Crack detection method, device and equipment, storage medium and product

Abstract

The embodiment of the invention provides a crack detection method and device, equipment, a storage medium and a product, and the method specifically comprises the steps that to-be-detected data of a pump head assembly is obtained, and the pump head assembly comprises at least one cylinder body assembly; the to-be-detected data is determined based on stroke frequency information of the pump head assembly and cylinder assembly data of each cylinder assembly in the pump head assembly, and the cylinder assembly data comprises vibration signal data of the cylinder assemblies; and processing the to-be-detected data of the pump head assembly based on a preset crack detection model to obtain a crack detection result corresponding to the pump head assembly. According to the embodiment of the invention, the crack in the mechanical equipment can be accurately and timely detected, so that the crack detection efficiency is improved.

Description

Technical Field

[0001] The present application belongs to the technical field of fault diagnosis, and in particular, relates to a crack detection method, device, equipment, storage medium and product. Background Art

[0002] As the core equipment in fracturing operations, the stable operation of the fracturing pump is crucial to the entire operation process. However, during the operation of the fracturing pump, the appearance of cracks in the pump head and cylinder cover may cause a significant decline in equipment performance and even cause serious safety hazards. Therefore, it is crucial to accurately and timely detect faults such as cracks in the pump head and cylinder cover and perform maintenance in a timely manner. Summary of the invention

[0003] The embodiments of the present application provide a crack detection method, device, equipment, storage medium and product, which can accurately and timely detect cracks in mechanical equipment such as fracturing pumps, thereby improving the efficiency of crack detection and facilitating subsequent timely maintenance.

[0004] In a first aspect, an embodiment of the present application provides a crack detection method, the method comprising:

[0005] Acquire the data to be detected of the pump head assembly, the pump head assembly includes at least one cylinder assembly, the data to be detected is determined based on the stroke information of the pump head assembly and the cylinder assembly data of each cylinder assembly in the pump head assembly, the cylinder assembly data includes the vibration signal data of the cylinder assembly;

[0006] The data to be detected of the pump head assembly is processed based on a preset crack detection model to obtain crack detection results corresponding to the pump head assembly.

[0007] In a second aspect, an embodiment of the present application provides a crack detection device, the device comprising:

[0008] An acquisition module, used for acquiring data to be detected of a pump head assembly, wherein the pump head assembly includes at least one cylinder assembly, and the data to be detected is determined based on stroke information of the pump head assembly and cylinder assembly data of each cylinder assembly in the pump head assembly, wherein the cylinder assembly data includes vibration signal data of the cylinder assembly;

[0009] The processing module is used to process the data to be detected of the pump head assembly based on a preset crack detection model to obtain crack detection results corresponding to the pump head assembly.

[0010] 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 crack detection method provided in the first aspect.

[0011] 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 crack detection method provided in the first aspect is implemented.

[0012] 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 crack detection method provided in the first aspect is implemented.

[0013] In an embodiment of the present application, the data to be detected of the pump head assembly can be obtained, and the pump head assembly includes at least one cylinder assembly. Based on this, the data to be detected of the above-mentioned pump head assembly is determined based on the stroke information of the pump head assembly and the cylinder assembly data of each cylinder assembly in the pump head assembly. The cylinder assembly data may include vibration signal data of the cylinder assembly, and then the data to be detected of the pump head assembly can be processed based on a preset crack detection model to obtain a crack detection result corresponding to the pump head assembly. In this way, the method of using the model to perform crack detection on the data to be detected of the pump head assembly improves the efficiency of crack detection compared to the method of manually disassembling equipment to determine cracks in the prior art, and crack detection can be performed in combination with the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly included in the pump head assembly, which also improves the accuracy of crack detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] 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.

[0015] Figure 1 This is one of the flow diagrams of a crack detection method provided in an embodiment of the present application;

[0016] Figure 2 This is the second flow chart of a crack detection method provided in an embodiment of the present application;

[0017] Figure 3 is a structural schematic diagram of a crack detection device provided in an embodiment of the present application;

[0018] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] 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.

[0020] 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 statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0021] 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.

[0022] As the background technology shows, in real life, during the operation of a fracturing pump, cracks in the pump head and the cylinder cover may cause equipment performance degradation and safety hazards. However, in the prior art, maintenance personnel generally disassemble the fracturing pump to determine whether cracks exist and where the cracks exist. This method is inefficient in determining cracks in mechanical equipment such as fracturing pumps.

