Fault detection method and apparatus for reciprocating plunger pump
By constructing a slider wear mechanism and dynamic model and combining it with real-time monitoring data, a digital twin model is established for fault detection. This solves the problems of low detection accuracy and insufficient interpretability in existing technologies, and realizes accurate quantification of the slider wear process and fault early warning.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- BEIJING TIANMA INTELLIGENT CONTROL TECHNOLOGY CO LTD
- Filing Date
- 2025-01-15
- Publication Date
- 2026-06-18
AI Technical Summary
In the existing technology, the fault detection of reciprocating piston pumps relies on measurement data, lacks guidance on fault mechanisms, and cannot accurately describe the wear evolution process of the slider, resulting in low detection accuracy and insufficient interpretability.
A slider wear mechanism model and a dynamic model are constructed, and a digital twin model is established. The model is dynamically calibrated by real-time monitoring of health status information to form a slider health monitoring model, thereby realizing fault detection and early warning.
It improves the accuracy and interpretability of fault detection, enabling a more comprehensive and precise reflection of the wear process throughout the slider's life cycle, and providing quantitative maintenance decisions.
Smart Images
Figure CN2025072448_18062026_PF_FP_ABST
Abstract
Description
A method and apparatus for fault detection of a reciprocating piston pump Technical Field
[0001] This application relates to the field of fault detection technology for reciprocating piston pumps, specifically to a fault detection method and apparatus for reciprocating piston pumps. Background Technology
[0002] Reciprocating piston pumps are core equipment in the hydraulic supply system of fully mechanized mining faces, providing hydraulic power to the hydraulic supports and serving as the power source for the entire hydraulic system. Slide wear and erosion are typical faults of piston pumps. If not detected and addressed promptly, they will lead to unplanned shutdowns of the reciprocating piston pump, affecting safe and efficient coal mine production. Therefore, condition monitoring and early fault diagnosis of the reciprocating piston pump slide are of great significance.
[0003] Currently, the monitoring and fault diagnosis of slider conditions mainly rely on crankcase oil temperature data or data collection from vibration sensors mounted on the crankcase surface. Meanwhile, slider wear fault detection models categorize slider wear into different levels, such as slight, moderate, severe, and extreme wear, and then classify them based on data analysis to ultimately determine the slider wear state. Clearly, data is a crucial foundation for establishing slider wear fault detection models. In addition to collecting data under normal slider conditions, it is also necessary to collect data under different wear states, such as slight, moderate, severe, and extreme wear. Based on this data, and combined with signal analysis and artificial intelligence models, the fault detection model can be trained and deployed to achieve intelligent identification of slider wear faults.
[0004] However, the above-mentioned technical solutions rely entirely on measured data. On the one hand, while data-driven fault detection models can accurately classify slider wear faults, they lack guidance on fault mechanisms, resulting in insufficient interpretability. On the other hand, because it is difficult to collect complete state data throughout the slider's entire lifecycle, data-driven fault detection models cannot accurately describe the slider's working state and the complete performance degradation process from normal to slight wear to ablation. They cannot provide an intuitive, gradual slider wear evolution process, thus failing to offer equipment managers a strong basis for maintenance. Summary of the Invention
[0005] This application aims to provide a fault detection method and apparatus for reciprocating piston pumps, in order to solve the technical problems in the prior art where fault detection of reciprocating piston pumps relies entirely on measurement data, the fault detection model cannot accurately describe the wear evolution process of the slider, the accuracy is low, and the interpretability of the fault detection model is insufficient.
[0006] To address the aforementioned technical problems, this application provides a fault detection method for a reciprocating piston pump, comprising:
[0007] Construct a slider wear mechanism model for a reciprocating piston pump slider;
[0008] Construct a dynamic model for the local wear propagation of the slider;
[0009] Based on the slider wear mechanism model and the dynamic model, a digital twin model mapping the slider's full life cycle wear is constructed;
[0010] The digital twin model is dynamically calibrated by monitoring the health status information of the slider in real time to obtain a slider health monitoring model.
[0011] The slider health monitoring model is used to detect and warn of slider wear in reciprocating piston pumps.
