Pressure data monitoring method and system of compressor sealing system

Abstract

The invention relates to the technical field of data processing, in particular to a pressure data monitoring method and system of a compressor sealing system. The method comprises the steps of collecting pressure data, clustering the pressure data by using a DIANA algorithm, marking any class cluster of any round of clustering as a current class cluster, and obtaining an overall distance in the current class cluster and a local distance in the current class cluster; obtaining the abnormal degree of the current class cluster based on the overall distance and the local distance; acquiring the fluctuation amplitude of the current class cluster, and acquiring a split threshold value of the class cluster according to the fluctuation amplitude of the class cluster and the abnormal degree of the class cluster; clustering the pressure data according to an acquisition method of a split threshold value of the class cluster to obtain a final clustering result, and performing anomaly monitoring on the pressure data of the compressor sealing system according to the final clustering result; according to the method, multiple class clusters are split at the same time in the clustering process, so that the sensitivity and accuracy of anomaly detection are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a pressure data monitoring method and system for a compressor sealing system. Background Art

[0002] As a key equipment in many industrial processes, the normal operation of the compressor is crucial to ensuring production efficiency and safety. The integrity of the sealing system in the compressor directly affects the operating status and safety of the compressor. Once the sealing system fails, it may cause gas leakage, reduced efficiency, and even cause safety accidents. By monitoring the pressure data of the sealing system, problems in the sealing system, such as leakage and blockage, can be discovered and solved, thereby improving the operating efficiency of the compressor.

[0003] Xu Kesheng, Journal of Dalian Jiaotong University, Vol. 28, No. 4, December 2007, proposed a clustering algorithm that automatically obtains the k value. The DIANA algorithm in the journal is a hierarchical clustering algorithm that adopts a top-down strategy. First, all objects are placed in one class, and then gradually subdivided into smaller and smaller classes until each object is a class by itself. It can stop when the termination condition is reached.

[0004] Since the pressure data of the compressor is often affected by factors such as environmental changes, operating conditions and load changes, this means that the pressure value may change significantly over time, resulting in different characteristics of the pressure data distribution in different time periods. The DIANA algorithm, as a hierarchical clustering algorithm, forms a hierarchical tree structure by repeatedly splitting clusters. This splitting method enables the algorithm to carefully analyze the changes in the pressure data, whether it is due to normal random fluctuations in the system or abnormal fluctuations caused by external disturbances. However, the DIANA algorithm only selects one cluster to split each time, so a single split may cause abnormal data to be submerged, thereby delaying the detection and response time of system failures and increasing the risk of equipment damage. Summary of the invention

[0005] In order to solve the technical problem that the DIANA algorithm only selects one cluster to split each time, and a single split may cause abnormal data to be submerged, thereby delaying the detection and response time of system faults and increasing the risk of equipment damage, the present invention provides a pressure data monitoring method and system for a compressor sealing system.

[0006] In a first aspect, the present invention provides a method for monitoring pressure data of a compressor sealing system, which adopts the following technical solution: A method for monitoring pressure data of a compressor sealing system comprises the steps of: Collect pressure data; cluster the pressure data using the DIANA algorithm, and record any cluster of any round of clustering as the current cluster; obtain the abnormality degree of the current cluster, where the abnormality degree is the ratio of the overall distance within the current cluster to the local distance within the current cluster; obtain the fluctuation amplitude of the current cluster; Get the split threshold of the current cluster , Represents the fluctuation amplitude of the current cluster; Represents the abnormality level of the current cluster; represents the first hyperparameter; represents the second hyperparameter; exp() represents an exponential function with a natural constant as the base; according to the method for obtaining the splitting threshold, the pressure data is clustered and split to obtain a final clustering result; according to the final clustering result, the pressure data of the compressor sealing system is monitored for abnormalities.

[0007] The innovation of the present invention lies in improving the DIANA algorithm. In each round of clustering, the split threshold of the cluster is used to determine whether the cluster is classified. By setting different split thresholds for different clusters, the split strategy can be flexibly adjusted according to the characteristics of each cluster, thereby improving the detection capability of abnormal situations. It can effectively reduce false positives and false negatives caused by excessive or insufficient splitting, thereby improving the reliability of the monitoring system and enabling operators to more accurately judge the status of the system.

