neighborhood range of any size, calculating the average Euclidean distance between the target point and each reference point, and taking the ratio of the radius of the neighborhood range to the average Euclidean distance as the local density.

[0013] The ratio reflects the relative density of the target point relative to other data points in its neighborhood, and can effectively distinguish the density of data points in different regions. When the target point is located in a dense area, the local density is high, while when it is in a sparse area, the local density is low.

[0014] Preferably, the degree of optimization includes: presetting an initial neighborhood range, respectively calculating the mean of all local densities of the target point from the initial neighborhood range to any neighborhood range; the degree of optimization satisfies the relationship:

[0015] , Represents the neighborhood range The degree of preference, Represents the neighborhood range The local density of Represents the range from the initial neighborhood to the neighborhood The mean of all local densities in Represents the range from the initial neighborhood to the neighborhood The mean of all local densities in Represents the neighborhood range The total number of reference points, represents the total number of reference points in the initial neighborhood, Represents the neighborhood range The total number of reference points, Represents an exponential function.

[0016] The degree of preference reflects the stability and consistency of the local density distribution within the neighborhood. When the density fluctuation within the neighborhood is small and similar to the initial range, the degree of preference is high, indicating that the neighborhood can more accurately represent the local structure of the target point.

[0017] Preferably, the preferred degree also satisfies the relationship:

[0018] , Represents the neighborhood range The degree of preference, Represents the neighborhood range The local density of Represents the neighborhood range The local density of Represents the neighborhood range The total number of reference points, Represents the neighborhood range The total number of reference points.

[0019] Preferably, the screening of the candidate center points to complete clustering and obtain cluster clusters includes: for any candidate center point, if there are other candidate center points except itself in the maximum neighborhood range of any candidate center point, then only the candidate center point corresponding to the maximum value of the cluster center possibility is retained; traversing the screening steps to obtain all cluster center points, and completing clustering according to the cluster center points using the density peak clustering algorithm to obtain cluster clusters.

[0020] The method of retaining the point with the highest probability of cluster center is to eliminate the redundant points in the overlapping area, so as to ensure that the center point of each cluster has higher discrimination and representativeness. It can accurately identify the density peak area in the data, further improving the quality and stability of the clustering results.

[0021] Preferably, the monitoring of the overflow dyeing equipment based on the clustering clusters includes: marking the clusters whose number of multidimensional operating data within the cluster is less than a preset number as abnormal clusters; in response to the ratio of the abnormal clusters to the total number of clusters being greater than a preset abnormal threshold, generating and sending an alarm signal.

[0022] In a second aspect, the present invention discloses a real-time monitoring system for overflow dyeing equipment data, comprising: a processor; and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the system executes the above-mentioned real-time monitoring method for overflow dyeing equipment data.

[0023] Beneficial effects of the present invention:

[0024] The present invention can evaluate the equipment operation status in real time and identify potential abnormal behaviors by performing local density calculation, optimization degree analysis and clustering processing on multidimensional operation data. By calculating the local density in different neighborhood ranges and screening the candidate center points according to the possibility of cluster centers, the operation data of the equipment can be effectively clustered and analyzed, thereby accurately monitoring the working status of the equipment. The results of the cluster analysis can timely identify abnormal clusters and remind equipment maintenance personnel through an alarm mechanism to avoid equipment failure or performance degradation. It not only improves the accuracy and real-time nature of monitoring, but also can adapt to complex multidimensional data environments, especially in improving equipment stability, reducing failure rates and optimizing dyeing processes, and can significantly improve the operating efficiency and production quality of overflow dyeing equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0026] Figure 1 It is a flow chart of a method for real-time monitoring of overflow dyeing equipment data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0028] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" 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 collections.

[0029] The present invention provides a real-time monitoring method for overflow dyeing equipment data. Figure 1 As shown, a real-time monitoring method for overflow dyeing equipment data includes steps S1 to S4, which are described in detail below.

