Anomaly Detection Method for Plunger Pumps Based on Simulation and Experimental Data Similarity Analysis

Abstract

This application discloses a plunger pump anomaly detection method based on simulation and experimental data similarity analysis, belonging to the field of plunger pump detection. The method includes: simulating and generating an ideal waveform for monitoring the plunger pump outlet pressure signal to obtain a standard reference signal; acquiring the plunger pump outlet pressure signal under healthy conditions to obtain a measured healthy signal; calculating the modal distance of the weighted graph similarity matrix between the measured healthy signal and the standard reference signal to obtain a similarity index; determining an alarm threshold based on the similarity index; monitoring the outlet pressure signal of the plunger pump under test to obtain a signal to be detected; calculating the similarity between the signal to be detected and the standard reference signal; and determining that the plunger pump under test is abnormal when the similarity is lower than the alarm threshold in a continuous number of target detections. This method can establish an anomaly detection model without fault samples, effectively solving the practical problem of scarce fault data and conforming to the background of practical engineering applications.

Description

Technical Field

[0001] This application belongs to the field of plunger pump detection technology, specifically relating to a plunger pump anomaly detection method based on simulation and experimental data similarity analysis. Background Technology

[0002] Piston pumps offer advantages such as high power density, compact structure, and high efficiency, making them widely used in aerospace, engineering machinery, and automotive industries. As a key power supply component in hydraulic systems, the health of the piston pump directly affects the system's efficiency and safety.

[0003] To ensure the normal operation of the hydraulic system, the health status of the piston pump needs to be monitored in real time to detect early failures of the piston pump, so as to make reasonable arrangements for the maintenance plan of the hydraulic system and avoid the risk of accidents and economic losses caused by emergency shutdowns.

[0004] In practical engineering applications, due to the fact that equipment operates in a healthy state for a long time, abnormal data is scarce, resulting in poor performance of data-driven anomaly detection methods. Summary of the Invention

[0005] The purpose of this application is to provide a plunger pump anomaly detection method based on simulation and experimental data similarity analysis to enable anomaly detection of plunger pumps when abnormal data is scarce.

[0006] According to a first aspect of the embodiments of this application, a method for detecting anomalies in a plunger pump based on simulation and experimental data similarity analysis is provided. This method may include:

[0007] The ideal waveform of the monitoring plunger pump outlet pressure signal is generated by simulation to obtain the standard reference signal; and the plunger pump outlet pressure signal under healthy conditions is collected to obtain the measured healthy signal.

[0008] The modal distance of the weighted similarity matrix between the measured health signal and the standard reference signal is calculated to obtain the similarity index; and the alarm threshold is determined based on the similarity index.

[0009] The pressure signal at the outlet of the plunger pump under test is monitored to obtain the signal to be detected; and the similarity between the signal to be detected and the standard reference signal is calculated.

[0010] When the number of consecutive similarity targets measured is lower than the alarm threshold, it is determined that the plunger pump under test is malfunctioning.

[0011] In some optional embodiments of this application, the outlet pressure signal of the plunger pump under healthy conditions is collected to obtain a measured healthy signal, including:

[0012] A pressure sensor is installed in the hydraulic line at the outlet end of the piston pump in a healthy state to collect the pressure signal of the piston pump in a healthy state; the hydraulic line is a rigid pipe.

[0013] The pressure signal is converted into a digital signal by an A / D converter, yielding the measured health signal. In some optional embodiments of this application, the sampling frequency of the pressure sensor satisfies the following formula:

[0014] f s ≥10nm / 60

[0015] Among them, f s is the sampling frequency; n is the piston pump speed in rpm; m is the number of pistons.

[0016] In some optional embodiments of this application, after installing a pressure sensor in the hydraulic pipeline at the outlet end of the piston pump in a healthy state to collect the pressure signal of the piston pump in a healthy state, the piston pump anomaly detection method based on simulation and experimental data similarity analysis further includes:

[0017] The pressure signal was resampled to 360 points / revolution using interpolation, and then truncated to a length of 400 as the pressure signal sample.

