Centrifugal pump operation fault detection method, device and equipment and storage medium

Abstract

The invention relates to a centrifugal pump operation fault detection method, device and equipment and a storage medium, the operation state of a centrifugal pump mechanical seal can be continuously monitored in real time by collecting acoustic emission signals at a mechanical seal cavity, the problem of monitoring interruption caused by the fact that manual inspection depends on regular inspection is solved, and the detection efficiency is improved. And the state change in the operation process of the sealing surface can be comprehensively captured. According to the method, the operation state is judged based on the frequency spectrum characteristic change of the acoustic emission signal, potential problems can be recognized when early faults occur in the mechanical seal, and compared with a traditional method which can only give an alarm after medium leakage, early warning can be conducted in advance, leakage accidents can be prevented, and the operation safety of equipment is remarkably improved. According to the method, the potential fault mode can be identified while the operation state is judged, a clear fault reason direction is provided for operation and maintenance personnel, a targeted maintenance strategy can be quickly formulated, the non-planned downtime is shortened, and the economic loss is reduced.

Description

Technical Field

[0001] This invention relates to the field of centrifugal pump fault detection technology, and in particular to a method, apparatus, equipment, and storage medium for detecting centrifugal pump operation faults. Background Technology

[0002] Centrifugal pumps are crucial fluid transport equipment in industries such as petroleum, chemical, and metallurgy, and their operational reliability directly affects the safety and stability of the entire production unit. Mechanical seals are one of the core components of centrifugal pumps, and their performance determines whether the pump will experience media leakage. When handling hazardous media (such as liquefied gas, light hydrocarbons, and toxic chemicals), mechanical seal failure not only causes unplanned downtime and significant economic losses but also leads to media leakage, causing serious safety accidents such as environmental pollution, personnel poisoning, and even fires and explosions.

[0003] Currently, the industry generally uses manual periodic inspections or leak detection methods for detecting and warning of operational faults in centrifugal pump mechanical seals.

[0004] Among them, the manual periodic inspection method relies on the subjective judgment of maintenance personnel, which requires a high level of experience from maintenance personnel, lacks accuracy, cannot achieve continuous monitoring, and is not sensitive to early faults. It is usually only discovered when the leak is already very obvious, which is too late and cannot effectively prevent accidents from happening.

[0005] Leak detection methods typically involve installing combustible or toxic gas detectors near the sealed cavity. However, this method only triggers an alarm when the medium has already leaked into the atmosphere, making it a reactive measure rather than a preventative measure for early warning of potential malfunctions. Summary of the Invention

[0006] Based on this, the present invention provides a method, device, equipment and storage medium for detecting centrifugal pump operation faults, with the aim of continuously detecting centrifugal pumps, providing fault early warning and automatically determining the cause of faults.

[0007] Firstly, the technical solution of the present invention is implemented as follows:

[0008] A method for detecting operational faults in a centrifugal pump, the method comprising:

[0009] Acoustic emission signals were collected from the mechanical seal cavity of the centrifugal pump.

[0010] The acoustic emission signal is processed to extract its spectral features;

[0011] Based on the changes in the spectral characteristics, the operating status of the sealing surface is determined, and potential fault modes are identified.

[0012] Based on the operating status and the fault mode, an alarm signal is output.

[0013] Furthermore, the operating states include abrasive wear on the sealing surface, abnormal friction on the sealing surface, and thermal stress crack propagation on the sealing surface.

[0014] Furthermore, the failure modes include the presence of particulate matter in the medium and abnormal specific pressure at the sealing surface.

[0015] Furthermore, the processing of the acoustic emission signal to extract its spectral features specifically includes:

[0016] The acoustic emission signal is converted from time to frequency to obtain spectrum data;

[0017] Calculate a first energy value for a preset high-frequency band and a second energy value for a preset low-frequency band from the spectrum data;

[0018] Based on the first energy value and the second energy value, a spectrum energy distribution ratio is calculated;

[0019] The spectral characteristics include the spectral energy distribution ratio.

[0020] Furthermore, the processing of the acoustic emission signal to extract its spectral features further includes:

[0021] Identify the signal type from the acoustic emission signal as either burst-type or continuous-type.

