Method, device and equipment for detecting abnormal state of hydraulic plunger pump

Abstract

The invention provides a hydraulic plunger pump abnormal state detection method, device and equipment. The method provided by the invention comprises the following steps: acquiring a real-time vibration signal of a to-be-detected hydraulic plunger pump, and determining a first frequency spectrum and a first envelope spectrum of the to-be-detected hydraulic plunger pump; based on the first frequency spectrum, the ratio of the frequency multiplication of the fundamental frequency of the hydraulic plunger pump to the mean value of the amplitude of the first specified frequency band and the ratio of the frequency multiplication of the plunger passing frequency of the hydraulic plunger pump to the mean value of the amplitude of the second specified frequency band are calculated, and the fundamental frequency characteristic and the plunger passing frequency characteristic are obtained; according to the first envelope spectrum, determining a frequency interval, calculating a ratio of a first average value of amplitudes of all side frequencies in the frequency interval to a second average value of amplitudes of other frequencies, and determining side frequency characteristics; determining the similarity between the first spectrum and a standard spectrum; and when at least one of the fundamental frequency characteristic, the plunger passing frequency characteristic and the side frequency characteristic is larger than a reference threshold value corresponding to the item and the similarity is smaller than a preset similarity threshold value, it is determined that the hydraulic plunger pump is in an abnormal state.

Description

Technical Field

[0001] The present application relates to the technical field of fault detection, and in particular to a method, device and equipment for detecting abnormal state of a hydraulic plunger pump. Background Art

[0002] As a commonly used high-pressure rotating mechanical equipment, the hydraulic plunger pump has internal parts failure (such as main shaft cracks, bearing wear, plunger cracks, etc., which are extremely harmful to the normal operation of the plunger pump). It will not only cause the plunger pump to stop running, but may also cause other upstream and downstream equipment to shut down, which has a great impact on the overall project progress. Therefore, it is very important to detect the abnormal status of the hydraulic plunger pump.

[0003] The existing method for detecting abnormal state of hydraulic piston pump usually adopts the performance parameter threshold monitoring method. However, the performance parameter threshold monitoring method can only detect more serious faults and has low accuracy. Summary of the invention

[0004] In view of this, the present application provides a method, device and equipment for detecting abnormal state of a hydraulic piston pump, so as to accurately identify the state of the hydraulic piston pump.

[0005] Specifically, the present application is implemented through the following technical solutions:

[0006] The first aspect of the present application provides a method for detecting an abnormal state of a hydraulic plunger pump, the method comprising:

[0007] Acquire a real-time vibration signal of the hydraulic piston pump to be tested, and determine a first frequency spectrum and a first envelope spectrum of the real-time vibration signal;

[0008] Calculate the ratio of the amplitude of the frequency multiple of the fundamental frequency of the hydraulic piston pump on the first frequency spectrum to the average value of the amplitude of the first designated frequency band on the first frequency spectrum to obtain the fundamental frequency characteristics of the real-time vibration signal; wherein the frequency multiple of the fundamental frequency at least includes the fundamental frequency; the first designated frequency band includes the left neighbor of the frequency multiple of the fundamental frequency and the right neighbor of the frequency multiple of the fundamental frequency;

[0009] Calculate the ratio of the amplitude of the multiple of the plunger passing frequency of the hydraulic plunger pump on the first spectrum to the average of the amplitude of the second designated frequency band on the first spectrum to obtain the plunger passing frequency characteristics of the real-time vibration signal; the multiple of the plunger passing frequency at least includes the plunger passing frequency; the second designated frequency band is the left neighbor of the multiple of the plunger passing frequency and the right neighbor of the multiple of the plunger passing frequency;

[0010] Determine, according to the first envelope spectrum, a frequency interval consisting of a first side frequency after the fundamental frequency and a last side frequency before the plunger passing frequency, and calculate a first average value of the amplitudes of all side frequencies in the frequency interval and a second average value of the amplitudes of other frequencies except the side frequencies in the frequency interval, and determine the side frequency characteristics of the real-time vibration signal by the ratio of the first average value to the second average value;

[0011] Determine the similarity between the first spectrum and a standard spectrum; wherein the standard spectrum is the spectrum of the vibration signal of the hydraulic piston pump in a normal state;

[0012] When at least one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is greater than the reference threshold value corresponding to the feature, and the similarity is less than the preset similarity threshold value, it is determined that the hydraulic plunger pump is in an abnormal state; wherein the reference threshold value corresponding to any one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is obtained based on statistics of multiple normal vibration signals of the hydraulic plunger pump in a normal state.

[0013] The second aspect of the present application provides a device for detecting abnormal state of a hydraulic plunger pump, the device comprising a processing module, a calculation module and a judgment module; wherein:

[0014] The processing module is used to obtain a real-time vibration signal of the hydraulic piston pump to be tested, and determine a first frequency spectrum and a first envelope spectrum of the real-time vibration signal;

[0015] The calculation module is used to calculate the ratio of the amplitude of the frequency multiple of the fundamental frequency of the hydraulic piston pump on the first frequency spectrum to the average value of the amplitude of the first designated frequency band on the first frequency spectrum, so as to obtain the fundamental frequency characteristics of the real-time vibration signal; wherein the frequency multiple of the fundamental frequency at least includes the fundamental frequency; the first designated frequency band includes the left neighbor of the frequency multiple of the fundamental frequency and the right neighbor of the frequency multiple of the fundamental frequency;

[0016] The calculation module is used to calculate the ratio of the amplitude of the multiple of the plunger passing frequency of the hydraulic plunger pump on the first spectrum to the average of the amplitude of the second specified frequency band on the first spectrum, so as to obtain the plunger passing frequency characteristics of the real-time vibration signal; the multiple of the plunger passing frequency at least includes the plunger passing frequency; the second specified frequency band is the left neighbor of the multiple of the plunger passing frequency and the right neighbor of the multiple of the plunger passing frequency;

[0017] The calculation module is used to determine the frequency interval consisting of the first side frequency after the fundamental frequency and the last side frequency before the plunger passing frequency according to the first envelope spectrum, and calculate the first average value of the amplitudes of all side frequencies in the frequency interval and the second average value of the amplitudes of other frequencies except the side frequencies in the frequency interval, and determine the side frequency characteristics of the real-time vibration signal by the ratio of the first average value to the second average value;

[0018] The processing module is used to determine the similarity between the first spectrum and a standard spectrum; wherein the standard spectrum is the spectrum of the vibration signal of the hydraulic piston pump in a normal state;

[0019] The judgment module is used to determine that the hydraulic plunger pump is in an abnormal state when at least one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is greater than a reference threshold corresponding to the feature and the similarity is less than a preset similarity threshold; wherein the reference threshold corresponding to any one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is obtained based on statistics of multiple normal vibration signals of the hydraulic plunger pump in a normal state.

[0020] The third aspect of the present application provides a hydraulic plunger pump abnormal state detection device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the methods provided in the first aspect of the present application are implemented.