[0018] In some optional embodiments of this application, the modal distance of the weighted graph similarity matrix between the measured health signal and the standard reference signal is calculated to obtain a similarity index, including:

[0019] The pressure signal samples of the measured health signals were extracted using the sliding window method. The similarity between the pressure signal samples and the standard reference signal was calculated, and the sample with the maximum similarity was taken as the aligned sample.

[0020] Based on graph similarity theory, the standard reference signal and the homogenized samples are used to generate corresponding graph adjacency matrices.

[0021] Construct a weighted matrix graph with the same size as the adjacency matrix graph, and use the Hadamard product of the weighted matrix graph and the adjacency matrix graph as its weighted graph similarity matrix;

[0022] The similarity index is obtained by using the distance between the weighted graph similarity matrices as a measure of the similarity between the measured health signal and the standard reference signal.

[0023] In some optional embodiments of this application, the sample length truncated by the sliding window method is 360 to ensure that the truncated sample length is consistent with the standard reference signal, the sliding window step size is 1, and the maximum offset distance is 40.

[0024] In some optional embodiments of this application, the offset phase when the pressure signal sample is aligned with the standard reference signal is calculated using the following formula:

[0025] x align =argmax S(G(s),G(w(x)))

[0026] Where, x align For the aligned pressure signal samples, s is the standard reference signal, x is the pressure signal sample, w(·) is the window function, G is the mapping function from the input signal to the weighted graph similarity matrix, and S represents the calculation of similarity.

[0027] According to a second aspect of the embodiments of this application, a plunger pump anomaly detection device based on simulation and experimental data similarity analysis is provided, the device may include:

[0028] The signal acquisition module is used to simulate and generate an ideal waveform for monitoring the outlet pressure signal of the plunger pump to obtain a standard reference signal; and to acquire the outlet pressure signal of the plunger pump under healthy conditions to obtain the measured healthy signal.

[0029] The calculation module is used to calculate the modal distance of the weighted graph similarity matrix between the measured health signal and the standard reference signal to obtain the similarity index; and to determine the alarm threshold based on the similarity index.

[0030] The monitoring module is used to monitor the pressure signal at the outlet of the plunger pump under test, obtain the signal to be detected, and calculate the similarity between the signal to be detected and the standard reference signal.

[0031] The determination module is used to determine that the plunger pump under test is malfunctioning when the similarity score is lower than the alarm threshold for consecutive target counts.

[0032] According to a third aspect of the embodiments of this application, an electronic device is provided, which may include:

[0033] processor;

[0034] Memory used to store processor-executable instructions;

[0035] The processor is configured to execute instructions to implement the plunger pump anomaly detection method based on simulation and experimental data similarity analysis, as shown in any embodiment of the first aspect.

[0036] According to a fourth aspect of the embodiments of this application, a storage medium is provided, which, when the instructions in the storage medium are executed by a processor of an information processing device or a server, enables the information processing device or server to implement the plunger pump anomaly detection method based on simulation and experimental data similarity analysis as shown in any embodiment of the first aspect.

[0037] The above-mentioned technical solution of this application has the following beneficial technical effects:

[0038] The method described in this application can establish an anomaly detection model under the premise of no fault samples, effectively solving the practical problem of scarce fault data and conforming to the background of actual engineering applications. Furthermore, by using simulated signals as standard reference signals and using the similarity between the monitored signals and the simulated reference signals as the monitoring feature indicators, the distinction between abnormal samples and normal samples is high, and the similarity indicators have clear physical meaning, exhibiting good interpretability and reliability. In addition, this method measures the health status of the plunger pump by using the similarity between the monitored signals and the simulated reference signals, which can detect minute deformations in the plunger pump pressure pulsation waveform and has high sensitivity to early plunger pump failures. Attached Figure Description

[0039] Figure 1 This is a flowchart illustrating an exemplary embodiment of the plunger pump anomaly detection method based on simulation and experimental data similarity analysis.

