Fracturing pump multi-cylinder vibration signal processing method, device, equipment, medium and product

Abstract

The application discloses a kind of fracturing pump multi-cylinder vibration signal processing method, device, equipment, medium and product, by obtaining vibration data sequence and key phase pulse signal, vibration data sequence is the vibration data collected by vibration sensor installed between adjacent cylinder body of fracturing pump, key phase pulse signal is the key phase pulse signal collected by phase sensor installed in crankshaft part of fracturing pump, then the correlation of vibration data sequence is eliminated by decorrelating vibration data sequence, the vibration data sequence after decorrelation is analyzed independently, output multiple vibration data sequences to be matched, finally based on key phase pulse signal, multiple vibration data sequences to be matched are matched with adjacent cylinder, the target vibration data sequence corresponding to each cylinder is obtained, can significantly reduce the amount of sensor, reduce cost and complexity while extracting the vibration data with stronger feature information, to effectively improve the accuracy and timeliness of fracturing pump fault diagnosis.

Description

Technical Field

[0001] This application belongs to the field of data processing technology, and in particular relates to a method, device, equipment, medium and product for processing vibration signals of a multi-cylinder fracturing pump. Background Technology

[0002] Currently, fault diagnosis of the hydraulic end equipment of a fracturing pump, a core component of the pump, is typically achieved through the collection and analysis of vibration data. When the characteristics of the vibration data undergo significant changes, a fault in the fracturing pump can be identified.

[0003] In existing technologies, vibration sensors are typically installed individually on the cylinder head of each cylinder of a fracturing pump to directly collect vibration data for the corresponding cylinder. Then, by analyzing the characteristic changes in the vibration data for each cylinder, it is possible to determine whether the fracturing pump has malfunctioned.

[0004] However, installing vibration sensors individually on the cylinder head of each cylinder of a fracturing pump is not only complex and costly, but also results in the vibration data collected by each sensor being affected by the vibration of adjacent cylinders, causing the vibration signals of multiple cylinders to overlap. In the early stages of a fault, the characteristic information indicating early anomalies is weak, leading to passive alarms only when the fault becomes severe, and failing to identify early, minor faults. This limits the accuracy and timeliness of fault diagnosis for the pressure pump. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, medium, and product for processing vibration signals in a multi-cylinder fracturing pump. This method can reduce the installation cost of vibration sensors and extract vibration data with stronger characteristic information, thereby improving the accuracy and timeliness of fracturing pump fault diagnosis.

[0006] In a first aspect, embodiments of this application provide a method for processing vibration signals from a multi-cylinder fracturing pump, the method comprising:

[0007] The vibration data sequence and the bond phase pulse signal are acquired. The vibration data sequence is vibration data collected by a vibration sensor installed between adjacent cylinders of the fracturing pump, and the bond phase pulse signal is a bond phase pulse signal collected by a phase sensor installed on the crankshaft of the fracturing pump.

[0008] The vibration data sequence is decorrelated to eliminate the correlation between the vibration data sequences, and then the decorrelated vibration data sequences are analyzed independently to output multiple vibration data sequences to be matched.

[0009] Based on the bond phase pulse signal, the multiple vibration data sequences to be matched are matched with each cylinder to obtain the target vibration data sequence corresponding to each cylinder.

[0010] In an optional implementation of the first aspect, the step of matching the plurality of vibration data sequences to be matched with adjacent cylinders based on the key phase pulse signal to obtain a target vibration data sequence corresponding to each cylinder includes:

[0011] For each vibration data sequence to be matched, based on the bond phase pulse signal, the characteristic moments of the vibration data sequence to be matched within one pulse interval are determined;

[0012] Calculate the phase difference of the characteristic moment relative to the key phase pulse signal;

[0013] Based on the phase difference and the operating sequence of each cylinder of the fracturing pump, the cylinder corresponding to each vibration data sequence to be matched is determined, and the target vibration data sequence corresponding to each cylinder is obtained.

[0014] In an optional implementation of the first aspect, before decorrelating the vibration data sequence to eliminate the correlation of the vibration data sequence, and then independently analyzing the decorrelated vibration data sequence to output multiple vibration data sequences to be matched, the method further includes:

[0015] The vibration data sequence is decentered to obtain the first vibration data sequence.

[0016] In an optional embodiment of the first aspect, after acquiring the vibration data sequence and the bond phase pulse signal, the method further includes:

[0017] Based on the bond phase pulse signal, the vibration data sequence is segmented and aligned to obtain multiple second vibration data sequences, each of which corresponds to a pulse interval;

[0018] Amplitude normalization is performed on the plurality of second vibration data sequences to obtain a plurality of third vibration data sequences;

[0019] The multiple third vibration data sequences are merged and their average values ​​are calculated to obtain the fourth vibration data sequence.

[0020] In an optional implementation of the first aspect, after matching multiple vibration data sequences to be matched with adjacent cylinders based on the bond phase pulse signal to obtain a target vibration data sequence corresponding to each cylinder, the method further includes:

[0021] The instantaneous rotational speed of the fracturing pump crankshaft is calculated based on the key phase pulse signal;

[0022] By using instantaneous rotational speed, the target vibration data sequence is resampled to obtain vibration data sequences corresponding to equal angular intervals;

[0023] Time-frequency analysis was performed on vibration data sequences corresponding to equal angular intervals to construct a three-dimensional spectrum characterizing the relationship between vibration characteristics and crankshaft rotation angle. The dimensions of the three-dimensional spectrum include crankshaft rotation angle, frequency, and amplitude.

[0024] Secondly, this application provides a multi-cylinder vibration signal processing system for a fracturing pump, which includes: a vibration sensor, a phase sensor, a data acquisition device, and a multi-cylinder vibration signal processing device for the fracturing pump.

