A method, device and system for detecting the sealing performance of a pneumatic sealing rotary joint

Abstract

The present application relates to the technical field of sealing detection, and specifically to a sealing detection method, device and system for a pneumatic sealing rotary joint, the method comprising: obtaining data of various parameters during the sealing detection process of the rotary joint; analyzing the difference between the data discreteness of each parameter in each cluster and the data of other parameters, and determining the relative characteristic value of each parameter in each cluster based on the correlation between each parameter and other parameters; determining the relative value of the state response of each cluster based on the difference between the relative characteristic value of each parameter in each cluster and other clusters; obtaining the sealing performance response value of each parameter based on the distribution of the relative value of each state response and the relative characteristic value of each parameter; determining the sealing performance detection value based on the proportion of the sealing performance response value of each parameter and the data fluctuation of each parameter, and performing sealing detection on the pneumatic sealing rotary joint. The present application can improve the sealing detection accuracy of the joint.

Description

Technical Field

[0001] The present application relates to the technical field of sealing detection, and in particular to a sealing detection method, equipment and system for a pneumatic sealing rotary joint. Background Art

[0002] As a key connecting component in mechanical equipment, rotary joints transfer pressure from fixed to rotating pipes. As hydraulic machinery increasingly moves toward higher pressures, higher requirements are placed on the pressure resistance and sealing performance of rotary joints. The sealing performance of rotary joints is directly related to fluid or gas leakage, which can lead to environmental pollution, waste of resources, and equipment damage. In some industries, poor sealing of rotary joints can cause serious safety hazards such as fires and explosions. Good sealing performance can reduce pressure loss within the system and improve the efficiency of industrial systems. Rotary joints with good sealing performance can reduce wear and extend the service life of equipment.

[0003] Currently, there are various methods available on the market for testing the tightness of rotary joints, such as pressure decay testing and the bubble method. With technological advancements, many leak testing processes have been automated, improving both efficiency and accuracy. However, during use, changes in fluid temperature, loose components, and rotating speed can affect the leak-tightness monitoring results of pneumatically sealed rotary joints. Current testing of rotary joint leaks fails to consider the correlated variation of test parameters in the presence of minor leaks, resulting in significant errors in leak-tightness testing of pneumatically sealed rotary joints. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a method, device and system for detecting the sealing performance of a pneumatic sealing rotary joint. The technical solutions adopted are as follows:

[0005] The present invention provides a method for detecting the sealing performance of a pneumatic sealing rotary joint, the method comprising the following steps:

[0006] Obtain data on various parameters during the rotary joint sealing test;

[0007] The data of all parameters at each acquisition moment are grouped into samples and clustered. The difference between the data dispersion of each parameter and other parameters in each cluster is analyzed. Combined with the correlation between the data of each parameter and other parameters, the relative characteristic value of each parameter in each cluster is determined.

[0008] Based on the difference between the relative characteristic values ​​of each parameter in each cluster and other clusters, the relative value of the state response corresponding to each cluster is determined;

[0009] According to the distribution of the relative values ​​of each state response and the relative characteristic values ​​of each parameter, the sealing performance response value of each parameter is obtained;

[0010] According to the proportion of the sealing performance response value of each parameter and the data fluctuation of each parameter, the sealing performance test value of the rotary joint is determined, and the sealing test of the pneumatic sealing rotary joint is performed.

[0011] Preferably, the determination of the relative characteristic value of each parameter in each cluster includes:

[0012] For each cluster, all the data of the same parameter in the cluster are combined into a row vector;

[0013] The difference between the element fluctuation degrees of the row vectors of any two parameters in the cluster is recorded as the combined state difference value between the two parameters in the cluster; the similarity between the row vectors of any two parameters in the cluster is recorded as the combined correlation feature value between the two parameters;

[0014] The relative characteristic value of each parameter in each cluster is determined by combining the combined state difference value and the combined associated characteristic value between each parameter in each cluster and other parameters.