[0012] In some embodiments, constructing a slider wear mechanism model includes:
[0013] Friction and wear tests were conducted on the slider friction pair material under different sliding speeds and loads to obtain the friction coefficient of the slider friction pair under different working conditions of the reciprocating plunger pump.
[0014] Based on the friction coefficients of the slider friction pair under different working conditions, a slider wear mechanism model is constructed based on the Arcard wear theory.
[0015] In some embodiments, the formula for the slider wear mechanism model is:
[0016] In the formula, h is the wear depth; K is the friction coefficient, obtained through friction and wear tests of the slider friction pair; H is the material hardness; p is the contact pressure; v is the relative sliding speed; m is the pressure index; and n is the speed index.
[0017] In some embodiments, a dynamic model for the local wear propagation of the slider is constructed, including:
[0018] The correlation between slider wear and housing vibration is established based on Hertzian contact theory;
[0019] A dynamic model for the local wear propagation of the slider is constructed based on the correlation between slider wear and housing vibration.
[0020] In some embodiments, the formula for calculating the slider deformation and the applied load in the correlation between slider wear and housing vibration is: F=Kδ n
[0021] In the formula, F is the Hertzian contact force; K is the total contact stiffness; δ is the contact deformation; and n is the load deformation coefficient.
[0022] In some embodiments, the displacement excitation during the propagation process of localized wear of the slider is represented as:
[0023] In the formula, M represents the mass of the slider; C represents the damping ratio; K represents the stiffness; F represents the excitation force; and y represents the displacement. The first derivative represents the displacement; It represents the second derivative of the displacement.
[0024] In some embodiments, a digital twin model mapping the full lifecycle wear of the slider is constructed based on the slider wear mechanism model and the dynamic model, including:
[0025] Based on the operating data of the reciprocating piston pump and the slider wear mechanism model, the correlation between wear depth and load is obtained;
[0026] The load is input into the dynamic model, and the simulated vibration signal and its characteristic trend corresponding to the wear size of the slider throughout its entire life cycle are calculated iteratively.
[0027] The simulated vibration signal and its characteristic trends are processed using a long short-term memory network to construct a mapping model between slider wear and vibration characteristics.
[0028] In some embodiments, the digital twin model is dynamically calibrated using real-time monitored slider health status information to obtain a slider health monitoring model, including:
[0029] The position of the slider is consistent with the position of the box that generates simulated vibration signals in the dynamic model, and the health status information of the slider is obtained in real time through a monitoring device set on the actual box.
[0030] The digital twin model is dynamically calibrated based on the health status information.
[0031] In some embodiments, dynamically calibrating the digital twin model based on the health status information includes:
[0032] The acquired measured signal is filtered and denoised to obtain the vibration signal segment corresponding to the crankshaft phase;
[0033] Extract the first energy feature of the vibration signal segment;
[0034] Acquire state data of the slider under different wear levels, and extract a second energy feature from the state data;
[0035] The digital twin model is dynamically calibrated based on the first energy characteristic and the second energy characteristic.
[0036] This application also provides a fault detection device for a reciprocating piston pump, comprising:
[0037] The first building module is configured to build a slider wear mechanism model for a reciprocating piston pump slider;
[0038] The second building module is configured to build a dynamic model of local wear propagation on the slider;
[0039] The third construction module is configured to construct a digital twin model that maps the wear of the slider throughout its entire life cycle, based on the slider wear mechanism model and the dynamic model.
[0040] The calibration module is configured to dynamically calibrate the digital twin model using real-time monitored health status information of the slider, thereby obtaining a slider health monitoring model.
[0041] The fault detection module is configured to perform fault detection and early warning of slider wear in the reciprocating piston pump through the slider health monitoring model.
[0042] This application also provides an electronic device, which includes at least a memory and a processor. The memory stores a computer program, and the processor executes the computer program in the memory to implement the steps of the above-described fault detection method for a reciprocating piston pump.
[0043] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described fault detection method for a reciprocating piston pump.
