Pumping unit fault diagnosis method and device, electronic equipment and computer readable medium

Abstract

The application relates to an oil pumping unit fault diagnosis method and device, electronic equipment and a computer readable medium. The method comprises the following steps: performing W transformation on an original signal from an oil pumping unit to generate a transformation result; calculating a multiple group time delay at each time-frequency position in a time-frequency domain of the original signal based on the transformation result; generating a time-frequency coefficient based on a time rearrangement synchronous extrusion algorithm and the multiple group time delay; generating a time rearrangement multiple synchronous extrusion W transformation spectrum based on the time-frequency coefficient; determining a target pulse based on a time-frequency envelope of the time rearrangement multiple synchronous extrusion W transformation spectrum; and determining a fault of the oil pumping unit based on a time feature of the target pulse. The oil pumping unit fault diagnosis method, device, electronic equipment and computer readable medium can highlight the real instantaneous frequency of a fault signal, are more accurate, improve the time and frequency resolution of the fault signal, and improve the accuracy of fault positioning.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of pumping unit fault diagnosis, in particular, to a pumping unit fault diagnosis method and device, an electronic device and a computer readable medium. BACKGROUND

[0002] Drilling operations use high-power mechanical equipment, and need to operate continuously day and night, and the noise disturbance to the public is more serious. Once the noise pollution is forced to be rectified and controlled, it will seriously affect the normal production work of the oil field. Therefore, it is imminent to effectively, quickly and accurately extract and automatically identify the noise characteristics of drilling operations, which has great research significance for ensuring oil field production. The noise source in the drilling process mainly comes from the continuous mechanical noise generated by large rotating machines such as pumping units. The most critical mechanical component in the pumping unit is the bearing, and the noise generated by bearing defects is the main source of pumping unit noise pollution. Bearing defects will produce periodic pulses, and such pulses can be captured by condition monitoring (CM) sensors installed on the machine. However, due to the small amplitude of the defect signal and the interference of environmental noise, it is often difficult to find the weak pulse component produced by early bearing defects. In addition, when there are multiple fault components in the signal or the signal is collected under non-stationary conditions, it is more difficult to identify.

[0003] In the prior art, the synchronous compressive transform (SST) technology and its improved versions, such as the SST based on wavelet transform (CWT), the SST based on STFT and the high-order SST, have been widely used in signal analysis in recent years due to their ability to produce high-energy concentrated TFRs for non-stationary signals. However, most SST techniques implicitly assume that the analyzed signal exhibits slow time-varying characteristics, while the pulse-like signals generated by bearing defects can occur in a very short time and can have a very wide frequency band. When the pulse-like signal occurs rapidly in a short time, the SST method cannot produce satisfactory TFRs. In view of the problem that SST cannot well process pulse-like signals, He (2019) proposed a time rearranged synchronous squeezing transform (TSST), which "squeezes" the time-frequency spectrum energy in the time direction and redistributes it around the true group delay (GD), so it has the ability to process strong time-varying signals. TSST can obtain relatively concentrated time-frequency representation results as a post-processing method, but the time-frequency analysis results of this method are largely dependent on the quality of the original time-frequency representation obtained by conventional methods, and the effect of further analysis on actual non-stationary signals is not ideal.

[0004] Therefore, there is a need for a new pumping unit fault diagnosis method, device, electronic device and computer readable medium.

[0005] The above information disclosed in this Background section is only for enhancing the understanding of the background of the present application, therefore, it can include information that does not constitute prior art that is already known to those of ordinary skill in the art. SUMMARY

[0006] Therefore, the present application provides an oil pumping unit fault diagnosis method and device, electronic equipment and computer readable medium, which can highlight the real instantaneous frequency of the fault signal, and is more accurate, improves the time and frequency resolution of the fault signal, and improves the accuracy of fault positioning.

[0007] Other characteristics and advantages of the present application will become apparent from the following detailed description, or will be learned by practice of the present application.

[0008] According to an aspect of the present application, an oil pumping unit fault diagnosis method is provided, which comprises: performing W transform on an original signal from an oil pumping unit to generate a transform result; calculating a multiple group time delay at each time-frequency position in a time-frequency domain of the original signal based on the transform result; generating a time-frequency coefficient based on a time rearrangement synchronous squeezing algorithm and the multiple group time delay; generating a time rearrangement multiple synchronous squeezing W transform spectrum based on the time-frequency coefficient; determining a target pulse based on a time-frequency envelope of the time rearrangement multiple synchronous squeezing W transform spectrum; and determining a fault of the oil pumping unit based on a time characteristic of the target pulse.

