Fault cavity assembly determination method and device

Abstract

The embodiment of the invention provides a fault cavity assembly determination method and device. The method specifically comprises the steps that at least one piece of to-be-processed data of target equipment is collected; for each piece of to-be-processed data, obtaining a first clustering result corresponding to the to-be-processed data by clustering multiple pieces of first vibration feature data in the to-be-processed data, and obtaining a second clustering result corresponding to the to-be-processed data by clustering multiple pieces of second vibration feature data in the to-be-processed data; and based on the first clustering result corresponding to each piece of to-be-processed data and the second clustering result of each piece of to-be-processed data, determining a fault cavity component in the plurality of cavity components. According to the embodiment of the invention, the determination efficiency of the fault cavity assembly in the mechanical equipment can be effectively improved.

Description

Technical Field

[0001] The present application belongs to the technical field of fault diagnosis, and in particular, relates to a method and device for determining a faulty cavity component. Background Art

[0002] The main function of the cavity formed by various components in the mechanical equipment is to contain, transmit or process fluids (including gas and liquid) to ensure the normal operation and efficient output of the mechanical equipment. Therefore, for mechanical equipment containing a cavity, if there is a fault in the component used to form the cavity in the mechanical equipment, it will not only lead to a decrease in the displacement and output of the mechanical equipment, but also cause the mechanical equipment to fail. However, in the prior art, the efficiency of determining the faulty cavity component in the mechanical equipment is low. Summary of the invention

[0003] The embodiments of the present application provide a method and device for determining a faulty cavity component, which can effectively improve the efficiency of determining a faulty cavity component in a mechanical device.

[0004] In a first aspect, an embodiment of the present application provides a method for determining a faulty cavity component, the method comprising: Collecting at least one data to be processed of a target device, the target device includes a plurality of cavity components, each cavity component includes a first type of valve and a second type of valve, and each data to be processed includes first vibration characteristic data corresponding to the first type of valve of each cavity component, and second vibration characteristic data corresponding to the second type of valve of each cavity component; For each data to be processed, a first clustering result corresponding to the data to be processed is obtained by clustering a plurality of first vibration characteristic data in the data to be processed, and a second clustering result corresponding to the data to be processed is obtained by clustering a plurality of second vibration characteristic data in the data to be processed; Based on the first clustering result corresponding to each data to be processed and the second clustering result of each data to be processed, a faulty cavity component among the multiple cavity components is determined.

[0005] In a second aspect, an embodiment of the present application provides a device for determining a faulty cavity component, the device comprising: an acquisition module, used for acquiring at least one data to be processed of a target device, the target device comprising a plurality of cavity components, each cavity component comprising a first type of valve and a second type of valve, each data to be processed comprising first vibration characteristic data corresponding to the first type of valve of each cavity component, and second vibration characteristic data corresponding to the second type of valve of each cavity component; A clustering module, for obtaining, for each piece of data to be processed, a first clustering result corresponding to the data to be processed by clustering a plurality of first vibration characteristic data in the data to be processed, and obtaining a second clustering result corresponding to the data to be processed by clustering a plurality of second vibration characteristic data in the data to be processed; The determination module is further used to determine a faulty cavity component among the multiple cavity components based on the first clustering result corresponding to each data to be processed and the second clustering result of each data to be processed.

[0006] In a third aspect, an electronic device is provided, comprising: a memory for storing computer program instructions; and a processor for reading and running the computer program instructions stored in the memory to execute the method for determining a faulty cavity component provided in the first aspect.

[0007] In a fourth aspect, a computer storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method for determining a faulty cavity component provided in the first aspect is implemented.

[0008] In a fifth aspect, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the method for determining a faulty cavity component provided in the first aspect is implemented.

[0009] In an embodiment of the present application, at least one data to be processed of the target device can be obtained through collection. Since the target device includes multiple cavity components, and each cavity component includes a first type of valve and a second type of valve, based on this, each data to be processed includes first vibration characteristic data corresponding to the first type of valve of each cavity component, and second vibration characteristic data corresponding to the second type of valve of each cavity component. Then, for each data to be processed, the clustering results of the vibration characteristic data of different categories of valves in the data to be processed can be respectively clustered to determine the faulty cavity component among the multiple cavity components. This can effectively improve the efficiency of determining the faulty cavity component in the mechanical equipment, and can also improve the accuracy of determining the faulty cavity component in the mechanical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0011] Figure 1 It is a time domain waveform diagram of a cavity valve provided by an embodiment of the present application when the spring is normal; Figure 2 It is a time domain waveform diagram of a cavity valve provided by an embodiment of the present application when the spring is broken; Figure 3 This is one of the flow charts of a method for determining a faulty cavity component provided in an embodiment of the present application; Figure 4This is a second flow chart of a method for determining a faulty cavity component provided in an embodiment of the present application; Figure 5 is a clustering schematic diagram of a first vibration data provided by an embodiment of the present application; Figure 6 is a clustering schematic diagram of a second vibration data provided by an embodiment of the present application; Figure 7 This is a third flow chart of a method for determining a faulty cavity component provided in an embodiment of the present application; Figure 8 It is a structural schematic diagram of a device for determining a faulty cavity component provided in an embodiment of the present application; Fig. 9 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0013] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0014] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0015] As described in the background art, for a mechanical device including a cavity, when a cavity component used to form the cavity in the mechanical device fails, it may not only cause a decrease in the displacement and output of the mechanical device, but also cause the mechanical device to fail.

[0016] Based on this, in order to accurately and effectively determine the faulty cavity components in mechanical equipment and perform timely maintenance on the faulty cavity components, thereby avoiding the reduction in displacement and output of the mechanical equipment and mechanical equipment failure due to cavity component failure, the prior art generally involves maintenance personnel disassembling the mechanical equipment to determine the faulty cavity components, but this method is less efficient in determining the faulty cavity components.