[0030] S1, obtain multi-dimensional operation data of overflow dyeing equipment after pre-processing.

[0031] It should be noted that overflow dyeing equipment is used for dyeing processes in the textile, printing and dyeing industries. The dye contacts the fabric or fiber during the dyeing process and completes the dyeing through overflow. In order to ensure the dyeing effect, reduce resource waste and improve production efficiency, it is necessary to monitor multiple parameters in the operation of the equipment and identify operational anomalies in a timely manner. When anomalies are identified, an alarm can be issued in a timely manner, thereby avoiding large-scale waste or equipment damage in the production process.

[0032] In one embodiment, the multidimensional operation data of the overflow dyeing device is obtained according to a preset sampling interval, and the preset sampling interval is set to 1 Hz. The missing multidimensional operation data is filled using the mean filling method, the outliers in the multidimensional operation data are identified and processed using the Z-score method, and the Kalman filter is used to reduce the noise in the multidimensional operation data.

[0033] Exemplarily, the multidimensional operation data are temperature data, flow data and pressure data. The temperature of the dyeing solution has an important influence on the dyeing effect. Too high or too low temperature will lead to unstable dyeing quality and even damage the fiber. The flow rate of the dyeing solution determines the uniformity of dyeing. The appropriate flow rate can ensure that the dye can evenly penetrate into the fiber or fabric. The pressure of the dyeing solution in the overflow dyeing equipment affects the contact effect between the dye and the plant. High pressure is conducive to the penetration of the dye, but too high pressure may cause equipment damage or mechanical damage to the fiber.

[0034] S2, preset neighborhood ranges of different sizes for the target point, calculate the local density and preference degree of the target point in different neighborhood ranges, take the neighborhood range with a preference degree greater than the preset preference threshold as the preferred range, and take the local density mean of all preferred ranges as the optimal local density of the target point.

[0035] It should be noted that the traditional density peak clustering algorithm mainly relies on local density distribution to identify the cluster center, but it may cause misjudgment for the parameter monitoring of overflow dyeing equipment. The parameter distribution of the equipment is uneven (such as the temperature control system adjusting the temperature resulting in data distribution differences). When the traditional algorithm calculates the local density at a single scale, it is easy to misjudge the low-density cluster as part of the high-density cluster. Therefore, the multi-scale method can be used to calculate the optimal local density of data points according to the distribution characteristics of different regions, thereby improving the clustering accuracy and avoiding misjudgment.

[0036] In one embodiment, any multi-dimensional operating data is used as a target point, and the multi-dimensional operating data in the neighborhood of the target point is used as a reference point.

[0037] Neighborhood ranges of different sizes are preset for the target point, and the local density and degree of preference of the target point in different neighborhood ranges are calculated.

[0038] The local density includes: for a neighborhood range of any size, calculating the average Euclidean distance between the target point and each reference point, and taking the inverse of the average Euclidean distance as the local density.

[0039] The optimization degree includes: presetting an initial neighborhood range, and calculating all local density means of the target point from the initial neighborhood range to any neighborhood range.

[0040] , Represents the neighborhood range The degree of preference, Represents the neighborhood range The local density of Represents the range from the initial neighborhood to the neighborhood The mean of all local densities in Represents the range from the initial neighborhood to the neighborhood The mean of all local densities in Represents the neighborhood range The total number of reference points, represents the total number of reference points in the initial neighborhood, Represents the neighborhood range The total number of reference points, Represents an exponential function.

[0041] The optimal density is calculated by gradually increasing the range of the neighborhood. Taking into account the differences in the distribution of overflow dyeing equipment parameters, the uniformity of the neighborhood also varies. Initially, the neighborhood of the target point is small and contains a limited number of reference points. It is usually manifested as a higher or lower local density around the target point, depending on whether it is located in a high-density area (such as the center of the cluster) or a low-density area (such as the edge). As the range of the neighborhood gradually increases, the number of reference points in the neighborhood increases, and the local density gradually stabilizes, indicating that the newly added reference points still belong to the same area. However, when the neighborhood range expands to the boundary of the area, the newly added reference points begin to cross different areas, and the local density changes significantly.