[0040] Figure 2 This is a schematic diagram of the structure of a plunger pump anomaly detection device based on simulation and experimental data similarity analysis in an exemplary embodiment of this application;

[0041] Figure 3 This is a schematic diagram of the structure of a plunger pump anomaly detection system based on simulation and experimental data similarity analysis in an exemplary embodiment of this application;

[0042] Figure 4 This is a flowchart illustrating an exemplary embodiment of the plunger pump anomaly detection method based on simulation and experimental data similarity analysis.

[0043] Figure 5 This is a flowchart illustrating the signal similarity evaluation module in an exemplary embodiment of the plunger pump anomaly detection method based on simulation and experimental data similarity analysis.

[0044] Figure 6 This is a waveform diagram of the standard reference signal in an exemplary embodiment of this application;

[0045] Figure 7 This is a waveform diagram of a measured health signal in an exemplary embodiment of this application;

[0046] Figure 8 This is a waveform diagram of a segment of a signal to be detected in an exemplary embodiment of this application;

[0047] Figure 9 This is the detection result of the plunger pump anomaly detection method based on simulation and experimental data similarity analysis in an exemplary embodiment of this application;

[0048] Figure 10 This is a schematic diagram of the structure of an electronic device in an exemplary embodiment of this application;

[0049] Figure 11 This is a schematic diagram of the hardware structure of an electronic device in an exemplary embodiment of this application. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to specific embodiments and accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of this application. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0051] The accompanying drawings illustrate layer structure diagrams according to embodiments of this application. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0052] Obviously, the described embodiments are only a part of the embodiments of this application, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0053] In the description of this application, it should be noted that the terms "first", "second", and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0054] Furthermore, the technical features involved in the different embodiments of this application described below can be combined with each other as long as they do not conflict with each other.

[0055] Among the various monitoring signals in a hydraulic system, pressure signals have the lowest acquisition cost and the widest application, so they are often used to monitor the health status of piston pumps.

[0056] The following description, in conjunction with the accompanying drawings, details the plunger pump anomaly detection method based on simulation and experimental data similarity analysis provided in this application, through specific embodiments and application scenarios.

[0057] like Figure 1 As shown, in a first aspect of this application, a method for detecting anomalies in a plunger pump based on similarity analysis of simulation and experimental data is provided. This method may include:

[0058] S110: Simulates and generates an ideal waveform for monitoring the outlet pressure signal of the plunger pump to obtain a standard reference signal; and collects the outlet pressure signal of the plunger pump under healthy conditions to obtain the measured healthy signal;

[0059] S120: Calculate the modal distance of the weighted graph similarity matrix between the measured health signal and the standard reference signal to obtain the similarity index; and determine the alarm threshold based on the similarity index;

[0060] S130: Monitor the pressure signal at the outlet of the piston pump under test to obtain the signal to be detected; and calculate the similarity between the signal to be detected and the standard reference signal;

[0061] S140: When the similarity is lower than the alarm threshold in the number of consecutive target detections, it is determined that the plunger pump under test is abnormal.

[0062] This embodiment's method can establish an anomaly detection model even without faulty samples, effectively solving the practical problem of scarce fault data and conforming to the background of actual engineering applications. Furthermore, by using simulated signals as standard reference signals and the similarity between the monitored signal and the simulated reference signal as the monitoring feature index, the method achieves high distinguishability between abnormal and normal samples, and the similarity index has clear physical meaning, exhibiting good interpretability and reliability. Additionally, this method measures the plunger pump's health status using the similarity between the monitored signal and the simulated reference signal, detecting minute deformations in the plunger pump's pressure pulsation waveform, and demonstrating high sensitivity to early-stage plunger pump failures. The target number in this embodiment is a preset value.

[0063] In some embodiments, the outlet pressure signal of the plunger pump under healthy conditions is acquired to obtain the measured healthy signal, including:

[0064] A pressure sensor is installed in the hydraulic line at the outlet end of the piston pump in a healthy state to collect the pressure signal of the piston pump in a healthy state; the hydraulic line is a rigid pipe.

[0065] The pressure signal is converted into a digital signal by an AD converter, and the measured health signal is obtained.

[0066] In this embodiment, the pressure sensor is a high-frequency pressure sensor. Since the hydraulic line between the pressure sensor and the plunger pump outlet should be a rigid pipe, the quality of the acquired signal can be guaranteed.