[0008] Preferably, the step of obtaining the overall distance within the current cluster is: ; In the formula, Q represents the overall distance within the current cluster; Represents the number of data in the current cluster; Represents the standard deviation of the data in the current cluster; Represents the Euclidean distance between the i-th data in the current cluster and the center data of the current cluster; Represents the interquartile range of the data in the current cluster; Represents the maximum data value in the current cluster; Represents the minimum data value in the current cluster.

[0009] The larger the overall distance within the cluster, the more dispersed the data in the cluster is, that is, the more abnormal the cluster is. Therefore, the degree of abnormality of the cluster can be obtained based on the overall distance within the cluster.

[0010] Preferably, the step of obtaining the local distance within the current cluster is: ; In the formula, Represents the local distance within the current cluster; Represents the number of data in the current cluster; Represents the mean of the Euclidean distances between the i-th data in the current cluster and all its neighboring points.

[0011] This facilitates the subsequent acquisition of the abnormality degree of the cluster based on the local distance within the cluster.

[0012] Preferably, obtaining the fluctuation amplitude of the current cluster includes: Get the fluctuation characteristics of each data in the current cluster; ; In the formula, Represents the fluctuation amplitude of the current cluster; Represents the number of data in the current cluster; Represents the fluctuation characteristics of the i-th data in the current cluster; Represents the maximum value of the fluctuation characteristics of all data in the current cluster; Represents the minimum value of the fluctuation characteristics of all data in the current cluster.

[0013] The larger the fluctuation range of the cluster, the more the cluster needs to be split, so that the splitting threshold of the cluster can be obtained according to the fluctuation range of the cluster.

[0014] Preferably, obtaining the fluctuation characteristics of each data in the current cluster includes: Obtain the Euclidean distance between the center data of the current cluster and the center data of each other cluster, and record the cluster corresponding to the minimum Euclidean distance as the nearest neighbor cluster of the current cluster; The distance from the i-th data in the current cluster to the central data of the current cluster and the distance from the i-th data in the current cluster to the central data of its nearest neighboring cluster are taken as the fluctuation feature vector of the i-th data in the current cluster, and the modulus of the fluctuation feature vector of the i-th data in the current cluster is taken as the fluctuation feature of the i-th data in the current cluster.

[0015] It is convenient to obtain the fluctuation amplitude of the cluster according to the fluctuation characteristics of each data in the cluster.

[0016] Preferably, the method for obtaining the splitting threshold value is used to cluster and split the pressure data to obtain a final clustering result, including: The clustering round T is preset. According to the clustering round, the DIANA algorithm is used to cluster the pressure data. In any round of clustering, the variance of each cluster and the splitting threshold of each cluster are obtained. If the variance of any cluster of this round of clustering is greater than or equal to the splitting threshold of the cluster of this round of clustering, the data farthest from the center of the cluster in this round of clustering is selected as the splitting point of the cluster of this round of clustering, and the cluster of this round of clustering is split into two subclasses to obtain the clustering result of this round of clustering. The clustering result of the last round is recorded as the final clustering result.

[0017] Preferably, the abnormality monitoring of the pressure data of the compressor sealing system according to the final clustering result includes: Preset data number , if the number of data in any cluster in the final clustering result is less than the preset number of data When , the cluster is considered abnormal in the final clustering result, and the early warning mechanism is triggered to remind relevant personnel to handle it, thus realizing the pressure data monitoring of the compressor sealing system.

[0018] In a second aspect, the present invention provides a pressure data monitoring system for a compressor sealing system, which adopts the following technical solution: A pressure data monitoring system for a compressor sealing system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the pressure data monitoring method for the compressor sealing system is implemented.

[0019] By adopting the above technical solution, the above-mentioned pressure data monitoring method of a compressor sealing system is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.