[0009] In an exemplary embodiment of the present application, performing W transform on an original signal from an oil pumping unit to generate a transform result comprises: acquiring an original signal of an oil pumping unit bearing based on a state monitoring sensor; performing W transform on the original signal to generate a W transform value; and obtaining the transform result by taking the modulus of the W transform value.

[0010] In an exemplary embodiment of the present application, calculating a multiple group time delay at each time-frequency position in a time-frequency domain of the original signal based on the transform result comprises: calculating a group time delay of the original signal at each time-frequency position based on the transform result; and calculating the multiple group time delay at each time-frequency position based on the group time delay at each time-frequency position.

[0011] In an exemplary embodiment of the present application, calculating a group time delay of the original signal at each time-frequency position based on the transform result comprises: calculating the group time delay of the original signal at each time-frequency position based on phase information in the transform result.

[0012] In an exemplary embodiment of the present application, calculating the multiple group time delay at each time-frequency position based on the group time delay at each time-frequency position comprises: iteratively calculating the group time delay at each time-frequency position to generate the multiple group time delay at each time-frequency position.

[0013] In an example embodiment of the present application, generating time-frequency coefficients based on the time rearrangement synchrosqueezing algorithm and the multiple group delays comprises: generating a time rearrangement synchrosqueezing operator based on the time rearrangement synchrosqueezing algorithm and the multiple group delays; and generating the time-frequency coefficients based on the time rearrangement synchrosqueezing operator.

[0014] In an example embodiment of the present application, generating a time rearrangement multiple synchrosqueezing W transform spectrum based on the time-frequency coefficients comprises: performing a modulo calculation on the time-frequency coefficients to generate the time rearrangement multiple synchrosqueezing W transform spectrum.

[0015] In an example embodiment of the present application, determining a target pulse based on a time-frequency envelope of the time rearrangement multiple synchrosqueezing W transform spectrum comprises: calculating the time-frequency envelope of the time rearrangement multiple synchrosqueezing W transform spectrum; taking a frequency corresponding to a maximum amplitude in the time-frequency envelope as a target frequency; and obtaining a target pulse corresponding to the target frequency.

[0016] In an example embodiment of the present application, determining a fault of the pumping unit based on a time characteristic of the target pulse comprises: matching the time characteristic of the target pulse with a plurality of preset time characteristics; and determining the fault of the pumping unit according to a matching result.

[0017] According to an aspect of the present application, a pumping unit fault diagnosis apparatus is provided, which comprises: a transform module configured to perform W transform on an original signal from a pumping unit to generate a transform result; a delay module configured to calculate multiple group delays at each time-frequency position in a time-frequency domain of the original signal based on the transform result; a coefficient module configured to generate time-frequency coefficients based on a time rearrangement synchrosqueezing algorithm and the multiple group delays; a transform spectrum module configured to generate a time rearrangement multiple synchrosqueezing W transform spectrum based on the time-frequency coefficients; a pulse module configured to determine a target pulse based on a time-frequency envelope of the time rearrangement multiple synchrosqueezing W transform spectrum; and a fault module configured to determine a fault of the pumping unit based on a time characteristic of the target pulse.

[0018] According to an aspect of the present application, an electronic device is provided, which comprises: one or more processors; a storage device configured to store one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above.

[0019] According to an aspect of the present application, a computer readable medium is provided, which stores a computer program, and the program is executed by a processor to implement the method as described above.

[0020] According to the pumping unit fault diagnosis method and device, the electronic device, and the computer readable medium, the original signal from the pumping unit is subjected to W transformation to generate a transformation result; multiple group time delays at each time-frequency position in a time-frequency domain of the original signal are calculated based on the transformation result; time-frequency coefficients are generated based on a time rearrangement synchronous squeezing algorithm and the multiple group time delays; a time rearrangement multiple synchronous squeezing W transformation spectrum is generated based on the time-frequency coefficients; a target pulse is determined based on a time-frequency envelope of the time rearrangement multiple synchronous squeezing W transformation spectrum; and a manner of determining a fault of the pumping unit based on a time characteristic of the target pulse can highlight a real instantaneous frequency of a fault signal, is more fine, improves time and frequency resolution of the fault signal, and improves accuracy of fault positioning.