[0017] Thus, in order to solve the above problems existing in the prior art, the embodiments of the present application take into account that the cavity assembly used to form the cavity in the mechanical device generally realizes the suction or discharge of the fluid through a valve, and the valve is generally composed of a valve seat, a valve body and a spring. For example, when the spring breaks, the vibration signal of the part will undergo a separable change, such as Figure 1 and Figure 2 As shown, Figure 1 is a time domain waveform diagram of a cavity valve provided in an embodiment of the present application when the spring is normal. Figure 2 This is a time domain waveform diagram of a cavity valve in the case of a broken spring provided by the embodiment of the present application. It can be seen that the peak value of the vibration signal collected when the spring is broken is higher than the peak value of the vibration signal when the spring is normal, that is, when the valve part of the cavity assembly in the mechanical equipment is damaged, the vibration signal generated will be different from the vibration signal generated when the valve part of the cavity assembly is normal. In addition, the embodiment of the present application also takes into account that in real life, the vibration signals of the valve that controls fluid intake and the valve that controls fluid discharge in the cavity assembly are also quite different.

[0018] Therefore, an embodiment of the present application provides a method and device for determining a faulty cavity component, which can obtain at least one data to be processed of a target device by acquisition. Since the target device includes multiple cavity components, and each cavity component includes a first type of valve and a second type of valve, based on this, each data to be processed includes first vibration characteristic data corresponding to the first type of valve of each cavity component, and second vibration characteristic data corresponding to the second type of valve of each cavity component. Then, for each data to be processed, the faulty cavity component among the multiple cavity components can be determined by respectively clustering the vibration characteristic data of different types of valves in the data to be processed to obtain clustering results. Compared with the method of manually disassembling mechanical equipment to determine the faulty cavity component in the prior art, the accuracy of determining the faulty cavity component in the mechanical equipment can be effectively improved, and the accuracy of determining the faulty cavity component in the mechanical equipment can also be improved.

[0019] It should be noted that the execution subject of the method for determining a faulty cavity component provided in the embodiment of the present application may be a device for determining a faulty cavity component, or a control module in the device for determining a faulty cavity component for executing the method for determining a faulty cavity component. In the embodiment of the present application, the method for determining a faulty cavity component provided in the embodiment of the present application is described by taking the method for determining a faulty cavity component executed by the device for determining a faulty cavity component as an example.

[0020] The method for determining a faulty cavity component provided in the embodiment of the present application is described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0021] Figure 3 It is one of the flow charts of the method for determining a faulty cavity component provided in an embodiment of the present application.

[0022] like Figure 3 As shown, the execution subject of the method may be a fault cavity component determination device, and the method may specifically include the following steps: S310, collecting at least one piece of data to be processed from a target device.

[0023] Among them, the target device can be a mechanical device including a cavity assembly for forming a cavity. For example, the target device can be a fracturing pump, a core device for shale gas extraction, etc., which is not specifically limited here. In this way, the target device can include multiple cavity assemblies, each cavity assembly is used to form a cavity, and each cavity assembly can include a first type of valve and a second type of valve. If the first type of valve is a valve for controlling fluid intake, then the second type of valve can be a valve for controlling fluid discharge. Correspondingly, if the first type of valve is a valve for controlling fluid discharge, then the second type of valve can be a valve for controlling fluid intake. The embodiment of the present application does not specifically limit the categories of the first type of valve and the second type of valve. In addition, each of the first type of valve and the second type of valve included in the cavity assembly can include at least one valve, and the embodiment of the present application does not specifically limit the number of the first type of valve and the second type of valve.

[0024] Based on this, the at least one data to be processed may be the data to be processed obtained by the target device at different acquisition times, wherein each data to be processed may include the first vibration characteristic data corresponding to the first type of valve of each cavity component in the above-mentioned multiple cavity components, and the second vibration characteristic data corresponding to the second type of valve of each cavity component in the above-mentioned multiple cavity components, that is, each data to be processed includes multiple first vibration characteristic data and multiple second vibration characteristic data.

[0025] S320, for each data to be processed, a first clustering result corresponding to the data to be processed is obtained by clustering a plurality of first vibration characteristic data in the data to be processed, and a second clustering result corresponding to the data to be processed is obtained by clustering a plurality of second vibration characteristic data in the data to be processed.

[0026] Specifically, since each data to be processed includes the first vibration characteristic data corresponding to the first type of valve of each cavity component and the second vibration characteristic data corresponding to the second type of valve of each cavity component, and the target device may include multiple cavity components, each cavity component includes a first type of valve and a second type of valve, that is, each data to be processed includes multiple first vibration characteristic data and multiple second characteristic data, based on this, the faulty cavity component determination device can obtain, for each data to be processed, a first clustering result corresponding to the data to be processed by clustering the multiple first vibration characteristic data in the data to be processed, and obtain a second clustering result corresponding to the data to be processed by clustering the multiple second vibration characteristic data in the data to be processed.

[0027] It should be noted that when clustering multiple first vibration feature data and multiple second vibration feature data, clustering can be performed by using methods such as Graph Neural Network (GNN), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), K-means clustering algorithm (K-means), and mean shift clustering algorithm, without making too many restrictions here.

[0028] S330 , determining a faulty cavity component among the multiple cavity components based on a first clustering result corresponding to each data to be processed and a second clustering result of each data to be processed.

[0029] Specifically, since the faulty cavity component determination device can obtain the first clustering result and the second clustering result corresponding to the data to be processed, based on this, the faulty cavity component determination device can, after obtaining the first clustering result and the second clustering result corresponding to each data to be processed, determine the faulty cavity component among the multiple cavity components included in the target device based on the first clustering result and the second clustering result corresponding to each data to be processed.

[0030] In an embodiment of the present application, at least one data to be processed of the target device can be obtained through collection. Since the target device includes multiple cavity components, and each cavity component includes a first type of valve and a second type of valve, based on this, each data to be processed includes first vibration characteristic data corresponding to the first type of valve of each cavity component, and second vibration characteristic data corresponding to the second type of valve of each cavity component. Then, for each data to be processed, the clustering results of the vibration characteristic data of different categories of valves in the data to be processed can be respectively clustered to determine the faulty cavity component among the multiple cavity components. Compared with the method of manually disassembling mechanical equipment to determine the faulty cavity component in the prior art, the efficiency of determining the faulty cavity component in the mechanical equipment can be effectively improved, and the accuracy of determining the faulty cavity component in the mechanical equipment can also be improved.