[0025] The vibration sensor is installed between adjacent cylinders of the fracturing pump to collect vibration data sequences;

[0026] The phase sensor is installed at the crankshaft of the fracturing pump and is used to collect the key phase pulse signal;

[0027] The data acquisition device is used to acquire the vibration data sequence and the bond phase pulse signal, and send the vibration data sequence and the bond phase pulse signal to the multi-cylinder vibration signal processing device of the fracturing pump;

[0028] The fracturing pump multi-cylinder vibration signal processing device is used to receive the vibration data sequence and the bond phase pulse signal, and to apply a fracturing pump multi-cylinder vibration signal processing method as described in any one of the first aspects to process the target vibration data sequence corresponding to each cylinder.

[0029] In a provided multi-cylinder vibration signal processing system for a fracturing pump, the system further includes:

[0030] The crankshaft of the fracturing pump is machined with a reference marking groove, which corresponds to a specific position in the cylinder of the fracturing pump.

[0031] When the groove passes through the phase sensor, the phase sensor generates a bond phase pulse signal.

[0032] In a fracturing pump multi-cylinder vibration signal processing system, the data acquisition equipment includes: a data acquisition card, an industrial control computer, a data buffer queue, a gateway, and a time-series database.

[0033] The vibration data sequence and the bond phase pulse signal are acquired based on the data acquisition card, and the vibration data sequence and the bond phase pulse signal are sent to the industrial control computer.

[0034] The industrial control computer transmits the vibration data sequence and the key phase pulse signal to the gateway in real time through the data buffer queue;

[0035] The gateway forwards the vibration data sequence and the key phase pulse signal to the time series database.

[0036] Thirdly, embodiments of this application provide a multi-cylinder vibration signal processing device for a fracturing pump, the device comprising:

[0037] The acquisition module is used to acquire vibration data sequences and bond phase pulse signals. The vibration data sequences are vibration data collected by vibration sensors installed between adjacent cylinders of the fracturing pump, and the bond phase pulse signals are bond phase pulse signals collected by phase sensors installed on the crankshaft of the fracturing pump.

[0038] The processing module is used to decorrelate the vibration data sequence to eliminate the correlation of the vibration data sequence, and then perform independent analysis on the decorrelated vibration data sequence to output multiple vibration data sequences to be matched.

[0039] The matching module is used to match the multiple vibration data sequences to be matched with the characteristics of each cylinder based on the key phase pulse signal, so as to obtain the target vibration data sequence corresponding to each cylinder.

[0040] Fourthly, embodiments of this application provide a computer-readable storage medium storing a program or instructions that, when executed by a processor, implement a fracturing pump multi-cylinder vibration signal processing method as described in any of the first aspects.

[0041] Fifthly, embodiments of this application provide a computer program product, wherein when the instructions in the computer program product are executed by the processor of an electronic device, the electronic device performs a fracturing pump multi-cylinder vibration signal processing method as described in any of the first aspects.

[0042] This application discloses a method, apparatus, device, medium, and product for processing vibration signals from multiple cylinders of a fracturing pump. The method involves acquiring vibration data sequences and bond phase pulse signals. The vibration data sequences are vibration data collected by vibration sensors between the cylinders of the fracturing pump, and the bond phase pulse signals are bond phase pulse signals collected by a phase sensor at the crankshaft of the fracturing pump. The vibration data sequences are then decorrelated to eliminate correlation. The decorrelated vibration data sequences are then independently analyzed to output multiple vibration data sequences to be matched. Finally, based on the bond phase pulse signals, the multiple vibration data sequences to be matched are matched with each cylinder to obtain a target vibration data sequence corresponding to each cylinder. Compared to existing technologies that individually install vibration sensors on the cylinder head of each fracturing pump cylinder to collect vibration data for fault analysis, leading to missed fault detection due to the inability to promptly identify fault characteristics in the early stages of a fault, this application addresses this issue by placing vibration sensors on the external structure of the pump body between the cylinders. This leverages the fact that this location can receive impact signals from adjacent cylinders at equal intervals and is less affected by interference from impact signals from unrelated cylinders, significantly improving the signal-to-noise ratio and feature saliency of the vibration signals, making it easier to extract early, subtle fault information. Furthermore, by performing decorrelation and independent component analysis on the vibration data sequence, the independent vibration components of each cylinder can be effectively separated from the mixed vibration data sequence, overcoming the information loss problem caused by having fewer sensors than cylinders. Finally, using bond-phase pulse signals, a precise mapping between the vibration data sequence to be matched and the cylinder is achieved. This significantly reduces the number of sensors, lowers costs and complexity, while enabling highly sensitive identification and diagnosis of early faults in each cylinder of the fracturing pump, thereby improving the accuracy and timeliness of pressure pump fault diagnosis. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 A schematic flowchart of a multi-cylinder vibration signal processing method for a fracturing pump according to an embodiment of this application is shown;

[0045] Figure 2 This describes the arrangement of the vibration sensors in this application;

[0046] Figure 3a This is the standard arrangement of vibration sensors for the discharge valve;

[0047] Figure 3b This is the standard arrangement for the vibration sensor of the intake valve;

[0048] Figure 4 A flowchart illustrating a multi-cylinder vibration signal processing method for a fracturing pump according to another embodiment of this application is shown.

[0049] Figure 5 A flowchart illustrating a multi-cylinder vibration signal processing method for a fracturing pump according to another embodiment of this application is shown.

[0050] Figure 6 This invention provides a schematic diagram of the structure of a multi-cylinder vibration signal processing system for fracturing pumps according to an embodiment of the present application.

[0051] Figure 7 A schematic diagram of the hardware structure of the multi-cylinder vibration signal processing device for fracturing pumps provided in an embodiment of this application is shown.

[0052] Figure 8 The crankshaft angle-frequency-amplitude spectrum is shown.