[0021] The fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods provided in the first aspect of the present application.

[0022] The present application provides a method, device and equipment for detecting an abnormal state of a hydraulic plunger pump. On the one hand, by comparing the fundamental frequency feature, the plunger passing frequency feature and the sideband feature with the corresponding reference threshold, and comparing the similarity between the first spectrum and the standard spectrum with the preset similarity threshold, a detection result based on threshold comparison and a detection result based on similarity comparison can be obtained simultaneously, and then when the detection result based on threshold comparison is abnormal and the detection result based on similarity comparison is abnormal, the hydraulic plunger pump is determined to be abnormal. In this way, the accuracy and robustness of the detection can be improved by combining threshold comparison and similarity comparison for abnormality detection. On the other hand, when comparing based on the threshold, the fundamental frequency feature, the plunger passing frequency feature and the sideband feature are comprehensively considered, so that the change of the state can be fully captured, the limitation of a single feature can be avoided, and the accuracy can be further improved. On the third hand, when determining the fundamental frequency feature, the plunger passing frequency feature and the sideband feature, dimensionlessness is achieved. In this way, the influence caused by equipment differences can be avoided, the versatility and applicability of the method can be improved, and the method can be effectively applied to different equipment or working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flow chart of a first embodiment of a method for detecting abnormal state of a hydraulic plunger pump provided in the present application;

[0024] Figure 2 A schematic diagram of a first frequency spectrum of a real-time vibration signal shown in an exemplary embodiment of the present application;

[0025] Figure 3 A schematic diagram of a first envelope spectrum of a real-time vibration signal shown in an exemplary embodiment of the present application;

[0026] Figure 4 A schematic diagram of a standard spectrum shown as an exemplary embodiment of the present application;

[0027] Figure 5 A flow chart of Embodiment 2 of the method for detecting abnormal state of a hydraulic plunger pump provided in the present application;

[0028] Figure 6 A flowchart of Embodiment 3 of the method for detecting abnormal state of a hydraulic plunger pump provided in the present application;

[0029] Figure 7 A hardware structure diagram of a hydraulic plunger pump abnormal state detection device in which the hydraulic plunger pump abnormal state detection device of the present application is located;

[0030] Figure 8 This is a structural schematic diagram of Example 1 of the hydraulic plunger pump abnormal state detection device provided in the present application. DETAILED DESCRIPTION

[0031] Here, exemplary embodiments are described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application.

[0032] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to and includes any or all possible combinations of one or more associated listed items.

[0033] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0034] Specific embodiments are given below to introduce the technical solution of the present application in detail.

[0035] Figure 1 This is a flow chart of the first embodiment of the method for detecting abnormal state of a hydraulic piston pump provided in this application. Figure 1 , the method provided in this embodiment may include:

[0036] S101. Acquire a real-time vibration signal of a hydraulic piston pump to be tested, and determine a first frequency spectrum and a first envelope spectrum of the real-time vibration signal.

[0037] It should be noted that a vibration sensor is installed on the hydraulic piston pump to be tested, and the vibration sensor can monitor the vibration signal caused by the internal movement of the hydraulic piston pump in real time. In this step, the real-time vibration signal of the hydraulic piston pump to be tested can be directly obtained from the vibration sensor. In addition, the vibration sensor can measure the axial vibration signal and / or radial vibration signal of the hydraulic piston pump, which is not limited in this embodiment.

[0038] It should be noted that the type of vibration sensor installed on the hydraulic piston pump to be tested is selected according to actual needs, and is not limited in the present application. For example, in one embodiment, the vibration sensor may be a piezoelectric vibration sensor or a capacitive vibration sensor. Furthermore, the number of vibration sensors installed on the hydraulic piston pump to be tested may also be selected according to actual needs, and is not limited in the present application. For example, in one embodiment, the number of vibration sensors is 1; in another embodiment, the number of vibration sensors is 2.

[0039] In this step, for the real-time vibration signal, a first frequency spectrum and a first envelope spectrum of the real-time vibration signal may be determined.

[0040] The spectrum is a frequency domain representation obtained after Fourier transform of the vibration signal, reflecting the amplitude and phase information of the vibration signal at different frequencies. In specific implementation, a vibration signal of a duration of t is taken, and Fourier transform and other operations are performed on the vibration signal (in specific implementation, the following operations can be performed on the vibration signal in sequence: modulus after Fourier transform, multiply by 2, divide by N, and take the first half of the spectrum) to obtain the spectrum (in this embodiment, for the convenience of explanation, the spectrum of the real-time vibration signal is recorded as the first spectrum).

[0041] Figure 2 FIG. 1 is a schematic diagram of a first spectrum of a real-time vibration signal according to an exemplary embodiment of the present application. Referring to the above description, Figure 2 It can be understood that in the first spectrum, the horizontal axis represents the frequency and the vertical axis represents the amplitude of each frequency. It should be noted that some specific frequencies in the first spectrum are related to the structure and working principle of the hydraulic piston pump to be tested. By analyzing the first spectrum, the specific frequency components of the hydraulic piston pump during operation can be determined, and the amplitude changes corresponding to the specific frequency components can provide clues for fault diagnosis of the hydraulic piston pump.

[0042] Furthermore, the envelope spectrum is a frequency domain representation obtained by extracting the envelope of the vibration signal (usually using envelope detection) and then performing Fourier transform on the envelope signal.

[0043] Specifically, the process of determining the envelope spectrum may include:

[0044] (1) Extracting the envelope curve; the envelope curve is the changing trend of the signal amplitude, which can be obtained through the envelope detection method. For example, the vibration signal can be subjected to Hilbert transform, and then the absolute value of the transform result can be taken to obtain the envelope curve.

[0045] (2) Performing Fourier transform on the extracted envelope to obtain an envelope spectrum (in this embodiment, for the convenience of description, the envelope spectrum of the real-time vibration signal is recorded as the first envelope spectrum).

[0046] Figure 3 This is a schematic diagram of a first envelope spectrum of a real-time vibration signal shown in an exemplary embodiment of the present application. Figure 3 In the first envelope spectrum, the horizontal axis represents the frequency and the vertical axis represents the amplitude of each frequency. It should be noted that the first envelope spectrum is used to extract the modulation characteristics of the vibration signal. For example, it can reflect the low-frequency components of the real-time vibration signal. These low-frequency components include signals generated by the modulation phenomenon caused by the impact of the hydraulic piston pump and friction.

[0047] S102. Calculate the ratio of the amplitude of the frequency multiple of the fundamental frequency of the hydraulic piston pump on the first frequency spectrum to the average of the amplitude of the first designated frequency band on the first frequency spectrum to obtain the fundamental frequency characteristics of the real-time vibration signal; wherein the frequency multiple of the fundamental frequency includes at least the fundamental frequency; and the first designated frequency band includes the left neighbor of the frequency multiple of the fundamental frequency and the right neighbor of the frequency multiple of the fundamental frequency.