[0021] It should be understood that the foregoing general description and the following detailed description are only examples and are not restrictive of the application. BRIEF DESCRIPTION OF DRAWINGS

[0022] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which:

[0023] Figure 1 FIG. 1 is a system block diagram of a pumping unit fault diagnosis method and device according to an example embodiment.

[0024] Figure 2 FIG. 2 is a flowchart of a pumping unit fault diagnosis method according to an example embodiment.

[0025] Figure 3 FIG. 3 is a time-frequency spectrum obtained by performing short-time Fourier transform (STFT) on a pumping unit bearing signal according to an example embodiment.

[0026] Figure 4 FIG. 4 is a time-frequency spectrum obtained by performing six-time rearrangement synchronous squeezing W transformation (TMSSWT) on a pumping unit bearing signal according to an example embodiment.

[0027] Figure 5 FIG. 5 is a pulse curve extracted by using a time-frequency envelope spectrum method on a pumping unit bearing signal according to an example embodiment.

[0028] Figure 6 FIG. 6 is a block diagram of a pumping unit fault diagnosis device according to another example embodiment.

[0029] Figure 7 FIG. 7 is a block diagram of an electronic device according to an example embodiment.

[0030] Figure 8 is a block diagram of a computer readable medium according to an example embodiment. DETAILED DESCRIPTION

[0031] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments, however, can be implemented in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. Like reference numerals refer to like elements throughout the several views and embodiments. Like components will not be repeated in description.

[0032] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the application can be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, devices, and operations have not been shown or described in detail to avoid obscuring aspects of the application.

[0033] The block diagrams in the drawings show only the functionality of the embodiments and do not necessarily imply a physical or architectural arrangement of the embodiments. That is, the functionality can be implemented in software, hardware, or a combination thereof. The embodiments can be implemented in one or more hardware components or integrated circuits, or in a computer program product comprising a computer readable medium storing the computer program of sequences of instructions. The computer program can be executed by one or more processors.

[0034] The flow diagrams depicted herein are examples of sequences of operations that can be performed by one or more of the components illustrated in the block diagrams. The flow diagrams are not necessarily exhaustive of all possible operations that can be executed by the components. That is, the flow diagrams can not include all operations performed by the components in some embodiments. The flow diagrams can not include all operations performed by the components in some embodiments. The flow diagrams can not represent the operations performed by the components in some embodiments. That is, the flow diagrams can not be performed by the components in some embodiments. The flow diagrams can not be performed in the order shown in some embodiments. That is, some operations can be performed in a different order, some operations can be performed concurrently, and some operations can be omitted in some embodiments.

[0035] It should be understood that although the terms first, second, third, etc. can be used herein to describe various components, these components should not be limited by these terms. These terms are used only to distinguish one component from another. Thus, a first component discussed below could be termed a second component without departing from the teachings of the present disclosure. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0036] Those skilled in the art will understand that the drawings described herein are merely illustrative and that the modules or flows in the drawings do not necessarily have to be implemented in order to implement the present application, and therefore should not be used to limit the scope of protection of the present application.

[0037] Example 1

[0038] Figure 1 is a system block diagram of an oil pumping unit fault diagnosis method and device according to an exemplary embodiment.

[0039] As shown in Figure 1 , the system architecture 10 can include monitoring devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a communication link medium between the monitoring devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0040] The monitoring devices 101, 102, 103 can be arranged near the oil pumping unit bearings and interact with the server 105 through the network 104 to receive or send messages, etc. Various monitoring type applications can be installed on the monitoring devices 101, 102, 103. The monitoring devices 101, 102, 103 can be various electronic devices with monitoring and wireless transmission functions, which are not limited by the present application.

[0041] The server 105 can be a server that provides various services, such as a background management server that analyzes signals transmitted by the monitoring devices 101, 102, 103. The background management server can analyze and process the received signals, and feed back the processing results (such as fault analysis results) to the administrator.

[0042] The server 105 can perform, for example, W transform on the original signals from the monitoring devices 101, 102, 103 to generate a transform result; the server 105 can calculate, for example, a multiple group time delay at each time-frequency position in the time-frequency domain of the original signals based on the transform result; the server 105 can generate, for example, time-frequency coefficients based on a time rearrangement synchronous squeeze algorithm and the multiple group time delay; the server 105 can generate, for example, a time rearrangement multiple synchronous squeeze W transform spectrum based on the time-frequency coefficients; the server 105 can determine, for example, a target pulse based on a time-frequency envelope of the time rearrangement multiple synchronous squeeze W transform spectrum; and the server 105 can determine, for example, a fault of the oil pumping unit based on a time feature of the target pulse.