[0067] In some embodiments, the sampling frequency of the pressure sensor satisfies the following formula:

[0068] f s ≥10nm / 60

[0069] Among them, f s is the sampling frequency; n is the piston pump speed in rpm; m is the number of pistons.

[0070] By utilizing the sampling frequency of this embodiment, it can be ensured that the pressure pulsation waveform is not distorted.

[0071] In some embodiments, after installing a pressure sensor in the hydraulic line at the outlet end of the piston pump in a healthy state to collect the pressure signal of the piston pump in a healthy state, the piston pump anomaly detection method based on simulation and experimental data similarity analysis further includes:

[0072] The pressure signal was resampled to 360 points / revolution using interpolation, and then truncated to a length of 400 as the pressure signal sample.

[0073] In this embodiment, the plunger pump outlet pressure signal is resampled to 360 points / revolution using interpolation, which ensures that it is consistent with the standard reference signal.

[0074] In some embodiments, the modal distance of the weighted graph similarity matrix between the measured health signal and the standard reference signal is calculated to obtain a similarity index, including:

[0075] The pressure signal samples of the measured health signals were extracted using the sliding window method. The similarity between the pressure signal samples and the standard reference signal was calculated, and the sample with the maximum similarity was taken as the aligned sample.

[0076] Based on graph similarity theory, the standard reference signal and the homogenized samples are used to generate corresponding graph adjacency matrices.

[0077] Construct a weighted matrix graph with the same size as the adjacency matrix graph, and use the Hadamard product of the weighted matrix graph and the adjacency matrix graph as its weighted graph similarity matrix;

[0078] The similarity index is obtained by using the distance between the weighted graph similarity matrices as a measure of the similarity between the measured health signal and the standard reference signal.

[0079] In some embodiments, the sample length truncated by the sliding window method is 360 to ensure that the truncated sample length is consistent with the standard reference signal, the sliding window step size is 1, and the maximum offset distance is 40.

[0080] In some embodiments, the offset phase when the pressure signal sample is aligned with the standard reference signal is calculated using the following formula:

[0081] x align =argmax S(G(s),G(w(x)))

[0082] Where, x align For the aligned pressure signal samples, s is the standard reference signal, x is the pressure signal sample, w(·) is the window function, G is the mapping function from the input signal to the weighted graph similarity matrix, and S represents the calculation of similarity.

[0083] During the calculation, the one-dimensional signal of length 360 is generated into a 360×360 adjacency matrix D, and the value of each element in the matrix is ​​defined by the following formula:

[0084]

[0085] In the formula, y i Let d represent the value of the i-th point in a one-dimensional signal. i,j Let i be an element in the adjacency matrix D, where i and j are the row and column of the element.

[0086] Define a weight matrix W of size 360×360 to assign weights to adjacent matrices. Generally, the weight matrix assigns higher weights to elements that are closer to the main diagonal of the matrix.

[0087] The weight matrix is ​​defined using the following formula:

[0088]

[0089] In the formula, w i,j Let i be an element in the adjacency matrix W, where i and j are the row and column of the element.

[0090] The weighted graph similarity matrix is ​​defined as the Hadamard product of the weighted graph and the adjacency matrix, i.e.:

[0091] ε=W⊙D

[0092] In the formula, ⊙ represents the Hadamard product, and ε represents the weighted graph similarity matrix.

[0093] The distance between the weighted similarity matrices corresponding to the standard reference signal and the monitoring signal is calculated, and the above distance is normalized to serve as a similarity measure between the two input signals.

[0094] The similarity metric is defined using the following formula:

[0095] S Modality =1-||π(ε)-π(ε′)||2 / max(||π(ε)||2,||π(ε′)||2)

[0096] In the formula S Modality Let represent modal similarity, ε and ε' represent the weighted similarity matrices generated by the standard reference signal and the monitoring signal, π(·) represent the Perron vector of the calculated matrix, ||·||2 represents the 2-norm of the calculated vector, and max(·,·) is used to find the maximum value.