[0048] It should be noted that the fundamental frequency of the hydraulic piston pump refers to the lowest frequency component in the real-time vibration signal of the hydraulic piston pump, represents the basic period of the real-time vibration signal, and is related to the speed of the hydraulic piston pump. For example, when the speed of the hydraulic piston pump is v revolutions per minute, the fundamental frequency is f=v / 60 Hz.

[0049] Furthermore, the frequency multiple of the base frequency is a frequency obtained by extending the base frequency by an integer multiple. For example, if the base frequency is f, the frequency multiple of the base frequency may include 1 frequency multiple f, 2 frequency multiple 2f, and 3 frequency multiple 3f.

[0050] In this step, the ratio of the amplitude of the frequency multiple of the fundamental frequency of the hydraulic piston pump on the first spectrum to the average of the amplitude of the first specified frequency band on the first spectrum is calculated to obtain the fundamental frequency characteristics of the real-time vibration signal. The frequency multiple of the fundamental frequency includes at least 1 frequency multiple of the fundamental frequency, that is, the fundamental frequency itself.

[0051] Further, the first designated frequency band is a frequency range including a left neighbor of a multiple of the base frequency and a right neighbor of a multiple of the base frequency.

[0052] In this step, the amplitude of the frequency multiple of the fundamental frequency of the hydraulic piston pump on the first spectrum can be determined through the first spectrum. Furthermore, the sum of the amplitudes of each frequency component in the first specified frequency band on the first spectrum can be calculated, and then the average value can be calculated. Then, the amplitude of the frequency multiple of the fundamental frequency of the hydraulic piston pump on the first spectrum is ratioed with the average value to obtain the fundamental frequency characteristics of the real-time vibration signal.

[0053] In specific implementation, the fundamental frequency characteristics of the real-time vibration signal can be calculated according to the following first formula:

[0054] ;

[0055] Among them, the is the fundamental frequency feature;

[0056] Said is the amplitude of the multiple of the fundamental frequency in the frequency spectrum;

[0057] Said is the amplitude of frequency i in the spectrum;

[0058] The ) is the left neighbor of the multiple of the fundamental frequency;

[0059] The ) is the right neighbor of the multiple of the fundamental frequency;

[0060] Said The first specified value.

[0061] It should be noted that It is set according to actual needs and is not limited in this embodiment. For example, referring to the previous description, It can be half of the frequency value corresponding to the fundamental frequency.

[0062] It should be noted that the first formula is a general formula for calculating the fundamental frequency characteristics of a signal, and the first formula can be used to calculate the fundamental frequency characteristics of different signals. For example, for the fundamental frequency itself, the corresponding fundamental frequency characteristics can be calculated based on the above formula; for another example, for the 2 times frequency of the fundamental frequency, the corresponding fundamental frequency characteristics can be calculated based on the above formula.

[0063] It can be understood that the fundamental frequency characteristics can reflect the rotation speed and normal operating status of the plunger in the hydraulic plunger pump. According to the fundamental frequency characteristics, the phenomenon of unstable rotation speed and mechanical wear inside the hydraulic plunger pump can be diagnosed.

[0064] S103. Calculate the ratio of the amplitude of the multiple of the plunger passing frequency of the hydraulic plunger pump on the first spectrum to the average of the amplitude of the second designated frequency band on the first spectrum to obtain the plunger passing frequency characteristics of the real-time vibration signal; the multiple of the plunger passing frequency includes at least the plunger passing frequency; the second designated frequency band is the left neighborhood of the multiple of the plunger passing frequency and the right neighborhood of the multiple of the plunger passing frequency.

[0065] It should be noted that the plunger passing frequency of a hydraulic plunger pump is the frequency at which the plunger passes a specific point during movement, and this frequency is usually related to the structural parameters of the hydraulic plunger pump (the structural parameters of the hydraulic plunger pump include the number of plungers, rotational speed, etc.) and the number of working cycles. For example, when the number of plungers is greater, at the same rotational speed, the plunger passing frequency of the hydraulic plunger pump is higher; the higher the rotational speed, the more working cycles the plunger completes per unit time, and the plunger passing frequency of the hydraulic plunger pump is higher; further, the number of working cycles is the number of times the plunger passes a specific point per working circle, and when the number of plungers and the rotational speed remain unchanged, the more working cycles, the higher the plunger passing frequency.

[0066] In specific implementation, the plunger passing frequency can be calculated according to the following formula:

[0067] ;

[0068] in, is the plunger passing frequency, is the number of plungers, is the speed of the plunger, The number of working cycles completed by the plunger for each working circle.

[0069] Further, the frequency multiple of the plunger passing frequency is an integer multiple frequency of the plunger passing frequency, and at least includes the plunger passing frequency itself. For example, when the plunger passing frequency is F, the frequency multiple of the hydraulic plunger pump can be F, 2F, or 3F.

[0070] In this step, the ratio of the amplitude of the multiple of the plunger passing frequency of the hydraulic plunger pump on the first spectrum to the average of the amplitude of the second specified frequency band on the first spectrum is calculated to obtain the plunger passing frequency characteristics of the real-time vibration signal.

[0071] Specifically, the second designated frequency band is a frequency range surrounding the multiple of the plunger passing frequency, including the left neighborhood and the right neighborhood of the multiple of the plunger passing frequency, wherein the left neighborhood is a range smaller than the multiple of the plunger passing frequency, and the right neighborhood is a range greater than the multiple of the plunger passing frequency.

[0072] In specific implementation, the corresponding amplitude on the first spectrum can be determined based on the frequency multiples of the plunger passing frequency of the hydraulic plunger pump; then, based on the first spectrum, the average value of the amplitude of the second specified frequency band on the first spectrum can be determined, and then the ratio of the two can be calculated to obtain the plunger passing frequency characteristics of the real-time vibration signal.

[0073] Referring to the above description, in specific implementation, the plunger passing frequency characteristic can be calculated according to the following second formula:

[0074] ;

[0075] Among them, the is the frequency characteristic of the plunger passing;

[0076] Said is the amplitude of the frequency multiple of the plunger passing frequency on the frequency spectrum;

[0077] Said is the amplitude of frequency i in the spectrum;

[0078] The ) is the left neighbor of the multiple of the plunger passing frequency;

[0079] The ) is the right neighbor of the multiple of the plunger passing frequency;

[0080] Said The second specified value.

[0081] It should be noted that It is set according to actual needs and is not limited in this embodiment. For example, referring to the previous description, It can be half of the frequency value corresponding to the fundamental frequency.

[0082] It can be understood that the second formula is a general formula for calculating the plunger passing frequency characteristics of a signal, and the second formula can be used to calculate the passing frequency characteristics of the signal for different signals. For example, based on the above formula, the plunger passing frequency characteristics can be calculated based on the plunger passing frequency characteristics corresponding to the plunger passing frequency itself, or based on the double frequency of the plunger passing frequency.

[0083] It can be understood that the plunger passing frequency characteristics can reflect the periodic motion of the plunger in the hydraulic plunger pump, and the periodic motion of the plunger and whether a fault occurs can be diagnosed based on the plunger passing frequency characteristics.