[0044] The fault detection method and apparatus for a reciprocating piston pump provided in this application constructs a slider wear mechanism model for the reciprocating piston pump slider; constructs a dynamic model of local wear propagation of the slider; constructs a digital twin model mapping the slider's full life-cycle wear based on the slider wear mechanism model and the dynamic model; dynamically calibrates the digital twin model using real-time monitored slider health status information to obtain a slider health monitoring model; and performs fault detection and early warning for slider wear in the reciprocating piston pump using the slider health monitoring model, enabling the correlation and mapping between the real-time simulated slider wear mechanism model and the real-time monitored vibration data. A digital twin model of the slider of a reciprocating piston pump, driven by mechanism and data fusion, is constructed for slider wear fault detection. Compared with the existing fuzzy classification of slider wear degree, the constructed slider health monitoring model can more comprehensively and accurately reflect the wear process of the slider throughout its entire life cycle, accurately quantify the wear degree of slider wear fault detection, provide quantitative and accurate results data for equipment management, improve the accuracy of fault detection, and thus provide more reasonable and accurate maintenance decisions. In addition, compared with the insufficient interpretability of data-driven fault detection models, the slider health monitoring model constructed in this application is based on slider wear mechanism model, dynamic model, etc., and has good interpretability. Attached Figure Description
[0045] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0046] Figure 1 is a flowchart of a fault detection method for a reciprocating piston pump according to an embodiment of this application;
[0047] Figure 2 is a schematic diagram of the structure of the fault detection device for the reciprocating piston pump according to an embodiment of this application. Detailed Implementation
[0048] Various embodiments and features of this application are described herein with reference to the accompanying drawings.
[0049] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope and spirit of this application will be apparent to those skilled in the art.
[0050] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.
[0051] These and other features of this application will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.
[0052] It should also be understood that although this application has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of this application, which have the features described in the claims and are therefore all within the scope of protection defined herein.
[0053] The above and other aspects, features and advantages of this application will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.
[0054] Specific embodiments of this application are described thereafter with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of this application, which can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the application. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but merely serve as the basis and representative basis for the claims to teach those skilled in the art to use this application in a variety of substantially any suitable detailed structures.
[0055] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in other embodiments,” all of which may refer to one or more of the same or different embodiments according to this application.
[0056] Figure 1 shows a flowchart of a fault detection method for a reciprocating piston pump according to an embodiment of this application. As shown in Figure 1, a first embodiment of this application provides a fault detection method for a reciprocating piston pump, including:
[0057] S101: Construct a slider wear mechanism model for a reciprocating piston pump slider.
[0058] Reciprocating piston pumps are important components of hydraulic systems, mainly consisting of a drive mechanism (e.g., a motor), a crankshaft connecting rod mechanism, and pistons. The reciprocating piston pump converts the rotational motion of the drive mechanism into the reciprocating motion of the pistons through the crankshaft connecting rod mechanism, achieving the intake and discharge of liquid. The crankshaft connecting rod mechanism includes a crankshaft, connecting rods, and a slider (crosshead). The slider connects the connecting rods and the pistons and is a crucial component of the piston pump; the rotation of the crankshaft drives the pistons in linear reciprocating motion via the slider. Since slider wear is a typical failure of piston pumps, this embodiment uses slider condition monitoring for fault detection in the reciprocating piston pump.
[0059] First, friction and wear tests were conducted on the slider friction pair material of the reciprocating plunger pump under different sliding speeds and loads using a friction and wear testing machine to obtain the friction coefficient of the slider friction pair under different operating conditions of the reciprocating plunger pump (hereinafter referred to as the plunger pump). Then, using the friction coefficient of the slider friction pair, a mechanism model of slider wear was constructed based on Archard wear theory, as shown in the following formula:
[0060] In the formula: h is the wear depth; K is the friction coefficient, obtained through friction and wear tests of the slider friction pair; H is the material hardness; p is the contact pressure; v is the relative sliding speed; m is the pressure index; and n is the speed index.
[0061] The mechanism model of slider wear is the failure mechanism model of slider wear (or slider damage mechanism model). When the slider fails, the degree of wear is different at different locations. Therefore, the location where the slider is most prone to wear and has the most severe wear is taken as the key location for measuring the degree of slider wear.
[0062] S102: Construct a dynamic model for the local wear propagation of the slider.