[0053] Figure 9 A schematic diagram of the multi-cylinder vibration signal processing device for fracturing pumps provided in this application is shown. Detailed Implementation

[0054] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0055] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0056] First, the terms used in this application will be explained:

[0057] Gain adjustment: The gain value is dynamically adjusted according to the intensity of the input vibration data signal. When the vibration data is strong, the gain is reduced to prevent distortion, and when the vibration data is weak, the gain is increased to optimize the signal-to-noise ratio.

[0058] Bottom dead center: refers to the position where the plunger is closest to the crankshaft centerline when it reciprocates within the cylinder.

[0059] Currently, vibration monitoring of fracturing pumps typically employs a method of installing individual vibration sensors on the cylinder head of each cylinder block. Vibration data is collected and analyzed to determine if a malfunction has occurred. However, this method suffers from interference from adjacent cylinder blocks, causing aliasing of vibration signals across multiple cylinders. This results in a lower overall signal-to-noise ratio for the corresponding cylinder's vibration data. In the early stages of a fault, the intensity of characteristic information representing early anomalies is weak, leading to missed detection of early fault features and the inability to identify subtle early faults. Consequently, this limits the accuracy and timeliness of fracturing pump fault diagnosis.

[0060] Based on this, this application provides a multi-cylinder vibration signal processing method for fracturing pumps. By arranging vibration sensors on the external structure of the pump body between adjacent cylinders, the vibration sensors installed between adjacent cylinders can receive impact signals from adjacent cylinders at equal intervals, and are less affected by interference from impact signals from other cylinders. This makes the fault characteristics more prominent in the collected vibration data. Furthermore, since this sensor arrangement simultaneously receives vibration impacts from two adjacent cylinders, this application processes key phase marking grooves on the crankshaft end face or coupling to obtain key phase pulse signals synchronized with the crankshaft rotation angle. Based on this, the mixed vibration data sequence is separated and identified to the corresponding cylinder. Ultimately, this achieves effective extraction of independent vibration signals from each cylinder and early fault feature identification, significantly improving the accuracy and timeliness of fracturing pump fault diagnosis.

[0061] The following section first introduces a multi-cylinder vibration signal processing method for fracturing pumps provided in the embodiments of this application.

[0062] Figure 1 This application provides a schematic flowchart of a multi-cylinder vibration signal processing method for fracturing pumps according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0063] S101: Acquire vibration data sequence and key phase pulse signal. The vibration data sequence is vibration data collected by vibration sensors installed between adjacent cylinders of the fracturing pump, and the key phase pulse signal is key phase pulse signal collected by phase sensors installed on the crankshaft of the fracturing pump.

[0064] In this embodiment of the application, vibration data sequence and bond phase pulse signal are acquired. The vibration data sequence is acquired by a vibration sensor arranged between adjacent cylinders of the fracturing pump, and the bond phase pulse signal is acquired by a phase sensor installed on the crankshaft of the fracturing pump.

[0065] In one example, a five-cylinder fracturing pump will be used for illustration. Figure 2 In the arrangement of the vibration sensors in this application, vibration sensor No. 1 is arranged between cylinder No. 1 and cylinder No. 2; vibration sensor No. 3 is arranged between cylinder No. 4 and cylinder No. 5; and vibration sensor No. 2 is arranged on the cylinder head of cylinder No. 3.

[0066] Figure 3a This is a standard arrangement of vibration sensors for the discharge valve. Figure 3b The conventional arrangement of the vibration sensor for the intake valve is as follows: Figure 3a As shown in 3b, vibration sensors are arranged on the cylinder head of the intake or exhaust valve of each cylinder to collect vibration data.

[0067] Because the vibration sensor of this application is arranged on the external structure of the pump body between two adjacent cylinders, the vibration sensor installed between adjacent cylinders can receive impact signals from adjacent cylinders at equal intervals, and is less affected by interference from impact signals from other cylinders. For example, Figure 2 In the arrangement shown, sensor 1 is closest to cylinders 1 and 2, and farther from cylinders 3, 4, and 5, thus significantly reducing interference from vibration signals from non-adjacent cylinders. In contrast, in traditional arrangements where vibration sensors are mounted on a single cylinder head, the signal is easily affected by vibrations from adjacent cylinders, leading to a decrease in the signal-to-noise ratio. Therefore, the vibration signal acquired at this type of measurement point has a significantly higher fundamental amplitude than the signal obtained from the traditional cylinder head arrangement, and the signal-to-noise ratio is also significantly improved, providing higher-quality raw data input for subsequent signal separation algorithms. Furthermore, the sensor arrangement used in this application requires fewer sensors than traditional sensor arrangements. By scientifically reducing the number of sensors used, it not only does not reduce the quality of vibration data signals but also improves them, while significantly reducing system hardware costs and installation complexity.

[0068] S102: Decorrelate the vibration data sequence to eliminate the correlation between the vibration data sequences, and then perform independent analysis on the decorrelated vibration data sequence to output multiple vibration data sequences to be matched.

[0069] In this embodiment, the vibration data sequence acquired by the vibration sensor is decorrelated to eliminate the correlation between the vibration data sequences. In one example, this decorrelation process is achieved through whitening, specifically based on principal component analysis. This involves calculating the covariance matrix of the vibration data sequence and performing eigenvalue decomposition, projecting the data into a space composed of eigenvectors, ensuring that the transformed components are uncorrelated and have unit variance. Then, the decorrelated vibration data sequence is independently analyzed, outputting multiple statistically independent vibration data sequences to be matched. In one example, this independent analysis is implemented using a blind source separation algorithm, such as Fast Fixed-Point Independent Component Analysis (FastICA), Information Maximization (Infomax), or Joint Approximate Diagonalization of Eigenmatrices (JADE).