[0031] In real life, if a cavity component in a mechanical device fails, the load of the mechanical device may fluctuate abnormally. Therefore, in order to accurately determine the failed cavity component and avoid unnecessary waste of costs due to blind judgment, in one embodiment, the above S310 may specifically include the following steps: For each data to be processed, collect the load data of the target device; When it is determined that the load data fluctuation is abnormal, the data to be processed is collected.

[0032] In some embodiments, the load data of the target device is collected earlier than the data to be processed.

[0033] Specifically, the faulty cavity component determination device can collect the load data of the target device for each data to be processed before collecting the data to be processed, and when it is determined that the load data fluctuation of the target device is abnormal, that is, indicating that the cavity component in the target device may be faulty, collect the data to be processed for further judgment later.

[0034] In this embodiment, it is possible to preliminarily determine whether the cavity component in the target device is faulty by first collecting the load data of the target device, so that when the cavity component in the target device may be faulty, the faulty cavity component can be further determined by collecting the data to be processed. In this way, not only can the faulty cavity component be accurately determined, but also the unnecessary waste of cost caused by blindly obtaining the data to be processed for judgment is avoided.

[0035] In another embodiment, in order to more accurately determine the faulty cavity component in the mechanical equipment, before the above S320, the method for determining the faulty cavity component provided in the embodiment of the present application may further include the following steps: For each data to be processed, collect the load data of the target device; When it is determined that the load data fluctuation is abnormal, a first clustering result corresponding to the data to be processed is obtained by clustering multiple first vibration characteristic data in the data to be processed, and a second clustering result corresponding to the data to be processed is obtained by clustering multiple second vibration characteristic data in the data to be processed.

[0036] The collection time of the load data of the target device is the same as the collection time of the data to be processed.

[0037] Specifically, since the collection time of the above-mentioned load data is the same as the collection time of the above-mentioned data to be processed, the faulty cavity component determination device can, for each data to be processed, collect the load data of the target device while collecting the data to be processed, and then, when it is determined that the load data fluctuation is abnormal, that is, when it indicates that the cavity component may have a fault, obtain the first clustering result corresponding to the data to be processed by clustering multiple first vibration characteristic data in the data to be processed, and obtain the second clustering result corresponding to the data to be processed by clustering multiple second vibration characteristic data in the data to be processed.

[0038] In this embodiment, the load data of the target device can be collected while collecting the data to be processed, and a preliminary judgment can be made whether there is an abnormality in the cavity component by judging whether the load data fluctuates abnormally. When it is determined that the load data fluctuates abnormally, that is, the cavity component may be faulty, a subsequent judgment process is performed. In this way, unnecessary waste of resources can be avoided. Moreover, since the collection time of the load data is the same as the collection time of the data to be processed, the fluctuation of the load data can more accurately reflect the state of the cavity component, so as to facilitate the subsequent accurate determination of the faulty cavity component in the mechanical equipment.

[0039] Since it is necessary to collect the data to be processed in the above embodiment when it is determined that the load data fluctuates abnormally, based on this, in order to accurately judge whether the load data fluctuates abnormally, in one embodiment, the above load data may include multiple load values, and the load value may be a load rate, which is not specifically limited here. In this way, in the above case where it is determined that the load data fluctuates abnormally, before collecting the data to be processed, or in the above case where it is determined that the load data fluctuates abnormally, a first clustering result corresponding to the data to be processed is obtained by clustering multiple first vibration characteristic data in the data to be processed, and a second clustering result corresponding to the data to be processed is obtained by clustering multiple second vibration characteristic data in the data to be processed, the method for determining a faulty cavity component provided in the embodiment of the present application may also include the following steps: Calculate load variance for multiple load values; When the load variance is greater than the first threshold, it is determined that the load data fluctuation is abnormal.

[0040] The first threshold may be preset based on actual experience or circumstances, and is not specifically limited here.

[0041] Specifically, since the load data of the target device may include multiple load values, the faulty cavity component determining device can determine that the load data fluctuation is abnormal through the load variance of the multiple load values ​​included in the load data, and further, when the load variance is greater than a first threshold value.

[0042] In this embodiment, the load variance of multiple load values ​​included in the load data can be calculated, and by judging whether the load variance is greater than a threshold, it can be accurately judged whether the load data fluctuates abnormally. This not only facilitates the subsequent improvement of the accuracy of determining the faulty cavity component, but also avoids unnecessary waste of resources.

[0043] In another embodiment, in the case where it is determined that the load data fluctuates abnormally, before collecting the data to be processed, or in the case where it is determined that the load data fluctuates abnormally, obtaining a first clustering result corresponding to the data to be processed by clustering multiple first vibration characteristic data in the data to be processed, and obtaining a second clustering result corresponding to the data to be processed by clustering multiple second vibration characteristic data in the data to be processed, the method for determining a faulty cavity component provided in the embodiment of the present application may further include the following steps: Calculating the difference between each two adjacent load values ​​in the plurality of load values ​​to obtain at least two difference values; When the average of at least two difference values ​​is greater than the second threshold, it is determined that the load data fluctuation is abnormal.

[0044] The second threshold may be preset based on actual experience or circumstances, and is not specifically limited here.

[0045] Specifically, since the load data of the target device may include multiple load values, the faulty cavity component determination device can obtain at least two differences by calculating the difference between each two adjacent load values ​​among the multiple load values, and then determine that the load data fluctuation is abnormal when the average value of the at least two differences is greater than a second threshold.

[0046] In this embodiment, the difference between each two adjacent load values ​​included in the load data can be calculated, and the average value of at least two difference values ​​obtained by calculation can be compared with the threshold to accurately determine whether the load data fluctuates abnormally. This not only facilitates the subsequent improvement of the accuracy of determining the faulty cavity component, but also avoids unnecessary waste of resources.

[0047] Since the signal generated by the mechanical equipment including the cavity assembly (for example, the pump head of the fracturing pump) is an impact signal, there is a lot of high-frequency information, and most of the abnormal frequencies of the mechanical equipment will be reflected in the high-frequency band. Based on this, in order to accurately obtain at least one to-be-processed data of the target equipment, in one embodiment, Figure 4 As shown, the above S310 may specifically include the following steps: S410, for each data to be processed, obtaining a first vibration signal corresponding to a first type of valve of each cavity assembly, and a second vibration signal corresponding to a second type of valve of each cavity assembly.