[0022] Furthermore, the step of determining the operating status of the mechanical seal and identifying potential failure modes based on the changes in the spectral characteristics specifically includes:

[0023] If the signal type is identified as burst type, and the current spectral energy distribution ratio is consistently and significantly higher than the preset health status baseline ratio, then the operating status is determined to be abrasive wear of the sealing surface, and the fault mode is that the medium contains particulate matter.

[0024] If the signal type is identified as continuous and the total energy level of the acoustic emission signal continues to rise, the operating state is determined to be abnormal friction of the sealing surface, and the fault mode is abnormal sealing surface specific pressure.

[0025] If the signal type is identified as continuous and intermittent energy spikes are detected in the low-frequency band from the spectrum data, the operating state is determined to be thermal stress crack propagation on the sealing surface, and the fault mode is abnormal sealing surface specific pressure.

[0026] Furthermore, the alarm signal includes operating status information, fault mode information, and solution information.

[0027] Secondly, the technical solution of the present invention is implemented as follows:

[0028] A centrifugal pump operation fault detection device, the device comprising:

[0029] The acquisition module is used to acquire acoustic emission signals from the mechanical seal cavity of the centrifugal pump.

[0030] The processing module is used to process the acoustic emission signal to extract its spectral features;

[0031] The status judgment and fault identification module is used to determine the operating status of the sealing surface and identify potential fault modes based on the changes in the spectrum characteristics.

[0032] The alarm module is used to output alarm signals based on the operating status and the fault mode.

[0033] Thirdly, the technical solution of the present invention is implemented as follows:

[0034] A computer device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of any of the methods described above.

[0035] Fourthly, the technical solution of the present invention is implemented as follows:

[0036] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0037] The technical solution of this application has at least the following advantages over the prior art:

[0038] Achieving continuous monitoring and overcoming the intermittent defects of manual periodic inspections: By collecting acoustic emission signals at the mechanical seal cavity, the operating status of the centrifugal pump mechanical seal can be monitored in real time and continuously, avoiding the monitoring interruption problem caused by manual inspections relying on periodic checks, and comprehensively capturing the state changes of the sealing surface during operation.

[0039] Achieving early fault warning and overcoming the lag of traditional leakage monitoring: This method judges the operating status based on the changes in the spectral characteristics of acoustic emission signals. It can identify potential problems when mechanical seals have early faults (such as abnormal friction of the sealing surface, slight abrasive wear, etc., before media leakage occurs). Compared with the traditional method that can only alarm after media leakage, it can provide early warning and prevent leakage accidents, significantly improving the safety of equipment operation.

[0040] Improving the objectivity and accuracy of fault diagnosis: By analyzing the spectral characteristics of acoustic emission signals and using quantified signal characteristics as the basis for judgment, the judgment bias caused by subjective experience in manual inspection is avoided, the reliance on operator experience is reduced, and the accuracy and reliability of fault detection are improved.

[0041] Automatic fault mode identification facilitates targeted handling: This method can identify potential fault modes while judging the operating status, providing maintenance personnel with clear fault cause indications, which helps to quickly formulate targeted maintenance strategies, reduce unplanned downtime, and reduce economic losses. Attached Figure Description

[0042] Figure 1 This is a flowchart of a centrifugal pump operation fault detection method according to an embodiment of this application;

[0043] Figure 2 This is a structural diagram of a centrifugal pump operation fault detection device according to an embodiment of this application; Detailed Implementation

[0044] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0045] This specific embodiment is merely an explanation of this application and is not intended to limit it. Those skilled in the art, after reading this specification, can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application. To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this application.

[0046] The term "comprising" and any variations thereof in the specification and claims of this application are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product or device.

[0047] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0048] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0049] Figure 1 This application provides an exemplary embodiment of a centrifugal pump operation fault detection method, the method comprising:

[0050] Step S100: Acoustic emission signal at the mechanical seal cavity of the centrifugal pump is collected;

[0051] Specifically, an acoustic emission sensor is installed in the mechanical seal cavity of the centrifugal pump. This sensor can detect acoustic emission signals generated inside the sealing cavity during the operation of the mechanical seal in real time. Acoustic emission signals are transient elastic waves generated within a material due to the rapid release of localized energy, such as stress wave signals generated by physical processes like friction, wear, and crack propagation on the sealing surface of the mechanical seal.