[0063] By constructing a dynamic model of the local wear propagation of the slider, the vibration signal of the housing characterizing the slider state can be obtained. The simulated vibration signal of the housing generated by the dynamic model has the same trend and fluctuation as the measured vibration signal. Therefore, vibration characteristic curves corresponding to slider wear under different operating conditions of the plunger pump can be constructed.
[0064] Step S102 specifically includes:
[0065] S1021: Establish the correlation between slider wear and box vibration based on Hertzian contact theory;
[0066] S1022: Construct a dynamic model for the local wear propagation of the slider based on the correlation between slider wear and box vibration.
[0067] In this embodiment, the correlation between slider wear and housing vibration is established based on Hertzian contact theory. The slider deformation and the applied load can be calculated using the following formula: F=Kδ n (2)
[0068] In the formula, F is the Hertzian contact force; K is the total contact stiffness; δ is the contact deformation; and n is the load deformation coefficient.
[0069] The dynamic model based on Hertzian contact theory can more accurately reflect the propagation process of local wear on the slider. The displacement excitation during the propagation process can be represented by a segmentation function, which is specifically expressed as follows:
[0070] In the formula, M represents the mass of the slider; C represents the damping ratio; K represents the stiffness; F represents the excitation force; and y represents the displacement, i.e., the wear depth. The first derivative represents the displacement, i.e., the wear rate; The second derivative of the displacement is represented by the wear acceleration.
[0071] Based on the above formulas (2) and (3), the dynamic model of local wear propagation of the slider can be derived.
[0072] It is understandable that the Hertzian contact force in formula (2) corresponds to the excitation force in formula (3) and is used to represent the vibration of the box. S103: Construct a digital twin model that maps the wear of the slider throughout its entire life cycle based on the slider wear mechanism model and the dynamic model.
[0073] Digital twins fully utilize physical models, sensors, operational history, and other data to integrate multi-disciplinary, multi-physical, multi-scale, and multi-probabilistic simulation processes, mapping these data in a virtual space to reflect the entire lifecycle of the corresponding physical equipment. In this step, a digital twin model mapping the entire lifecycle wear of the reciprocating piston pump is constructed by combining real-time operating data, a real-time simulated slider wear mechanism model, and the dynamic model built in step S102, resulting in an initial slider health monitoring model. The digital twin model can be obtained by training a neural network. Step S103 specifically includes:
[0074] S1031: Based on the operating data of the reciprocating piston pump and the slider wear mechanism model, obtain the correlation between wear depth and load;
[0075] S1032: Input the load into the dynamic model and iteratively calculate the simulated vibration signal and its characteristic trend corresponding to the wear size of the slider throughout its entire life cycle;
[0076] S1033: The simulated vibration signal and its characteristic trend are processed using a long short-term memory network to construct a mapping relationship model between slider wear and vibration characteristics.
[0077] Specifically, the relative sliding speed of the slider can be calculated in real time by measuring the crankshaft speed of the plunger pump. Combined with other parameters and the failure mechanism model of slider wear, the correlation between wear depth and load can be obtained. Substituting the load into the dynamic model of local wear propagation of the slider obtained in step S102, the simulated vibration signal and its characteristic trend corresponding to the wear size (0-10mm, with intervals of 0.1mm) throughout the slider's entire life cycle can be iteratively calculated.
[0078] The wear depth of the slider is a direct representation of the slider's condition. In this step, a mapping model between slider wear and vibration characteristics is established using a long short-term memory network (slider wear-vibration characteristic mapping model). This model obtains a relationship between the wear degree corresponding to the entire life cycle of the slider and the vibration characteristics of the housing, and this relationship is continuous.
[0079] S104: The digital twin model is dynamically calibrated using the real-time monitored health status information of the slider to obtain a slider health monitoring model.
[0080] In this step, the initial slider health monitoring model (the data of the initial health monitoring model is the theoretical data obtained by simulation) obtained by using the slider wear mechanism model of real-time simulation can be associated and mapped with the health status information of the slider obtained by real-time monitoring (such as the vibration monitoring data of actual monitoring). The digital twin model constructed in step S103 is dynamically calibrated to construct a slider health monitoring model driven by the fusion of mechanism and measured data.