[0070] In one example, to improve the convergence and stability of the decorrelation processing and independent analysis algorithms, the following steps are included before step S102:

[0071] The vibration data sequence is decentered to obtain the first vibration data sequence.

[0072] In this embodiment of the application, the vibration data sequence is decentered to obtain a first vibration data sequence. Specifically, the decentralization process can be implemented as follows: calculate the average value of all data points in the vibration data sequence; then, subtract the average value from each data point in the vibration data sequence to obtain a first vibration data sequence with a mean of zero.

[0073] In this embodiment of the application, before decorrelation processing and independent analysis of the vibration data, the original vibration data sequence is first preprocessed by decentering to eliminate the DC component or constant offset in the signal, so that the vibration data sequence is distributed with zero mean. By adjusting the center of the vibration data to zero, a standardized data input basis is provided for subsequent decorrelation and independent analysis algorithms based on second-order or higher-order statistical properties, avoiding the interference of offset on the covariance matrix and independence measure.

[0074] S103: Based on the bond phase pulse signal, multiple vibration data sequences to be matched are matched with adjacent cylinders to obtain the target vibration data sequence corresponding to each cylinder.

[0075] In this embodiment, although the multiple vibration data sequences to be matched output after blind source separation are statistically independent, they have not yet been established as corresponding to the specific cylinder number of the fracturing pump. Therefore, by utilizing the precise phase reference provided by the bond phase pulse signal, each vibration data sequence to be matched is compared and matched with the theoretical phase during operation of each cylinder, thereby obtaining the target vibration data sequence corresponding to each cylinder.

[0076] In this embodiment, vibration data sequences and bond phase pulse signals are acquired. The vibration data sequences are vibration data collected by vibration sensors between the cylinder bodies of the fracturing pump, and the bond phase pulse signals are bond phase pulse signals collected by phase sensors at the crankshaft of the fracturing pump. The vibration data sequences are then decorrelated to eliminate correlation. The decorrelated vibration data sequences are then independently analyzed to output multiple vibration data sequences to be matched. Finally, based on the bond phase pulse signals, these multiple matching vibration data sequences are matched with each cylinder to obtain the target vibration data sequence for each cylinder. Compared to existing technologies that install vibration sensors separately on the cylinder head of each fracturing pump cylinder to collect vibration data for fault analysis, which leads to missed fault detection due to the inability to promptly obtain fault characteristics in the early stages of a fault, this application, by arranging vibration sensors on the external structure of the pump body between the cylinder bodies, fully utilizes the low stiffness of this location and its minimal influence from impact signals from unrelated cylinder bodies, significantly improving the signal-to-noise ratio and feature saliency of the vibration signals, making it easier to extract early, weak fault information. Furthermore, by performing decorrelation and independent component analysis on the vibration data sequence, the independent vibration components of each cylinder can be effectively separated from the mixed vibration data sequence, overcoming the information loss problem caused by the number of sensors being less than the number of cylinders. Finally, by using bond-phase pulse signals, a precise mapping between the vibration data sequence to be matched and the cylinder body is achieved. This significantly reduces the number of sensors, lowers costs and complexity, while enabling highly sensitive identification and diagnosis of early faults in each cylinder of the fracturing pump, thereby improving the accuracy and timeliness of pressure pump fault diagnosis.

[0077] Figure 4 This illustration shows a flowchart of a multi-cylinder vibration signal processing method for a fracturing pump according to another embodiment of this application. Figure 1 Based on the illustrated embodiment, one specific implementation of step S103 is as follows:

[0078] S401: For each vibration data sequence to be matched, based on the bond phase pulse signal, determine the characteristic moment of the vibration data sequence to be matched within one pulse interval.

[0079] In this embodiment, for the multiple vibration data sequences to be matched, the precise time reference provided by the bond phase pulse signal is used to extract the characteristic moment of each vibration data sequence within a complete pulse interval (i.e., one revolution of the crankshaft). In one example, the characteristic moment refers to the moment corresponding to the maximum peak value of the vibration data sequence in the current cycle, which originates from the strong mechanical impact generated when the fracturing pump valve is opened or closed.

[0080] S402: Calculate the phase difference of the characteristic moment relative to the key phase pulse signal.

[0081] In this embodiment, the phase difference between a characteristic moment and the key phase pulse signal is calculated. In one example, the moment corresponding to the maximum peak value of the vibration data within a pulse interval is first obtained, and the time difference between this moment and the rising edge of the key phase pulse signal is calculated. Subsequently, this time difference is converted into a crankshaft angle to obtain a precise phase difference. The phase difference characterizes the specific angular position of the vibration impact event within the crankshaft motion cycle. The specific calculation formula is as follows:

[0082] Phase difference = (time difference / pulse period) × 360° (1)

[0083] S403: Based on the phase difference and the operating sequence of each cylinder of the fracturing pump, determine the cylinder corresponding to each vibration data sequence to be matched, and obtain the target vibration data sequence corresponding to each cylinder.

[0084] In this embodiment, based on the calculated phase difference of each vibration data sequence to be matched, and combined with the inherent working order of each cylinder of the fracturing pump (for example, the working order of a five-cylinder fracturing pump is 1-4-2-5-3, with a 72° phase difference between the crankshafts of adjacent cylinders), each vibration data sequence to be matched is assigned to the corresponding cylinder, thus obtaining the target vibration data sequence for each cylinder. In a specific example, the calculated phase difference is compared one by one with the theoretical working phase angle of each cylinder (e.g., the discharge stroke of cylinder 1 starts at 0° phase). The cylinder whose phase difference is closest to the theoretical working phase angle is determined to be the cylinder to which the vibration data sequence belongs.