[0020] The present invention has the following technical effects: The purpose of the present invention is to improve the DIANA algorithm. In each round of clustering, the split threshold of the cluster is used to determine whether the cluster is classified. By setting different split thresholds for different clusters, the split strategy can be flexibly adjusted according to the characteristics of each cluster, thereby improving the detection capability of abnormal situations. False positives and false negatives caused by excessive or insufficient splitting can be effectively reduced, thereby improving the reliability of the monitoring system, allowing operators to more accurately judge the status of the system. Furthermore, the acquisition of the split threshold of the cluster takes into account the overall distance within the cluster and the local distance within the cluster, so that the split threshold of the obtained cluster is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, 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-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0022] Figure 1 It is a flow chart of a method for monitoring pressure data of a compressor sealing system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] 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.

[0024] 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.

[0025] The embodiment of the present invention discloses a method for monitoring pressure data of a compressor sealing system. Figure 1 , comprising steps S1 to S3: S1: Collect pressure data.

[0026] In the embodiment of the present invention, a pressure sensor is installed in the compressor sealing system, and pressure data is collected every two minutes as a sampling moment. The pressure data is collected for a total of two hours to obtain all the pressure data.

[0027] S2: Use the DIANA algorithm to cluster the pressure data, record any cluster of any round of clustering as the current cluster, obtain the overall distance within the current cluster and the local distance within the current cluster, and obtain the abnormality of the current cluster based on the overall distance within the current cluster and the local distance within the current cluster; obtain the fluctuation amplitude of the current cluster.

[0028] It should be noted that since the pressure data of the compressor is often affected by factors such as environmental changes, operating conditions and load changes, this means that the pressure value may change significantly over time, resulting in different characteristics of the pressure data distribution in different time periods. The DIANA algorithm, as a hierarchical clustering algorithm, forms a hierarchical tree structure by repeatedly splitting clusters. This splitting method enables the algorithm to carefully analyze the changes in the pressure data, whether it is due to normal random fluctuations of the system or abnormal fluctuations caused by external disturbances. However, the DIANA algorithm only selects one cluster for splitting each time, so a single split may cause abnormal data to be submerged, thereby delaying the detection and response time of system faults and increasing the risk of equipment damage. Therefore, the DIANA algorithm is improved. In each round of clustering, multiple clusters need to be selected for splitting to ensure the accuracy of the clustering results, thereby improving the sensitivity and accuracy of anomaly detection. When selecting clusters, it is necessary to judge whether the clusters are classified according to the split threshold of the clusters to ensure the accuracy of the clustering results, thereby improving the sensitivity and accuracy of anomaly monitoring.

[0029] Step S2 includes steps S20 and S21, which are specifically as follows: S20: Use the DIANA algorithm to cluster the pressure data, record any cluster of any round of clustering as the current cluster, obtain the overall distance within the current cluster and the local distance within the current cluster, and obtain the abnormality degree of the current cluster based on the overall distance within the current cluster and the local distance within the current cluster.

[0030] It should be noted that when a cluster has a high degree of abnormality, it often means that there is noise or outliers inside the cluster, which will reduce the overall quality of the cluster. It needs to be split accordingly to ensure that the data in each sub-cluster is more consistent, so as to better isolate the abnormal data. At the same time, the fluctuation range of the data in the cluster is a key indicator to measure the fluctuation of the data in the cluster. A larger fluctuation range means that the data in the cluster changes greatly, which may indicate potential abnormalities or changes. Monitoring the fluctuation range of the cluster will help identify potential abnormalities in the compressor sealing system. Therefore, based on the degree of abnormality and fluctuation range of the cluster, the necessity of splitting the cluster is comprehensively analyzed, and the splitting threshold of the cluster is obtained to determine whether the cluster needs to be split, to ensure that each cluster can contain more similar samples, thereby improving the effect and accuracy of clustering, so as to facilitate the identification and monitoring of abnormal data.

[0031] It should be noted that when obtaining the degree of abnormality within a cluster, it is often measured based on the mean Euclidean distance from all data in the cluster to the cluster center data. This distance provides global information about the cluster and indicates the overall dispersion of the cluster. The larger the value, the more dispersed the data in the cluster is, which may contain abnormal values. Therefore, the overall distance within the cluster is first obtained based on this feature. However, in the actual data distribution of the cluster, there may be some data that appear normal overall but are abnormal locally. In this case, it is necessary to combine the mean Euclidean distance between each data in the cluster and all its neighboring points to comprehensively judge the local distance within the cluster to improve the accuracy of anomaly detection. Finally, the degree of abnormality of the cluster is obtained based on the overall distance and the local distance within the cluster.