[0084] S104. Determine, based on the first envelope spectrum, a frequency interval consisting of a first sideband after the fundamental frequency to a last sideband before the plunger passing frequency, and calculate a first average value of the amplitudes of all sidebands within the frequency interval and a second average value of the amplitudes of frequencies other than the sidebands within the frequency interval, and determine the sideband characteristics of the real-time vibration signal by the ratio of the first average value to the second average value.

[0085] Please note that, please refer to Figure 3When the plunger pump rotates abnormally (the rotation or vibration of the plunger pump is not stable), an additional frequency will be generated near the plunger passing frequency, and this additional frequency is the side frequency. Among them, the frequency of the side frequency is a multiple of the fundamental frequency. For example, if the fundamental frequency is f, the side frequency fs= n*f, where n is an integer.

[0086] In specific implementation, the sideband characteristics of the real-time vibration signal can be calculated according to the following third formula:

[0087] ;

[0088] in, is the side frequency feature, fre1 is the first frequency value corresponding to the first side frequency; fre2 is the second frequency value corresponding to the last side frequency; To sum the amplitudes of all frequencies between the first frequency value and the second frequency value on the envelope spectrum; is the amplitude of the side frequency on the envelope spectrum; is the amplitude of the first side frequency on the envelope spectrum; is the amplitude of the last sideband on the envelope spectrum; The amplitudes of all side frequencies between the first side frequency and the last side frequency are summed.

[0089] It should be noted that, refer to Figure 2 , the first side frequency after the fundamental frequency refers to the frequency after the fundamental frequency, and the first frequency value is equal to the integer multiple of the fundamental frequency (the frequency value corresponding to the first side frequency is greater than the fundamental frequency, and the frequency value is equal to the frequency corresponding to the integer multiple of the fundamental frequency for the first time, that is, after the fundamental frequency, before the first side frequency, there is no frequency equal to the integer multiple of the fundamental frequency). In addition, the frequency constituted by the last side frequency before the plunger passing frequency refers to the frequency after the fundamental frequency, before the plunger passing frequency, and the last frequency value is equal to the integer multiple of the fundamental frequency (the frequency value of the last side frequency is greater than the fundamental frequency, less than the plunger passing frequency, and the last time is equal to the integer multiple of the fundamental frequency, that is, after the last side frequency, before the plunger passing frequency, there is no frequency equal to the integer multiple of the fundamental frequency).

[0090] Furthermore, the frequencies other than the sidebands in the frequency interval refer to frequencies in the frequency interval whose frequency values ​​are not equal to integer multiples of the fundamental frequency.

[0091] It should be noted that the third formula is a general formula for calculating the sideband characteristics of a signal. For different signals, the third formula can be used to calculate the sideband characteristics of the signal.

[0092] It can be understood that the sideband characteristics can reflect the vibration characteristics caused by unevenness or faults inside the hydraulic piston pump, so that damage or wear of parts inside the hydraulic piston pump can be diagnosed.

[0093] S105. Determine the similarity between the first spectrum and a standard spectrum; wherein the standard spectrum is the spectrum of the vibration signal of the hydraulic piston pump in a normal state.

[0094] Figure 4 This is a schematic diagram of a standard spectrum shown in an exemplary embodiment of the present application. Figure 4 ,In the standard spectrum, the main frequency components include the fundamental frequency, the plunger passing frequency and its ,multiple frequency components, the amplitudes of other frequency components are low, and the high frequency band mainly appears as noise.

[0095] It should be noted that the first spectrum is the spectrum corresponding to the real-time vibration signal collected by the hydraulic piston pump in the actual operating state, and the standard spectrum is the spectrum corresponding to the vibration signal collected by the hydraulic piston pump signal in the normal state. In specific implementation, in one possible implementation, the similarity between the first spectrum and the standard spectrum can be directly calculated, and the matching degree between the hydraulic piston pump in the actual operating conditions and the normal state can be judged to monitor the abnormal situation of the hydraulic piston pump in the actual operating state.

[0096] Furthermore, the method for calculating the similarity between the first spectrum and the standard spectrum is set according to actual needs and is not limited in this embodiment.

[0097] S106. When at least one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is greater than a reference threshold value corresponding to the feature, and the similarity is less than a preset similarity threshold value, it is determined that the hydraulic plunger pump is in an abnormal state; wherein the reference threshold value corresponding to any one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is obtained based on statistics of multiple normal vibration signals of the hydraulic plunger pump in a normal state.

[0098] Specifically, the fundamental frequency characteristics, plunger passing characteristics and side frequency characteristics of multiple normal vibration signals of the hydraulic plunger pump in a normal state can be statistically analyzed in advance to obtain a first reference threshold corresponding to the fundamental frequency characteristic, a second reference threshold corresponding to the plunger passing frequency characteristic and a third reference threshold corresponding to the side frequency characteristic. The method for determining the reference threshold corresponding to any one of the fundamental frequency characteristic, the plunger passing frequency characteristic and the side frequency characteristic will be described in detail in the following embodiments and will not be described here.

[0099] It should be noted that the reference thresholds corresponding to 1 times the fundamental frequency and 2 times the fundamental frequency are different and are determined based on the corresponding times; similarly, the reference thresholds corresponding to 1 times the plunger passing frequency and 2 times the plunger passing frequency are also different and are determined based on the corresponding times.

[0100] After extracting the fundamental frequency characteristics, plunger passing characteristics and sideband characteristics of the real-time vibration signal of the plunger pump in the actual operating state, in this step, they are compared with the corresponding reference thresholds.

[0101] Further, it is determined whether the similarity between the first spectrum and the standard spectrum is less than a preset similarity threshold. It should be noted that the preset similarity threshold is set according to actual needs and is not limited in this embodiment.

[0102] Furthermore, whether the hydraulic piston pump is in an abnormal state at this time is determined based on whether the fundamental frequency characteristics, plunger passing frequency characteristics and side frequency characteristics of the real-time vibration signal are greater than the corresponding reference thresholds, and whether the similarity between the first spectrum and the standard spectrum is less than the preset similarity threshold. For example, when the fundamental frequency characteristics, plunger passing frequency characteristics and side frequency characteristics of the real-time vibration signal are all greater than the corresponding reference thresholds, and the similarity between the first spectrum and the standard spectrum is less than the preset similarity threshold, at this time, it can be determined that the hydraulic piston pump is in an abnormal state at this time.

[0103] Referring to the previous description, it can be understood that the fundamental frequency characteristic, the plunger passing frequency characteristic, and the sideband characteristic are essentially a ratio, which is a dimensionless quantity. In this way, the influence caused by differences in equipment characteristics can be avoided, so that the method provided in this embodiment can be applicable to different hydraulic plunger pumps, thereby improving applicability.