[0023] Based on this, in order to solve the problems existing in the above-mentioned prior art, the embodiments of the present application provide a crack detection method, device, equipment, storage medium and product, which can obtain the data to be detected of the pump head assembly, and the pump head assembly includes at least one cylinder assembly. Based on this, the data to be detected of the above-mentioned pump head assembly is determined based on the stroke information of the pump head assembly and the cylinder assembly data of each cylinder assembly in the pump head assembly. The cylinder assembly data may include the vibration signal data of the cylinder assembly, and then the data to be detected of the pump head assembly can be processed based on the preset crack detection model to obtain the crack detection result corresponding to the pump head assembly. In this way, the method of using the model to perform crack detection on the data to be detected of the pump head assembly improves the efficiency of crack detection compared to the method of manually disassembling the equipment to determine the crack in the prior art, and the crack detection can be combined with the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly included in the pump head assembly to perform crack detection, which also improves the accuracy of crack detection.

[0024] It should be noted that the crack detection method provided in the embodiment of the present application can be executed by a crack detection device or a control module in the crack detection device for executing the crack detection method. In the embodiment of the present application, the crack detection method provided in the embodiment of the present application is described by taking the crack detection device executing the crack detection method as an example.

[0025] The crack detection method provided in the embodiment of the present application is described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0026] Figure 1 It is a flow chart of a crack detection method provided in an embodiment of the present application.

[0027] like Figure 1 As shown, the execution subject of the method may be a crack detection device, and the method may specifically include the following steps:

[0028] S110, obtaining the data to be tested of the pump head assembly.

[0029] It should be noted here that the pump head assembly can be a related assembly for fluid transmission, pressure conversion, etc. in the target device, which is not specifically limited here. The target device can be, for example, a pressure pump or other related equipment with a pump system, and the target device can include at least one pump head assembly, which is not specifically limited here.

[0030] Each of the above-mentioned pump head components may include at least one cylinder component, and each cylinder component may form a cavity, which is not specifically limited here. Based on this, the data to be detected of the above-mentioned pump head component can be determined based on the stroke information of the pump head component and the cylinder component data of each cylinder component in the pump head component. Among them, the stroke information of the above-mentioned pump head component may refer to the number of times the piston of the pump head component reciprocates within a preset time, and the stroke information of the pump head component may be determined based on the stroke gear selected by the user, that is, the stroke information corresponding to different stroke gears is different, which is not specifically limited here. The above-mentioned cylinder component data may include vibration signal data of the cylinder component, and the vibration signal data may be data related to the vibration signal of the cylinder component within a preset time, which may include multiple vibration signals, which are not specifically limited here. In this way, since the stroke information of the above-mentioned pump head component is key information that can determine the vibration frequency and vibration amplitude of the vibration, in this way, it is possible to judge whether the pump head component is abnormal based on the stroke information of the pump head component and the vibration signal data of each cylinder component in the pump head component.

[0031] In addition, the above-mentioned preset time can be pre-set based on actual experience or circumstances, and the embodiment of the present application does not specifically limit the duration of the above-mentioned preset time.

[0032] S120, processing the data to be detected of the pump head assembly based on a preset crack detection model to obtain a crack detection result corresponding to the pump head assembly.

[0033] The above-mentioned preset crack detection model may be a relevant model for crack detection that is pre-set based on actual experience or obtained through pre-training, and is not specifically limited here.

[0034] In addition, the crack detection result corresponding to the above-mentioned pump head assembly may include the crack type and the crack location. Among them, the above-mentioned crack type may include pump head crack (i.e., crack appears on the pump head) and cylinder head crack (i.e., crack appears on the cylinder head). The above-mentioned crack location may refer to the specific location where the crack appears.

[0035] Specifically, the crack detection device can obtain the data to be detected of the pump head assembly, and input the data to be detected into a preset crack detection model, so that the preset crack detection model processes the data to be detected of the pump head assembly to obtain a crack detection result corresponding to the pump head assembly.

[0036] It should also be noted that after obtaining the crack detection result of the pump head assembly, the crack detection device can also generate prompt information corresponding to the crack type, and the prompt information may include the crack location. For example, if the crack type is a pump head crack, the prompt information generated by the crack detection device may include the crack location of the pump head crack, so as to prompt the user to repair or replace the pump head. If the crack type is a cylinder head crack, the prompt information generated by the crack detection device may include the crack location of the cylinder head crack, so as to prompt the user to replace the corresponding cylinder head to ensure timely and effective maintenance.