[0032] In the embodiment of the present invention, the DIANA algorithm is used to cluster the pressure data, and any cluster of any round of clustering is recorded as the current cluster, and the overall distance within the current cluster is obtained: ; In the formula, Q represents the overall distance within the current cluster; Represents the number of data in the current cluster; Represents the standard deviation of the data in the current cluster; Represents the Euclidean distance between the i-th data in the current cluster and the center data of the current cluster; Represents the interquartile range of the data in the current cluster; Represents the maximum data value in the current cluster; Represents the minimum data value in the current cluster; Represents the mean Euclidean distance from all data in the current cluster to the center data of the current cluster. Here The role of is to standardize the Euclidean distance from all data in the current cluster to the center data of the current cluster. The larger the mean of the Euclidean distance from all data in the current cluster to the center data of the current cluster, the larger the overall distance within the current cluster. The larger the value is, the more concentrated the distribution of data in the current cluster is, which means the overall distance within the current cluster is smaller; is the range of the data in the current cluster. The larger its value is, the greater the overall distance within the current cluster is.

[0033] In this embodiment of the present invention, the local distance within the current cluster is obtained: ; In the formula, Represents the local distance within the current cluster; Represents the number of data in the current cluster; Represents the mean of the Euclidean distances between the i-th data and all its neighboring points in the current cluster; the larger the mean of the Euclidean distances between each data in the current cluster and all its neighboring points, the larger the local distance in the current cluster.

[0034] The ratio of the overall distance within the current cluster to the local distance within the current cluster is taken as the abnormality degree of the current cluster. It should be noted that when the overall distance within the current cluster is larger than the local distance within the current cluster, it indicates that there is a relatively large abnormal dispersion phenomenon in the current cluster, and the abnormality degree of the current cluster is higher.

[0035] S21: Get the fluctuation range of the current cluster.

[0036] It should be noted that if the distance from any data in the cluster to the center data of the cluster and the distance from the data in the cluster to the center data of its nearest neighbor cluster are larger, it indicates the fluctuation characteristics of the data in the cluster; if the mean of the fluctuation characteristics of all data in the cluster is larger, it indicates that the fluctuation amplitude of the cluster is larger.

[0037] In the embodiment of the invention, the Euclidean distance between the center data of the current cluster and the center data of each other cluster is obtained, and the cluster corresponding to the minimum Euclidean distance is recorded as the nearest neighbor cluster of the current cluster.

[0038] The distance from the i-th data in the current cluster to the central data of the current cluster and the distance from the i-th data in the current cluster to the central data of its nearest neighboring cluster are used as the fluctuation feature vector of the i-th data in the current cluster. The modulus of the fluctuation feature vector of the i-th data in the current cluster is used as the fluctuation feature of the i-th data in the current cluster. Similarly, the fluctuation feature of each data in the current cluster is obtained.

[0039] Get the fluctuation range of the current cluster: ; In the formula, Represents the fluctuation amplitude of the current cluster; Represents the number of data in the current cluster; Represents the fluctuation characteristics of the i-th data in the current cluster; Represents the maximum value of the fluctuation characteristics of all data in the current cluster; Represents the minimum value of the fluctuation characteristics of all data in the current cluster; the larger the mean value of the fluctuation characteristics of all data in the current cluster, the greater the fluctuation amplitude of the current cluster.

[0040] S3: According to the fluctuation amplitude of the current cluster and the abnormality degree of the current cluster, the splitting threshold of the current cluster is obtained; according to the splitting threshold of the current cluster, the pressure data is clustered and split to obtain the final clustering result, and the pressure data of the compressor sealing system is monitored for abnormalities according to the final clustering result.

[0041] Step S3 includes steps S30 and S31, which are specifically as follows: S30: Obtaining a split threshold of the current cluster according to the fluctuation amplitude of the current cluster and the abnormality degree of the current cluster.