[0043] The server 105 can be a server of one entity, and can also be composed of multiple servers, for example. It should be noted that the oil pumping unit fault diagnosis method provided in the embodiments of the present application can be executed by the server 105, and accordingly, the oil pumping unit fault diagnosis device can be arranged in the server 105. The application end for monitoring is generally located in the monitoring devices 101, 102, 103.

[0044] Embodiment 2

[0045] Figure 2is a flow chart of an oil pumping unit fault diagnosis method according to an exemplary embodiment. The oil pumping unit fault diagnosis method 20 comprises at least steps S202 to S212.

[0046] As shown in S202, a W transform is performed on a raw signal from an oil pumping unit to generate a transform result. For example, a raw signal of an oil pumping unit bearing can be acquired based on a condition monitoring sensor; a W transform is performed on the raw signal to generate a W transform value; and the W transform value is modulated to obtain the transform result. Figure 2

[0047] In one specific application, the raw oil pumping unit bearing signal to be analyzed is x(t);

[0048] A W transform is performed on the input signal to obtain a W transform value W(t,f), and the W transform value is modulated to obtain a time-frequency spectrum |W(t,f)| of the W transform;

[0049] The calculation method of W(t,f) is as follows:

[0050]

[0051] wherein t represents a time center, f represents a frequency center, g(τ-t,f;t) represents a Gaussian window function, τ is a time variable, i is an imaginary unit, and the Gaussian window function g(τ-t,f;t) is:

[0052]

[0053] wherein k is a scalar factor for adjusting the shape of the window function, f0(t) represents a time-varying principal frequency of the signal, and |Δf(t)|=|f0(t)-f|. The time-varying principal frequency f0(t) can be calculated according to a weighted average value of an instantaneous frequency, i.e.,

[0054]

[0055] wherein represents an instantaneous frequency, a(t) represents an instantaneous amplitude, L(τ) is a low-pass filter defined by a Gaussian function, and r is a proportional factor inversely proportional to the low-pass filter.

[0056] In S204, multiple group delays at each time-frequency position in a time-frequency domain of the raw signal are calculated based on the transform result. For example, group delays of the raw signal at each time-frequency position can be calculated based on the transform result; and multiple group delays at each time-frequency position can be calculated based on the group delays at each time-frequency position.

[0057] ​In one embodiment, the group delay of the original signal at each time-frequency position is calculated based on the transform result, including: calculating the group delay of the original signal at each time-frequency position based on the phase information in the transform result.

[0058] In one embodiment, the multiple group delay at each time-frequency position is calculated based on the group delay at each time-frequency position, including: iteratively calculating the group delay at each time-frequency position to generate the multiple group delay at each time-frequency position.

[0059] The phase information of the obtained time-frequency spectrum estimates the group delay t0(t, f) of the signal x at each time-frequency position (t, f):

[0060]

[0061] Wherein, W tg is the W transform result under the window function tg(t, f), and Re represents the real part.

[0062] According to the group delay estimation result t0(t, f), the fixed point iterative algorithm is used to calculate the multiple group delay estimation, and the multiple group delay estimation value t0 [N] (t, f) at each time-frequency position (t, f) is calculated.

[0063] t0 [N] (t, f) = t0(t0 [N-1] (t, f), f) (5)

[0064] Wherein, N is a positive integer, representing the order of time rearrangement, when N = 1,

[0065] t0 [1] (t, f) = t0(t, f) (6)

[0066] In S206, the time-frequency coefficients are generated based on the time rearrangement synchronous squeezing algorithm and the multiple group delay. For example, a time rearrangement synchronous squeezing operator can be generated based on the time rearrangement synchronous squeezing algorithm and the multiple group delay; and the time-frequency coefficients can be generated based on the time rearrangement synchronous squeezing operator.