[0037] In an embodiment of the present application, the data to be detected of the pump head assembly can be obtained, and the pump head assembly includes at least one cylinder assembly. Based on this, the data to be detected of the above-mentioned pump head assembly is determined based on the stroke information of the pump head assembly and the cylinder assembly data of each cylinder assembly in the pump head assembly. The cylinder assembly data may include vibration signal data of the cylinder assembly, and then the data to be detected of the pump head assembly can be processed based on a preset crack detection model to obtain a crack detection result corresponding to the pump head assembly. In this way, the method of using the model to perform crack detection on the data to be detected of the pump head assembly improves the efficiency of crack detection compared to the method of manually disassembling equipment to determine cracks in the prior art, and crack detection can be performed in combination with the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly included in the pump head assembly, which also improves the accuracy of crack detection.

[0038] In the above embodiment, the data to be detected of the pump head assembly needs to be input into the preset crack detection model to obtain the crack detection result corresponding to the pump head assembly. Based on this, in order to accurately obtain the data to be detected so that crack detection can be performed more accurately later, in one embodiment, the above S110 may specifically include the following steps:

[0039] Obtain the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly;

[0040] The stroke information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly are integrated to obtain the data to be detected corresponding to the pump head assembly.

[0041] Specifically, the crack detection device can obtain the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly, and then can fuse the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly to obtain the data to be detected corresponding to the pump head assembly.

[0042] It should be noted that in the process of integrating the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly to obtain the data to be detected corresponding to the pump head assembly, the weights of the above-mentioned data or information can be adaptively determined for effective integration.

[0043] In this embodiment, the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly can be acquired and integrated to obtain the data to be detected of the pump head assembly, thereby facilitating the subsequent use of the model to process the data to be detected of the pump head assembly to obtain crack detection results, thereby improving the efficiency of crack detection. In this process, crack detection can be performed in combination with the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly included in the pump head assembly, thereby also improving the accuracy of crack detection.

[0044] Since the vibration signal data of each cylinder assembly in the pump head assembly needs to be obtained in the above embodiment, based on this, in order to accurately and in detail describe the crack detection method provided in the embodiment of the present application, in one embodiment, Figure 2 As shown, the step of obtaining the vibration signal data of each cylinder assembly in the pump head assembly may specifically include:

[0045] S210, acquiring multiple vibration signals of each cylinder assembly in the pump head assembly, and determining frequency spectrum information of each vibration signal.

[0046] S220 , for each vibration signal, based on the frequency spectrum information of the vibration signal, decompose the vibration signal in the time domain to obtain a plurality of first intrinsic mode function IMF components.

[0047] S230, calculating a similarity coefficient between each first IMF component and the vibration signal.

[0048] S240: based on the similarity coefficient between each first IMF component and the vibration signal, at least one second IMF component having a similarity coefficient greater than a preset threshold is selected from the plurality of first IMF components.

[0049] S250: Reconstruct a reconstructed signal corresponding to the vibration signal based on at least one second IMF component.

[0050] Among them, each of the above-mentioned first intrinsic mode function (IMF) components corresponds to a specific frequency range, and the amplitude change of the vibration signal within the frequency range, that is, each first IMF component reflects the different frequency components in the vibration signal. It should also be noted that the above-mentioned multiple first IMF components are usually arranged in order from high to low frequency, that is, the first IMF component corresponding to the high-frequency component in the vibration signal generally appears before the first IMF component corresponding to the low-frequency component in the vibration signal.

[0051] In addition, the similarity coefficient between each of the first IMF components and the vibration signal may be a Pearson similarity coefficient, and the preset threshold may be a domain value of the similarity coefficient pre-set based on actual experience or circumstances. For example, the preset threshold may be 0.6, which is not specifically limited here.

[0052] It should be noted that the reconstructed signal corresponding to each of the above-mentioned vibration signals is also a vibration signal. Therefore, in the process of acquiring the vibration signal, since each cylinder component corresponds to multiple vibration signals and each vibration signal corresponds to a reconstructed signal, the vibration signal data of each cylinder component may include the reconstructed signals corresponding to the multiple vibration signals respectively.