[0097] Furthermore, other similarity measures can be used to evaluate the similarity between two matrices, but all similarity measures should possess the following properties:

[0098] Property 1: Normalization, the similarity between any two inputs should be in the range of 0-1, that is, S(G,G')∈[0,1];

[0099] Property 2: Identity, the similarity between the same signal and itself is 1, that is, S(G,G)=1;

[0100] Property 3: Symmetry. When the two input signals are exchanged, the similarity remains unchanged, i.e., S(G,G')=S(G',G).

[0101] In some embodiments, based on the similarity value distribution, the 3σ criterion is adopted, and the lower bound of the 3σ similarity index is taken as the alarm threshold. Based on the similarity value distribution, the minimum similarity value is taken as the alarm threshold.

[0102] It should be noted that the plunger pump anomaly detection method based on simulation and experimental data similarity analysis provided in this application can be executed by a plunger pump anomaly detection device based on simulation and experimental data similarity analysis, or by a control module within that device for executing the method. This application uses the example of a plunger pump anomaly detection device executing the method based on simulation and experimental data similarity analysis to illustrate the device for plunger pump anomaly detection provided in this application.

[0103] like Figure 2 As shown, in a second aspect of this application, a plunger pump anomaly detection device based on simulation and experimental data similarity analysis is provided. This device may include:

[0104] The signal acquisition module 210 is used to simulate and generate an ideal waveform of the monitoring plunger pump outlet pressure signal to obtain a standard reference signal; and to acquire the plunger pump outlet pressure signal under healthy conditions to obtain the measured healthy signal.

[0105] The calculation module 220 is used to calculate the modal distance of the weighted graph similarity matrix between the measured health signal and the standard reference signal to obtain the similarity index; and to determine the alarm threshold based on the similarity index.

[0106] The monitoring module 230 is used to monitor the pressure signal at the outlet of the plunger pump under test, obtain the signal to be detected, and calculate the similarity between the signal to be detected and the standard reference signal.

[0107] The determination module 240 is used to determine that the plunger pump under test is abnormal when the similarity is lower than the alarm threshold in the number of consecutive target detections.

[0108] In one specific embodiment, the plunger pump anomaly detection device based on the similarity analysis of simulation and experimental data can build an anomaly detection system established by the plunger pump anomaly detection method, such as... Figure 3 As shown.

[0109] The anomaly detection system consists of monitoring sensors in the hydraulic system, an edge monitoring and early warning system, and a cloud simulation computing center. In the piston pump anomaly detection system, a simulation model is established based on the piston pump parameters in the hydraulic system, and the simulation model is deployed in the cloud computing center to generate simulation reference signals.

[0110] In the plunger pump anomaly detection system, the anomaly monitoring model is deployed in the edge computing node, and the anomaly detection method is deployed in the edge computing node. The anomaly detection model is composed of simulation reference signal, similarity evaluation module and threshold, and is used for the health status monitoring of plunger pump.

[0111] In edge computing nodes, edge computing terminals have modules such as CPU, network communication, and 5G communication to realize functions such as monitoring signal processing and analysis calculation, communication between edge nodes and AD conversion modules, cloud computing centers, and databases.

[0112] In the plunger pump anomaly detection system, a pressure sensor is installed at the outlet of the monitored hydraulic pump for pressure signal monitoring; the signal is converted by an A / D converter and then input to the edge computing node via network communication.

[0113] For example, the plunger pump outlet pressure signal is truncated into a 400-unit segment to meet the signal alignment requirements of the sliding window method. Since the maximum offset of the sliding window is 40, the final truncated sample length is 360, so the truncated signal length is 360 + 40 = 400.

[0114] Furthermore, the pressure signal segment and the simulated reference signal are input into the similarity evaluation module to calculate the similarity between the two signals. The monitoring signal is sampled several times at intervals, and the similarity between the obtained similarity and the reference signal is calculated sequentially. If the similarity of z consecutive samples is lower than the threshold, the plunger pump is determined to be abnormal, where z is a preset parameter.