[0042] Exemplarily, the initial neighborhood range is 10, and the size is gradually increased with a step size of 1. The neighborhood range of the target point gradually increases from the initial neighborhood range, and the local density and the degree of preference of the neighborhood range after each increase are calculated. The neighborhood range is screened according to the degree of preference, and the neighborhood range with a degree of preference greater than a preset preferred threshold is taken as the preferred range. Preferably, the preset preferred threshold is set to 0.8. At this time, the local density average of all preferred ranges is taken as the optimal local density of the target point.

[0043] According to the above method, the optimal local density of the target point can be obtained, and the neighborhood range corresponding to the optimal local density is the maximum neighborhood range.

[0044] In one embodiment, the method for obtaining the local density can be replaced by: for a neighborhood range of any size, calculating the average Euclidean distance between the target point and each reference point, and taking the ratio of the radius of the neighborhood range to the average Euclidean distance as the local density.

[0045] In one embodiment, the method for obtaining the preference level can be replaced by:

[0046] , Represents the neighborhood range The degree of preference, Represents the neighborhood range The local density of Represents the neighborhood range The local density of Represents the neighborhood range The total number of reference points, Represents the neighborhood range The total number of reference points.

[0047] S3, traverses to obtain the optimal local density of each multidimensional running data to calculate the cluster center possibility of the target point.

[0048] It should be noted that in the clustering process, it is generally believed that the center of a region with higher density or uniform density distribution is more likely to become a cluster center. Therefore, the present invention evaluates the possibility of a data point as a cluster center by calculating the optimal local density of any data point and the distribution of data points in its neighborhood.

[0049] In one embodiment, the cluster center likelihood satisfies the relationship:

[0050] , represents the cluster center possibility, represents the optimal local density, represents the total number of reference points in the maximum neighborhood range, Indicates reference point In Dimension The value of Indicates that the target point is in dimension The value of Represents the total number of dimensions, represents the exponential function, Represents the normalization function.

[0051] S4, taking the target point whose cluster center possibility is greater than the preset threshold as the candidate center point, screening the candidate center point to complete clustering, obtaining the cluster cluster, and completing the monitoring of the overflow dyeing equipment according to the cluster cluster.

[0052] It should be noted that in the same area, multidimensional operation data that are closer to the cluster center usually have similar optimal local density, and due to their close locations, their cluster center possibilities are also similar. Therefore, in order to avoid the distance between different cluster centers being too small, which will lead to inaccurate clustering results, it is necessary to screen all multidimensional operation data based on their cluster center possibilities to ensure appropriate spacing between cluster centers.

[0053] In one embodiment, for any candidate center point, if there are other candidate center points except itself in the maximum neighborhood range of any candidate center point, only the candidate center point corresponding to the maximum value of the cluster center possibility is retained; all cluster center points are obtained by traversing the screening steps, and clustering is completed according to the cluster center points using the density peak clustering algorithm to obtain a cluster cluster.

[0054] The clusters whose number of multi-dimensional operation data is less than a preset number are marked as abnormal clusters; in response to the ratio of the abnormal cluster to the total number of clusters being greater than a preset abnormal threshold, an alarm signal is generated and sent.

[0055] Exemplarily, clusters with less than 10 multi-dimensional operation data within the cluster are marked as abnormal clusters. If the ratio of the abnormal clusters to the total number of clusters is greater than 0.2, an early warning is issued to determine that the overflow dyeing equipment is abnormal.

[0056] An embodiment of the present invention also discloses a real-time monitoring system for overflow dyeing equipment data, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a real-time monitoring method for overflow dyeing equipment data according to the present invention is implemented.

