Method and device for health assessment of main pump in whole life cycle based on dynamic and static coupling

Abstract

This application relates to the field of hydraulic machinery technology, providing a method and apparatus for full life-cycle health assessment of a main pump based on dynamic-static coupling. The method includes: collecting multi-source heterogeneous data; the multi-source heterogeneous data includes a dynamic operation dataset during the operation of the main pump equipment and a static mechanical resistance dataset under shutdown and decoupling conditions; performing dimensionless processing on the multi-source heterogeneous data and introducing a trend penalty factor to correct rapid deterioration indicators, obtaining dynamic evaluation values; calculating the dynamic weights of each indicator using a state-dependent variable weight model, and determining a comprehensive health index based on the dynamic weights and dynamic evaluation values. This application introduces a static mechanical resistance dataset under shutdown and decoupling conditions of the main pump and integrates it with the dynamic operation dataset during operation. This dynamic-static coupling mechanism effectively avoids excessive maintenance and indiscriminate dismantling, achieving improved operation and maintenance efficiency and significant cost optimization.

Description

Technical Field

[0001] This application relates to the field of hydraulic machinery technology, and in particular to a method and apparatus for full life-cycle health assessment of main pumps based on dynamic-static coupling. Background Technology

[0002] Large hydraulic machinery such as main pumps for long-distance pipelines and pumps for large pumping stations are core equipment in water conservancy transportation and energy conversion systems, and their operating status directly affects the safety and energy efficiency of the entire system. Currently, the industry's health assessment and maintenance strategies for such equipment mainly face the following problems: First, time-based maintenance (TBM) solutions are inherently flawed. Traditional maintenance models strictly adhere to fixed cycles, such as mandatory disassembly and overhaul after a certain number of hours of operation. Because the true mechanical wear and tear on the equipment cannot be accurately determined, this approach often leads to over-maintenance, resulting not only in high spare parts and downtime costs but also a high risk of introducing iatrogenic malfunctions due to human error during disassembly and assembly—that is, introducing new potential problems during the maintenance process.

[0003] Second, condition-based maintenance (CBM) solutions have the limitation of separating dynamic and static data. Existing online monitoring systems mainly rely on dynamic data during equipment operation, such as vibration, temperature, and pressure. However, relying solely on dynamic data has significant monitoring blind spots. On the one hand, this method is insensitive to early internal mechanical friction. When early minor wear or dynamic-static rubbing occurs in the pump body inlet ring or bearing, the online vibration signal often has not yet deteriorated significantly, easily leading to missed diagnoses. On the other hand, dynamic data is highly susceptible to causing fault mode confusion. For example, a decrease in hydraulic efficiency due to flow channel cavitation or wear is often misdiagnosed as a mechanical structural failure in dynamic data representation, thus incorrectly triggering expensive disassembly and maintenance orders. Summary of the Invention

[0004] This application provides a method and apparatus for full life cycle health assessment of main pumps based on dynamic-static coupling, which can effectively integrate the mechanical resistance characteristics under shutdown state with the thermodynamic characteristics under operating state, and can dynamically capture subtle deterioration trends and accurately quantify equipment health.

[0005] This application provides a method for full life-cycle health assessment of a main pump based on dynamic-static coupling, comprising: collecting multi-source heterogeneous data of hydraulic machinery integrating dynamic and static data, wherein the multi-source heterogeneous data includes dynamic operation datasets during the operation of the main pump equipment and static mechanical resistance datasets in the shutdown and decoupled state of the main pump equipment; performing dimensionless processing on the multi-source heterogeneous data and introducing a trend penalty factor to correct the rapid deterioration indicators to obtain dynamic evaluation values; calculating the dynamic weights of each indicator based on a state-dependent variable weight model using the dynamic evaluation values, and determining the comprehensive health index based on the dynamic weights and dynamic evaluation values.

[0006] According to the method for full life cycle health assessment of a main pump based on dynamic-static coupling provided in this application, the method is based on a state-dependent variable weight model. After calculating the dynamic weights of each indicator using dynamic evaluation values ​​and determining the comprehensive health index based on the dynamic weights and dynamic evaluation values, the method further includes: based on the comprehensive health index, combining the hydraulic efficiency indicators in the static mechanical resistance dataset and the dynamic operation dataset, outputting maintenance decision instructions through dynamic-static coupling judgment logic.