[0048] Among them, the above-mentioned first vibration signal may include multiple first sub-signals, and the above-mentioned second vibration signal may also include multiple second sub-signals. The embodiment of the present application does not specifically limit the number of sub-signals included in the above-mentioned first vibration signal and the number of sub-signals included in the above-mentioned second vibration signal.

[0049] Specifically, for each data to be processed, the faulty cavity component determination device can collect a first vibration signal corresponding to a first type of valve of each cavity component, and a second vibration signal corresponding to a second type of valve of each cavity component.

[0050] S420: For each vibration signal among the multiple vibration signals, determine frequency spectrum information of the vibration signal.

[0051] The multiple vibration signals may include multiple first vibration signals and multiple second vibration signals.

[0052] Specifically, the faulty cavity component determination device can collect and obtain the first vibration signal corresponding to the first type of valve of each cavity component and the second vibration signal corresponding to the second type of valve of each cavity component. Since the target device may include multiple cavity components, and each cavity component includes a first type of valve and a second type of valve, the faulty cavity component determination device can obtain multiple first vibration signals and multiple second vibration signals, and then can determine the frequency spectrum information of each vibration signal among the multiple first vibration signals and the multiple second vibration signals.

[0053] S430, reconstructing a target vibration signal corresponding to the vibration signal based on a signal portion having a frequency greater than a preset frequency threshold in the frequency spectrum information of the vibration signal, thereby obtaining a plurality of target vibration signals.

[0054] The above-mentioned preset frequency threshold may be preset based on actual experience or circumstances, and is not specifically limited here.

[0055] Specifically, after determining the frequency spectrum information of the vibration signal, the faulty cavity component determination device can reconstruct the target vibration signal corresponding to the vibration signal based on the signal part in the frequency spectrum information of the vibration signal whose frequency is greater than a preset frequency threshold, and thus can obtain multiple target vibration signals.

[0056] In some embodiments, since the above-mentioned multiple vibration signals include multiple first vibration signals and multiple second vibration signals, after obtaining the target vibration signal corresponding to each vibration signal, the above-mentioned multiple target vibration signals may include first target vibration signals corresponding to the above-mentioned multiple first vibration signals respectively and second target vibration signals corresponding to the above-mentioned multiple second vibration signals respectively.

[0057] S440: extracting first vibration characteristic data from each first target vibration signal, and extracting second vibration characteristic data from each second target vibration signal.

[0058] Specifically, after obtaining multiple target vibration signals, the target vibration signals may include multiple first target vibration signals and multiple second target vibration signals. Based on this, the faulty cavity component determination device can extract first vibration characteristic data from each first target vibration signal, that is, the first characteristic data corresponding to the first type of valve of each cavity component, and extract second vibration characteristic data from each second target vibration signal, that is, the second characteristic data corresponding to the second type of valve of each cavity component.

[0059] In this embodiment, the first vibration signal of the first type of valve of each cavity component and the second vibration signal corresponding to the second type of valve of each cavity component can be collected, and then the frequency spectrum information of each vibration signal can be determined, and the corresponding target vibration signal can be obtained based on the part with high-frequency information in each vibration signal. And the corresponding vibration characteristic data can be obtained based on the target vibration signal. In this way, the characteristic data can be extracted by reconstructing the signal part with high-frequency information based on the vibration signal, so that the faulty cavity component among multiple cavity components can be determined more accurately in the future.

[0060] In the above embodiment, the vibration signals at the first-type valves and the second-type valves of each cavity assembly need to be collected separately. Therefore, in order to avoid confusion between the vibration signals at the first-type valves and the vibration signals at the second-type valves, the vibration signals at each first-type valve and the vibration signals at each second-type valve are accurately collected.

[0061] Based on this, in one embodiment, a first vibration sensor may be installed at the first type of valve of each of the above-mentioned chamber components, and a second vibration sensor may be installed at the second type of valve of each of the above-mentioned chamber components. Exemplarily, if the above-mentioned target device may be a fracturing pump, the fracturing pump may include five chamber components, and each chamber component may have a valve at the top and bottom, the bottom of the chamber component is the suction end of the fracturing pump, and the valve at the bottom of the chamber component is the suction valve (first type of valve), and the top of the chamber component is the discharge end of the suction pump of the fracturing pump, and the valve at the top of the chamber component is the discharge valve (second type of valve). In this way, considering the structure of the fracturing pump, a vibration sensor may be installed in the horizontal direction to monitor the vibration signal of the suction valve, and a vibration sensor may be installed in the vertical direction to monitor the vibration signal of the discharge valve, that is, for the five chamber components included in the fracturing pump, five vibration sensors need to be installed in the horizontal direction and the vertical direction, that is, a vibration sensor is installed at the suction valve and the discharge valve of each of the above-mentioned chamber components.

[0062] Thus, the above S410 may specifically include the following steps: For each first-type valve, collecting a first vibration signal corresponding to the first-type valve by using a first vibration sensor corresponding to the first-type valve; For each second-type valve, a second vibration signal corresponding to the second-type valve is collected by a second vibration sensor corresponding to the second-type valve.

[0063] Specifically, since a first vibration sensor is installed at the first type of valve of each cavity assembly, and a second vibration sensor is installed at the second type of valve of each cavity assembly, the faulty cavity assembly determination device can, for each first type of valve, collect a first vibration signal corresponding to the first type of valve through the first vibration sensor installed at the first type of valve, and can, for each second type of valve, collect a second vibration signal corresponding to the second type of valve through the second vibration sensor installed at the second type of valve.

[0064] In this embodiment, a first vibration sensor can be installed at the first type of valve in each cavity assembly, and a second vibration sensor can be installed at the second type of valve in each cavity assembly. In this way, corresponding vibration signals can be collected by the vibration sensors installed at the corresponding valves, thereby avoiding confusion of vibration signals at different types of valves, and accurately collecting vibration signals at each valve.