[0052] Step S200: Process the acoustic emission signal to extract its spectral features;

[0053] Step S300: Based on the changes in the spectral characteristics, determine the operating status of the sealing surface and identify potential fault modes;

[0054] The operating states include abrasive wear on the sealing surface, abnormal friction on the sealing surface, and thermal stress crack propagation on the sealing surface.

[0055] The failure modes include the presence of particulate matter in the medium and abnormal specific pressure at the sealing surface.

[0056] Step S400: Output an alarm signal based on the operating status and the fault mode.

[0057] In this embodiment, by collecting acoustic emission signals at the mechanical seal cavity, the operating status of the centrifugal pump mechanical seal can be monitored in real time and continuously, avoiding the monitoring interruption problem caused by manual inspection relying on periodic checks, and comprehensively capturing the state changes of the sealing surface during operation.

[0058] This method determines the operating status based on the changes in the spectral characteristics of acoustic emission signals. It can identify potential problems in the early stages of mechanical seal failure (such as abnormal friction of the sealing surface, slight abrasive wear, etc., before media leakage occurs). Compared with traditional methods that can only alarm after media leakage, it can provide early warning and prevent leakage accidents, significantly improving the safety of equipment operation.

[0059] By analyzing the spectral characteristics of acoustic emission signals and using quantified signal features as the basis for judgment, the bias caused by subjective experience in manual inspection is avoided, the reliance on operator experience is reduced, and the accuracy and reliability of fault detection are improved.

[0060] This method can identify potential failure modes while judging the operating status, providing maintenance personnel with clear indications of the cause of failure, which helps to quickly develop targeted maintenance strategies, reduce unplanned downtime, and reduce economic losses.

[0061] In some embodiments, step S200 specifically includes:

[0062] The acoustic emission signal is converted from time to frequency to obtain spectrum data;

[0063] Calculate the first energy value (E_high) of the preset high frequency band (H) and the second energy value (E_low) of the preset low frequency band (L) from the spectrum data.

[0064] Based on the first energy value and the second energy value, a spectrum energy distribution ratio (R=E_high / E_low) is calculated.

[0065] The spectral characteristics include the spectral energy distribution ratio (R).

[0066] Specifically, during the operation of a centrifugal pump, the dynamic and static rings of the mechanical seal continuously rotate relative to each other. The friction, wear, or particle impact on the sealing surface will generate acoustic emission signals. Through time-frequency conversion, the collected acoustic emission signals are decomposed into signals distributed with frequency, and finally, spectrum data is obtained. Through spectrum data, it is possible to clearly identify which frequencies of vibration signals are stronger and which are weaker during the operation of the centrifugal pump sealing surface. Different faults (such as abrasive wear and abnormal friction) will cause the signal of specific frequencies to be enhanced, which serves as the core basis for subsequent judgment of fault modes.

[0067] For example, when a centrifugal pump is running normally, the friction of the sealing surface is stable, and the time domain signal fluctuates gently. The spectrum data after time-frequency conversion will show that the low-frequency signal is stronger and the high-frequency signal is weaker. When particulate matter is mixed into the medium, causing abrasive wear, the time domain signal will show frequent pulse fluctuations, and the spectrum data will show that the high-frequency signal is significantly enhanced. This is the direct manifestation of the fault in the spectrum.