[0053] Specifically, the crack detection device can obtain multiple vibration signals of each cylinder assembly in the pump head assembly, and determine the frequency spectrum information of each vibration signal. Then, for each vibration signal, based on the frequency spectrum information of the vibration signal, the vibration signal can be decomposed in the time domain to obtain multiple first IMF components, and the similarity coefficient between each first IMF component and the vibration signal can be calculated. Then, based on each first IMF component, at least one second IMF component with a similarity coefficient greater than a preset threshold can be screened out, that is, the at least one second IMF component is the main component in the vibration signal, and then the reconstructed signal corresponding to the vibration signal can be reconstructed based on the at least one second IMF component.

[0054] It should be noted that the crack types can include pump head cracks and cylinder head cracks, and the relevant features of pump head cracks generally exist in the high-frequency information of the vibration signal, and the relevant features of cylinder head cracks generally exist in the low-frequency information of the vibration signal. Therefore, if the crack type is a pump head crack, the high-frequency information in the reconstructed signal will be more significant. Correspondingly, if the crack type is a cylinder head crack, the low-frequency information in the reconstructed signal will be more significant. In the application process, it plays a role in eliminating the influence of noise as much as possible and retaining key information features for subsequent model classification.

[0055] In this embodiment, the vibration signal can be decomposed in the time domain based on the spectrum information of the vibration signal to obtain multiple IMF components, and at least one second IMF component with a similarity coefficient with the original vibration signal greater than a preset threshold can be screened out, so as to reconstruct the first sub-signal based on the at least one second IMF component. In this way, the main part of the original vibration signal can be accurately extracted from each vibration signal, the influence of noise can be eliminated to a certain extent, and the key information features can be retained, so that the crack type can be accurately identified later.

[0056] It should be noted that, in the process of decomposing the vibration signal in the time domain based on the spectrum information of the vibration signal to obtain the first IMF components corresponding to multiple frequency ranges, the ensemble empirical mode decomposition (EEMD) method can be used to decompose the vibration signal in the time domain based on the spectrum information of the vibration signal.

[0057] Since it is necessary to obtain multiple vibration signals of each cylinder assembly in the pump head assembly in the above embodiments, it should be noted that, in some embodiments, each cylinder assembly may include at least two cylinder heads, and a vibration sensor is installed at each cylinder head. For example, each pump head of a fracturing pump may include five cylinders, each of which may include two cylinder heads. Thus, according to the structural characteristics of the fracturing pump, a vibration sensor may be installed in the horizontal direction and the vertical direction of each cylinder, that is, a vibration sensor is installed at each cylinder head of each cylinder assembly to fully cover the cylinder head and avoid data omission.

[0058] Based on this, the above S210 may specifically include the following steps:

[0059] For each cylinder assembly in the pump head assembly, multiple vibration signals of the cylinder assembly are acquired through vibration sensors corresponding to at least two cylinder heads included in the cylinder assembly.

[0060] Specifically, since each cylinder assembly may include at least two cylinder heads and a vibration sensor is installed at each cylinder head, based on this, the crack detection device can obtain multiple vibration signals of each cylinder assembly in the pump head assembly through the vibration sensors corresponding to the at least two cylinder heads included in the cylinder assembly.

[0061] In this embodiment, a vibration sensor can be installed at each cylinder head of each cylinder assembly so as to accurately and timely obtain multiple vibration signals corresponding to each cylinder assembly, and the accuracy of crack detection results can be avoided from being affected by signal omission, thereby improving the accuracy of crack detection.

[0062] Considering that cracks in the pump head will cause fluid leakage, reduce the efficiency and output pressure of the pump, and further affect the pressure in the cavity formed by the cylinder assembly, pressure is an important indicator for observing fluid leakage. Based on this, in order to be able to describe the crack detection method provided in the embodiment of the present application in more detail, in one embodiment, the cylinder assembly data of each cylinder assembly mentioned above may also include pressure signal data of the cylinder assembly, and the pressure signal data may include multiple pressure signals, which are not specifically limited here. In this way, before the above-mentioned fusion of the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly to obtain the data to be detected corresponding to the pump head assembly, the crack detection method provided in the embodiment of the present application may also include the following steps:

[0063] Obtain pressure signal data for each cylinder assembly in the pump head assembly.

[0064] Based on this, the above-mentioned step of integrating the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly to obtain the data to be detected corresponding to the pump head assembly may specifically include:

[0065] The stroke information of the pump head assembly and the vibration signal data and pressure signal data of each cylinder assembly in the pump head assembly are integrated to obtain the data to be detected corresponding to the pump head assembly.