[0067] According to the principle of time rearrangement synchronous squeezing, a time rearrangement synchronous squeezing operator TSTO(t, f) is constructed on the time-frequency domain, which is centered on the multiple group delay curve of the signal, and is used to squeeze the original time-frequency spectrum energy along the time direction to the curve to obtain new time-frequency coefficients, and obtain the time rearrangement multiple synchronous squeezing W transform result T S [N] (t, f);

[0068] According to the time rearrangement synchronous extrusion principle, a time rearrangement synchronous extrusion operator TSTO(t, f) is constructed in the time-frequency domain, which is centered on the multiple group time delay curve of a signal, for "extruding" the original time-frequency spectrum energy along the time direction to the curve to obtain new time-frequency coefficients T S [N] (t, f); and rearranging the time-frequency energy to the real group time delay ridge of the signal.

[0069] The calculation method of TSTO(t, f) is as follows:

[0070]

[0071] Wherein, δ(·) is a unit impulse function.

[0072] In S208, a time rearrangement multiple synchronous extrusion W transform spectrum is generated based on the time-frequency coefficients. For example, the time-frequency coefficients are subjected to a modulo calculation to generate the time rearrangement multiple synchronous extrusion W transform spectrum |T S [N] (t, f)|.

[0073] The new time-frequency coefficients T S [N] (t, f) are obtained.

[0074]

[0075] In S210, a target pulse is determined based on the time-frequency envelope of the time rearrangement multiple synchronous extrusion W transform spectrum. For example, the time-frequency envelope of the time rearrangement multiple synchronous extrusion W transform spectrum is calculated; the frequency corresponding to the maximum amplitude in the time-frequency envelope is taken as a target frequency; and the target pulse corresponding to the target frequency is obtained.

[0076] In S212, a fault of the pumping unit is determined based on the time characteristics of the target pulse. For example, the time characteristics of the target pulse are matched with a plurality of preset time characteristics; and the fault of the pumping unit is determined according to the matching result. The pulse characteristics of the frequency corresponding to the strongest amplitude in the obtained time-frequency spectrum are extracted, and the time intervals of the pulse characteristics are compared with the matching degrees between a plurality of known fault signals to identify the bearing fault of the pumping unit.

[0077] According to the pumping unit fault diagnosis method, the original signal from the pumping unit is subjected to W transform to generate a transform result; a multiple group time delay at each time-frequency position in a time-frequency domain of the original signal is calculated based on the transform result; a time-frequency coefficient is generated based on the time rearrangement synchronous extrusion algorithm and the multiple group time delay; a time rearrangement multiple synchronous extrusion W transform spectrum is generated based on the time-frequency coefficient; a target pulse is determined based on a time-frequency envelope of the time rearrangement multiple synchronous extrusion W transform spectrum; and a manner of determining the fault of the pumping unit based on a time characteristic of the target pulse can highlight the real instantaneous frequency of the fault signal and is more accurate, thereby improving the time and frequency resolution of the fault signal and improving the accuracy of fault positioning.

[0078] The pumping unit fault diagnosis method of the present application first uses WT to obtain a time-frequency representation result of the original signal, and then constructs a time-frequency post-processing representation operator "extrusion operator" for estimating the real group delay (GD) of the signal on the time-frequency domain, which is used to perform "extrusion" operation on the time-frequency spectrum energy calculated by the original W transform. Then, the iterative algorithm of fixed point is used to rearrange the time-frequency energy to the real group delay ridge line of the signal. Finally, the time-frequency envelope is calculated, the pulse characteristics of the frequency corresponding to the strongest amplitude in the obtained TMSSWT time-frequency spectrum are extracted, and the time interval of the pulse characteristics is compared to identify the bearing fault of the pumping unit.

[0079] It should be clearly understood that the present application describes how to form and use specific examples, but the principles of the present application are not limited to any details of these examples. On the contrary, based on the teachings of the disclosure of the present application, these principles can be applied to many other embodiments.

[0080] Embodiment 3

[0081] The present application is based on the time rearrangement synchronous extrusion transform W transform, which combines the advantages of the time rearrangement multiple synchronous extrusion transform and the W transform, has higher time-frequency decomposition accuracy, and has great practical prospect in mechanical fault diagnosis.

[0082] The time rearrangement multiple synchronous extrusion W transform of the present application is different from the time rearrangement multiple synchronous extrusion transform. The reason for the different effects of the time rearrangement synchronous extrusion transform and the time rearrangement synchronous extrusion transform W transform algorithm is analyzed. The time rearrangement synchronous extrusion transform is based on the short-time Fourier transform result, so the time-frequency characteristics of the short-time Fourier transform will inevitably affect the final "compressed" result.