[0015] Preferably, the relative characteristic values ​​of each parameter in each cluster further include:

[0016] The average value of the product of the combined state difference value and the combined associated eigenvalue between each parameter in each cluster and all other parameters is used as the relative eigenvalue of each parameter in each cluster.

[0017] Preferably, the relative value of the state response corresponding to each cluster is calculated using the following formula:

[0018] Among them, H m Indicates the relative value of the state response corresponding to the mth cluster; M m and M k They represent the relative eigenvalue sequences of the mth and kth clusters respectively. The relative eigenvalue sequence of each cluster is composed of the relative eigenvalues ​​of all parameters in each cluster; r represents the number of clusters; md() represents the Manhattan distance.

[0019] Preferably, the sealing performance response values ​​of the parameters further include:

[0020] The proportion of the relative state response value corresponding to each cluster in the relative state response values ​​of all clusters is determined as the importance weight of each cluster. The sealing performance response value of each parameter is calculated based on the importance weight and the relative characteristic value:

[0021] Among them, G x Indicates the sealing performance response value of the xth parameter; D u,x represents the relative eigenvalue of the xth parameter in the uth cluster; H u Indicates the importance weight corresponding to the u-th cluster.

[0022] Preferably, the sealing performance test value further includes:

[0023] The proportion of the sealing performance response value of each parameter in the sealing performance response values ​​of all parameters is used as the response weight of each parameter;

[0024] Determine the deviation value of each parameter based on the difference between the preset standard value of each parameter and the current parameter data;

[0025] The sealing performance test value is calculated based on the response weight and the deviation value of each parameter: Where L represents the sealing performance test value, s q and f q They represent the response weight and deviation value of the qth parameter respectively, and t is the number of parameter types.

[0026] Preferably, the deviation value of each parameter is a calculation result of dividing the difference between the current moment data of each parameter and the standard value of each parameter by the standard value of each parameter.

[0027] Preferably, the sealing test on the pneumatic sealing rotary joint further comprises: when the sealing performance test value is greater than a preset threshold value, the sealing performance of the pneumatic sealing rotary joint is unqualified; otherwise, the sealing performance of the pneumatic sealing rotary joint is qualified.

[0028] In a second aspect, an embodiment of the present application provides a sealing detection device for a pneumatic sealing rotary joint, the device comprising:

[0029] Sealing detection parameter acquisition module, used to obtain data of various parameters during the sealing detection process of the rotary joint;

[0030] The sealing detection analysis module is used to group the data of all parameters at each collection moment into samples and perform clustering, analyze the difference between the data dispersion degree of each parameter and other parameters in each cluster, and determine the relative characteristic value of each parameter in each cluster based on the correlation between the data of each parameter and other parameters;

[0031] Based on the difference between the relative characteristic values ​​of each parameter in each cluster and other clusters, the relative value of the state response corresponding to each cluster is determined;

[0032] According to the distribution of the relative values ​​of each state response and the relative characteristic values ​​of each parameter, the sealing performance response value of each parameter is obtained;

[0033] The test result module is used to determine the sealing performance test value of the rotary joint according to the proportion of the sealing performance response value of each parameter combined with the data fluctuation of each parameter, and perform sealing detection on the pneumatic sealing rotary joint.

[0034] In a third aspect, an embodiment of the present application also provides a sealing detection system for a pneumatic sealing rotary joint, the system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above methods when executing the computer program.

[0035] As can be seen from the above, the sealing detection method, device and system for a pneumatic sealing rotary joint provided by the present application have at least the following beneficial effects:

[0036] The present application considers that the reasons for poor sealing during the sealing detection of rotary joints include the combined influence of loose components and device defects, and different influencing factors have different responses to the sealing characteristics during the detection process, which affects the accuracy of the sealing detection of the rotary joint; in response to the above problems, the present application divides the parameter analysis of the sealing detection at the current moment based on the instantaneous state characteristics, and responds to the influence of the intermittent characteristics of the detection parameters caused by different influencing factors; according to the division results, the relative characteristics of different parameter compositions under different instantaneous state characteristic data are analyzed, and the relative analysis results of all instantaneous state characteristic data are integrated to obtain the sealing performance response value of each parameter in the sealing detection process of the rotary joint, and the final result of the sealing detection of the rotary joint is obtained based on the sealing performance response value. Its beneficial effect is to comprehensively consider the differences in the influencing factors of the sealing detection, and reduce the large problem of rotary joint sealing detection error caused by the combined influence of loose components and device defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0038] Figure 1 A flowchart of the steps of a method for detecting the sealing performance of a pneumatic sealing rotary joint provided in this application;