[0104] The method for detecting the abnormal state of a hydraulic plunger pump provided in the present embodiment, on the one hand, by comparing the fundamental frequency feature, the plunger passing frequency feature and the sideband feature with the corresponding reference threshold, and comparing the similarity between the first spectrum and the standard spectrum with the preset similarity threshold, the detection result based on the threshold comparison and the detection result based on the similarity comparison can be obtained simultaneously, and then when the detection result based on the threshold comparison is abnormal and the detection result based on the similarity comparison is abnormal, the hydraulic plunger pump is determined to be abnormal, so that the accuracy and robustness of the detection can be improved by combining the threshold comparison and the similarity comparison for abnormality detection; on the other hand, when comparing based on the threshold, the fundamental frequency feature, the plunger passing frequency feature and the sideband feature are comprehensively considered, so that the change of the state can be fully captured, the limitation of a single feature can be avoided, and the accuracy can be further improved; on the third hand, when determining the fundamental frequency feature, the plunger passing frequency feature and the sideband feature, they are dimensionless, so that the influence caused by equipment differences can be avoided, the versatility and applicability of the method can be improved, and the method can be effectively applied to different equipment or working conditions.

[0105] Figure 5 This is a flow chart of Embodiment 2 of the method for detecting abnormal state of a hydraulic piston pump provided in this application. Figure 5 The method for determining the reference threshold corresponding to any one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature provided in this embodiment may include:

[0106] S501. Acquire a plurality of normal vibration signals of the hydraulic piston pump in a normal state, and for each normal vibration signal, acquire a second frequency spectrum and a second envelope spectrum of the normal vibration signal.

[0107] It should be noted that multiple normal vibration signals of the hydraulic piston pump in a normal state can be obtained in a variety of ways, which are not limited in this application. For example, in one embodiment, a vibration sensor can be installed on the hydraulic piston pump in a normal working state through a field monitoring method, and multiple normal vibration signals can be obtained through the vibration sensor; for another example, in another embodiment, the normal working state of the hydraulic piston pump can be simulated in a laboratory environment to obtain multiple normal vibration signals.

[0108] Furthermore, after obtaining multiple normal vibration signals, for each normal vibration signal, the frequency spectrum and envelope spectrum of the normal vibration signal are obtained. For the convenience of explanation, the frequency spectrum and envelope spectrum of the normal vibration signal are respectively recorded as the second frequency spectrum and the second envelope spectrum.

[0109] It should be noted that the specific implementation method and implementation principle for obtaining the second spectrum and the second envelope spectrum can be found in the description in the previous implementation, and will not be repeated here.

[0110] S502: Determine fundamental frequency characteristics and plunger passing frequency characteristics of the normal vibration signal according to the second frequency spectrum, and determine sideband characteristics of the normal vibration signal according to the second envelope spectrum.

[0111] Referring to the above description, based on the second frequency spectrum, the fundamental frequency characteristics of the normal vibration signal can be determined using the first formula, and the plunger passing frequency characteristics can be determined using the second formula.

[0112] Furthermore, according to the second envelope spectrum, the sideband characteristics of the normal vibration signal can be determined using the third formula.

[0113] The specific implementation principles and implementation processes of the first formula, the second formula and the third formula can be found in the description in the previous embodiments, and will not be repeated here.

[0114] S503: Count the maximum value among the multiple fundamental frequency features of the multiple normal vibration signals, and determine a reference threshold corresponding to the fundamental frequency feature according to the maximum value.

[0115] S504: Count the maximum values ​​of the multiple plunger passing frequency characteristics of the multiple normal vibration signals, and determine a reference threshold value corresponding to the plunger passing frequency characteristic according to the maximum value.

[0116] S505: Count the maximum values ​​of the multiple sideband features of the multiple normal vibration signals, and determine a reference threshold corresponding to the sideband feature according to the maximum value.

[0117] Specifically, in steps S503 to S505, based on multiple fundamental frequency features, multiple plunger passing frequency features and multiple sideband features, the maximum values ​​of multiple fundamental frequency features, the maximum values ​​of multiple plunger passing frequency features and the maximum value of multiple sideband features can be counted respectively, and a reference threshold corresponding to the fundamental frequency feature can be determined based on the maximum value of the multiple fundamental frequency features, a reference threshold corresponding to the plunger passing frequency feature can be determined based on the maximum value of the multiple plunger passing frequency features, and a reference threshold corresponding to the sideband feature can be determined based on the maximum value of the multiple sideband features.

[0118] Optionally, in a possible implementation, the maximum value of multiple fundamental frequency characteristics can be recorded as max1, the maximum value of multiple plunger passing frequency characteristics can be recorded as max2, and the maximum value of multiple side frequency characteristics can be set as max3. For example, in a possible implementation, max1 can be used as the reference threshold of the fundamental frequency characteristic, max2 can be used as the reference threshold of the plunger passing frequency characteristic, and max3 can be used as the reference threshold of multiple side frequency characteristics; for another example, in another possible implementation, max1, max2 and max3 can be multiplied by w1, w2 and w3 respectively, and then w1*max1 can be used as the reference threshold of the fundamental frequency characteristic, w2*max2 can be used as the reference threshold of the plunger passing frequency characteristic, and w3*max3 can be used as the reference threshold of multiple side frequency characteristics. It should be noted that w1, w2 and w3 are safety factors greater than 1, and the specific values ​​can be set according to actual needs. In this application, they are not limited.

[0119] It should be noted that, referring to the previous description, when the fundamental frequency characteristics include characteristics corresponding to 1 times the fundamental frequency, the corresponding benchmark threshold can be determined based on the above method; when the fundamental frequency characteristics also include characteristics corresponding to M (M is an integer greater than 1) times the fundamental frequency, the corresponding benchmark threshold can be further determined based on the above method.

[0120] Similarly, when the frequency characteristics of the plunger passing include characteristics corresponding to 1 times the fundamental frequency, the corresponding reference threshold can be determined based on the above method. When the frequency characteristics of the plunger passing also include characteristics corresponding to K times (K is an integer greater than 1) the frequency of the plunger passing, the corresponding reference threshold can be further determined based on the above method.

[0121] The method for detecting an abnormal state of a hydraulic piston pump provided in the present embodiment acquires a second frequency spectrum and a second envelope spectrum of the plurality of normal vibration signals by collecting a plurality of normal vibration signals, and determines the fundamental frequency characteristic and the plunger passing frequency characteristic of the normal vibration signal according to the second frequency spectrum, and determines the sideband characteristic of the normal vibration signal according to the second envelope spectrum, and then determines a reference threshold corresponding to the fundamental frequency characteristic according to the maximum value of the plurality of fundamental frequency characteristics, determines a reference threshold corresponding to the plunger passing frequency characteristic according to the maximum value of the plurality of plunger passing frequency characteristics, and determines a reference threshold corresponding to the sideband characteristic according to the maximum value of the plurality of sideband characteristics. In this way, a reference threshold that can accurately describe the normal working range of the hydraulic piston pump can be acquired, and then subsequent abnormal state detection can be performed based on the reference threshold, thereby enhancing the reliability of subsequent abnormal state detection.