[0083] The time rearrangement multiple synchronous extrusion W transform is based on the result of the W transform. Since the W transform uses a Gaussian window function with frequency weights symmetrical around the main frequency to obtain the original time-frequency representation result of the signal, the time rearrangement multiple synchronous extrusion W transform result has not only good time-frequency resolution but also strong flexibility.

[0084] Compared with the W transform, the time rearrangement multiple synchronous extrusion W transform can highlight the real group time delay of a signal and make it more accurate by multiple estimation of the group time delay of the signal on the W transform time-frequency spectrum and by a "compression" operation, thereby greatly improving the time and frequency resolution of the signal on the basis of the W transform. The time interval of the pulse characteristics corresponding to the strongest amplitude can be extracted, and bearing faults can be identified by comparing the time interval of the pulse characteristics.

[0085] According to one embodiment of the present application, the pump unit bearing fault vibration signal is taken as an example for testing.

[0086] Referring to Figure 2 and Figure 3 The time-frequency spectrum of the pump unit bearing fault vibration signal processed by the STFT and the TMSSWT, the time-frequency energy focusing of the STFT is poor, while the TMSSWT can provide a time-frequency spectrum with highly focused time-frequency energy distribution, and the time-frequency ridge thereof presents a very detailed pulse curve without energy diffusion around the curve. It can be seen that the TMSSWT can more accurately depict the time-frequency ridge of the pulse characteristics, which will be beneficial to accurately depict the pulse characteristics of the mechanical signal. Referring to Figure 4 For the extracted pulse curve, it can be analyzed that each pulse characteristic of the pump unit bearing fault can be accurately identified, and the time interval of two pulse characteristics is 9.3 milliseconds as indicated by the bidirectional arrow in the figure. The results show that the method of the present application can accurately capture the pulse interval caused by the pump unit bearing fault, which indicates that it has great application prospect in the pump unit bearing fault diagnosis.

[0087] The application of the pump unit fault diagnosis method in the pump unit fault diagnosis has the following beneficial effects: compared with the W transform, the time rearrangement multiple synchronous extrusion W transform of the present application can highlight the real instantaneous frequency of a signal and make it more accurate by multiple estimation of the group time delay of the signal on the W transform time-frequency spectrum and by a "compression" operation, thereby improving the time and frequency resolution of the signal on the basis of the W transform. The time interval of the pulse characteristics corresponding to the strongest amplitude can be extracted, and bearing faults can be identified by comparing the time interval of the pulse characteristics.

[0088] Those skilled in the art can understand that all or part of the steps of the above embodiments are implemented as a computer program executed by a CPU. When the computer program is executed by the CPU, the above functions defined by the above method provided by the present application are executed. The program can be stored in a computer readable storage medium, which can be a read-only memory, a disk or an optical disk, etc.

[0089] In addition, it should be noted that the above-described figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not intended for limiting purposes. It is easy to understand that the processes shown in the above-described figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be executed synchronously or asynchronously, for example, in multiple modules.

[0090] Embodiment 4

[0091] The following is a device embodiment of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0092] Figure 6 is a block diagram of an oil pumping unit fault diagnosis device according to another exemplary embodiment. As shown in Figure 6 , the oil pumping unit fault diagnosis device 60 includes a transform module 602, a delay module 604, a coefficient module 606, a transform spectrum module 608, a pulse module 610, and a fault module 612.

[0093] The transform module 602 is configured to perform W transform on an original signal from an oil pumping unit to generate a transform result;

[0094] The delay module 604 is configured to calculate multiple group time delays at each time-frequency position in a time-frequency domain of the original signal based on the transform result;

[0095] The coefficient module 606 is configured to generate time-frequency coefficients based on a time rearrangement synchronous squeeze algorithm and the multiple group time delays;

[0096] The transform spectrum module 608 is configured to generate a time rearrangement multiple synchronous squeeze W transform spectrum based on the time-frequency coefficients;

[0097] The pulse module 610 is configured to determine a target pulse based on a time-frequency envelope of the time rearrangement multiple synchronous squeeze W transform spectrum;

[0098] The fault module 612 is configured to determine a fault of the oil pumping unit based on a time feature of the target pulse.