[0039] Figure 2 A schematic diagram of the process of determining the relative characteristic values ​​of each parameter in the cluster provided by this application;

[0040] Figure 3This is a block diagram of a sealing detection device for a pneumatic sealing rotary joint provided in this application. DETAILED DESCRIPTION

[0041] To further illustrate the technical means and effectiveness of this application to achieve the intended invention objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a method, device, and system for detecting the sealing properties of a pneumatic sealed rotary joint, including its specific implementation, structure, features, and effectiveness. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0042] Unless otherwise specified and limited, terms such as "comprises", "includes" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device comprising a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the article or device comprising the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items. All technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs.

[0043] The following describes in detail a method, device and system for detecting the sealing performance of a pneumatic sealing rotary joint provided by the present application with reference to the accompanying drawings.

[0044] See also Figure 1 , which shows a flowchart of a method for detecting the sealing performance of a pneumatic sealing rotary joint provided by one embodiment of the present application, the method comprising the following steps:

[0045] Step 1: Obtain data on various parameters during the rotary joint sealing test.

[0046] The sealing detection equipment for the pneumatically sealed rotary joint may include a frame, a base, a rotating seat, a main shaft, a motor, a water tank, a return pipe, and an intelligent sensor. In this embodiment, the sealing detection equipment is equipped with a speed sensor, a pressure sensor, a temperature sensor and a vibration frequency sensor, which are used to collect parameter data during the sealing detection process of each rotary joint respectively. The parameters include joint speed, pressure, temperature and vibration frequency.

[0047] During each rotary joint sealing test, the time interval for data collection by each sensor element in this embodiment is 0.1s. The data of the parameters collected by each sensor element up to the current moment are organized into a detection parameter sequence in ascending time order, that is, one parameter corresponds to one detection parameter sequence. Due to the influence of device operation and environmental interference during the data collection process, the data in each detection parameter sequence is affected by noise interference. Therefore, each detection parameter sequence is used as input, and a median filter is used to obtain the noise-reduced detection parameter sequence.

[0048] So far, the detection parameter sequence in the sealing detection process of the pneumatic sealing rotary joint has been obtained.

[0049] Step 2: Cluster the data sequences of all parameters at each acquisition moment, analyze the difference between the data dispersion of each parameter and other parameters in each cluster, and determine the relative characteristic value of each parameter in each cluster based on the correlation between each parameter and other parameters.

[0050] The main reasons for the sealing defects of pneumatic sealing rotary joints include defects in the rotary joints and loose rotary joint seals. Usually, during the inspection process of the rotary joint, a certain amount of liquid medium is filled and the rotary joint is rotated at a set speed. If the sealing of the rotary joint is good, the pressure inside the rotary joint is in a relatively stable state; if the sealing effect of the rotary joint is poor, the pressure inside the rotary joint is greatly reduced; nowadays, rotary joints are usually used in high-pressure environments, so the accuracy of the sealing has a greater impact on the actual production and use of the rotary joint.

[0051] The current process of detecting the sealing performance of rotary joints does not take into account the impact of minor leaks and component looseness on the sealing parameter analysis, resulting in a large deviation in the sealing performance detection of rotary joints. This embodiment analyzes the intermittent state characteristics of the changes in the detection parameter data when components are loose and there are minor leaks, obtains accurate detection results of the sealing performance of the rotary joint, and thereby solves the problem of large deviations in the sealing performance detection of rotary joints due to differences in component looseness and leakage characteristics.