[0081] Step S104 specifically includes:
[0082] S1041: The position of the box that generates simulated vibration signals in the dynamic model is kept consistent with the position of the slider, and the health status information of the slider is obtained in real time through a monitoring device set on the actual box.
[0083] S1042: Dynamically calibrate the digital twin model based on the health status information.
[0084] Specifically, vibration acceleration sensors can be installed on the actual housing to monitor the vibration signals of the housing in real time, thereby obtaining the health status information of the slider in real time. This health status information is the measured signal. Then, the real-time monitored health status information is compared and fused with the constructed initial slider health monitoring model to obtain a more accurate slider health monitoring model.
[0085] Step S1042 specifically includes:
[0086] S201: Obtain measured vibration data of the slider under different wear levels, and extract energy characteristics from the measured vibration data;
[0087] S204: Dynamically calibrate the digital twin model based on the energy characteristics.
[0088] In this step, the state data of the slider under different wear levels can be monitored in real time to obtain the measured vibration state data of the slider. For example, the measured vibration state data of the slider under different wear levels such as slight, moderate, heavy, and severe can be obtained. The slider wear-vibration characteristic mapping model obtained in step S103 is a continuous curve or straight line. The slider wear depth corresponding to the measured vibration state data can be obtained from the slider wear-vibration characteristic mapping model. The slider wear depth in the model is compared with the slider wear degree corresponding to the measured vibration state data. If the slider wear depth in the model falls within the range of the slider wear degree corresponding to the measured vibration state data, or if the slider wear depth in the model deviates relatively close to the slider wear degree corresponding to the measured vibration state data, the model is considered accurate and requires no calibration, or only minor adjustments. However, if the slider wear depth in the model does not fall within the range of the slider wear degree corresponding to the measured vibration state data, or if the slider wear depth in the model deviates significantly from the slider wear degree corresponding to the measured vibration state data, the measured vibration state data is input into the digital twin model for dynamic calibration training, resulting in a more accurate slider health monitoring model that integrates the slider wear mechanism and the measured data.
[0089] Optionally, step S201 specifically includes:
[0090] S2011: Filter and denoise the acquired measured vibration state data to obtain vibration signal segments corresponding to the crankshaft phase;
[0091] S2012: Extract the energy characteristics of the vibration signal segment. After filtering and denoising the measured signal, obtain the vibration signal segment corresponding to the crankshaft phase, acquire its energy characteristics, and dynamically calibrate the digital twin model to obtain a slider health monitoring model that can characterize the mechanism of slider wear throughout its entire life cycle and is driven by data fusion.
[0092] As shown above, in this embodiment, through steps S101 to S103, a mechanism model of slider wear is constructed based on Arcard wear theory, the correlation between slider wear and housing vibration is established based on Hertzian contact theory, and a mapping relationship model between slider wear and vibration characteristics is established using a long short-term memory network. This yields a model that characterizes the relationship between the wear degree and housing vibration characteristics throughout the slider's entire lifespan, resulting in an initial slider health monitoring model characterizing the slider's lifespan wear. Then, through step S104, a mechanism- and data-fusion-driven slider health monitoring model characterizing the slider's lifespan wear is obtained. In step S104, the wear-vibration characteristic mapping relationship model for the slider's entire lifespan is dynamically calibrated and updated using measured sensor data, making the model used for slider wear fault detection more accurate.
[0093] It is understood that in this embodiment, the health status information of the slider is the slider's vibration data. In other embodiments, the slider's health status information may also include the slider's mass, the pressure, temperature, and flow rate of the environment in which the slider is located, thereby enabling more comprehensive monitoring of the slider's health status. For example, at higher temperatures, slider wear accelerates; therefore, the digital twin model can be dynamically calibrated based on measured vibration data within the same temperature range to obtain a more accurate slider health monitoring model.
[0094] S105: The wear of the reciprocating piston pump slider is detected and faults are identified using the slider health monitoring model.