[0099] The oil pumping unit fault diagnosis device according to the present application generates a transform result by performing W transform on the original signal from the oil pumping unit; calculates multiple group time delays at each time-frequency position in the time-frequency domain of the original signal based on the transform result; generates time-frequency coefficients based on the time rearrangement synchronous extrusion algorithm and the multiple group time delays; generates a time rearrangement multiple synchronous extrusion W transform spectrum based on the time-frequency coefficients; determines a target pulse based on the time-frequency envelope of the time rearrangement multiple synchronous extrusion W transform spectrum; and determines the mode of the fault of the oil pumping unit based on the time characteristics of the target pulse, so that the real instantaneous frequency of the fault signal can be highlighted and is more accurate, the time and frequency resolution of the fault signal is improved, and the accuracy of fault positioning is improved.

[0100] Embodiment 5

[0101] Figure 7 is a block diagram of an electronic device according to an exemplary embodiment.

[0102] The electronic device 700 according to this embodiment of the present application will be described below with reference to Figure 7 Figure 7 The displayed electronic device 700 is merely an example and should not impose any limitation on the function and scope of use of the embodiments of the present application.

[0103] As shown in Figure 7 , the electronic device 700 is in the form of a general computing device. The components of the electronic device 700 can include, but are not limited to, at least one processing unit 710, at least one storage unit 720, a bus 730 connecting different system components (including the storage unit 720 and the processing unit 710), a display unit 740, etc.

[0104] The storage unit stores program codes that can be executed by the processing unit 710, so that the processing unit 710 performs the steps described in the present specification according to various exemplary embodiments of the present application. For example, the processing unit 710 can perform the steps as shown in Figure 2

[0105] The storage unit 720 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 7201 and / or a cache memory unit 7202, and can further include a read-only memory (ROM) 7203.

[0106] The storage unit 720 can also include program / utilities 7204 with a set of (at least one) program modules 7205, such as an operating system, one or more application programs, other program modules, and program data, each of which or some combination of which can include the implementation of a network environment.​​

[0107] Bus 730 can be one of several types of bus structures including a memory bus or memory controller, a peripheral bus, a graphics bus, a processor or local bus using any of a variety of bus structures, and the like.

[0108] Electronic device 700 can also communicate with one or more external devices 700' such as a keyboard or pointing device, a Bluetooth device, etc. using the communications interface 750. Communications interface 750 can also include an infrared, Bluetooth® or other device adapted to facilitate communication with an external device. Electronic device 700 can communicate with one or more other computing devices using the communications interface 750, such as a router, a modem, or the like. Such communications can be facilitated by a communications interface 750. Electronic device 700 can also communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the public network, such as the Internet, using a network adapter 760. Network adapter 760 can communicate with the other components of electronic device 700 via bus 730. It will be appreciated that other hardware and / or software modules can be used in conjunction with electronic device 700, such as microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0109] Those skilled in the art will readily recognize that the example embodiments described herein can be implemented using software, hardware, or a combination of software and hardware. As such, the example embodiments described herein can be implemented using a software product, such as a computer program tangibly embodied on a non-transitory computer readable medium, such as a magnetic or optical disk, a magnetic tape, a semiconductor memory chip, etc. The software product can include one or more instructions for causing a computing device (such as a personal computer, a server, a network device, etc.) to perform the methods described above. Figure 8

[0110] The software product can be embodied in any combination of one or more computer readable media or storage media. The computer readable media or storage media can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. ​

[0111] The computer readable storage medium can include a non-transitory computer-readable medium (e.g., volatile or non-volatile memory device), a media such as those listed above, or any suitable combination of the preceding types of computer-readable storage media. The computer readable storage medium can be non-transitory as at the time of the computer readable storage medium is created or formed. In various embodiments, the computer readable storage medium can be non-transitory in that it can not be a propagated signal. The computer-readable storage medium can be tangible and non-transitory.

[0112] Program code, used by or in connection with the routines, can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider (ISP).

[0113] The computer readable medium described above can carry one or more programs, when executed by the device, cause the computer readable medium to implement the following functions: performing W transform on an original signal from a pumping unit to generate a transform result; calculating multiple group time delays at each time-frequency position in a time-frequency domain of the original signal based on the transform result; generating time-frequency coefficients based on a time rearrangement synchronous squeeze algorithm and the multiple group time delays; generating a time rearrangement multiple synchronous squeeze W transform spectrum based on the time-frequency coefficients; determining a target pulse based on a time-frequency envelope of the time rearrangement multiple synchronous squeeze W transform spectrum; and determining a fault of the pumping unit based on a time feature of the target pulse.