[0052] Specifically, during the inspection process of the pneumatic sealing rotary joint, if the components of the rotary joint are loose, it will cause the speed and vibration frequency to change during the inspection process of the rotary joint, or there will be minor defects in the components, and then the pressure data in the rotary joint will fluctuate. Therefore, based on the above relationship and the above process, the sealing characteristics of the rotary joint during the inspection process are analyzed.

[0053] Since the pressure changes caused by the rotary joint detection process may be affected by the combined influence of multiple factors, the error in judging the sealing performance only through time-series trend analysis and numerical analysis is large. Therefore, the data of all parameters at each collection moment are combined into sequences for analysis. For the convenience of expression and understanding, in this embodiment, the sequence composed of the speed data, pressure data, temperature data and vibration frequency data of all detection parameter sequences in the rotary joint detection process at the same collection moment is recorded as an instantaneous state sample, and the set of all instantaneous state samples is used as the instantaneous state sample set for rotary joint sealing detection.

[0054] During the inspection process of the rotary joint, the change in the sealing state of the rotary joint may be intermittent due to the presence of small leaks or loose components. That is, the change in leakage characteristics or component looseness under different inspection states leads to different parameter-related changes in different time periods. Therefore, the parameter data at each time is constructed into an instantaneous state sample, and the data is divided based on the instantaneous state difference.

[0055] Specifically, in this embodiment, a set of transient state samples is used as input, and an agglomerative hierarchical clustering algorithm is employed to obtain clustering results for all samples in the transient state sample set. Each cluster in the clustering results represents a collection of samples with similar transient state characteristics during the rotary joint sealing test, i.e., each cluster corresponds to a transient state characteristic. It should be noted that the specific clustering process is conventional and will not be elaborated upon in this embodiment. Furthermore, in actual applications, implementers may employ other clustering methods to cluster the transient state sample set, and this embodiment does not impose any particular limitations thereon.

[0056] Furthermore, based on the sample partitioning results of the instantaneous state sample set from the rotary joint sealing test, a comparative analysis is performed on samples with similar instantaneous comprehensive state characteristics. Specifically, to facilitate analysis, in this embodiment, the data sequence of each instantaneous state sample in each cluster is used as a column element in a matrix. Each row vector of the sealing state characteristic matrix represents the data of each parameter at different acquisition times within the cluster.

[0057] According to the relationship between the row vectors in the sealing state characteristic matrix, the relative eigenvalue of the rotary joint sealing detection is calculated: the difference between the element fluctuation degrees of the row vectors of any two parameters in the cluster is recorded as the combined state difference value between the any two parameters in the cluster; the similarity between the row vectors of any two parameters in the cluster is recorded as the combined association eigenvalue between the any two parameters; the relative eigenvalue of each parameter in each cluster is determined by combining the combined state difference value and the combined association eigenvalue between each parameter in each cluster and other parameters.

[0058] Preferably, in this embodiment, the specific calculation process is as follows:

[0059] Taking the p-th cluster as an example, for each row vector in the sealing state characteristic matrix of the p-th cluster, it should be noted that each row vector corresponds to a parameter, and the Flamenche distance between the moving standard deviation of all elements in each row vector and the moving standard deviation of other row vectors is used as the combined state difference value A between each parameter and other parameters. The larger the combined state difference value, the greater the combined state difference of different parameters during the rotary joint sealing test, and the higher the sealing characteristic response characteristic of the rotary sealing joint reflected by the current parameter change;

[0060] The cosine similarity between each row vector and the other row vectors is used as the combined correlation eigenvalue B between each parameter and the other parameters. The larger the combined correlation eigenvalue, the higher the possibility that the current parameter change reflects the existence of a sealing difference in the rotary sealing joint;

[0061] The relative eigenvalue D of the rotary joint sealing detection is calculated based on the combined state difference value and combined correlation eigenvalue between different row vectors in the sealing state characteristic matrix:

[0062] Preferably, the specific calculation relationship in this embodiment is:

[0063] Among them, D v A represents the relative eigenvalue of the parameter corresponding to the vth row in the sealing state matrix; v,i and B v,i They represent the combined state difference value and combined associated eigenvalue between the vth row and the ith row in the sealing state matrix respectively; t represents the number of parameter types, that is, the number of rows in the sealing state matrix; the relative eigenvalue D obtained for the sealing test of the rotary joint is v The larger the value of , the more significant the relative characteristics of the rotary joint sealing state reflected by the v-th row vector in the sealing state matrix of the corresponding cluster are, that is, the greater the consistency between the change of the current row vector and the response to the change of the rotary joint sealing state.