[0085] In this embodiment, by extracting the characteristic moments of each vibration data sequence to be matched and calculating its phase difference relative to the bond phase pulse signal, cylinder matching is completed according to the operating sequence of each cylinder of the fracturing pump. Finally, a corresponding target vibration data sequence is output for each cylinder. By associating vibration events with crankshaft rotation angle, the inherent phase working law of the fracturing pump itself is fully utilized, and the vibration data sequence can be accurately matched to each cylinder. This mechanism can accurately match vibration data for each cylinder under the sparse vibration sensing layout of this application, making the technical solution of this application feasible for engineering implementation.

[0086] Figure 5This illustration shows a flowchart of a multi-cylinder vibration signal processing method for a fracturing pump according to another embodiment of this application. Figure 1 Based on the illustrated embodiment, after step S101, the method further includes:

[0087] S501: Based on the bond phase pulse signal, the vibration data sequence is segmented and aligned to obtain multiple second vibration data sequences, each of which corresponds to a pulse interval.

[0088] In this embodiment, based on the key phase pulse signal, the continuously acquired vibration data sequence is segmented and aligned according to the crankshaft rotation cycle to obtain multiple second vibration data sequences of equal length. Each second vibration data sequence corresponds to a complete pulse interval, that is, the time period of one crankshaft rotation, or one working cycle of the engine.

[0089] S502: Amplitude normalization is performed on multiple second vibration data sequences to obtain multiple third vibration data sequences.

[0090] In this embodiment, multiple second vibration data sequences are subjected to amplitude normalization processing to obtain multiple third vibration data sequences. In one example, the maximum absolute value normalization method can be used, which divides the data points in each vibration data sequence by the maximum absolute value, thereby unifying the amplitude scale of different second vibration data sequences to the range of [-1, 1].

[0091] S503: Merge multiple third vibration data sequences and calculate the average value to obtain a fourth vibration data sequence.

[0092] In this embodiment of the application, multiple third vibration data sequences after amplitude normalization are superimposed and their arithmetic mean is calculated to finally obtain a fourth vibration data sequence.

[0093] In this embodiment, based on the key phase pulse signal, the vibration data sequence is segmented and aligned to obtain multiple second vibration data sequences. Then, the amplitude of the multiple second vibration data sequences is normalized to obtain multiple third vibration data sequences, eliminating the energy differences in vibration data of each cycle caused by load fluctuations or speed changes of the fracturing pump. Then, the multiple third vibration data sequences are merged and the average value is calculated to obtain a fourth vibration data sequence. Since the periodic impact signal (such as valve seat wear impact) has a fixed phase in each cycle, it is enhanced during the superposition and averaging process. On the other hand, the phase of non-periodic noise and random interference (such as fluid impact) is random in each cycle, and they cancel each other out and are significantly attenuated during the averaging process. Therefore, the fourth vibration data sequence obtained by the above processing can reduce the interference caused by non-periodic fluid impact during fracturing operations, smooth short-term fluctuations, more clearly reflect long-term trends, and improve the reliability and accuracy of vibration data.

[0094] Figure 6 A schematic diagram of a multi-cylinder vibration signal processing system for fracturing pumps according to an embodiment of this application is shown. Figure 6 As shown, the multi-cylinder vibration signal processing system 60 for fracturing pumps includes: a vibration sensor 61, a phase sensor 62, a data acquisition device 63, and a multi-cylinder vibration signal processing device 64 for fracturing pumps.

[0095] Vibration sensor 61 is installed between adjacent cylinders of the fracturing pump to collect vibration data sequences.

[0096] In this embodiment, vibration sensors 61 are sparsely installed between the fracturing pump cylinders to collect vibration data sequences composed of the mixed vibrations of adjacent cylinders. In one example, the vibration sensors 61 can be magnetically fixed between the fracturing pump cylinders. In another example, the vibration sensors 61 can be acceleration sensors or velocity sensors.

[0097] Phase sensor 62 is installed at the crankshaft of the fracturing pump to collect key phase pulse signals.

[0098] In this embodiment, the phase sensor 62 is installed on the end face of the crankshaft of the fracturing pump or at the coupling to collect key phase pulse signals synchronized with the crankshaft rotation angle. In one example, the phase sensor can be a Hall sensor.

[0099] In one example, to accurately generate and record the bond phase pulse signal, the following is also included:

[0100] The crankshaft of the fracturing pump is machined with a reference mark groove, which corresponds to a specific position in the fracturing pump cylinder.

[0101] In the embodiments of this application, the position of the reference mark groove corresponds to a specific position in the fracturing pump cylinder. In one example, taking a five-cylinder fracturing pump as an example, the position of the reference mark groove can be precisely matched with the bottom dead center position of cylinder 1 of the five-cylinder fracturing pump.

[0102] When the reference mark groove passes through the phase sensor 62, the phase sensor 62 generates a key phase pulse signal.

[0103] In this embodiment, for each revolution of the fracturing pump crankshaft, the reference mark groove passes through the phase sensor 62 once, triggering the phase sensor 62 to generate a synchronous key phase pulse signal. For a five-cylinder fracturing pump, the crankshaft phases differ by 72°. This key phase pulse signal provides a precise phase reference for the subsequent segmentation, alignment, and cylinder matching of vibration data sequences, forming the hardware basis for multi-cylinder vibration signal separation.

[0104] In this embodiment, the precise correspondence between the reference mark groove and the specific mechanical position of the fracturing pump ensures that each key phase pulse signal is generated at an absolutely fixed phase angle on the fracturing pump crankshaft, providing a unique, accurate, and condition-independent time synchronization reference for vibration data processing. Furthermore, the key phase pulse signal establishes a direct correlation between vibration data and crankshaft rotation angle. By combining this with the multi-cylinder operating sequence of the fracturing pump, the separated vibration signals can be accurately mapped to the corresponding physical cylinders based on their phase characteristics, thus laying a solid hardware foundation for the accurate separation and identification of multi-cylinder vibration signals. Moreover, achieving this function by machining physical grooves on the fracturing pump crankshaft eliminates the need for complex sensors or significant modifications, offering advantages such as low cost, reliable structure, and ease of implementation.