[0068] The preset high-frequency band (H) is a frequency range pre-set based on the fault mechanism of the centrifugal pump's mechanical seal, primarily used to capture vibration signals related to abrasive wear. When abrasive wear occurs in a centrifugal pump, particles mixed in the medium (such as rust and impurities) will squeeze and impact the sealing surface between the rotating and stationary rings. This instantaneous and intense small-scale collision will cause high-frequency vibrations on the sealing surface. Therefore, the preset high-frequency band is set within a range that can accurately reflect this type of high-frequency vibration, specifically targeting abrasive wear faults. The first energy value (E_high) is the sum of the vibration signal intensities corresponding to all frequencies within the preset high-frequency band (H), which directly reflects the activity level of vibration in this frequency band. When there is no abrasive wear in the centrifugal pump, the high-frequency band vibration is weak, and the first energy value is small; once abrasive wear occurs, the frequency and force of particles impacting the sealing surface increase, the high-frequency band vibration signal strengthens, and the first energy value also increases accordingly. For example, when a centrifugal pump is running normally, the first energy value is only 50 relative intensity units; when the media filter is clogged and particles enter the sealing surface, the first energy value will gradually rise to 200 relative intensity units, which directly reflects the enhancement of high-frequency vibration and indicates that there may be abrasive wear.

[0069] Conversely, the preset low-frequency band (L) is also a frequency range set according to the fault mechanism of the centrifugal pump, used to capture vibration signals related to abnormal friction. When abnormal friction occurs on the sealing surface of the centrifugal pump (such as excessive sealing surface pressure, abnormal spring preload, or poor cooling), the liquid lubrication layer on the sealing surface will fail, and the metal surfaces of the rotating ring and stationary ring will directly and continuously contact and rub against each other. This smooth and continuous large-area contact motion will cause the sealing surface to generate low-frequency vibration. Therefore, the preset low-frequency band is set in a range that can reflect this type of low-frequency vibration, specifically corresponding to abnormal friction faults. The second energy value (E_low) is the sum of the vibration signal intensities corresponding to all frequencies within the preset low-frequency band (L), reflecting the activity level of the low-frequency band vibration. When the centrifugal pump is running normally, the sealing surface is well lubricated, the low-frequency band vibration is stable, and the second energy value is small and stable; if abnormal friction occurs, the continuous dry friction of the sealing surface will increase the low-frequency band vibration, and the second energy value will also rise accordingly. For example, when a centrifugal pump is running normally, the second energy value is 100 relative intensity units; when the sealing surface pressure is abnormal and dry friction occurs, the second energy value will gradually rise to 300 relative intensity units, clearly showing the enhancement of low-frequency vibration, indicating that there may be abnormal friction.

[0070] Furthermore, the spectral energy distribution ratio (R) is used to eliminate interference caused by increased overall equipment vibration. For example, a loose foundation of a centrifugal pump may lead to increased overall vibration. In this case, both the first and second energy values ​​will rise simultaneously. Looking at the magnitudes of the two energy values ​​alone is insufficient to accurately determine which fault is causing the problem. However, the ratio allows us to focus on the relative relationship between high and low frequency vibrations. For instance, when a centrifugal pump is operating normally, the first energy value is 50, the second energy value is 100, and the ratio is 0.5. When abrasive wear occurs, the first energy value rises to 200, the second energy value is 120, and the ratio is approximately 1.67, significantly increasing. When abnormal friction occurs, the first energy value is 60, the second energy value rises to 300, and the ratio is 0.2, significantly decreasing. By observing changes in the ratio, the type of fault can be quickly identified.

[0071] In some embodiments, step S200 further includes:

[0072] Identify the signal type from the acoustic emission signal as either burst-type or continuous-type.

[0073] Among them, burst-type signals are characterized by being pulse-like, brief, and intermittent; continuous-type signals are characterized by being stable, continuous, and without obvious intervals. By identifying the signal type and combining it with the spectral energy ratio, the fault mode can be pinpointed.

[0074] In some embodiments, step S300 includes:

[0075] If the signal type is identified as bursty, and the current spectral energy distribution ratio (R_current) is consistently and significantly higher than the preset health status baseline ratio (R_baseline), then the operating status is determined to be abrasive wear of the sealing surface, and the fault mode is that the medium contains particulate matter.

[0076] Specifically, burst signals correspond to instantaneous impacts. When a centrifugal pump is running, if particulate matter is mixed in the medium, these particles will be carried into the gap between the sealing surfaces as the rotating ring rotates. Under the compression of the rotating and stationary rings, they briefly impact the sealing surface, and each impact generates a pulse-like burst signal. The core of abrasive wear is the high-frequency grinding of the sealing surface by particles, which leads to enhanced high-frequency vibrations, thus significantly increasing the spectral energy distribution ratio.