[0122] Figure 6 This is a flow chart of Embodiment 3 of the method for detecting abnormal state of a hydraulic piston pump provided in this application. Figure 6The method provided in this embodiment, based on the above embodiment, the determining of the similarity between the first spectrum and the standard spectrum may include:

[0123] S601: Divide the first spectrum into multiple sub-spectrum segments according to a preset division rule.

[0124] Specifically, during the operation of the hydraulic plunger pump, the plunger passing frequency and its frequency harmonic components will be generated. The amplitudes of these frequency components will affect the shape of the first spectrum. Therefore, in the present application, the first spectrum is divided into multiple sub-spectrum segments to more accurately characterize the true characteristics of the first spectrum.

[0125] It should be noted that the preset division rules are based on actual needs and are not limited in the present application. For example, in one embodiment, the first spectrum can be divided based on the preset interval length, that is, the width of each sub-spectrum segment obtained after the division is the above-mentioned preset interval length; for another example, in another embodiment, the plunger passing frequency and its multiples can be used as the center of each sub-spectrum segment, and half of the plunger passing frequency can be used as the left neighboring interval and the right neighboring interval of the sub-spectrum segment. It should be noted that in this division method, the leftmost and rightmost sides of the first spectrum are respectively used as a sub-spectrum segment.

[0126] S602 : For each sub-spectral segment, extract multiple types of shape feature vectors of the sub-spectral segment, and merge all shape feature vectors of all sub-spectral segments to obtain a comprehensive shape feature vector of the first spectrum.

[0127] It should be noted that the multi-class shape feature vectors of each sub-spectral segment may include amplitude features, frequency features, and distribution features, etc.; among which, the amplitude features include the peak value, average amplitude, and amplitude volatility of each sub-spectral segment; the frequency features include the frequency center, frequency offset, and frequency distribution of each sub-spectral segment; and the distribution features may include the distribution of frequency components within each sub-spectral segment.

[0128] In a specific implementation, for example, in a possible implementation, dimensional quantities such as skewness, kurtosis, waveform index, peak index, etc. can be extracted as shape feature vectors.

[0129] Furthermore, after extracting multiple types of shape feature vectors from each sub-spectrum segment, all shape feature vectors from all sub-spectrum segments can be combined to obtain a comprehensive feature vector of the first spectrum, which can fully describe the overall characteristics of the first spectrum.

[0130] It should be noted that different merging methods can be selected according to actual needs to merge all shape feature vectors, and this application does not limit them. For example, in one embodiment, all shape feature vectors can be directly spliced ​​to obtain a comprehensive shape feature vector; in another embodiment, all shape feature vectors can be weighted merged to obtain a comprehensive shape feature vector.

[0131] S603, calculating the similarity between the comprehensive shape feature vector and the standard shape feature vector, and determining the similarity as the similarity between the first spectrum and the standard spectrum; wherein the standard shape feature vector is obtained based on the spectrum analysis of multiple normal vibration signals of the hydraulic piston pump in a normal state.

[0132] It should be noted that by analyzing the frequency spectra of multiple normal vibration signals of the hydraulic piston pump in a normal state, a standard shape feature vector can be obtained. In this step, the similarity between the comprehensive shape feature vector and the standard shape feature vector can be calculated, and the obtained similarity is determined as the similarity between the first spectrum and the standard spectrum.

[0133] It should be noted that the method for calculating the similarity between the comprehensive shape feature vector and the standard shape feature vector can be selected according to actual needs, and is not limited in this application.

[0134] In a possible implementation, the similarity between two vectors may be calculated using the Kendall coefficient. The larger the calculation result, the higher the similarity, and the smaller the calculation result, the lower the similarity.

[0135] Furthermore, in a possible implementation, the method of acquiring the standard shape feature vector includes:

[0136] Step 1: Acquire a plurality of normal vibration signals of the hydraulic piston pump in a normal state, and acquire a third frequency spectrum of each normal vibration signal.

[0137] The specific implementation method and implementation principle of this step can be found in the description of the previous embodiment and will not be repeated here.

[0138] It should be noted that the multiple normal vibration signals obtained in this step may be the same as or different from the multiple normal vibration signals obtained in step S501, and this is not limited in the present application.

[0139] Step 2: For each third spectrum, obtain a comprehensive shape feature vector of the third spectrum.

[0140] Referring to the previous description, in this step, for each third spectrum, the third spectrum can be divided into multiple sub-spectrum segments according to a preset division rule. Furthermore, for each sub-spectrum segment, multiple types of shape feature vectors of the sub-spectrum segment are extracted, and all shape feature vectors of all sub-spectrum segments are merged to obtain a comprehensive shape feature vector of the third spectrum.

[0141] For the division method, extraction method, and merging method, please refer to the description in steps S601 and S602, which will not be repeated here.

[0142] Step 3: Set the number of clusters to 1, and use the clustering method to cluster the comprehensive shape feature vectors of all third spectra to obtain clustering results.

[0143] Step 4: Determine the center of the clustering result as the standard shape feature vector.

[0144] Specifically, combining step 3 and step 4, assuming that step 1 obtains n1 normal vibration signals, and then step 2 obtains n1 comprehensive shape feature vectors corresponding to these n1 normal vibration signals, in step 3, the number of clusters is set to 1, and these n1 comprehensive shape feature vectors are clustered by clustering method to obtain clustering results. Furthermore, in step 4, the cluster center can be obtained from the clustering result and used as the standard shape feature vector.

[0145] In specific implementation, in step 3, the kmeans clustering method can be used for clustering.

[0146] Referring to the previous description, it can be seen that when determining the standard shape feature vector, multiple normal vibration signals of the hydraulic piston pump in a normal state are obtained, and for each normal vibration signal, the third spectrum of the normal vibration signal is obtained, and for each third spectrum, the comprehensive shape feature vector of the third spectrum is obtained, and then the number of clusters is set to 1, and the comprehensive shape feature vectors of all third spectra are clustered using a clustering method to obtain clustering results, and finally the center of the clustering results is determined as the standard shape feature vector, so that the normal working state characteristics of the hydraulic piston pump can be accurately and stably obtained and described, which is helpful for subsequent fault detection. In addition, only selecting the cluster center as the basis for subsequent identification and comparison can reduce the amount of calculation for subsequent identification.

[0147] The method provided in this embodiment predetermines the standard shape feature vector, and then directly extracts the comprehensive shape feature vector when calculating the similarity between the first spectrum and the standard spectrum, and then calculates the similarity based on the feature vector, which can reduce the amount of calculation, shorten the state recognition time, and improve the state recognition effect.

[0148] Optionally, in a possible implementation, the method further includes:

[0149] In response to the feedback result fed back by the user, the preset similarity threshold is updated according to the feedback result; wherein the feedback result is used to characterize whether the state detection is accurate and the deviation of the state detection.