[0115] In the plunger pump anomaly detection system, the edge computing terminal monitors the operating conditions of the plunger pump (such as pump speed, pressure, swashplate tilt angle, etc.) through sensors. When the operating conditions of the plunger pump change, the edge computing node sends the new operating parameters to the cloud computing center. The cloud computing center re-performs the simulation calculation by changing the simulation model, and sends the generated new simulation pressure signal to the edge computing node to update the reference signal.

[0116] The cloud computing center and edge computing nodes communicate via wired or wireless network ports using the HTTP protocol. The edge computing nodes send real-time operating information to the cloud computing center, and the cloud computing center sends simulation signals to the edge computing nodes to update the model.

[0117] The edge computing terminal stores and reports the monitored pressure pulsation waveform, operating condition information, and calculated similarity values. The stored data is stored in the form of time-series signals.

[0118] Optionally, depending on data storage requirements, the above data can be uploaded to a server database or cloud database via wireless network, wired network, 5G communication, or other means.

[0119] Specifically, the detection process of anomaly monitoring methods, such as... Figure 4-5 As shown; the simulated reference signal waveform of the plunger pump outlet pressure, as follows. Figure 6 As shown; Figure 7 A time-domain plot of a normal sample of the plunger pump outlet pressure signal; Figure 8 The image shows a time-domain plot of an abnormal sample of the plunger pump outlet pressure signal; the result of anomaly detection of the test sample using the method described in this embodiment is shown below. Figure 9 As shown.

[0120] The plunger pump anomaly detection device based on simulation and experimental data similarity analysis in this application embodiment can be a device, or it can be a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0121] The plunger pump anomaly detection device based on simulation and experimental data similarity analysis in this application embodiment can be a device with an operating system. This operating system can be Windows, Linux, Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0122] The plunger pump anomaly detection device based on simulation and experimental data similarity analysis provided in this application embodiment can achieve… Figure 1 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0123] Optionally, such as Figure 10 As shown, this application embodiment also provides an electronic device 1000, including a first processor 1001, a second memory 1002, and a program or instruction stored in the second memory 1002 that can run on the first processor 1001. When the program or instruction is executed by the first processor 1001, it implements the various processes of the above-described embodiment of the plunger pump anomaly detection method based on simulation and experimental data similarity analysis, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0124] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0125] Figure 11 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application.

[0126] The hardware structure 1100 of the electronic device includes, but is not limited to, the following components: radio frequency unit 1101, network module 1102, audio output unit 1103, input unit 1104, sensor 1105, display unit 1106, user input unit 1107, interface unit 1108, second memory 1109, and second processor 1110.

[0127] Those skilled in the art will understand that the hardware structure 1100 of the electronic device may also include a power supply (such as a battery) for supplying power to various components. The power supply can be logically connected to the second processor 1110 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 11 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0128] It should be understood that, in this embodiment, the input unit 1104 may include a graphics processing unit (GPU) 11041 and a microphone 11042. The GPU 11041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1106 may include a display panel 11061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1107 includes a touch panel 11071 and other input devices 11072. The touch panel 11071 is also called a touch screen. The touch panel 11071 may include a touch detection device and a touch controller. Other input devices 11072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here. The second memory 1109 can be used to store software programs and various data, including but not limited to applications and operating systems. The second processor 1110 can integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the second processor 1110.

[0129] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described embodiment of the plunger pump anomaly detection method based on simulation and experimental data similarity analysis, and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0130] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0131] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described embodiment of the plunger pump anomaly detection method based on simulation and experimental data similarity analysis, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0132] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0133] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0134] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0135] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for detecting anomalies in a plunger pump based on similarity analysis of simulation and experimental data, characterized in that, include: The ideal waveform of the monitoring plunger pump outlet pressure signal is generated by simulation to obtain the standard reference signal; The outlet pressure signal of the plunger pump under healthy conditions was collected to obtain the measured healthy signal; The modal distance of the weighted graph similarity matrix between the measured health signal and the standard reference signal is calculated to obtain a similarity index; and an alarm threshold is determined based on the similarity index. The pressure signal at the outlet of the plunger pump under test is monitored to obtain the signal to be detected; and the similarity between the signal to be detected and the standard reference signal is calculated. When the similarity is lower than the alarm threshold in a continuous number of target detections, it is determined that the plunger pump under test is malfunctioning.