[0042] It should be noted that the greater the abnormality of a known cluster, the smaller the splitting threshold needs to be set for the cluster to ensure that it is split and better highlight the abnormal points; and the larger the fluctuation range of the cluster, it means that there may be potential anomalies in the cluster, and it may also contain different data change trends, which requires more detailed splitting to identify and manage these changes, and a smaller splitting threshold needs to be set. Therefore, the splitting threshold of the cluster is obtained according to the abnormality degree of the cluster and the fluctuation range of the cluster.

[0043] In this embodiment of the present invention, the splitting threshold of the current cluster is obtained: ; In the formula, Represents the splitting threshold of the current cluster; Represents the fluctuation amplitude of the current cluster; Represents the abnormality level of the current cluster; represents the first hyperparameter; represents the second hyperparameter; Represents the abnormality weight of the current cluster; represents the fluctuation amplitude weight of the current cluster; since the abnormality degree of the current cluster can directly reflect the situation of abnormal data in the current cluster, and the fluctuation amplitude of the current cluster mainly reflects whether there is potential abnormality in the current cluster, the acquisition of the splitting threshold of the current cluster mainly depends on the abnormality degree of the current cluster to adjust it, and the fluctuation amplitude of the current cluster is only to avoid some potential abnormalities from being ignored. It is necessary to combine the fluctuation amplitude of the current cluster for comprehensive analysis to obtain the splitting threshold of the current cluster to ensure the accuracy of the final result. Therefore, in the embodiment of the present invention, the preset , ; exp() represents an exponential function with a natural constant as the base; if the abnormality of the current cluster is greater, a smaller split threshold needs to be set for the current cluster to ensure that the cluster is split and better highlight the abnormal data; if the fluctuation amplitude of the current cluster is larger, it means that there may be potential anomalies in the current cluster or it contains different data change trends. A smaller split threshold needs to be set for the current cluster to identify and manage these changes.

[0044] S31: Clustering and splitting the pressure data according to the splitting threshold of the current cluster to obtain a final clustering result, and performing abnormal monitoring on the pressure data of the compressor sealing system according to the final clustering result.

[0045] It should be noted that the traditional DIANA algorithm is known to usually select the cluster with the largest inter-class variance for splitting, and this single split may cause abnormal data to be submerged, thereby delaying fault detection and response time and increasing the risk of equipment damage. Therefore, the DIANA algorithm is improved. In each round of clustering, it is necessary to select multiple clusters for splitting to ensure the accuracy of the clustering results, thereby improving the sensitivity and accuracy of anomaly detection. When selecting clusters, it is necessary to judge whether the clusters are classified based on the split threshold of the clusters to ensure the accuracy of the clustering results, thereby improving the sensitivity and accuracy of anomaly monitoring.

[0046] In an embodiment of the present invention, a clustering round T is preset, and the DIANA algorithm is used to cluster the pressure data. In any round of clustering, the variance of each cluster and the splitting threshold of each cluster are obtained. If the variance of any cluster of this round of clustering is greater than or equal to the splitting threshold of the cluster of this round of clustering, the data farthest from the center of the cluster in this round of clustering is selected as the splitting point of the cluster of this round of clustering, and the cluster of this round of clustering is split into two sub-classes to obtain the clustering result of this round of clustering, and the clustering result of the last round of clustering is recorded as the final clustering result.

[0047] Preset data number , if the number of data in any cluster in the final clustering result is less than the preset number of data , this cluster is an abnormal cluster in the final clustering result, that is, there is an abnormality in the pressure data of the compressor sealing system. At this time, the early warning mechanism is triggered and the relevant personnel are reminded to handle it to realize the pressure data monitoring of the compressor sealing system.

[0048] In the embodiment of the present invention, the preset clustering round T=10, the preset data number Q=10, in other embodiments, the implementer may preset the values ​​of the clustering round and the data number according to the specific implementation method.

[0049] An embodiment of the present invention further discloses a pressure data monitoring system for a compressor sealing system, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a pressure data monitoring method for a compressor sealing system according to the present invention is implemented.

[0050] 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.

[0051] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage 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 the device or accessible or connectable to the device.

[0052] 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.