[0064] See also Figure 2 , Figure 2 Schematic diagram of the process of determining the relative eigenvalues ​​of each parameter in the cluster.

[0065] Step 3: Based on the difference between the relative characteristic values ​​of each parameter in each cluster and other clusters, the relative value of the state response corresponding to each cluster is determined.

[0066] After the above analysis, the instantaneous state data detected at different time points during the sealing test of the rotary joint were divided. The combined relative change characteristics of different types of data were analyzed for the division results. The relative eigenvalue corresponding to each row vector in the sealing state matrix of each cluster of cluster division was obtained, that is, the relative eigenvalue corresponding to each parameter in each cluster;

[0067] The sequence of relative eigenvalues ​​of all parameters in each cluster is taken as the relative eigenvalue sequence M of each cluster. The relative state response value H of the rotary joint sealing test is calculated according to the relative characteristics of the test parameters under different test states during the rotary joint test. The specific calculation and analysis process is as follows:

[0068] Among them, H m Indicates the relative value of the state response corresponding to the mth cluster; M m and M k Represent the relative eigenvalue sequences of the mth and kth clusters respectively; r represents the number of clusters; md() represents the Manhattan distance; the relative value H of the state response of the rotary joint sealing test is obtained m The larger the value is, the more sensitive the response of the instantaneous state characteristics corresponding to the mth cluster after the instantaneous state division is to the sealing detection. In other words, the data of each parameter in the cluster has a greater impact on the accuracy of the sealing detection of the rotary joint, and is more important in the sealing detection process.

[0069] Step 4: According to the distribution of the relative values ​​of each state response and the relative characteristic values ​​of each parameter, the sealing performance response value of each sealing parameter is obtained.

[0070] Furthermore, according to the above analysis process, in order to reflect the importance of the data in each cluster and the sensitivity of the sealing detection response, in this embodiment, the proportion of the relative state response value corresponding to each cluster in the relative state response values ​​of all clusters is used as the importance weight corresponding to each cluster;

[0071] The sealing performance response value of each parameter in the rotary joint sealing test process is calculated according to the relative characteristic value and importance weight of each parameter in different clusters during the rotary joint testing process. The specific calculation relationship is:

[0072] Among them, G x Indicates the sealing performance response value of the xth parameter; D u,x represents the relative eigenvalue of the xth parameter in the uth cluster; H urepresents the importance weight corresponding to the u-th cluster; r represents the number of clusters; the larger the calculated sealing performance response value is, the more significant the relative response characteristics of the difference in the x-th parameter in the current rotary joint sealing test process reflecting the difference in sealing status are.

[0073] At this point, the sealing performance response value of each parameter in the rotary joint sealing test process was obtained.

[0074] Step 5: Determine the sealing performance test value of the rotary joint based on the proportion of the sealing performance response value of each sealing parameter and the data fluctuation of each sealing parameter, and perform a sealing test on the pneumatic sealing rotary joint.

[0075] The sealing performance test value of the rotary joint sealing test is calculated based on the deviation value and sealing response value of each parameter up to the current test time. The specific calculation and analysis process is as follows:

[0076] The proportion of the sealing performance response value of each parameter in the sealing performance response values ​​of all parameters is used as the response weight of each parameter. Preferably, in this embodiment, the proportion of the sealing performance response value of each parameter obtained up to the current moment in the sealing performance response values ​​of all parameters is used as the response weight s of each parameter;

[0077] Based on the difference between the preset standard value of each parameter and the current data of each parameter, the deviation value of each parameter is determined, wherein the deviation value of each parameter is the difference between the current data of each parameter and the standard value of each parameter divided by the standard value of each parameter. Preferably, in this embodiment, the absolute value of the difference between the standard value of each parameter and the current data of each parameter during the rotary joint sealing test is taken, and the ratio of this absolute value to the standard value of each parameter is used as the deviation value f;

[0078] It should be noted that the standard values ​​of the data of each parameter are set by the operator. In this embodiment, a pneumatic sealing rotary joint of qualified quality is manually selected and the data of each parameter of the joint is used as the standard value.