[0150] Specifically, when obtaining the status detection result, the user can check the status detection result and then make feedback to determine whether the status detection result is accurate, and when the detection result is inaccurate, feedback the specific deviation situation, wherein the deviation situation is used to characterize the specific type of error, for example, whether the normal status detection is mistakenly identified as an abnormal state, or the abnormal state is mistakenly identified as a normal state.

[0151] Furthermore, in this embodiment, in response to the user's feedback result, the preset similarity threshold is updated according to the feedback result. For example, if the user's feedback result is that the state detection result is consistent with the actual situation, the similarity threshold is not updated; if the user's feedback result is that the state detection is inconsistent with the actual situation, a preset step length is set, and the preset similarity threshold is updated using the preset step length. Further, when the preset similarity threshold is updated, when the state detection result is an abnormal state, but the actual situation is a normal state, that is, the deviation situation is that the normal state detection is mistakenly identified as an abnormal state, then the difference between the current value and the preset step length is determined as the updated value; when the state detection result is a normal state, but the actual situation is an abnormal state, that is, the deviation situation is that the abnormal state is mistakenly identified as a normal state, then the sum of the current value and the preset step length is determined as the updated value.

[0152] The method provided in this embodiment responds to the feedback results of user feedback by updating the preset similarity threshold according to the feedback results. In this way, the preset similarity threshold can be updated in real time based on user feedback. Through this update, it can better adapt to different usage environments and needs, thereby improving its reliability and adaptability, and ultimately bringing more accurate status detection results and less deviations, ensuring the accuracy and effectiveness of detection.

[0153] Corresponding to the aforementioned embodiment of a method for detecting an abnormal state of a hydraulic plunger pump, the present application also provides an embodiment of a device for detecting an abnormal state of a hydraulic plunger pump.

[0154] The embodiment of the hydraulic plunger pump abnormal state detection device of the present application can be applied to the hydraulic plunger pump abnormal state detection device. The device embodiment can be implemented by software, or by hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by the processor of the hydraulic plunger pump abnormal state detection device in which it is located reading the corresponding computer program instructions in the non-volatile memory into the memory and running them. From the hardware level, if Figure 7 As shown, it is a hardware structure diagram of the hydraulic plunger pump abnormal state detection device in which the hydraulic plunger pump abnormal state detection device of the present application is located, except Figure 7 In addition to the processor, memory, network interface, and non-volatile memory shown, the hydraulic plunger pump abnormal state detection device in the embodiment where the device is located may also include other hardware based on the actual function of the hydraulic plunger pump abnormal state detection device, which will not be described in detail.

[0155] Figure 8 This is a structural diagram of the first embodiment of the abnormal state detection device for the hydraulic piston pump provided in this application. Figure 8 The device provided in this embodiment includes a processing module 810, a calculation module 820 and a judgment module 830; wherein:

[0156] The processing module 810 is used to obtain a real-time vibration signal of the hydraulic piston pump to be tested, and determine a first frequency spectrum and a first envelope spectrum of the real-time vibration signal;

[0157] The calculation module 820 is used to calculate the ratio of the amplitude of the frequency multiple of the fundamental frequency of the hydraulic piston pump on the first spectrum to the average value of the amplitude of the first designated frequency band on the first spectrum, so as to obtain the fundamental frequency characteristics of the real-time vibration signal; wherein the frequency multiple of the fundamental frequency at least includes the fundamental frequency; the first designated frequency band includes the left neighbor of the frequency multiple of the fundamental frequency and the right neighbor of the frequency multiple of the fundamental frequency;

[0158] The calculation module 820 is used to calculate the ratio of the amplitude of the multiple of the plunger passing frequency of the hydraulic plunger pump on the first spectrum to the average of the amplitude of the second specified frequency band on the first spectrum, so as to obtain the plunger passing frequency characteristics of the real-time vibration signal; the multiple of the plunger passing frequency at least includes the plunger passing frequency; the second specified frequency band is the left neighbor of the multiple of the plunger passing frequency and the right neighbor of the multiple of the plunger passing frequency;

[0159] The calculation module 820 is used to determine the frequency interval consisting of the first side frequency after the fundamental frequency and the last side frequency before the plunger passing frequency according to the first envelope spectrum, and calculate the first average value of the amplitudes of all side frequencies in the frequency interval and the second average value of the amplitudes of other frequencies except the side frequencies in the frequency interval, and determine the side frequency characteristics of the real-time vibration signal by the ratio of the first average value to the second average value;

[0160] The processing module 810 is used to determine the similarity between the first spectrum and a standard spectrum; wherein the standard spectrum is the spectrum of the vibration signal of the hydraulic piston pump in a normal state;

[0161] The judgment module 830 is used to determine that the hydraulic piston pump is in an abnormal state when at least one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is greater than a reference threshold corresponding to the feature, and the similarity is less than a preset similarity threshold; wherein the reference threshold corresponding to any one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is obtained based on statistics of multiple normal vibration signals of the hydraulic piston pump in a normal state.

[0162] The device of this embodiment can be used to perform Figure 1 The steps, specific implementation principles and implementation processes of the method embodiment shown are similar and will not be repeated here.

[0163] Please continue to refer to 7. The present application also provides a hydraulic plunger pump abnormal state detection device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of any one of the methods provided in the first aspect of the present application are implemented.

[0164] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of any one of the methods provided in the present application are implemented.

[0165] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0166] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0167] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for detecting abnormal state of a hydraulic piston pump, characterized in that: The method comprises: Acquire a real-time vibration signal of the hydraulic piston pump to be tested, and determine a first frequency spectrum and a first envelope spectrum of the real-time vibration signal; Calculate the ratio of the amplitude of the frequency multiple of the fundamental frequency of the hydraulic piston pump on the first frequency spectrum to the average value of the amplitude of the first designated frequency band on the first frequency spectrum to obtain the fundamental frequency characteristics of the real-time vibration signal; wherein the frequency multiple of the fundamental frequency at least includes the fundamental frequency; the first designated frequency band includes the left neighbor of the frequency multiple of the fundamental frequency and the right neighbor of the frequency multiple of the fundamental frequency; Calculate the ratio of the amplitude of the multiple of the plunger passing frequency of the hydraulic plunger pump on the first spectrum to the average of the amplitude of the second designated frequency band on the first spectrum to obtain the plunger passing frequency characteristics of the real-time vibration signal; the multiple of the plunger passing frequency at least includes the plunger passing frequency; the second designated frequency band is the left neighbor of the multiple of the plunger passing frequency and the right neighbor of the multiple of the plunger passing frequency; Determine, according to the first envelope spectrum, a frequency interval consisting of a first side frequency after the fundamental frequency and a last side frequency before the plunger passing frequency, and calculate a first average value of the amplitudes of all side frequencies in the frequency interval and a second average value of the amplitudes of other frequencies except the side frequencies in the frequency interval, and determine the side frequency characteristics of the real-time vibration signal by the ratio of the first average value to the second average value; Determine the similarity between the first spectrum and a standard spectrum; wherein the standard spectrum is the spectrum of the vibration signal of the hydraulic piston pump in a normal state; When at least one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is greater than the reference threshold value corresponding to the feature, and the similarity is less than the preset similarity threshold value, it is determined that the hydraulic plunger pump is in an abnormal state; wherein the reference threshold value corresponding to any one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is obtained based on statistics of multiple normal vibration signals of the hydraulic plunger pump in a normal state.