[0066] Specifically, since the cylinder assembly data of each of the above-mentioned cylinder assemblies can also include the pressure signal data of the cylinder assembly, the crack detection device can obtain the pressure signal data of each cylinder assembly in the pump head assembly, and then can integrate the stroke information of the pump head assembly and the vibration signal data and pressure signal data of each cylinder assembly in the above-mentioned pump head assembly to obtain the data to be detected of the pump head assembly.

[0067] In this embodiment, the data to be detected of the pump head assembly can be obtained by acquiring the pressure signal data of each cylinder assembly and fusing the stroke information of the pump head assembly and the vibration signal data and pressure signal data of each cylinder assembly in the pump head assembly. In this way, more accurate data to be detected can be obtained, which is convenient for improving the accuracy of crack detection in the future.

[0068] Based on this, it should be noted that, since each cylinder assembly is used to form a cavity, in order to better obtain pressure signal data so that it can be combined with vibration signal data and stroke frequency information for joint diagnosis and improve the accuracy of crack detection, in the crack detection method provided in the embodiment of the present application, a pressure sensor is installed inside each of the above-mentioned cylinder assemblies to accurately monitor the pressure in the cavity in real time. Based on this, the step of obtaining the pressure signal data of each cylinder assembly in the pump head assembly can specifically include the following steps:

[0069] For each cylinder assembly in the pump head assembly, pressure signal data of the cylinder assembly is obtained through a pressure sensor corresponding to the cylinder assembly.

[0070] Specifically, since a pressure sensor is installed inside each cylinder assembly, the crack detection device can obtain the pressure signal data of the cylinder assembly for each cylinder assembly in the pump head component through the pressure sensor corresponding to the cylinder assembly, that is, the pressure sensor installed inside the cylinder assembly.

[0071] In this embodiment, a pressure sensor can be installed inside each cylinder assembly to accurately obtain pressure signal data of the cylinder assembly in real time through the pressure sensor, so that the intracavity pressure of the cylinder assembly can be monitored in real time, so that the vibration signal data and stroke information can be combined for joint diagnosis later to improve the accuracy of crack detection.

[0072] In order to accurately describe the crack detection method provided in the embodiment of the present application, in one embodiment, the above S130 may specifically include the following steps:

[0073] Based on a preset crack detection model, feature extraction is performed on the data to be detected of the pump head assembly to obtain feature data to be detected;

[0074] The characteristic data to be detected are classified and processed based on a preset crack detection model to obtain a crack detection result of the pump head assembly, wherein the crack detection result includes a crack type and a crack position.

[0075] Specifically, after obtaining the data to be detected, the crack detection device can input the data to be detected into a preset crack detection model, and perform feature extraction on the data to be detected of the pump head assembly through the preset crack detection model to obtain feature data to be detected, and then can classify and process the feature data to be detected based on the preset crack detection model to obtain the crack detection result corresponding to the pump head assembly.

[0076] In one example, the preset crack detection model may include a deep residual convolutional neural network and a fully connected layer. Based on this, the crack detection device can adaptively extract feature data to be detected from the data to be detected through the deep residual convolutional neural network, and then perform binary classification based on the feature data to be detected through the fully connected layer to obtain the crack detection result corresponding to the pump head assembly.

[0077] In this embodiment, the data to be detected of the pump head assembly can be feature extracted by using a preset crack detection model to obtain feature data to be detected, and the feature data to be detected can be classified and processed based on the preset crack detection model to obtain the crack detection result corresponding to the pump head assembly. In this way, the crack detection result corresponding to the pump head assembly can be obtained accurately and timely, which not only improves the efficiency of crack detection, but also improves the accuracy of crack detection.

[0078] Based on the same inventive concept, the present application embodiment provides a crack detection device, specifically combined with Figure 3 The crack detection device provided in the embodiment of the present application is described in detail.

[0079] Figure 3 It is a structural schematic diagram of a crack detection device provided in an embodiment of the present application.

[0080] like Figure 3 As shown, the crack detection device 300 may specifically include:

[0081] An acquisition module 310 is used to acquire data to be detected of a pump head assembly, wherein the pump head assembly includes at least one cylinder assembly, and the data to be detected is determined based on stroke information of the pump head assembly and cylinder assembly data of each cylinder assembly in the pump head assembly, wherein the cylinder assembly data includes vibration signal data of the cylinder assembly;

[0082] The processing module 320 is used to process the to-be-detected data of the pump head assembly based on a preset crack detection model to obtain crack detection results corresponding to the pump head assembly.