[0079] The sealing performance test value of the rotary joint sealing test is calculated based on the response weight and deviation value. The specific calculation formula is: L = ∑ t q＝1 (s q ×f q ); where L represents the sealing performance test value of the rotary joint, s q and f q They represent the response weight and deviation value of the qth parameter respectively, and t is the number of parameter types.

[0080] Finally, the pneumatic sealing rotary joint is subjected to a sealing test. When the sealing performance test value is greater than a preset threshold value, the sealing performance of the pneumatic sealing rotary joint is unqualified; otherwise, the sealing performance of the pneumatic sealing rotary joint is qualified.

[0081] In this embodiment, a threshold value T is set for the rotary joint sealing test. If the sealing performance test value of the rotary joint sealing test at the current moment is greater than the threshold value, it indicates that the pneumatic sealing rotary joint has failed to meet the sealing requirements. The poor sealing of the rotary joint may be caused by loose components or defective leakage, and requires repair. Otherwise, the pneumatic sealing rotary joint has met the sealing requirements. It should be noted that the threshold value T is set by the implementer based on the actual application scenario. In this embodiment, it is set to 0.1.

[0082] On the other hand, an embodiment of the present application further provides a sealing detection device for a pneumatic sealing rotary joint, comprising:

[0083] Sealing detection parameter acquisition module, used to obtain data of various parameters during the sealing detection process of the rotary joint;

[0084] The sealing detection analysis module is used to group the data of all parameters at each collection moment into samples and perform clustering, analyze the difference between the data dispersion degree of each parameter and other parameters in each cluster, and determine the relative characteristic value of each parameter in each cluster based on the correlation between the data of each parameter and other parameters;

[0085] Based on the difference between the relative characteristic values ​​of each parameter in each cluster and other clusters, the relative value of the state response corresponding to each cluster is determined;

[0086] According to the distribution of the relative values ​​of each state response and the relative characteristic values ​​of each parameter, the sealing performance response value of each parameter is obtained;

[0087] The test result module is used to determine the sealing performance test value of the rotary joint according to the proportion of the sealing performance response value of each parameter combined with the data fluctuation of each parameter, and perform sealing detection on the pneumatic sealing rotary joint.

[0088] See also Figure 3 , Figure 3 This is a block diagram of a sealing detection device for a pneumatic sealing rotary joint.

[0089] Based on the same inventive concept as the above method, an embodiment of the present application also provides a sealing detection system for a pneumatic sealing rotary joint, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned methods for sealing detection of a pneumatic sealing rotary joint are implemented.

[0090] It should be understood that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0091] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0092] The above content is only an implementation method of the present application and is not intended to limit the scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the scope of protection of the present application.

Claims

1. A method for detecting the sealing performance of a pneumatic sealing rotary joint, characterized in that: The method comprises the following steps: Obtain data on various parameters during the rotary joint sealing test; The data of all parameters at each acquisition moment are grouped into samples and clustered. The difference between the data dispersion of each parameter and other parameters in each cluster is analyzed. Combined with the correlation between the data of each parameter and other parameters, the relative characteristic value of each parameter in each cluster is determined. Based on the difference between the relative characteristic values ​​of each parameter in each cluster and other clusters, the relative value of the state response corresponding to each cluster is determined; According to the distribution of the relative values ​​of each state response and the relative characteristic values ​​of each parameter, the sealing performance response value of each parameter is obtained; According to the proportion of the sealing performance response value of each parameter and the data fluctuation of each parameter, the sealing performance test value of the rotary joint is determined, and the sealing test of the pneumatic sealing rotary joint is performed.