[0065] In addition, in order to accurately obtain the signal part having high-frequency information in each vibration signal so as to reconstruct a more accurate target vibration signal, in one embodiment, the above S430 may specifically include the following steps: Decomposing the vibration signal in the frequency domain based on the frequency spectrum information of the vibration signal to obtain first internal mode function IMF components corresponding to multiple frequency ranges respectively; Selecting at least one second IMF component having a frequency greater than a preset frequency threshold from the plurality of first IMF components; A target vibration signal corresponding to the vibration signal is reconstructed based on at least one second IMF component.

[0066] Each of the first internal mode function (IMF) components corresponds to a specific frequency range and the amplitude variation of the vibration signal within the frequency range.

[0067] Specifically, the faulty cavity component determination device can, after determining the spectral information of the vibration signal, decompose the vibration signal in the frequency domain based on the spectral information of the vibration signal to obtain first IMF components corresponding to multiple frequency ranges respectively. Since each first IMF component corresponds to a frequency range, based on this, at least one second IMF component having a frequency greater than a preset frequency threshold can be screened out from the multiple first IMF components, and then the target vibration signal corresponding to the vibration signal can be reconstructed based on the at least one second IMF component.

[0068] In this embodiment, the vibration signal can be decomposed in the frequency domain to obtain multiple first IMF components of the vibration signal, and at least one second IMF component with high-frequency information can be obtained from the multiple first IMF components. Then, the target vibration signal can be reconstructed based on the at least one second IMF component with high-frequency information, so that the faulty cavity component among the multiple cavity components can be determined more accurately in the subsequent process.

[0069] In order to accurately describe the fault cavity component determination method provided by the embodiment of the present application, in one embodiment, the first clustering result may include a first distance between each first vibration characteristic data in the data to be processed and a first center point of multiple first characteristic data, and correspondingly, the second clustering result may include a second distance between each second characteristic data and a second center point of multiple second characteristic data. Based on this, the above S320 may specifically include the following steps: By clustering a plurality of first vibration characteristic data in the data to be processed, a first center point of the plurality of first vibration characteristic data is obtained, and a first distance between each first vibration characteristic data and the first center point is determined to obtain a plurality of first distances; The second center points of the plurality of second vibration characteristic data are obtained by clustering the plurality of second vibration characteristic data in the data to be processed, and the second distance of each second vibration characteristic data from the second center point is determined to obtain the plurality of second distances.

[0070] Specifically, the fault cavity component determination device can obtain the first center point of the plurality of first vibration characteristic data by clustering the plurality of first vibration characteristic data in the data to be processed, and can determine the first distance of each first characteristic data from the first center point, so that the fault cavity component determination device can obtain the plurality of first distances. For example, Figure 5 As shown, each sphere corresponds to a first vibration characteristic data, and the cross mark is the above-mentioned first center point.

[0071] At the same time, the fault cavity component determination device can obtain the second center point of the plurality of second vibration data by clustering the plurality of second vibration characteristic data in the data to be processed, and can determine the second distance of each second characteristic data from the second center point, so that the fault cavity component determination device can obtain the plurality of second distances. For example, Figure 6 As shown, each sphere corresponds to a second vibration characteristic data, and the cross mark is the above-mentioned second center point.

[0072] In this embodiment, multiple first vibration characteristic data in the data to be processed can be clustered to obtain the first center point of the multiple first vibration data, and then the first distance of each first vibration characteristic data from the first center point can be determined. Similarly, the second center point of the multiple second vibration characteristic data can be obtained by clustering the multiple second vibration characteristic data in the data to be processed, and then the second distance of each second vibration characteristic data from the second center point can be determined. In this way, the first clustering result and the second clustering result corresponding to the data to be processed can be obtained, so as to determine the faulty cavity component among the multiple cavity components by respectively clustering the vibration characteristic data of different categories of valves in the data to be processed, which not only improves the accuracy of determining the faulty cavity component, but also improves the efficiency of determining the faulty cavity component.

[0073] Based on this, in one embodiment, Figure 7 As shown, the above S330 may specifically include the following steps: S710 , for each data to be processed, obtain a third clustering result corresponding to the data to be processed by clustering a plurality of first distances corresponding to the data to be processed and a plurality of second distances corresponding to the data to be processed.

[0074] The third clustering result may be used to indicate at least one candidate faulty valve among the plurality of first-type valves and the plurality of second-type valves.

[0075] Specifically, the faulty cavity component determining device can obtain, for each data to be processed, a third clustering result corresponding to the data to be processed by clustering a plurality of first distances corresponding to the data to be processed and a plurality of second distances corresponding to the data to be processed.

[0076] It should be noted that when clustering multiple first distances and multiple second distances of the data to be processed, GNN, DBSCAN, K-means, mean shift clustering algorithm and other methods can be used for clustering, and no excessive restrictions are made here.

[0077] S720: Determine the abnormal probability of each candidate faulty valve based on a third clustering result of at least one data to be processed.

[0078] The abnormal probability of the candidate faulty valve is used to characterize the possibility of abnormality or failure of the candidate faulty valve, that is, the greater the abnormal probability, the greater the possibility of abnormality or failure of the corresponding candidate faulty valve, and vice versa.

[0079] Specifically, since the faulty cavity component determination device can obtain at least one data to be processed, correspondingly, the faulty cavity determination component device can obtain a third clustering result corresponding to at least one data to be processed, and the third clustering result is used to indicate at least one candidate faulty valve, and then the abnormal probability of each candidate faulty valve can be determined based on the third clustering result corresponding to the at least one data to be processed.

[0080] In one example, in the process of determining the abnormal probability of a candidate faulty valve, the number of occurrences of a candidate faulty valve in the third clustering result corresponding to at least one data to be processed can be counted, and the ratio between the number of occurrences and the number of the at least one data to be processed is the abnormal probability of the candidate faulty valve.

[0081] S730, determining that a candidate faulty valve with an abnormal probability greater than a preset probability threshold among at least one candidate faulty valve is a faulty valve, and determining that a cavity assembly including the faulty valve is a faulty cavity assembly.

[0082] The above-mentioned preset probability threshold may be preset based on actual experience or circumstances, and is not specifically limited here.