[0007] According to the method for full life cycle health assessment of a main pump based on dynamic-static coupling provided in this application, the rapid degradation index includes the degradation rate slope. Dimensionless processing is performed on multi-source heterogeneous data, and a trend penalty factor is introduced to correct the rapid degradation index to obtain a dynamic evaluation value. The method includes: performing dimensionless processing on multi-source heterogeneous data to obtain an initial health index, calculating the degradation rate slope of the dynamic operating dataset based on time series analysis, and introducing a trend penalty factor to correct the initial health index to obtain a dynamic evaluation value.

[0008] According to the dynamic-static coupling-based full life cycle health assessment method for a main pump provided in this application, the dynamic operation dataset includes at least: bearing temperatures at the drive end and non-drive end, vibration amplitude of the shaft system in three orthogonal directions, and inlet and outlet pressure differences and instantaneous flow rates used to calculate hydraulic efficiency; the static mechanical resistance dataset includes at least: the maximum starting static friction torque and average dynamic friction torque of the rotor system obtained by a torque measuring device.

[0009] According to the dynamic-static coupling-based full life cycle health assessment method for main pumps provided in this application, the calculation process of the trend penalty factor and dynamic evaluation value is as follows: The slope k of the degradation rate of each parameter within a preset period is calculated using the least squares method; when k≤0, the trend penalty factor... for: When k>0, the trend penalty factor for: ;in, The preset trend weight coefficient and 0 < <1; Dynamic evaluation value for: ;in, This is the initial health index after dimensionless processing.

[0010] According to the dynamic-static coupling-based full life-cycle health assessment method for main pumps provided in this application, the calculation formula of the state-dependent variable weight model is as follows: Dynamic weights of each indicator satisfy: ;in, For the first The basic constant weights of each indicator, where exp() is the natural exponential function. α is the variable-weight sensitivity coefficient and α>0, n represents the total number of evaluation indicators, and j represents the traversal sequence number of the indicators; the comprehensive health index is the sum of the products of the corrected dynamic evaluation values ​​of each indicator and the corresponding dynamic weights.

[0011] According to the dynamic-static coupling-based full life cycle health assessment method for main pumps provided in this application, based on a comprehensive health index and combined with hydraulic efficiency indicators in static mechanical resistance datasets and dynamic operation datasets, maintenance decision commands are output through dynamic-static coupling judgment logic. These commands include: when the comprehensive health index is below a preset alarm threshold, hydraulic efficiency is below a set benchmark, and static mechanical resistance is above a preset reference value, it is determined that there is severe friction between dynamic and static components, and an immediate shutdown and disassembly repair command is output; when the comprehensive health index is below a preset alarm threshold, hydraulic efficiency is below a set benchmark, but static mechanical resistance is within a preset reference range, it is determined that there is hydraulic damage to the flow components, and a command to postpone disassembly and prioritize flow channel repair is output; when the comprehensive health index is within a preset warning range, static mechanical resistance is within a preset reference range, and the slope of the vibration index deterioration rate is greater than zero and exhibits periodic fluctuations, it is determined that there is slight rotor imbalance or misalignment, and an external adjustment command is output.

[0012] This application also provides a main pump lifecycle health assessment device based on dynamic-static coupling, comprising: a data acquisition module for acquiring multi-source heterogeneous data of hydraulic machinery, wherein the multi-source heterogeneous data includes dynamic operation datasets during the operation of the main pump equipment and static mechanical resistance datasets in the shutdown and decoupled state of the main pump equipment; a dynamic evaluation value module for performing dimensionless processing on the multi-source heterogeneous data and introducing a trend penalty factor to correct the rapid deterioration indicators to obtain dynamic evaluation values; and a comprehensive health index module for calculating the dynamic weights of each indicator based on a state-dependent variable weight model using the dynamic evaluation values, and determining the comprehensive health index based on the dynamic weights and dynamic evaluation values.

[0013] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the main pump full life cycle health assessment method based on dynamic-static coupling as described above.

[0014] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the main pump full life cycle health assessment method based on dynamic-static coupling as described above.

[0015] This application provides a method and apparatus for full life-cycle health assessment of a main pump based on dynamic-static coupling. The method includes: collecting multi-source heterogeneous data of hydraulic machinery, including a dynamic operation dataset during main pump operation and a static mechanical resistance dataset under shutdown and decoupling conditions; performing dimensionless processing on the multi-source heterogeneous data and introducing a trend penalty factor to correct rapid deterioration indicators, obtaining dynamic evaluation values; calculating the dynamic weights of each indicator using a state-dependent variable weight model, and determining a comprehensive health index based on the dynamic weights and dynamic evaluation values. Through this approach, this application introduces a static mechanical resistance dataset under main pump shutdown and decoupling conditions and integrates it with the dynamic operation dataset during operation. This dynamic-static coupling mechanism effectively avoids excessive maintenance and blind disassembly, achieving improved operation and maintenance efficiency and significant cost optimization. Furthermore, this application introduces a trend penalty factor to achieve sensitive capture and early warning of weak deterioration trends, and employs a state-dependent variable weight model to highlight the impact of local faults on overall health, significantly improving the sensitivity of identifying early wear or local failures. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in 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 some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the main pump lifecycle health assessment method based on dynamic-static coupling provided in this application embodiment. Figure 2 This is a schematic diagram of the architecture of the dynamic-static coupled data acquisition and processing system provided in the embodiments of this application.