2. The method for detecting the sealing performance of a pneumatic sealing rotary joint according to claim 1, wherein: The determination of the relative characteristic value of each parameter in each cluster includes: For each cluster, all the data of the same parameter in the cluster are combined into a row vector; The difference between the element fluctuation degrees of the row vectors of any two parameters in the cluster is recorded as the combined state difference value between the two parameters in the cluster; the similarity between the row vectors of any two parameters in the cluster is recorded as the combined correlation feature value between the two parameters; The relative characteristic value of each parameter in each cluster is determined by combining the combined state difference value and the combined associated characteristic value between each parameter in each cluster and other parameters.

3. The method for detecting the sealing performance of a pneumatic sealing rotary joint according to claim 2, wherein: The relative characteristic values ​​of each parameter in each cluster further include: The average value of the product of the combined state difference value and the combined associated eigenvalue between each parameter in each cluster and all other parameters is used as the relative eigenvalue of each parameter in each cluster.

4. A method for detecting the sealing performance of a pneumatic sealing rotary joint according to claim 3, characterized in that: The relative value of the state response corresponding to each cluster is calculated as follows: ;in, Indicates the The relative value of the state response corresponding to the clusters; and Respectively represent and The relative eigenvalue sequence of each cluster is composed of the relative eigenvalues ​​of all parameters in each cluster; Indicates the number of clusters; represents the Manhattan distance.

5. The method for detecting the sealing performance of a pneumatic sealing rotary joint according to claim 4, wherein: The sealing performance response values ​​of the parameters further include: The proportion of the relative state response value corresponding to each cluster in the relative state response values ​​of all clusters is determined as the importance weight of each cluster. The sealing performance response value of each parameter is calculated based on the importance weight and the relative characteristic value: ;in, Indicates the Sealing performance response values ​​of various parameters; Indicates the The first Relative characteristic values ​​of various parameters; Indicates the The importance weight corresponding to each cluster.

6. The method for detecting the sealing performance of a pneumatic sealing rotary joint according to claim 5, wherein: The sealing performance test value further includes: The proportion of the sealing performance response value of each parameter in the sealing performance response values ​​of all parameters is used as the response weight of each parameter; Determine the deviation value of each parameter based on the difference between the preset standard value of each parameter and the current parameter data; The sealing performance test value is calculated based on the response weight and the deviation value of each parameter: ;in Indicates the sealing performance test value, and Respectively represent The response weights and deviation values ​​of the parameters are given, and t is the number of parameter types.

7. A method for detecting the sealing performance of a pneumatic sealing rotary joint according to claim 6, characterized in that: The deviation value of each parameter is a calculation result of dividing the difference between the current moment data of each parameter and the standard value of each parameter by the standard value of each parameter.

8. The method for detecting the sealing performance of a pneumatic sealing rotary joint according to claim 6, wherein: The sealing test of the pneumatic sealing rotary joint further includes: when the sealing performance test value is greater than a preset threshold, the sealing performance of the pneumatic sealing rotary joint is unqualified; otherwise, the sealing performance of the pneumatic sealing rotary joint is qualified.

9. A sealing detection device for a pneumatic sealing rotary joint, characterized in that: The device comprises: Sealing detection parameter acquisition module, used to obtain data of various parameters during the sealing detection process of the rotary joint; The sealing detection analysis module is used to group the data of all parameters at each collection moment into samples and perform clustering, analyze the difference between the data dispersion degree of each parameter and other parameters in each cluster, and determine the relative characteristic value of each parameter in each cluster based on the correlation between the data of each parameter and other parameters; Based on the difference between the relative characteristic values ​​of each parameter in each cluster and other clusters, the relative value of the state response corresponding to each cluster is determined; According to the distribution of the relative values ​​of each state response and the relative characteristic values ​​of each parameter, the sealing performance response value of each parameter is obtained; The test result module is used to determine the sealing performance test value of the rotary joint according to the proportion of the sealing performance response value of each parameter and the data fluctuation of each parameter, and perform sealing test on the pneumatic sealing rotary joint.

10. A sealing detection system for a pneumatic sealing rotary joint, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images