[0083] Specifically, after determining the abnormal probability of each candidate faulty valve, the faulty cavity assembly determination device can determine that a candidate faulty valve among the at least one candidate faulty valve whose abnormal probability is greater than a preset probability threshold is a faulty valve, and determine that the cavity assembly containing the faulty valve is a faulty cavity assembly.

[0084] In this embodiment, for each data to be processed, at least one candidate faulty valve can be determined by clustering the vibration characteristic data of valves of different categories in the data to be processed to obtain clustering results, and then the abnormal probability of each candidate faulty valve can be determined in combination with the clustering results corresponding to at least one data to be processed, so that the faulty valve can be more accurately determined based on the abnormal probability, and the faulty cavity component can be further accurately determined, thereby improving the accuracy of determining the faulty cavity component.

[0085] Based on this, in one embodiment, the above S710 may specifically include the following steps: Determine a third center point of the plurality of first distances and the plurality of second distances by clustering the plurality of first distances corresponding to the data to be processed and the plurality of second distances corresponding to the data to be processed; For each of the multiple first distances and the multiple second distances, when the target distance between the distance and the third center point is greater than a preset distance threshold, the valve corresponding to the distance is determined as a candidate faulty valve, and at least one candidate faulty valve is obtained.

[0086] The above-mentioned preset distance threshold may be preset based on actual conditions or experience, and is not specifically limited here.

[0087] Specifically, the faulty cavity component determination device can determine the third center point of the multiple first distances and the multiple second distances by clustering the multiple first distances corresponding to the data to be processed and the multiple second distances corresponding to the data to be processed, and then for each of the multiple first distances and the multiple second distances, when the target distance between the distance and the third center point is greater than a preset distance threshold, determine that the valve corresponding to the distance is a candidate faulty valve, so that at least one candidate faulty valve can be obtained.

[0088] In this embodiment, it is possible to take into account the large differences in vibration data of valves of different categories. By clustering the vibration characteristic data of valves of different categories in the data to be processed, candidate faulty valves can be determined. Compared with the data clustering method that does not distinguish between valve categories in the prior art, the state of the valve can be determined more accurately, which makes it easier to subsequently determine the faulty cavity component from multiple cavity components, thereby improving the accuracy of faulty cavity determination.

[0089] Based on the same inventive concept, the present application embodiment provides a device for determining a faulty cavity component, specifically in combination with Figure 8 The faulty cavity component determination device provided in the embodiment of the present application is described in detail.

[0090] Figure 8 It is a structural schematic diagram of a fault cavity component determination device provided in an embodiment of the present application.

[0091] like Figure 8 As shown, the fault cavity component determination device 800 may include: The acquisition module 810 is used to acquire at least one data to be processed of the target device, the target device includes a plurality of cavity components, each cavity component includes a first type of valve and a second type of valve, each data to be processed includes first vibration characteristic data corresponding to the first type of valve of each cavity component, and second vibration characteristic data corresponding to the second type of valve of each cavity component; A clustering module 820 is used for obtaining, for each piece of data to be processed, a first clustering result corresponding to the data to be processed by clustering a plurality of first vibration characteristic data in the data to be processed, and obtaining a second clustering result corresponding to the data to be processed by clustering a plurality of second vibration characteristic data in the data to be processed; The determination module 830 is further used to determine a faulty cavity component among the multiple cavity components based on the first clustering result corresponding to each data to be processed and the second clustering result of each data to be processed.

[0092] In one embodiment, the acquisition module is specifically used to acquire the load data of the target device for each data to be processed, and the acquisition time of the load data of the target device is earlier than the acquisition time of the data to be processed; The above-mentioned acquisition module is specifically used to collect the data to be processed when it is determined that the load data fluctuates abnormally; or, The above-mentioned acquisition module is specifically used to acquire the load data of the target device for each data to be processed, and the acquisition time of the load data of the target device is the same as the acquisition time of the data to be processed; The above-mentioned acquisition module is specifically used to obtain a first clustering result corresponding to the data to be processed by clustering multiple first vibration characteristic data in the data to be processed when it is determined that the load data fluctuation is abnormal, and to obtain a second clustering result corresponding to the data to be processed by clustering multiple second vibration characteristic data in the data to be processed.

[0093] In one embodiment, the load data includes multiple load values; based on this, the fault cavity component determination device provided in the embodiment of the present application includes: A calculation module, for calculating a load variance of a plurality of load values; A determination module, configured to determine that the load data fluctuation is abnormal when the load variance is greater than a first threshold; or, A calculation module, used for calculating the difference between each two adjacent load values ​​in the plurality of load values ​​to obtain at least two difference values; The determination module is used to determine that the load data fluctuation is abnormal when the average value of at least two differences is greater than a second threshold.

[0094] In one embodiment, the apparatus for determining a faulty cavity component provided in the embodiment of the present application may include: The acquisition module is specifically used to acquire, for each data to be processed, a first vibration signal corresponding to the first type of valve of each cavity assembly and a second vibration signal corresponding to the second type of valve of each cavity assembly; A determination module, configured to determine frequency spectrum information of a vibration signal for each of a plurality of vibration signals, wherein the plurality of vibration signals include a plurality of first vibration signals and a plurality of second vibration signals; a reconstruction module, configured to reconstruct a target vibration signal corresponding to the vibration signal based on a signal portion having a frequency greater than a preset frequency threshold in the spectrum information of the vibration signal, and obtain a plurality of target vibration signals, wherein the plurality of target vibration signals include first target vibration signals corresponding to the plurality of first vibration signals respectively and second target vibration signals corresponding to the plurality of second vibration signals respectively; The extraction module is used to extract first vibration characteristic data from each first target vibration signal, and to extract second vibration characteristic data from each second target vibration signal.

[0095] In one embodiment, a first vibration sensor is installed at the first type of valve of each cavity assembly, and a second vibration sensor is installed at the second type of valve of each cavity assembly; The acquisition module is specifically used to acquire the first vibration signal corresponding to each first-type valve through the first vibration sensor corresponding to the first-type valve; The acquisition module is specifically used to acquire the second vibration signal corresponding to each second type valve through the second vibration sensor corresponding to the second type valve.