[0083] In one embodiment, the crack detection device provided in the embodiment of the present application may include:

[0084] An acquisition module, used to acquire the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly;

[0085] The fusion module is used to fuse the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly to obtain the data to be detected corresponding to the pump head assembly.

[0086] In one embodiment, the crack detection device provided in the embodiment of the present application may include:

[0087] An acquisition module, specifically used to acquire multiple vibration signals of each cylinder assembly in the pump head assembly, and determine the frequency spectrum information of each vibration signal;

[0088] A decomposition module, configured to decompose each vibration signal in the time domain based on the frequency spectrum information of the vibration signal to obtain a plurality of first intrinsic mode function IMF components;

[0089] A calculation module, used for calculating a similarity coefficient between each first IMF component and the vibration signal;

[0090] A screening module, configured to screen out at least one second IMF component whose similarity coefficient is greater than a preset threshold from the plurality of first IMF components based on a similarity coefficient between each first IMF component and the vibration signal;

[0091] A reconstruction module is used to reconstruct a reconstructed signal corresponding to the vibration signal based on the at least one second IMF component, and the vibration signal data includes reconstructed signals corresponding to the multiple vibration signals respectively.

[0092] In one embodiment, each cylinder assembly includes at least two cylinder heads, and a vibration sensor is installed at each cylinder. Based on this, the acquisition module is specifically used to:

[0093] For each cylinder assembly in the pump head assembly, multiple vibration signals of the cylinder assembly are acquired through vibration sensors corresponding to at least two cylinder heads included in the cylinder assembly.

[0094] In one embodiment, the cylinder assembly data of each cylinder assembly also includes pressure signal data of the cylinder assembly; based on this, the acquisition module is also used to acquire the pressure signal data of each cylinder assembly in the pump head assembly;

[0095] The above-mentioned fusion module is also used to fuse the stroke information of the pump head assembly and the first sub-signal data, the second sub-signal data and the pressure signal data of each cylinder assembly in the pump head assembly to obtain the data to be detected corresponding to the pump head assembly.

[0096] In one embodiment, the crack detection device provided in the embodiment of the present application may further include:

[0097] A feature extraction module, used for extracting features of the data to be detected of the pump head assembly based on a preset crack detection model to obtain feature data to be detected;

[0098] The classification module is used to classify the feature data to be detected based on a preset crack detection model to obtain the crack detection result of the pump head assembly.

[0099] In an embodiment of the present application, the data to be detected of the pump head assembly can be obtained, and the pump head assembly includes at least one cylinder assembly. Based on this, the data to be detected of the above-mentioned pump head assembly is determined based on the stroke information of the pump head assembly and the cylinder assembly data of each cylinder assembly in the pump head assembly. The cylinder assembly data may include vibration characteristic data of the cylinder assembly, and then the data to be detected of the pump head assembly can be processed based on a preset crack detection model to obtain a crack detection result corresponding to the pump head assembly. In this way, the method of using the model to perform crack detection on the data to be detected of the pump head assembly improves the efficiency of crack detection compared to the method of manually disassembling equipment to determine cracks in the prior art, and crack detection can be performed in combination with the stroke information of the pump head assembly and the vibration signal data of each cylinder assembly included in the pump head assembly, which also improves the accuracy of crack detection.

[0100] Each module in the crack detection device provided in the embodiment of the present application can be implemented Figure 1 or Figure 2 The method steps provided in the illustrated embodiment can achieve the corresponding technical effects, and for the sake of brevity, they will not be repeated here.

[0101] Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0102] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0103] Specifically, the processor 401 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.

[0104] Memory 402 may include a large capacity memory for data or instructions. By way of example and not limitation, memory 402 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, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside of an electronic device. In a particular embodiment, memory 402 is a non-volatile solid-state memory.

[0105] 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.

[0106] The processor 401 implements any one of the crack detection methods in the above embodiments by reading and executing computer program instructions stored in the memory 402 .

[0107] In one example, the electronic device may further include a communication interface 403 and a bus 410. Figure 4 As shown, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0108] The communication interface 403 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0109] Bus 410 includes hardware, software or both, and the parts of electronic equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (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. In appropriate cases, bus 410 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0110] In addition, in combination with the crack detection method 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 crack detection method provided in the embodiment of the present application is implemented.