2. The plunger pump anomaly detection method based on simulation and experimental data similarity analysis according to claim 1, characterized in that, The process of acquiring the plunger pump outlet pressure signal under healthy conditions to obtain the measured healthy signal includes: A pressure sensor is installed in the hydraulic line at the outlet end of the piston pump in a healthy state to collect the pressure signal of the piston pump in the healthy state; the hydraulic line is a rigid pipe. The pressure signal is converted into a digital signal by an AD converter to obtain the measured health signal.

3. The plunger pump anomaly detection method based on simulation and experimental data similarity analysis according to claim 2, characterized in that, The sampling frequency of the pressure sensor satisfies the following formula: f s ≥10nm / 60 Among them, f s is the sampling frequency; n is the piston pump speed in rpm; m is the number of pistons.

4. The plunger pump anomaly detection method based on simulation and experimental data similarity analysis according to claim 3, characterized in that, After installing a pressure sensor at the outlet end of the piston pump in a healthy state within the hydraulic pipeline to collect the pressure signal of the piston pump in the healthy state, the piston pump anomaly detection method based on simulation and experimental data similarity analysis further includes: The pressure signal was resampled to 360 points / revolution using interpolation, and a 400-unit length was used as the pressure signal sample.

5. The plunger pump anomaly detection method based on simulation and experimental data similarity analysis according to claim 1, characterized in that, The calculation of the modal distance of the weighted graph similarity matrix between the measured health signal and the standard reference signal to obtain a similarity index includes: The pressure signal sample of the measured health signal is extracted using the sliding window method. The similarity between the pressure signal sample and the standard reference signal is calculated, and the sample with the maximum similarity is taken as the aligned sample. Based on graph similarity theory, the standard reference signal and the aligned sample are respectively used to generate corresponding adjacency matrix graphs; Construct a weighted matrix graph with the same size as the adjacency matrix graph, and use the Hadamard product of the weighted matrix graph and the adjacency matrix graph as its weighted graph similarity matrix; The distance between the weighted graph similarity matrices is used as a similarity measure between the measured health signal and the standard reference signal to obtain a similarity index.

6. The plunger pump anomaly detection method based on simulation and experimental data similarity analysis according to claim 5, characterized in that, The sample length truncated by the sliding window method is 360 to ensure that the truncated sample length is consistent with the standard reference signal. The sliding window step size is 1, and the maximum offset distance is 40.

7. The plunger pump anomaly detection method based on simulation and experimental data similarity analysis according to claim 6, characterized in that, The offset phase when the pressure signal sample is aligned with the standard reference signal is calculated using the following formula: x align =argmax S(G(s),G(w(x))) Where, x align For the aligned pressure signal samples, s is the standard reference signal, x is the pressure signal sample, w(·) is the window function, G is the mapping function from the input signal to the weighted graph similarity matrix, and S represents the calculation of similarity.

8. A plunger pump anomaly detection device based on simulation and experimental data similarity analysis, characterized in that, include: The signal acquisition module is used to simulate and generate an ideal waveform for monitoring the outlet pressure signal of the plunger pump, and obtain a standard reference signal. The outlet pressure signal of the plunger pump under healthy conditions was collected to obtain the measured healthy signal; The calculation module is used to calculate the modal distance of the weighted graph similarity matrix between the measured health signal and the standard reference signal to obtain a similarity index; and to determine the alarm threshold based on the similarity index. The monitoring module is used to monitor the pressure signal at the outlet of the plunger pump under test, obtain the signal to be detected, and calculate the similarity between the signal to be detected and the standard reference signal. The determination module is used to determine that the plunger pump under test is malfunctioning when the similarity is lower than the alarm threshold in a number of consecutive target measurements.

9. An electronic device, characterized in that, include: A processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the plunger pump anomaly detection method based on simulation and experimental data similarity analysis as described in any one of claims 1-7.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions, which, when executed by a processor, implement the steps of the plunger pump anomaly detection method based on simulation and experimental data similarity analysis as described in any one of claims 1-7.

Images