[0096] In one embodiment, the apparatus for determining a faulty cavity component provided in the embodiment of the present application further includes: A decomposition module, used for decomposing the vibration signal in the frequency domain based on the frequency spectrum information of the vibration signal to obtain first internal mode function IMF components corresponding to multiple frequency ranges respectively; A screening module, used for screening at least one second IMF component having a frequency greater than a preset frequency threshold from the plurality of first IMF components; The reconstruction module is used to reconstruct a target vibration signal corresponding to the vibration signal based on at least one second IMF component.

[0097] In one embodiment, the first clustering result includes a first distance between each first vibration characteristic data in the data to be processed and a first center point of the plurality of first vibration characteristic data; the second clustering result includes a second distance between each second vibration characteristic data in the data to be processed and a second center point of the plurality of second vibration characteristic data; The clustering module is specifically used to obtain a first center point of the plurality of first vibration characteristic data by clustering the plurality of first vibration characteristic data in the data to be processed, and determine a first distance between each first vibration characteristic data and the first center point to obtain a plurality of first distances; The clustering module is specifically used to obtain the second center point of the multiple second vibration characteristic data by clustering the multiple second vibration characteristic data in the data to be processed, and determine the second distance of each second vibration characteristic data from the second center point to obtain multiple second distances.

[0098] In one embodiment, the clustering module is further used to obtain, for each data to be processed, a third clustering result corresponding to the data to be processed by clustering a plurality of first distances corresponding to the data to be processed and a plurality of second distances corresponding to the data to be processed, wherein the third clustering result is used to indicate at least one candidate faulty valve among the plurality of first-type valves and the plurality of second-type valves; The above-mentioned determination module is specifically used to determine the abnormal probability of each candidate faulty valve based on the third clustering result of at least one data to be processed; The above-mentioned determination module is specifically used to determine that a candidate faulty valve with an abnormal probability greater than a preset probability threshold among at least one candidate faulty valve is a faulty valve, and to determine that a cavity assembly including the faulty valve is a faulty cavity assembly.

[0099] In one embodiment, the clustering module is specifically used to determine a third center point of the plurality of first distances and the plurality of second distances by clustering the plurality of first distances corresponding to the data to be processed and the plurality of second distances corresponding to the data to be processed; The above-mentioned determination module is also used to determine, for each distance among the multiple first distances and the multiple second distances, that the valve corresponding to the distance is a candidate faulty valve when the target distance between the distance and the third center point is greater than a preset distance threshold, and obtain at least one candidate faulty valve.

[0100] In an embodiment of the present application, at least one data to be processed of the target device can be obtained through collection. Since the target device includes multiple cavity components, and each cavity component includes a first type of valve and a second type of valve, based on this, each data to be processed includes first vibration characteristic data corresponding to the first type of valve of each cavity component, and second vibration characteristic data corresponding to the second type of valve of each cavity component. Then, for each data to be processed, the faulty cavity component among the multiple cavity components can be determined by respectively clustering the vibration characteristic data of different types of valves in the data to be processed to obtain clustering results. Compared with the method of manually disassembling mechanical equipment to determine the faulty cavity component in the prior art, not only the efficiency of determining the faulty cavity component in the mechanical equipment can be effectively improved, but also the accuracy of determining the faulty cavity component in the mechanical equipment can be improved.

[0101] Each module in the fault cavity component determination device provided in the embodiment of the present application can be implemented Figure 3 , Figure 4 as well as Figure 7 The method steps of any of the embodiments shown in the figure can achieve the corresponding technical effects, which will not be repeated here for the sake of brevity.

[0102] Fig. 9 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0103] The electronic device may include a processor 901 and a memory 902 storing computer program instructions.

[0104] Specifically, the processor 901 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0105] The memory 902 may include a large capacity memory for data or instructions. For example, but not limitation, the memory 902 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 902 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 902 may be inside or outside the electronic device. In a specific embodiment, the memory 902 is a non-volatile solid-state memory.

[0106] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0107] The processor 901 implements any one of the faulty cavity component determination methods in the above embodiments by reading and executing computer program instructions stored in the memory 902 .

[0108] In one example, the electronic device may further include a communication interface 903 and a bus 910. Fig. 9As shown, the processor 901, the memory 902, and the communication interface 903 are connected via a bus 910 and communicate with each other.

[0109] The communication interface 903 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0110] Bus 910 includes hardware, software or both, and couples the components of electronic equipment to each other. For example, but not limitation, the bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnect (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. Where appropriate, bus 910 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0111] In addition, in combination with the method for determining a faulty cavity component in the above embodiment, the embodiment of the present application may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, the method for determining a faulty cavity component provided in the embodiment of the present application is implemented.

[0112] An embodiment of the present application also provides a computer program product, which includes a computer program, and the computer program is executed by a processor to implement the method for determining a faulty cavity component as provided in the embodiment of the present application.

[0113] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0114] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0115] The above are only specific implementation methods of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for determining a faulty cavity component, characterized in that: The method comprises: Collecting at least one data to be processed of a target device, wherein the target device includes a plurality of cavity components, each of the cavity components includes a first type of valve and a second type of valve, and each of the data to be processed includes first vibration characteristic data corresponding to the first type of valve of each cavity component, and second vibration characteristic data corresponding to the second type of valve of each cavity component; For each of the data to be processed, a first clustering result corresponding to the data to be processed is obtained by clustering a plurality of first vibration characteristic data in the data to be processed, and a second clustering result corresponding to the data to be processed is obtained by clustering a plurality of second vibration characteristic data in the data to be processed; Based on the first clustering result corresponding to each of the data to be processed and the second clustering result corresponding to each of the data to be processed, a faulty cavity component among the plurality of cavity components is determined.

2. The method according to claim 1, characterized in that The collecting at least one piece of data to be processed of the target device includes: For each of the data to be processed, collecting the load data of the target device, where the collection time of the load data of the target device is earlier than the collection time of the data to be processed; In the case where it is determined that the load data fluctuates abnormally, collecting the data to be processed; or, Before obtaining, for each of the data to be processed, a first clustering result corresponding to the data to be processed by clustering a plurality of first vibration characteristic data in the data to be processed, and obtaining a second clustering result corresponding to the data to be processed by clustering a plurality of second vibration characteristic data in the data to be processed, the method further comprises: For each of the data to be processed, the load data of the target device is collected, and the collection time of the load data of the target device is the same as the collection time of the data to be processed; When it is determined that the load data fluctuation is abnormal, a first clustering result corresponding to the data to be processed is obtained by clustering multiple first vibration characteristic data in the data to be processed, and a second clustering result corresponding to the data to be processed is obtained by clustering multiple second vibration characteristic data in the data to be processed.