2. The method according to claim 1, characterized in that: The method for determining the reference threshold corresponding to any one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature comprises: Acquire a plurality of normal vibration signals of the hydraulic piston pump in a normal state, and for each normal vibration signal, acquire a second frequency spectrum and a second envelope spectrum of the normal vibration signal; Determine the fundamental frequency characteristics and plunger passing frequency characteristics of the normal vibration signal according to the second frequency spectrum, and determine the sideband characteristics of the normal vibration signal according to the second envelope spectrum; Counting the maximum value among the multiple fundamental frequency features of the multiple normal vibration signals, and determining the reference threshold corresponding to the fundamental frequency feature according to the maximum value; Counting the maximum value of the multiple plunger passing frequency characteristics of the multiple normal vibration signals, and determining the reference threshold value corresponding to the plunger passing frequency characteristic according to the maximum value; The maximum value among the multiple sideband features of the multiple normal vibration signals is counted, and the reference threshold corresponding to the sideband feature is determined according to the maximum value.

3. The method according to claim 1, characterized in that The determining the similarity between the first spectrum and the standard spectrum includes: Dividing the first spectrum into a plurality of sub-spectrum segments according to a preset division rule; For each sub-spectrum segment, extract multiple types of shape feature vectors of the sub-spectrum segment, and combine all shape feature vectors of all sub-spectrum segments to obtain a comprehensive shape feature vector of the first spectrum; The similarity between the comprehensive shape feature vector and the standard shape feature vector is calculated, and the similarity is determined as the similarity between the first spectrum and the standard spectrum; wherein the standard shape feature vector is obtained based on the spectrum analysis of multiple normal vibration signals of the hydraulic piston pump in a normal state.

4. The method according to claim 3, characterized in that: The method for obtaining the standard shape feature vector includes: Acquire a plurality of normal vibration signals of the hydraulic piston pump in a normal state, and acquire a third frequency spectrum of each normal vibration signal; For each third spectrum, obtaining a comprehensive shape feature vector of the third spectrum; The number of clusters is set to 1, and the comprehensive shape feature vectors of all third spectra are clustered using a clustering method to obtain a clustering result; The center of the clustering result is determined as the standard shape feature vector.

5. The method according to claim 1 or 2, characterized in that: The method for calculating the fundamental frequency characteristics of the real-time vibration signal or the fundamental frequency characteristics of the normal vibration signal includes: The fundamental frequency characteristics are calculated according to the first formula below: ； Among them, the is the fundamental frequency feature; Said is the amplitude of the multiple of the fundamental frequency in the frequency spectrum; Said is the amplitude of frequency i in the spectrum; The ) is the left neighbor of the multiple of the fundamental frequency; The ) is the right neighbor of the multiple of the fundamental frequency; Said The first specified value.

6. The method according to claim 1 or 2, characterized in that: The method for calculating the plunger passing frequency characteristics of the real-time vibration signal or the plunger passing frequency characteristics of the normal vibration signal includes: The plunger passing frequency characteristic is calculated according to the second formula below: ； Among them, the is the frequency characteristic of the plunger passing; Said is the amplitude of the frequency multiple of the plunger passing frequency on the frequency spectrum; Said is the amplitude of frequency i in the spectrum; The ) is the left neighbor of the multiple of the plunger passing frequency; The ) is the right neighbor of the multiple of the plunger passing frequency; Said The second specified value.

7. The method according to claim 1 or 2, characterized in that: The method for calculating the sideband characteristics of the real-time vibration signal or the sideband characteristics of the normal vibration signal comprises: The sideband characteristics are calculated according to the third formula below: ； in, is the side frequency feature, fre1 is the first frequency value corresponding to the first side frequency; fre2 is the second frequency value corresponding to the last side frequency; To sum the amplitudes of all frequencies between the first frequency value and the second frequency value on the envelope spectrum; is the amplitude of the side frequency on the envelope spectrum, is the amplitude of the first sideband on the envelope spectrum, is the amplitude of the last sideband on the envelope spectrum, The amplitudes of all side frequencies between the first side frequency and the last side frequency are summed.

8. The method according to claim 1, characterized in that The method further comprises: In response to the feedback result fed back by the user, the preset similarity threshold is updated according to the feedback result; wherein the feedback result is used to characterize whether the state detection is accurate and the deviation of the state detection.

9. A hydraulic piston pump abnormal state detection device, characterized in that: The device comprises a processing module, a calculation module and a judgment module; wherein: The processing module is used to obtain a real-time vibration signal of the hydraulic piston pump to be tested, and determine a first frequency spectrum and a first envelope spectrum of the real-time vibration signal; The calculation module is used to calculate the ratio of the amplitude of the frequency multiple of the fundamental frequency of the hydraulic piston pump on the first frequency spectrum to the average value of the amplitude of the first designated frequency band on the first frequency spectrum, so as to obtain the fundamental frequency characteristics of the real-time vibration signal; wherein the frequency multiple of the fundamental frequency at least includes the fundamental frequency; the first designated frequency band includes the left neighbor of the frequency multiple of the fundamental frequency and the right neighbor of the frequency multiple of the fundamental frequency; The calculation module is used to calculate the ratio of the amplitude of the multiple of the plunger passing frequency of the hydraulic plunger pump on the first spectrum to the average of the amplitude of the second specified frequency band on the first spectrum, so as to obtain the plunger passing frequency characteristics of the real-time vibration signal; the multiple of the plunger passing frequency at least includes the plunger passing frequency; the second specified frequency band is the left neighbor of the multiple of the plunger passing frequency and the right neighbor of the multiple of the plunger passing frequency; The calculation module is used to determine the frequency interval consisting of the first side frequency after the fundamental frequency and the last side frequency before the plunger passing frequency according to the first envelope spectrum, and calculate the first average value of the amplitudes of all side frequencies in the frequency interval and the second average value of the amplitudes of other frequencies except the side frequencies in the frequency interval, and determine the side frequency characteristics of the real-time vibration signal by the ratio of the first average value to the second average value; The processing module is used to determine the similarity between the first spectrum and a standard spectrum; wherein the standard spectrum is the spectrum of the vibration signal of the hydraulic piston pump in a normal state; The judgment module is used to determine that the hydraulic plunger pump is in an abnormal state when at least one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is greater than a reference threshold corresponding to the feature and the similarity is less than a preset similarity threshold; wherein the reference threshold corresponding to any one of the fundamental frequency feature, the plunger passing frequency feature and the sideband feature is obtained based on statistics of multiple normal vibration signals of the hydraulic plunger pump in a normal state.

10. A hydraulic piston pump abnormal state detection device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 8 when executing the program.

Images