[0053] 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 method for monitoring pressure data of a compressor sealing system, characterized in that: Includes steps: Collect pressure data; cluster the pressure data using the DIANA algorithm, and record any cluster of any round of clustering as the current cluster; obtain the abnormality degree of the current cluster, where the abnormality degree is the ratio of the overall distance within the current cluster to the local distance within the current cluster; obtain the fluctuation amplitude of the current cluster; Get the split threshold of the current cluster , Represents the fluctuation amplitude of the current cluster; Represents the abnormality level of the current cluster; represents the first hyperparameter; represents the second hyperparameter; exp() represents an exponential function with a natural constant as the base; according to the method for obtaining the splitting threshold, the pressure data is clustered and split to obtain a final clustering result; according to the final clustering result, the pressure data of the compressor sealing system is monitored for abnormalities.

2. The method for monitoring pressure data of a compressor sealing system according to claim 1, characterized in that: The steps for obtaining the overall distance within the current cluster are: ； In the formula, Q represents the overall distance within the current cluster; Represents the number of data in the current cluster; Represents the standard deviation of the data in the current cluster; Represents the Euclidean distance between the i-th data in the current cluster and the center data of the current cluster; Represents the interquartile range of the data in the current cluster; Represents the maximum data value in the current cluster; Represents the minimum data value in the current cluster.

3. The method for monitoring pressure data of a compressor sealing system according to claim 1, characterized in that: The steps for obtaining the local distance within the current cluster are: ； In the formula, Represents the local distance within the current cluster; Represents the number of data in the current cluster; Represents the mean of the Euclidean distances between the i-th data in the current cluster and all its neighboring points.

4. The method for monitoring pressure data of a compressor sealing system according to claim 1, characterized in that: The obtaining of the fluctuation range of the current cluster includes: Get the fluctuation characteristics of each data in the current cluster; ； In the formula, Represents the fluctuation amplitude of the current cluster; Represents the number of data in the current cluster; Represents the fluctuation characteristics of the i-th data in the current cluster; Represents the maximum value of the fluctuation characteristics of all data in the current cluster; Represents the minimum value of the fluctuation characteristics of all data in the current cluster.

5. A method for monitoring pressure data of a compressor sealing system according to claim 4, characterized in that: The step of obtaining the fluctuation characteristics of each data in the current cluster includes: Obtain the Euclidean distance between the center data of the current cluster and the center data of each other cluster, and record the cluster corresponding to the minimum Euclidean distance as the nearest neighbor cluster of the current cluster; The distance from the i-th data in the current cluster to the central data of the current cluster and the distance from the i-th data in the current cluster to the central data of its nearest neighboring cluster are taken as the fluctuation feature vector of the i-th data in the current cluster, and the modulus of the fluctuation feature vector of the i-th data in the current cluster is taken as the fluctuation feature of the i-th data in the current cluster.

6. The method for monitoring pressure data of a compressor sealing system according to claim 1, characterized in that: The method for obtaining the splitting threshold value is used to cluster and split the pressure data to obtain a final clustering result, including: The clustering round T is preset. According to the clustering round, the DIANA algorithm is used to cluster the pressure data. In any round of clustering, the variance of each cluster and the splitting threshold of each cluster are obtained. If the variance of any cluster of this round of clustering is greater than or equal to the splitting threshold of the cluster of this round of clustering, the data farthest from the center of the cluster in this round of clustering is selected as the splitting point of the cluster of this round of clustering, and the cluster of this round of clustering is split into two subclasses to obtain the clustering result of this round of clustering. The clustering result of the last round is recorded as the final clustering result.

7. The method for monitoring pressure data of a compressor sealing system according to claim 1, characterized in that: The abnormal monitoring of the pressure data of the compressor sealing system according to the final clustering result includes: Preset data number , if the number of data in any cluster in the final clustering result is less than the preset number of data When , the cluster is considered abnormal in the final clustering result, and the early warning mechanism is triggered to remind relevant personnel to handle it, thus realizing the pressure data monitoring of the compressor sealing system.

8. A pressure data monitoring system for a compressor sealing system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a pressure data monitoring method for a compressor sealing system according to any one of claims 1 to 7 is implemented.

Images