[0018] Figure 3 This is a schematic diagram of the dynamic weight change curve based on the variable weight theory provided in the embodiments of this application.

[0019] Figure 4This is a logic matrix diagram for determining dynamic and static coupling faults provided in the embodiments of this application.

[0020] Figure 5 This is a schematic diagram of the structure of the main pump full life cycle health assessment device based on dynamic-static coupling provided in the embodiments of this application.

[0021] Figure 6 This is a schematic diagram of the physical structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0024] This application provides a method for assessing the health of a main pump throughout its entire lifecycle based on dynamic-static coupling. It aims to solve the technical problem that existing technologies cannot accurately distinguish between "hydraulic performance degradation" and "mechanical structure damage" in hydraulic machinery in a non-disassembly state, and to provide an assessment method that can accurately quantify equipment health, extend operating cycles, and reduce operation and maintenance costs.

[0025] Please see Figure 1 , Figure 1 This is a flowchart illustrating the main pump lifecycle health assessment method based on dynamic-static coupling provided in this application embodiment. In this embodiment, the main pump lifecycle health assessment method based on dynamic-static coupling may include steps S110 to S130, each step as follows: S110: Collect multi-source heterogeneous data of dynamic and static fusion of hydraulic machinery. The multi-source heterogeneous data includes dynamic operation datasets during the operation of the main pump equipment and static mechanical resistance datasets when the main pump equipment is stopped and decoupled.

[0026] S120: Dimensionless processing is performed on multi-source heterogeneous data, and a trend penalty factor is introduced to correct the rapid degradation index, resulting in a dynamic evaluation value.

[0027] S130: Based on a state-dependent variable weighting model, the dynamic weights of each indicator are calculated using dynamic evaluation values, and the comprehensive health index is determined based on the dynamic weights and dynamic evaluation values.

[0028] This embodiment adopts a three-in-one architecture of "dynamic and static fusion data acquisition + trend penalty quantification + state-dependent variable weighting". By introducing static mechanical resistance in a decoupled state as a key benchmark, a full-dimensional evaluation coordinate system is constructed.

[0029] First, a basic database can be established using multi-source heterogeneous data; not only should the absolute values ​​of the parameters be considered after dimensionless processing, but the rate of change of the parameters should also be considered through the trend penalty factor; then, a state-dependent variable weight model is used to change the problem of fixed weights in the weighted average method.

[0030] Through the above methods, this embodiment eliminates monitoring blind spots and solves the problem of subtle mechanical wear being masked by fluid pulsation during operation of hydraulic machinery. Furthermore, it improves early warning foresight: by applying trend penalties, the system can detect equipment failures in their early stages (i.e., rapid deterioration even though indicators are not yet exceeding limits).

[0031] Optionally, the dynamic running dataset includes at least: the bearing temperatures at the drive end and non-drive end, the vibration amplitude of the shaft system in three orthogonal directions, and the inlet and outlet pressure difference and instantaneous flow rate used to calculate hydraulic efficiency.

[0032] Optionally, the static mechanical resistance dataset includes at least the maximum starting static friction torque and average dynamic friction torque of the rotor system obtained by a torque measuring device.

[0033] This embodiment defines the data content of the dynamic-static fusion. The dynamic side integrates three dimensions: thermal (temperature), mechanical (vibration), and hydraulic (pressure difference / flow rate). The static side selects the maximum starting static friction torque (to overcome static friction) and the average dynamic friction torque (to evaluate rotational smoothness).

[0034] In this embodiment, static torque reflects the internal fit clearance and friction state, while dynamic efficiency reflects the geometric integrity of the flow channel. The combination of the two achieves a deep coupling and decoupling of mechanics and performance.

[0035] For example, a full-dimensional state database of hydraulic machinery is constructed, and the data in the database can be divided into dynamic operation datasets and static mechanical resistance datasets.