[0057] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0058] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0059] Although this specification has shown and described a number of 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 conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0060] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A real-time monitoring method for overflow dyeing equipment data, characterized in that: include: Obtain multi-dimensional operation data of overflow dyeing equipment after pretreatment; Taking any multidimensional running data as the target point, taking the multidimensional running data in the neighborhood range of the target point as the reference point, presetting neighborhood ranges of different sizes for the target point, calculating the local density and the degree of preference of the target point in different neighborhood ranges, taking the neighborhood range with a degree of preference greater than the preset preferred threshold as the preferred range, and taking the local density mean of all preferred ranges as the optimal local density of the target point, and the neighborhood range corresponding to the optimal local density is the maximum neighborhood range; The optimal local density of each multidimensional running data is obtained by traversing to calculate the cluster center possibility of the target point. The cluster center possibility satisfies the relationship: , represents the cluster center possibility, represents the optimal local density, represents the total number of reference points in the maximum neighborhood range, Indicates reference point In Dimension The value of Indicates that the target point is in dimension The value of Represents the total number of dimensions, represents the exponential function, represents the normalization function; The target points whose cluster center probability is greater than a preset threshold are taken as candidate center points, and the candidate center points are screened to complete clustering, and cluster clusters are obtained. The overflow dyeing equipment is monitored based on the cluster clusters.

2. A real-time monitoring method for overflow dyeing equipment data according to claim 1, characterized in that: The local density includes: For any size of neighborhood, the average Euclidean distance between the target point and each reference point is calculated, and the inverse of the average Euclidean distance is used as the local density.

3. A real-time monitoring method for overflow dyeing equipment data according to claim 1, characterized in that: The local density also includes: For any size of neighborhood, the average Euclidean distance between the target point and each reference point is calculated, and the ratio of the radius of the neighborhood to the average Euclidean distance is used as the local density.

4. The real-time monitoring method for overflow dyeing equipment data according to claim 1, characterized in that: The preferred levels include: Preset the initial neighborhood range, and calculate the mean of all local densities of the target point from the initial neighborhood range to any neighborhood range; The degree of preference satisfies the relationship: , Represents the neighborhood range The degree of preference, Represents the neighborhood range The local density of Represents the range from the initial neighborhood to the neighborhood The mean of all local densities in Represents the range from the initial neighborhood to the neighborhood The mean of all local densities in Represents the neighborhood range The total number of reference points, represents the total number of reference points in the initial neighborhood, Represents the neighborhood range The total number of reference points, Represents an exponential function.

5. The method for real-time monitoring of overflow dyeing equipment data according to claim 1, characterized in that: The preference also satisfies the relationship: , Represents the neighborhood range The degree of preference, Represents the neighborhood range The local density of Represents the neighborhood range The local density of Represents the neighborhood range The total number of reference points, Represents the neighborhood range The total number of reference points.

6. A real-time monitoring method for overflow dyeing equipment data according to claim 1, characterized in that: The screening of the center points to be selected to complete clustering and obtain the clusters includes: For any candidate center point, if there are other candidate center points except itself in the maximum neighborhood range of any candidate center point, only the candidate center point corresponding to the maximum value of cluster center possibility is retained; All cluster center points are obtained by traversing the screening steps, and clustering is completed according to the cluster center points using the density peak clustering algorithm to obtain cluster clusters.

7. The method for real-time monitoring of overflow dyeing equipment data according to claim 1, characterized in that: The monitoring of overflow dyeing equipment according to the clustering clusters includes: Marking clusters whose number of multi-dimensional running data is less than a preset number as abnormal clusters; In response to the ratio of the abnormal cluster to the total number of clustered clusters being greater than a preset abnormal threshold, an alarm signal is generated and sent.

8. A real-time monitoring system for overflow dyeing equipment data, characterized in that: include: Processor; and A memory storing computer instructions, wherein when the computer instructions are executed by a processor, the system executes a method for real-time monitoring of overflow dyeing equipment data according to any one of claims 1 to 7.

Images