[0105] The data acquisition device 63 is used to acquire vibration data sequences and bond phase pulse signals, and send the vibration data sequences and bond phase pulse signals to the multi-cylinder vibration signal processing device 64 of the fracturing pump.

[0106] In this embodiment, the data acquisition device 63 is used to acquire vibration data sequence and bond phase pulse signal, and send the vibration data sequence and bond phase pulse signal to the multi-cylinder vibration signal processing device 64 of the fracturing pump for vibration signal processing to obtain vibration data corresponding to each fracturing pump cylinder.

[0107] In one example, to achieve high-precision synchronous acquisition and reliable transmission of vibration data sequences and key phase pulse signals, the data acquisition device 63 includes: a data acquisition card 631, an industrial control computer 632, a data buffer queue 633, a gateway 634, and a time series database 635.

[0108] The vibration data sequence and bond phase pulse signal are acquired using a data acquisition card and then sent to an industrial control computer.

[0109] In this embodiment, the data acquisition card 631 is connected to the vibration sensor 61 and the phase sensor 62 to synchronously acquire multi-channel vibration data sequences and key phase pulse signals. In one example, the vibration sensor 61 and the phase sensor 62 can be connected to the data acquisition card 631 via a cable. The data acquisition card 631 is connected to the industrial control computer 632 through an interface, and the data acquisition card 631 sends the acquired vibration data sequences and key phase pulse signals to the industrial control computer 632.

[0110] In one example, before sending the vibration data sequence and the key phase pulse signal to the industrial control computer 632, the gain of the vibration data sequence can be adjusted by the signal conditioning module to make the vibration data sequence have the best amplitude range and the highest signal-to-noise ratio.

[0111] The industrial control computer transmits the vibration data sequence and key phase pulse signal to the gateway in real time through a data buffer queue.

[0112] In this embodiment, the industrial control computer 632 receives the vibration data sequence from the data acquisition card 631, and performs real-time buffering and packetization of the vibration data sequence through the deployed data buffer queue 633, and then transmits the data stream to the gateway 634 through the standard communication protocol.

[0113] The gateway forwards the vibration data sequence and the key phase pulse signal to the time series database.

[0114] In this embodiment, the gateway 634 receives data packets from the industrial control computer 652 and forwards them to the cloud or local time series database 635 for storage. When the fracturing pump malfunctions, maintenance personnel can query the time series database 635 as needed to extract vibration data sequences before and after the fault for analysis.

[0115] In this embodiment, the data acquisition card 631 synchronously acquires vibration data sequences and key phase pulse signals and sends them to the industrial control computer 632, ensuring that the vibration data and key phase pulse signals share the same acquisition clock. This hardware-level assignment of a unified timestamp to all data provides a precise time synchronization basis for subsequent vibration data alignment and phase calculation. After receiving the data, the industrial control computer 632 buffers and packages the vibration data sequences and key phase pulse signals in real time through the data buffer queue 633 before transmitting them to the gateway 634. The introduction of the data buffer queue 633 effectively addresses the pressure of high-throughput data arriving instantaneously, avoiding data congestion or packet loss problems that may occur from directly transmitting vibration data and key phase pulse signals to the backend time-series database 635, thus ensuring the continuity and reliability of data transmission. Finally, the gateway 634 forwards the integrated data to the time-series database 635 for storage. Storing vibration data and key phase pulse signals not only supports the rapid extraction of data before and after a fault for accurate analysis, but also lays a solid data foundation for advanced analysis functions such as fault prediction and health status assessment based on long-term historical data.

[0116] Figure 7 A schematic diagram of the hardware structure of the multi-cylinder vibration signal processing device for fracturing pumps provided in an embodiment of this application is shown.

[0117] The multi-cylinder vibration signal processing device 64 for fracturing pumps may include a processor 641 and a memory 642 storing computer program instructions.

[0118] Specifically, the processor 641 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0119] Memory 642 may include mass storage for data or instructions. For example, and not limitingly, memory 642 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. In one instance, memory 642 may include removable or non-removable (or fixed) media, or memory 642 may be a non-volatile solid-state memory.

[0120] In one instance, memory 642 may be read-only memory (ROM). In one instance, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0121] Memory 642 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, generally, 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 one aspect of this application.

[0122] The processor 641 reads and executes computer program instructions stored in the memory 642 to implement the multi-cylinder vibration signal processing method for fracturing pumps in any of the embodiments shown above.

[0123] In one example, the multi-cylinder vibration signal processing device for a fracturing pump may also include a communication interface 643 and a bus 644. For example, Figure 7 As shown, the processor 641, memory 642, and communication interface 643 are connected through bus 644 and complete communication with each other.

[0124] The communication interface 643 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0125] Bus 644 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not as a limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 644 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0126] In this embodiment, vibration sensors 61 are installed between the cylinders of the fracturing pump. This sparse arrangement significantly reduces the total number of sensors, lowering system hardware costs and installation complexity. Simultaneously, because the sensors are located on the external structure of the pump body between adjacent cylinders, they can receive impact signals from adjacent cylinders at equal intervals, minimizing interference from other cylinder impact signals. This results in higher raw signal-to-noise ratios for the acquired vibration data, providing higher-quality input for subsequent vibration data processing. Phase sensors 62, installed on the crankshaft of the fracturing pump, acquire key phase pulse signals that are strictly synchronized with the crankshaft rotation angle. This provides a precise timing reference for vibration signal segmentation, alignment, and phase matching, forming the hardware foundation for multi-cylinder vibration signal separation. Finally, the data acquisition device 63 sends the synchronously acquired vibration data sequence and key phase pulse signals to the multi-cylinder vibration signal processing device 64. The multi-cylinder vibration signal processing method running within this device accurately separates and identifies the target vibration data sequence corresponding to each cylinder from the mixed vibration data. The combination of this system and method can significantly reduce the number of sensors without sacrificing signal quality, and even improve the identification of fault characteristics, providing a reliable data foundation for health monitoring and early fault diagnosis of fracturing pumps.