[0114] Those skilled in the art can understand that the above modules can be distributed in the device according to the description of the embodiments, and can also be changed to be in one or more devices different from the embodiments. The modules of the above embodiments can be combined into one module, or can be further split into multiple sub-modules.

[0115] Through the above description of the embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present application.

[0116] The example embodiments of the present application are specifically shown and described above. It should be understood that the present application is not limited to the detailed structure, arrangement or implementation method described herein; on the contrary, the present application is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the appended claims.

Claims

1. A method for diagnosing a fault of an oil pumping unit, characterized in that: include: Perform W transformation on the original signal from the pumping unit to generate a transformation result; Calculating multiple group delays at each time-frequency position in the time-frequency domain of the original signal based on the transformation result; generating time-frequency coefficients based on a time-rearrangement synchronization squeezing algorithm and the multiple group delays; generating a time-rearranged multiple synchronously squeezed W-transform spectrum based on the time-frequency coefficients; Determine the target pulse based on the time-frequency envelope of the time-rearranged multiple synchronously squeezed W transform spectrum; determining a fault of the pumping unit based on a time characteristic of the target pulse; The step of calculating the multiple group delays at each time-frequency position in the time-frequency domain of the original signal based on the transformation result includes: Calculating the group delay of the original signal at each time-frequency position based on the transformation result; The multiple group delays at each time-frequency position are calculated based on the group delays at each time-frequency position.

2. The method according to claim 1, wherein Perform W transformation on the original signal from the pumping unit to generate transformation results, including: Obtaining the original signal of the pumping unit bearing based on the condition monitoring sensor; Performing a W transform on the original signal to generate a W transform value; The transformation result is obtained by performing a modulo operation on the W transformation value.

3. The method according to claim 1, wherein Calculating the group delay of the original signal at each time-frequency position based on the transformation result, including: The group delay of the original signal at each time-frequency position is calculated based on the phase information in the transformation result.

4. The method according to claim 1, wherein Calculating multiple group delays at each time-frequency position based on the group delays at each time-frequency position, including: The group delay at each time-frequency position is iteratively calculated to generate multiple group delays at each time-frequency position.

5. The method according to claim 1, wherein Generating time-frequency coefficients based on a time rearrangement synchronization squeezing algorithm and the multiple group delays includes: generating a time-rearrangement synchronization-squeezing operator based on the time-rearrangement synchronization-squeezing algorithm and the multiple group delays; The time-frequency coefficients are generated based on the time-rearrangement synchronization squeezing operator.

6. The method according to claim 1, wherein Generating a time-rearranged multiple synchronously squeezed W transform spectrum based on the time-frequency coefficients, comprising: A modulo calculation is performed on the time-frequency coefficients to generate a time-rearranged multiple synchronously squeezed W transform spectrum.

7. The method according to claim 1, wherein The target pulse is determined based on the time-frequency envelope of the time-rearranged multiple synchronously squeezed W transform spectrum, including: Compute the time-frequency envelope of the time-rearranged multiple synchronously squeezed W transform spectrum; Taking the frequency corresponding to the maximum amplitude in the time-frequency envelope as the target frequency; A target pulse corresponding to the target frequency is obtained.

8. The method according to claim 1, wherein Determining a fault of the oil pumping unit based on a time characteristic of the target pulse includes: Matching the time characteristic of the target pulse with a plurality of preset time characteristics; The fault of the oil pumping unit is determined according to the matching result.

9. A pumping unit fault diagnosis device, characterized in that: include: A transformation module, used for performing W transformation on the original signal from the pumping unit to generate a transformation result; A delay module, configured to calculate the multiple group delays at each time-frequency position in the time-frequency domain of the original signal based on the transformation result; A coefficient module, configured to generate time-frequency coefficients based on a time rearrangement synchronization squeezing algorithm and the multiple group delays; A transform spectrum module, configured to generate a time-rearranged multiple synchronously squeezed W transform spectrum based on the time-frequency coefficients; A pulse module for determining target pulses based on the time-frequency envelope of the time-rearranged multiple synchronously squeezed W transform spectrum; a fault module, configured to determine a fault of the oil pumping unit based on a time characteristic of the target pulse; The step of calculating the multiple group delays at each time-frequency position in the time-frequency domain of the original signal based on the transformation result includes: Calculating the group delay of the original signal at each time-frequency position based on the transformation result; The multiple group delays at each time-frequency position are calculated based on the group delays at each time-frequency position.

10. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer-readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images