[0095] In this step, during the operation of the reciprocating piston pump, the health status information of the slider can be acquired in real time through monitoring devices such as sensors installed in the housing. This information is then input into the slider health monitoring model to monitor slider wear in real time, determine whether a fault has occurred, and issue corresponding fault warnings if a fault occurs. On the one hand, by combining the operating data of the reciprocating piston pump, the slider wear mechanism model can be dynamically simulated in real time, and the mapping relationship model can be dynamically updated to match the current operating conditions, resulting in a more accurate slider health monitoring model. On the other hand, the real-time monitored slider health status information is input into the slider health monitoring model, and the wear degree of the slider is calculated based on the real-time monitored vibration signals. This provides direct data support for the health management of the reciprocating piston pump. When the calculated slider wear reaches a certain level, an early warning signal is issued, prompting the user to arrange maintenance work as soon as possible to avoid the piston pump malfunctioning and to prevent safety accidents.
[0096] The fault detection method for a reciprocating piston pump provided in this application involves constructing a slider wear mechanism model for the reciprocating piston pump slider; constructing a dynamic model of local wear propagation of the slider; constructing a digital twin model mapping the slider's full life-cycle wear based on the slider wear mechanism model and the dynamic model; dynamically calibrating the digital twin model using real-time monitored slider health status information to obtain a slider health monitoring model; and using the slider health monitoring model to perform fault detection and early warning for slider wear in the reciprocating piston pump. This method can correlate and map the real-time simulated slider wear mechanism model with real-time monitored vibration data to form a... A digital twin model of the slider of a reciprocating piston pump, driven by mechanism and data fusion, is used for slider wear fault detection. Compared with the existing fuzzy classification of slider wear degree, the constructed slider health monitoring model can more comprehensively and accurately reflect the wear process of the slider throughout its entire life cycle. It can accurately quantify the wear degree of slider wear fault detection, provide quantitative and accurate results data for equipment management, improve the accuracy of fault detection, and thus provide more reasonable and accurate maintenance decisions. In addition, compared with the insufficient interpretability of data-driven fault detection models, the slider health monitoring model constructed in this application is based on slider wear mechanism model, dynamic model, etc., and has good interpretability.
[0097] Figure 2 shows a schematic diagram of the structure of a fault detection device for a reciprocating piston pump according to an embodiment of this application. As shown in Figure 2, a second embodiment of this application provides a fault detection device for a reciprocating piston pump, comprising:
[0098] The first construction module 10 is configured to construct a slider wear mechanism model for a reciprocating piston pump slider;
[0099] The second building module 20 is configured to build a dynamic model of local wear propagation of the slider;
[0100] The third construction module 30 is configured to construct a digital twin model that maps the wear of the slider throughout its entire life cycle based on the slider wear mechanism model and the dynamic model.
[0101] The calibration module 40 is configured to dynamically calibrate the digital twin model using real-time monitored health status information of the slider to obtain a slider health monitoring model.
[0102] The fault detection module 50 is configured to perform fault detection and fault warning for the wear of the slider of the reciprocating plunger pump through the slider health monitoring model.
[0103] In some embodiments, the first building module 10 is further configured as follows:
[0104] Friction and wear tests were conducted on the slider friction pair material under different sliding speeds and loads to obtain the friction coefficient of the slider friction pair under different working conditions of the reciprocating plunger pump.
[0105] Based on the friction coefficients of the slider friction pair under different working conditions, a slider wear mechanism model is constructed based on the Arcard wear theory.
[0106] In some embodiments, the formula for the slider wear mechanism model is:
[0107] In the formula, h is the wear depth; K is the friction coefficient, obtained through friction and wear tests of the slider friction pair; H is the material hardness; p is the contact pressure; v is the relative sliding speed; m is the pressure index; and n is the speed index.
[0108] In some embodiments, the second building module 20 is further configured to:
[0109] The correlation between slider wear and housing vibration is established based on Hertzian contact theory;
[0110] A dynamic model for the local wear propagation of the slider is constructed based on the correlation between slider wear and housing vibration.
[0111] In some embodiments, the formula for calculating the slider deformation and the applied load in the correlation between slider wear and housing vibration is: F=Kδ n
[0112] In the formula, F is the Hertzian contact force; K is the total contact stiffness; δ is the contact deformation; and n is the load deformation coefficient.