[0127] Furthermore, in order to extract deeper vibration signal anomaly information from the vibration data obtained in this application, after obtaining the target vibration data sequence corresponding to each cylinder, the following steps are also included:

[0128] The instantaneous rotational speed of the fracturing pump crankshaft is calculated based on the key phase pulse signal.

[0129] In this embodiment, since the phase sensor receives a key phase pulse signal for each revolution of the crankshaft, the instantaneous rotational speed can be obtained by acquiring the time interval between two consecutive key phase pulse signals.

[0130] (2)

[0131] in, Indicates time The instantaneous rotational speed; Indicates the crankshaft at the 1st Transfer to the corresponding time; Indicates the crankshaft at the 1st Transfer to the corresponding time.

[0132] By using instantaneous rotational speed, the target vibration data sequence is resampled to obtain vibration data sequences corresponding to equal angular intervals.

[0133] In this embodiment, the rotational speed at any given time point can be determined using a resampling algorithm, thus establishing the relationship between angle and time. In one example, an interpolation algorithm can be used based on known discrete data points (…). , (), , ), ... ( , Estimate the continuous rotational speed function RPM(t) at any time t, and then integrate the rotational speed function to obtain the angle through which the crankshaft rotates from the first pulse to any time t. :

[0134] (3)

[0135] in, This represents the angle corresponding to time t; Indicates time The corresponding rotational speed.

[0136] Therefore, vibration data corresponding to time can be converted into vibration data corresponding to angle, avoiding the occurrence of fuzzy and scattered fault features in the spectrum analysis due to the non-fixed time interval of fault features in the time domain caused by speed fluctuations.

[0137] Time-frequency analysis was performed on vibration data sequences corresponding to equal angular intervals to construct a three-dimensional spectrum characterizing the relationship between vibration characteristics and crankshaft rotation angle. The dimensions of the three-dimensional spectrum include crankshaft rotation angle, frequency, and amplitude.

[0138] In this embodiment, the vibration data of each complete 360° working cycle can be divided into equal angular intervals, and then a short-time Fourier transform (STFT) is performed on the vibration data corresponding to each equal angle to obtain a spectrum. Figure 8 The crankshaft angle-frequency-amplitude spectrum is shown, as follows: Figure 8 As shown, the horizontal axis represents crankshaft angle, and the vertical axis represents frequency. To clearly display the three dimensions of crankshaft angle, frequency, and amplitude on a two-dimensional graph, in Figure 8 The amplitude information is represented by color, ultimately constructing a graph of crankshaft angle, frequency, and amplitude, which is then visualized. In one example, to provide a more multi-dimensional perspective, the graphs of crankshaft angle, frequency, and amplitude can be stacked along the time axis, allowing viewing of the amplitude evolution over time for specific combinations of crankshaft angle and frequency across multiple operating cycles.

[0139] In this embodiment, the three-dimensional atlas provides multiple perspectives for observing the operating status of fracturing pump equipment: Time domain perspective: By observing the changes in amplitude information over time at specific crankshaft angles and frequencies, the development trend of faults can be tracked; Frequency domain perspective: By observing the frequency distribution at specific angles, characteristic frequency components related to faults can be identified; Angle domain perspective: A mapping relationship between key phases and vibration characteristics in the operating cycle of the fracturing pump equipment is constructed. By quantitatively analyzing the phase shift and amplitude intensity of the vibration signal corresponding to a specific phase point, the working status of the associated mechanism at that phase point can be evaluated and faults can be determined. The phase shift represents the angular offset between the theoretical phase fault point and the actually measured signal fault characteristic phase in the angle domain. In other words, the three-dimensional atlas of this application can clearly reveal the relationship between vibration characteristic information and crankshaft phase changes, thereby accurately locating abnormal data and improving the interpretation capability of vibration signals and the accuracy of fault diagnosis.

[0140] Figure 9 A schematic diagram of the multi-cylinder vibration signal processing device for fracturing pumps provided in this application is shown. Figure 9 As shown, the fracturing pump multi-cylinder vibration signal processing device 900 provided in this application includes:

[0141] The acquisition module 901 is used to acquire vibration data sequence and key phase pulse signal. The vibration data sequence is vibration data collected by vibration sensor installed between adjacent cylinders of fracturing pump, and the key phase pulse signal is key phase pulse signal collected by phase sensor installed at crankshaft of fracturing pump.

[0142] The processing module 902 is used to decorrelate the vibration data sequence to eliminate the correlation of the vibration data sequence, and then perform independent analysis on the decorrelated vibration data sequence to output multiple vibration data sequences to be matched.

[0143] The matching module 903 is used to match multiple vibration data sequences to be matched with the features of adjacent cylinders based on the bond phase pulse signal, so as to obtain the target vibration data sequence corresponding to each cylinder.

[0144] In one example, matching module 903 includes:

[0145] The first determining module is used to determine the characteristic moments of each vibration data sequence to be matched within one pulse interval based on the bond phase pulse signal.

[0146] The calculation module is used to calculate the phase difference of the characteristic moment relative to the key phase pulse signal;

[0147] The second determining module is used to determine the cylinder corresponding to each vibration data sequence to be matched based on the phase difference and the operating sequence of each cylinder of the fracturing pump, so as to obtain the target vibration data sequence corresponding to each cylinder.

[0148] In one example, the multi-cylinder vibration signal processing device 900 for a fracturing pump also includes:

[0149] The first processing module is used to decenter the vibration data sequence to obtain the first vibration data sequence.