[0036] (1) Dynamic operation dataset: During the operation of the hydraulic machinery, the following parameters are collected in real time: ①Thermodynamic parameters: bearing temperatures at the driving and non-driving ends ( ); ② Vibration spectrum parameters: the vibration amplitude of the shaft system in the three orthogonal directions X / Y / Z ( and fluid noise spectrum; ③ Hydraulic performance parameters: including inlet and outlet pressure difference ( ) and instantaneous flow ( ), used to calculate the hydraulic efficiency under the current operating conditions in real time based on Bernoulli's equation ( ).

[0037] (2) Static mechanical resistance dataset: Under no-load conditions where the hydraulic machinery is shut down and decoupled from the drive motor (e.g., the coupling pin is removed), the resistance characteristics of the rotor system are obtained using a digital torque measurement device: ① Maximum starting static friction torque ( ): Characterizes the maximum static friction force that the rotor overcomes at the instant it starts from rest; ② Average dynamic friction torque ( ): Characterizes the average resistance when the rotor rotates at a low and constant speed.

[0038] The present application provides a method for assessing the full life-cycle health of a main pump based on dynamic-static coupling, which can achieve the following beneficial effects: 1. Eliminating blind spots in dynamic and static monitoring to achieve precise decoupling of fault modes. This application innovatively integrates the static mechanical resistance dataset from when the main pump is shut down and decoupled with the dynamic operation dataset during operation. This dynamic-static coupling mechanism effectively solves the technical challenge of distinguishing between hydraulic and mechanical damage when relying solely on online monitoring data. It can accurately identify different types of faults such as hydraulic performance degradation, flow channel wear, structural friction, and ring seizure. By accurately locating the root cause of the fault, unnecessary blind disassembly and repair are greatly reduced, significantly lowering operation and maintenance costs.

[0039] 2. Introducing a trend penalty factor to enhance early warning capabilities for minor degradation. Addressing the pain point that early fault characteristics are easily masked by absolute values, this application introduces a trend penalty factor after dimensionless processing to dynamically correct rapid degradation indicators. This means that even if the absolute value of a monitoring parameter has not yet exceeded a preset alarm threshold, as long as it shows a rapid deterioration trend, the health score will be forcibly lowered through the penalty factor. This mechanism enables early exposure of potential hazards, providing valuable early warning time for equipment maintenance and effectively preventing sudden downtime accidents.

[0040] 3. A state-dependent variable weighting model is adopted to avoid the averaging effect of local anomalies. Traditional constant-weight evaluation models can easily lead to a majority of normal indicators masking a few critically abnormal indicators. This application's embodiment uses dynamic evaluation values ​​to calculate the weights of each indicator in real time. When an indicator shows signs of deterioration, the variable weighting model exponentially amplifies the proportion of that abnormal indicator in the overall health index. This non-linear, dynamically adaptive weighting adjustment mechanism significantly highlights the contribution of local faults to overall health, greatly improving the system's sensitivity to identifying early wear and tear or localized failures.

[0041] 4. Driving scientific management throughout the entire lifecycle and achieving precise transformation of operation and maintenance models. This application's embodiments deeply integrate multi-dimensional data from both operational and maintenance states of the equipment, coupled with precise health index calculation methods, supporting the scientific transformation of main pump maintenance strategies from traditional periodic maintenance to precise condition-based maintenance. While comprehensively ensuring the safe operation of the equipment, this method effectively extends the actual operating cycle of the equipment and improves the efficiency of asset management throughout its entire lifecycle.

[0042] In some embodiments, the steps following the calculation of dynamic weights for each indicator based on a state-dependent variable weighting model, and the determination of the comprehensive health index based on the dynamic weights and dynamic evaluation values, may further include: Based on the comprehensive health index, and combining the hydraulic efficiency indicators in the static mechanical resistance dataset and the dynamic operation dataset, maintenance decision instructions are output through dynamic-static coupling judgment logic.

[0043] The implementation example can logically backtrack the evaluation results, such as the comprehensive health index (i.e., the PHI index), with the underlying original characteristics, such as static resistance and hydraulic efficiency, thereby transforming the numerical evaluation into engineering instructions.

[0044] For example, after obtaining the PHI index, instead of simply giving a score, a decision matrix can be used to compare the contradictory relationship between the two dimensions of static resistance and hydraulic efficiency, thereby outputting targeted maintenance recommendations.

[0045] In summary, this embodiment achieves accurate diagnosis without disassembly: it provides precise guidance on whether to "disassemble and repair the machinery" or "repair the flow channel online" without disassembling the machine, significantly reducing the costs and human risks associated with blind disassembly.