[0113] In some embodiments, the displacement excitation during the propagation process of localized wear of the slider is represented as:
[0114] In the formula, M represents the mass of the slider; C represents the damping ratio; K represents the stiffness; F represents the excitation force; and y represents the displacement. The first derivative represents the displacement; It represents the second derivative of the displacement.
[0115] In some embodiments, the third building module 30 is further configured as follows:
[0116] Based on the operating data of the reciprocating piston pump and the slider wear mechanism model, the correlation between wear depth and load is obtained;
[0117] The load is input into the dynamic model, and the simulated vibration signal and its characteristic trend corresponding to the wear size of the slider throughout its entire life cycle are calculated iteratively.
[0118] The simulated vibration signal and its characteristic trends are processed using a long short-term memory network to construct a mapping model between slider wear and vibration characteristics.
[0119] In some embodiments, the calibration module 40 is further configured to:
[0120] The position of the slider is consistent with the position of the box that generates simulated vibration signals in the dynamic model, and the health status information of the slider is obtained in real time through a monitoring device set on the actual box.
[0121] The digital twin model is dynamically calibrated based on the health status information.
[0122] In some embodiments, the calibration module 40 is further configured to:
[0123] Acquire measured vibration data of the slider under different wear levels, and extract energy features from the measured vibration data;
[0124] The digital twin model is dynamically calibrated based on the energy characteristics.
[0125] The aforementioned reciprocating piston pump fault detection device corresponds to the reciprocating piston pump fault detection method in the above embodiments. Therefore, based on the aforementioned reciprocating piston pump fault detection method, those skilled in the art can understand the specific implementation methods and various variations of the reciprocating piston pump fault detection device in this application. The reciprocating piston pump fault detection device will not be described in detail here. Any reciprocating piston pump fault detection device that implements the reciprocating piston pump fault detection method in this application falls within the scope of protection of this application.
[0126] The third embodiment of this application provides an electronic device, including at least a memory and a processor. The memory stores a computer program, and the processor, when executing the computer program in the memory, implements the steps of the above-described fault detection method for a reciprocating piston pump.
[0127] In some embodiments, the processor executing a computer program may be a processing device that includes one or more general-purpose processing devices, such as a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), etc. More specifically, the processor may be a Complex Instruction Set Computing (CISC) microprocessor, a Reduced Instruction Set Computing (RISC) microprocessor, a Very Long Instruction Word (VLIW) microprocessor, a processor that runs other instruction sets, or a processor that runs a combination of instruction sets. The processor may also be one or more special-purpose processing devices, such as an Application-Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), a System-on-a-Chip (SoC), etc.
[0128] The memory may be a read-only memory (ROM), random access memory (RAM), phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), electrically erasable programmable read-only memory (EEPROM), other types of random access memory (RAM), flash drives or other forms of flash memory, cache, registers, static memory, optical disc read-only memory (CD-ROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape cassette or other magnetic storage device, or any other possible non-transitory medium used to store information or instructions that can be accessed by computer equipment.
[0129] The electronic devices in this application embodiment may include, but are not limited to, fixed terminal devices such as servers, desktop computers, and digital TVs, as well as mobile terminal devices such as in-vehicle devices (e.g., head-up displays), handheld devices (e.g., mobile phones, tablets, etc.), and wearable devices (e.g., smartwatches, smart bracelets, etc.).
[0130] Electronic devices may include more or fewer components, such as wireless communication interfaces, or combinations of certain components, or different arrangements of components.
[0131] The fourth embodiment of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described fault detection method for a reciprocating piston pump.
[0132] The computer-readable storage medium of this application embodiment may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.
[0133] In this application embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, the computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.
[0134] The computer programs of embodiments of this application can be organized into one or more computer-executable components or modules. Various aspects of this application can be implemented with any number and combination of such components or modules. For example, aspects of this application are not limited to the specific computer-executable instructions or specific components or modules shown in the drawings and described herein. Other embodiments may include different computer-executable instructions or components having more or fewer functions than those shown and described herein.
[0135] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0136] Those skilled in the art will recognize that the modules and algorithm steps of the various examples of energy harvesting devices described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0137] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0138] Furthermore, the features of the embodiments shown in the accompanying drawings or the various embodiments mentioned in this specification should not be construed as independent embodiments. Rather, each feature described in one example of an embodiment can be combined with one or more other desired features from other embodiments to produce other embodiments not described in words or with reference to the accompanying drawings.