3. The method according to claim 2, characterized in that The load data includes a plurality of load values; the method further includes: calculating a load variance of the plurality of load values; When the load variance is greater than a first threshold, determining that the load data fluctuation is abnormal; or, Calculating a difference between every two adjacent load values ​​in the plurality of load values ​​to obtain at least two difference values; When the average value of the at least two differences is greater than a second threshold, it is determined that the load data fluctuation is abnormal.

4. The method according to any one of claims 1 to 3, characterized in that The collecting of at least one piece of data to be processed by the target device includes: For each of the data to be processed, a first vibration signal corresponding to the first type of valve of each of the cavity components and a second vibration signal corresponding to the second type of valve of each of the cavity components are collected; For each vibration signal of a plurality of vibration signals, determining frequency spectrum information of the vibration signal, the plurality of vibration signals comprising a plurality of first vibration signals and a plurality of second vibration signals; reconstructing a target vibration signal corresponding to the vibration signal based on a signal portion whose frequency is greater than a preset frequency threshold in the frequency spectrum information of the vibration signal, and obtaining a plurality of target vibration signals, wherein the plurality of target vibration signals include first target vibration signals corresponding to the plurality of first vibration signals respectively and second target vibration signals corresponding to the plurality of second vibration signals respectively; First vibration characteristic data is extracted from each of the first target vibration signals, and second vibration characteristic data is extracted from each of the second target vibration signals.

5. The method according to claim 4, characterized in that A first vibration sensor is installed at the first type valve of each cavity assembly, and a second vibration sensor is installed at the second type valve of each cavity assembly; The collecting of the first vibration signal corresponding to the first type of valve of each of the cavity components and the second vibration signal corresponding to the second type of valve of each of the cavity components comprises: For each of the first-type valves, collecting a first vibration signal corresponding to the first-type valve by using a first vibration sensor corresponding to the first-type valve; For each of the second-type valves, a second vibration signal corresponding to the second-type valve is collected by a second vibration sensor corresponding to the second-type valve.

6. The method according to claim 4, characterized in that The reconstructing a target vibration signal corresponding to the vibration signal based on a signal portion whose frequency is greater than a preset frequency threshold in the frequency information of the vibration signal comprises: Decomposing the vibration signal in the frequency domain based on the frequency spectrum information of the vibration signal to obtain first internal mode function IMF components corresponding to multiple frequency ranges respectively; Selecting at least one second IMF component having a frequency greater than a preset frequency threshold from the plurality of first IMF components; A target vibration signal corresponding to the vibration signal is reconstructed based on the at least one second IMF component.

7. The method according to claim 1, characterized in that The first clustering result includes a first distance between each first vibration characteristic data in the data to be processed and a first center point of the plurality of first vibration characteristic data; the second clustering result includes a second distance between each second vibration characteristic data in the data to be processed and a second center point of the plurality of second vibration characteristic data; The obtaining of a first clustering result corresponding to the data to be processed by clustering a plurality of first vibration characteristic data in the data to be processed, and obtaining of a second clustering result corresponding to the data to be processed by clustering a plurality of second vibration characteristic data in the data to be processed, comprises: By clustering a plurality of first vibration characteristic data in the data to be processed, a first center point of the plurality of first vibration characteristic data is obtained, and a first distance between each first vibration characteristic data and the first center point is determined to obtain a plurality of first distances; A plurality of second vibration characteristic data in the data to be processed are clustered to obtain a second center point of the plurality of second vibration characteristic data, and a second distance between each second vibration characteristic data and the second center point is determined to obtain a plurality of second distances.

8. The method according to claim 7, characterized in that: The determining a faulty cavity component among the plurality of cavity components based on the first clustering result corresponding to each of the to-be-processed data and the second clustering result of each of the to-be-processed data comprises: For each of the data to be processed, a third clustering result corresponding to the data to be processed is obtained by clustering a plurality of first distances corresponding to the data to be processed and a plurality of second distances corresponding to the data to be processed, wherein the third clustering result is used to indicate at least one candidate faulty valve among the plurality of first-type valves and the plurality of second-type valves; Determining the abnormal probability of each of the candidate faulty valves based on the third clustering result of the at least one data to be processed; A candidate faulty valve with an abnormal probability greater than a preset probability threshold among the at least one candidate faulty valve is determined to be a faulty valve, and a cavity assembly including the faulty valve is determined to be a faulty cavity assembly.

9. The method according to claim 8, characterized in that The step of obtaining a third clustering result corresponding to the data to be processed by clustering the plurality of first distances corresponding to the data to be processed and the plurality of second distances corresponding to the data to be processed includes: Determine a third center point of the plurality of first distances and the plurality of second distances by clustering the plurality of first distances corresponding to the data to be processed and the plurality of second distances corresponding to the data to be processed; For each of the multiple first distances and the multiple second distances, when the target distance between the distance and the third center point is greater than a preset distance threshold, the valve corresponding to the distance is determined to be a candidate faulty valve, and at least one candidate faulty valve is obtained.

10. A device for determining a faulty cavity component, characterized in that: The device comprises: A collection module, used for collecting at least one data to be processed of a target device, wherein the target device comprises a plurality of cavity components, each of the cavity components comprises a first type of valve and a second type of valve, and each of the data to be processed comprises first vibration characteristic data corresponding to the first type of valve of each cavity component, and second vibration characteristic data corresponding to the second type of valve of each cavity component; A clustering module, for obtaining, for each of the data to be processed, a first clustering result corresponding to the data to be processed by clustering a plurality of first vibration characteristic data in the data to be processed, and obtaining a second clustering result corresponding to the data to be processed by clustering a plurality of second vibration characteristic data in the data to be processed; The determination module is further used to determine the faulty cavity components among the multiple cavity components based on the first clustering result corresponding to each of the data to be processed and the second clustering result of each of the data to be processed.

Images