[0150] In one example, the multi-cylinder vibration signal processing device 900 for a fracturing pump also includes:

[0151] The alignment module is used to segment and align the vibration data sequence based on the bond phase pulse signal to obtain multiple second vibration data sequences, each of which corresponds to a pulse interval;

[0152] The second processing module is used to normalize the amplitude of multiple second vibration data sequences to obtain multiple third vibration data sequences.

[0153] The third processing module is used to merge multiple third vibration data sequences and calculate the average value to obtain a fourth vibration data sequence.

[0154] Furthermore, in conjunction with the multi-cylinder vibration signal processing method for fracturing pumps described in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the multi-cylinder vibration signal processing methods for fracturing pumps described in the above embodiments.

[0155] This application also provides a computer program product, including a computer program, which, when executed, implements any of the fracturing pump multi-cylinder vibration signal processing methods described in the above embodiments.

[0156] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. 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 embodiments, or in a different order, or several steps can be performed simultaneously.

[0157] The aspects of this application have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and program products according to embodiments of this application. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by a computer program or instructions. These programs or instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0158] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for processing multi-cylinder vibration signals of a fracturing pump, characterized in that, The method comprises: obtaining a vibration data sequence and a key phase pulse signal, the vibration data sequence being vibration data collected by a vibration sensor installed between adjacent cylinder blocks of a fracturing pump, and the key phase pulse signal being a key phase pulse signal collected by a phase sensor installed at a crankshaft part of the fracturing pump; after obtaining the vibration data sequence and the key phase pulse signal, the method further comprises: segmenting and aligning the vibration data sequence based on the key phase pulse signal to obtain a plurality of second vibration data sequences, each of the second vibration data sequences corresponding to a pulse interval; performing amplitude normalization on the plurality of second vibration data sequences to obtain a plurality of third vibration data sequences; merging the plurality of third vibration data sequences and calculating an average value to obtain a fourth vibration data sequence; decentering the vibration data sequence to obtain a first vibration data sequence; performing decorrelation on the vibration data sequence to eliminate the correlation of the vibration data sequence, and then performing independent analysis on the decorrelated vibration data sequence to output a plurality of to-be-matched vibration data sequences; based on the key phase pulse signal, matching the plurality of to-be-matched vibration data sequences with adjacent cylinders to obtain a target vibration data sequence corresponding to each cylinder; the matching of the plurality of to-be-matched vibration data sequences with adjacent cylinders based on the key phase pulse signal to obtain a target vibration data sequence corresponding to each cylinder comprises: for each to-be-matched vibration data sequence, determining a characteristic time point of the to-be-matched vibration data sequence within a pulse interval based on the key phase pulse signal; calculating a phase difference of the characteristic time point relative to the key phase pulse signal; based on the phase difference and the operation sequence of each cylinder of the fracturing pump, determining a cylinder corresponding to each to-be-matched vibration data sequence to obtain a target vibration data sequence corresponding to each cylinder.

2. The method of claim 1, wherein, after matching the plurality of to-be-matched vibration data sequences with adjacent cylinders based on the key phase pulse signal to obtain a target vibration data sequence corresponding to each cylinder, the method further comprises: calculating an instantaneous speed of the crankshaft of the fracturing pump based on the key phase pulse signal; using the instantaneous speed to resample the target vibration data sequence to obtain an equal-angle-interval corresponding vibration data sequence; performing time-frequency analysis on the equal-angle-interval corresponding vibration data sequence to construct a three-dimensional graph representing the relationship between vibration characteristics and crank angle, the dimensions of the three-dimensional graph including crank angle, frequency, and amplitude.

3. A fracturing pump multi-cylinder vibration signal processing system, characterized in that, The multi-cylinder vibration signal processing system of the fracturing pump comprises a vibration sensor, a phase sensor, a data acquisition device, and a multi-cylinder vibration signal processing device of the fracturing pump; the vibration sensor is installed between adjacent cylinder blocks of the fracturing pump and is used to collect a vibration data sequence; the phase sensor is installed at a crankshaft of the fracturing pump and is used to collect a key phase pulse signal; the data acquisition device is used to obtain the vibration data sequence and the key phase pulse signal, and send the vibration data sequence and the key phase pulse signal to the multi-cylinder vibration signal processing device of the fracturing pump; The fracturing pump multi-cylinder vibration signal processing device is used for receiving the vibration data sequence and the key phase pulse signal, and applying the fracturing pump multi-cylinder vibration signal processing method according to any one of claims 1-2 to process the target vibration data sequence corresponding to each cylinder.

4. The fracturing pump multi-cylinder vibration signal processing system of claim 3, wherein, Further comprising: The fracturing pump crankshaft is processed with a reference mark groove corresponding to a specific position of the fracturing pump cylinder body. When the groove passes through the phase sensor, the phase sensor generates a key phase pulse signal.

5. The fracturing pump multi-cylinder vibration signal processing system of claim 4, wherein, The data acquisition device comprises a data acquisition card, an industrial computer, a data cache queue, a gateway and a time series database. The data acquisition card is used for acquiring the vibration data sequence and the key phase pulse signal, and sending the vibration data sequence and the key phase pulse signal to the industrial computer. The industrial computer is used for transmitting the vibration data sequence and the key phase pulse signal to the gateway in real time through the data cache queue. The gateway is used for forwarding the vibration data sequence and the key phase pulse signal to the time series database.

6. A computer readable storage medium characterized by The computer readable storage medium stores computer program instructions, and the computer program instructions are executed by the processor to realize the fracturing pump multi-cylinder vibration signal processing method according to any one of claims 1-2.

7. A computer program product, characterised in that, The instructions in the computer program product are executed by the processor of the electronic device, so that the electronic device executes the fracturing pump multi-cylinder vibration signal processing method according to any one of claims 1-2.

Images