[0077] Furthermore, the setting of "consistently and significantly higher" is to eliminate occasional signal fluctuations and ensure the reliability of the judgment. For example, when a centrifugal pump is operating normally, the baseline ratio is 0.5. If the signal continuously shows a sudden pattern and the ratio rises to 1.2 and remains stable, it indicates that there is continuous particle impact on the sealing surface. At this time, it can be determined that it is abrasive wear, and the fault is caused by particulate matter in the medium.

[0078] If the signal type is identified as continuous and the total energy level of the acoustic emission signal continues to rise, the operating state is determined to be abnormal friction of the sealing surface, and the fault mode is abnormal sealing surface specific pressure.

[0079] Specifically, a continuous signal corresponds to continuous friction. During normal operation, the centrifugal pump's sealing surface relies on a liquid lubrication layer to isolate the dynamic and static rings, resulting in slight and stable friction and low total energy. However, if the sealing surface pressure is abnormal, it damages the lubrication layer, leading to direct metal-to-metal contact and continuous friction, generating a stable and continuous vibration signal (continuous type). As the friction time increases, the sealing surface temperature rises, friction intensifies, and the total vibration energy continues to rise. For example, if the total energy of the centrifugal pump is stable at 100 units in the initial stage of operation, and the signal is continuous with a 20-unit increase per hour, it indicates that friction is constantly intensifying. Combined with the mechanism that abnormal pressure damages lubrication, this can be identified as abnormal friction, and the fault originates from abnormal sealing surface pressure.

[0080] If the signal type is identified as continuous and intermittent energy spikes are detected in the low-frequency band from the spectrum data, the operating state is determined to be thermal stress crack propagation on the sealing surface, and the fault mode is abnormal sealing surface specific pressure.

[0081] Specifically, continuous signals indicate that the sealing surface is still in a state of continuous friction (the continuation of abnormal friction); while intermittent energy spikes in the low-frequency band correspond to the instantaneous impact of crack propagation. When abnormal friction caused by abnormal specific pressure continues to develop, the sealing surface will generate thermal stress due to local overheating, and micro-cracks will appear on the material surface. These cracks will periodically propagate during frictional vibration, and each propagation will trigger a low-frequency vibration impact, forming a low-frequency energy spike.

[0082] Through the above three logics, accurate deduction from signal characteristics to operating status and then to the root cause of the fault is achieved, which greatly improves the accuracy and pertinence of fault diagnosis.

[0083] In some embodiments, the alarm signal includes operating status information, fault mode information, and solution information.

[0084] The alarm signal in this embodiment simultaneously includes three key types of information: operating status, fault mode, and solution. This completely solves the pain point of traditional centrifugal pump fault alarms, which only indicate a fault but do not specify the cause. Especially for centrifugal pumps transporting high-risk media such as liquefied gas and toxic chemicals, this embodiment's comprehensive information guidance can directly guide maintenance personnel to quickly and accurately handle faults, significantly shortening unplanned downtime, reducing the risk of safety accidents caused by media leaks, and avoiding secondary damage to equipment due to improper operation, ultimately ensuring production safety and stability.

[0085] like Figure 2As shown, one embodiment of this application also provides a centrifugal pump operation fault detection device, the device comprising:

[0086] The acquisition module is used to acquire acoustic emission signals from the mechanical seal cavity of the centrifugal pump.

[0087] The processing module is used to process the acoustic emission signal to extract its spectral features;

[0088] The status judgment and fault identification module is used to determine the operating status of the sealing surface and identify potential fault modes based on the changes in the spectrum characteristics.

[0089] The alarm module is used to output alarm signals based on the operating status and the fault mode.

[0090] The modules in the centrifugal pump fault detection device described above can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0091] An embodiment of this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the centrifugal pump operation fault detection method described above.

[0092] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for detecting faults in a centrifugal pump. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the device's casing, or an external keyboard, touchpad, or mouse.