[0111] An embodiment of the present application also provides a computer program product, which includes a computer program. The computer program is executed by a processor to implement the crack detection method provided in the embodiment of the present application.

[0112] 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.

[0113] 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.

[0114] 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 crack detection method, characterized in that: The method comprises: Acquire the data to be detected of the pump head assembly, the pump head assembly includes at least one cylinder assembly, the data to be detected is determined based on the stroke information of the pump head assembly and the cylinder assembly data of each cylinder assembly in the pump head assembly, the cylinder assembly data includes the vibration signal data of the cylinder assembly; The data to be detected of the pump head assembly is processed based on a preset crack detection model to obtain a crack detection result corresponding to the pump head assembly.

2. The method according to claim 1, characterized in that: The step of obtaining the data to be detected of the pump head assembly comprises: Acquire the stroke frequency information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly; The stroke frequency information of the pump head assembly and the vibration signal data of each cylinder assembly in the pump head assembly are integrated to obtain the to-be-detected data corresponding to the pump head assembly.

3. The method according to claim 2, characterized in that Obtaining vibration signal data of each cylinder assembly in the pump head assembly, including: Acquire multiple vibration signals of each cylinder assembly in the pump head assembly, and determine frequency spectrum information of each vibration signal; For each of the vibration signals, based on the frequency spectrum information of the vibration signal, decompose the vibration signal in the time domain to obtain a plurality of first intrinsic mode function IMF components; Calculating a similarity coefficient between each first IMF component and the vibration signal; Based on a similarity coefficient between each of the first IMF components and the vibration signal, screening out at least one second IMF component whose similarity coefficient is greater than a preset threshold from a plurality of first IMF components; A reconstructed signal corresponding to the vibration signal is obtained based on the at least one second IMF component reconstruction, and the vibration signal data includes reconstructed signals corresponding to the multiple vibration signals respectively.

4. The method according to claim 3, characterized in that Each of the cylinder assemblies comprises at least two cylinder heads, and a vibration sensor is installed at each of the cylinder assemblies; The step of obtaining a plurality of vibration signals of each cylinder assembly in the pump head assembly comprises: For each cylinder assembly in the pump head assembly, multiple vibration signals of the cylinder assembly are acquired through vibration sensors corresponding to at least two cylinder heads included in the cylinder assembly.

5. The method according to claim 2, characterized in that: The cylinder assembly data of each cylinder assembly also includes pressure signal data of the cylinder assembly; Before fusing the stroke information of the pump head assembly and the first sub-signal data and the second sub-signal data of each cylinder assembly in the pump head assembly to obtain the to-be-detected data corresponding to the pump head assembly, the method further includes: Acquiring pressure signal data of each cylinder assembly in the pump head assembly; The method of fusing the stroke information of the pump head assembly and the first sub-signal data and the second sub-signal data of each cylinder assembly in the pump head assembly to obtain the to-be-detected data corresponding to the pump head assembly includes: The stroke information of the pump head assembly and the first sub-signal data, the second sub-signal data and the pressure signal data of each cylinder assembly in the pump head assembly are integrated to obtain the data to be detected corresponding to the pump head assembly.

6. The method according to claim 1, characterized in that The method of processing the data to be detected of the pump head assembly based on the preset crack detection model to obtain the crack detection result corresponding to the pump head assembly includes: Based on the preset crack detection model, feature extraction is performed on the data to be detected of the pump head assembly to obtain feature data to be detected; The characteristic data to be detected are classified and processed based on the preset crack detection model to obtain the crack detection result of the pump head assembly.

7. A crack detection device, characterized in that: The device comprises: An acquisition module, used for acquiring data to be detected of a pump head assembly, wherein the pump head assembly includes at least one cylinder assembly, and the data to be detected is determined based on stroke information of the pump head assembly and cylinder assembly data of each cylinder assembly in the pump head assembly, wherein the cylinder assembly data includes vibration signal data of the cylinder assembly; The processing module is used to process the to-be-detected data of the pump head assembly based on a preset crack detection model to obtain crack detection results corresponding to the pump head assembly.

8. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the crack detection method according to any one of claims 1-6.

9. A computer storage medium, characterized in that The computer storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the crack detection method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the crack detection method according to any one of claims 1 to 6 is implemented.

Images