[0139] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.
Claims
1. A fault detection method for a reciprocating piston pump, characterized in that, include: Construct a slider wear mechanism model for a reciprocating piston pump slider; Construct a dynamic model for the local wear propagation of the slider; Based on the slider wear mechanism model and the dynamic model, a digital twin model mapping the slider's full life cycle wear is constructed; The digital twin model is dynamically calibrated by monitoring the health status information of the slider in real time to obtain a slider health monitoring model. The slider health monitoring model is used to detect and warn of slider wear in reciprocating piston pumps.
2. The method according to claim 1, characterized in that, A model of the slider wear mechanism in a reciprocating piston pump is constructed, including: Friction and wear tests were conducted on the slider friction pair material under different sliding speeds and loads to obtain the friction coefficient of the slider friction pair under different working conditions of the reciprocating plunger pump. Based on the friction coefficients of the slider friction pair under different working conditions, a slider wear mechanism model is constructed based on the Arcard wear theory.
3. The method according to claim 2, characterized in that, The formula for the slider wear mechanism model is: In the formula, h is the wear depth; K is the friction coefficient, obtained through friction and wear tests of the slider friction pair; H is the material hardness; p is the contact pressure; v is the relative sliding speed; m is the pressure index; and n is the speed index.
4. The method according to claim 1, characterized in that, Construct a dynamic model for the local wear propagation of the slider, including: The correlation between slider wear and housing vibration is established based on Hertzian contact theory; A dynamic model for the local wear propagation of the slider is constructed based on the correlation between slider wear and housing vibration.
5. The method according to claim 4, characterized in that, In the correlation between slider wear and housing vibration, the formula for calculating slider deformation and the applied load is: F=Kδ n In the formula, F is the Hertzian contact force; K is the total contact stiffness; δ is the contact deformation; and n is the load deformation coefficient.
6. The method according to claim 4, characterized in that, The displacement excitation during the propagation process of local wear on the slider is expressed as: In the formula, M represents the mass of the slider; C represents the damping ratio; K represents the stiffness; F represents the excitation force; and y represents the displacement. The first derivative represents the displacement; It represents the second derivative of the displacement.
7. The method according to claim 1, characterized in that, Based on the slider wear mechanism model and the dynamic model, a digital twin model mapping the slider's full life-cycle wear is constructed, including: Based on the operating data of the reciprocating piston pump and the slider wear mechanism model, the correlation between wear depth and load is obtained; The load is input into the dynamic model, and the simulated vibration signal and its characteristic trend corresponding to the wear size of the slider throughout its entire life cycle are calculated iteratively. The simulated vibration signal and its characteristic trends are processed using a long short-term memory network to construct a mapping model between slider wear and vibration characteristics.
8. The method according to claim 1, characterized in that, The digital twin model is dynamically calibrated using real-time monitored slider health status information to obtain a slider health monitoring model, including: The position of the slider is consistent with the position of the box that generates simulated vibration signals in the dynamic model, and the health status information of the slider is obtained in real time through a monitoring device set on the actual box. The digital twin model is dynamically calibrated based on the health status information.
9. The method according to claim 8, characterized in that, Dynamically calibrating the digital twin model based on the health status information includes: Acquire measured vibration data of the slider under different wear levels, and extract energy features from the measured vibration data; The digital twin model is dynamically calibrated based on the energy characteristics.
10. A fault detection device for a reciprocating piston pump, characterized in that, include: The first building module is configured to build a slider wear mechanism model for a reciprocating piston pump slider; The second building module is configured to build a dynamic model of local wear propagation on the slider; The third construction module is configured to construct a digital twin model that maps the wear of the slider throughout its entire life cycle, based on the slider wear mechanism model and the dynamic model. The calibration module is configured to dynamically calibrate the digital twin model using real-time monitored health status information of the slider, thereby obtaining a slider health monitoring model. The fault detection module is configured to perform fault detection and early warning of slider wear in the reciprocating piston pump through the slider health monitoring model.