[0093] An embodiment of this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the centrifugal pump operation fault detection method described above.

[0094] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0095] In summary, this application provides a method, device, equipment, and storage medium for detecting faults in centrifugal pumps. By collecting acoustic emission signals from the mechanical seal cavity, the operating status of the centrifugal pump's mechanical seal can be monitored in real time and continuously, avoiding the monitoring interruption problem caused by manual inspections relying on periodic checks. It can comprehensively capture the state changes of the sealing surface during operation.

[0096] This method determines the operating status based on the changes in the spectral characteristics of acoustic emission signals. It can identify potential problems in the early stages of mechanical seal failure (such as abnormal friction of the sealing surface, slight abrasive wear, etc., before media leakage occurs). Compared with traditional methods that can only alarm after media leakage, it can provide early warning and prevent leakage accidents, significantly improving the safety of equipment operation.

[0097] By analyzing the spectral characteristics of acoustic emission signals and using quantified signal features as the basis for judgment, the bias caused by subjective experience in manual inspection is avoided, the reliance on operator experience is reduced, and the accuracy and reliability of fault detection are improved.

[0098] This method can identify potential failure modes while judging the operating status, providing maintenance personnel with clear indications of the cause of failure, which helps to quickly develop targeted maintenance strategies, reduce unplanned downtime, and reduce economic losses.

[0099] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0100] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present invention.

Claims

1. A method for detecting operational faults in a centrifugal pump, characterized in that, The method includes: Acoustic emission signals were collected from the mechanical seal cavity of the centrifugal pump. The acoustic emission signal is processed to extract its spectral features; Based on the changes in the spectral characteristics, the operating status of the sealing surface is determined, and potential fault modes are identified. Based on the operating status and the fault mode, an alarm signal is output.

2. The method according to claim 1, characterized in that: The operating states include abrasive wear on the sealing surface, abnormal friction on the sealing surface, and thermal stress crack propagation on the sealing surface.

3. The method according to claim 2, characterized in that: The failure modes include the presence of particulate matter in the medium and abnormal specific pressure at the sealing surface.

4. The method according to claim 3, characterized in that: The processing of the acoustic emission signal to extract its spectral features specifically includes: The acoustic emission signal is converted from time to frequency to obtain spectrum data; Calculate a first energy value for a preset high-frequency band and a second energy value for a preset low-frequency band from the spectrum data; Based on the first energy value and the second energy value, a spectrum energy distribution ratio is calculated; The spectral characteristics include the spectral energy distribution ratio.

5. The method according to claim 4, characterized in that: The process of processing the acoustic emission signal to extract its spectral features further includes: Identify the signal type from the acoustic emission signal as either burst-type or continuous-type.

6. The method according to claim 5, characterized in that: The process of determining the operating status of the mechanical seal and identifying potential failure modes based on changes in the spectral characteristics specifically includes: If the signal type is identified as burst type, and the current spectral energy distribution ratio is consistently and significantly higher than the preset health status baseline ratio, then the operating status is determined to be abrasive wear of the sealing surface, and the fault mode is that the medium contains particulate matter. If the signal type is identified as continuous and the total energy level of the acoustic emission signal continues to rise, the operating state is determined to be abnormal friction of the sealing surface, and the fault mode is abnormal sealing surface specific pressure. If the signal type is identified as continuous and intermittent energy spikes are detected in the low-frequency band from the spectrum data, the operating state is determined to be thermal stress crack propagation on the sealing surface, and the fault mode is abnormal sealing surface specific pressure.

7. The method according to claim 1, characterized in that: The alarm signals include operating status information, fault mode information, and solution information.

8. A centrifugal pump operation fault detection device, characterized in that, The device includes: The acquisition module is used to acquire acoustic emission signals from the mechanical seal cavity of the centrifugal pump. The processing module is used to process the acoustic emission signal to extract its spectral features; The status judgment and fault identification module is used to determine the operating status of the sealing surface and identify potential fault modes based on the changes in the spectrum characteristics. The alarm module is used to output alarm signals based on the operating status and the fault mode.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images