[0046] In some embodiments, the rapid degradation index includes a degradation rate slope. The steps of performing dimensionless processing on multi-source heterogeneous data and introducing a trend penalty factor to correct the rapid degradation index to obtain a dynamic evaluation value may specifically include: The initial health index is obtained by dimensionless processing of multi-source heterogeneous data, and the degradation rate slope of the dynamic running dataset is calculated based on time series analysis. A trend penalty factor is introduced to correct the initial health index to obtain a dynamic evaluation value.

[0047] This embodiment clarifies the generation mechanism of the trend penalty factor, employing time series analysis to transform static state snapshots into dynamic time-varying trajectories. This approach suppresses evaluation lag and, for sudden, rapidly evolving faults, forces a score reduction to ensure a safety margin.

[0048] Dimensionlessness can be achieved through normalization. For example, constructing a nonlinear membership function can map various physical quantities (such as temperature, vibration, efficiency, and torque) to a health index within a unified range. .

[0049] Optionally, , where 1 can represent the optimal state and 0 can represent complete failure.

[0050] In some embodiments, the calculation process of the trend penalty factor and the dynamic evaluation value is as follows: the slope k of the degradation rate of each parameter within a preset period is calculated using the least squares method; When k≤0, trend penalty factor for: ; When k>0, the trend penalty factor for: ; in, The preset trend weight coefficient and 0 < <1; Dynamic evaluation value for: ;in, This is the initial health index after dimensionless processing.

[0051] In this embodiment, trend degradation correction involves performing time series analysis on the dynamic dataset and using the least squares method to calculate the most recent trend of each parameter. Degradation rate slope within the cycle This ensures that even if the absolute value of the parameter does not exceed the limit, its score will be forcibly lowered if there is a rapid deterioration trend.

[0052] Among them, trend penalty factor Calculation: ; Trend weighting coefficient ( ), used to adjust the severity of the penalty for the rate of degradation.

[0053] Among them, the corrected dynamic evaluation value is: .

[0054] In some embodiments, the calculation formula for the state-dependent variable weight model is as follows: Dynamic weights of each indicator satisfy: ; in, For the first The basic constant weights of each indicator, where exp() is the natural exponential function. α is the variable-weight sensitivity coefficient and α>0, n represents the total number of evaluation indicators, and j represents the traversal sequence number of the indicators; the comprehensive health index is the sum of the products of the corrected dynamic evaluation values ​​of each indicator and the corresponding dynamic weights.

[0055] This embodiment introduces a state-driven exponential variable weight function, which can solve the classic problem of a few fault indicators being overwhelmed by a majority of normal indicators.

[0056] This embodiment can achieve a fault amplification effect: when a critical component (such as a bearing) suffers severe deterioration, the weight of this indicator will automatically "skyrocket," causing the total score PHI to rapidly converge towards the fault item. Experimental data shows that its sensitivity is more than 40% higher than the traditional constant weight method.

[0057] For example, the dynamic weights of each indicator can be calculated using the variable weight theory, breaking the limitation of the traditional constant weight model where most normal indicators mask a few abnormal indicators.

[0058] The dynamic weight model can be expressed as: ; For the first The basic constant weights of each indicator (satisfying) ); It is a natural exponential function; The variable weight sensitivity coefficient ( When a certain indicator When it deteriorates (becomes smaller), its weight It will grow exponentially and non-linearly, thus highlighting the impact of this failure indicator on overall health.

[0059] Where n represents the total number of evaluation indicators, and j represents the traversal index of the indicator. Finally, the Physical Health Index (PHI) can be expressed as: .

[0060] In some embodiments, the step of outputting maintenance decision instructions based on a comprehensive health index, combined with hydraulic efficiency indicators from static mechanical resistance datasets and dynamic operation datasets, through a dynamic-static coupling judgment logic, may specifically include at least one of the following: 1) When the overall health index is lower than the preset alarm threshold, the hydraulic efficiency is lower than the set benchmark, and the static mechanical resistance is greater than the preset reference value, it is determined that there is severe friction between the moving and static parts, and an immediate shutdown and disassembly repair command is output. 2) When the overall health index is lower than the preset alarm threshold, the hydraulic efficiency is lower than the set benchmark, but the static mechanical resistance is within the preset reference range, it is determined that the flow component is hydraulically damaged, and the command to postpone disassembly and prioritize the flow channel repair is output. 3) When the comprehensive health index is in the preset warning range, the static mechanical resistance is in the preset reference range, and the slope of the vibration index deterioration rate is greater than zero and shows periodic fluctuations, it is determined that the rotor is slightly unbalanced or misaligned, and an external adjustment command is output.

[0061] This embodiment maps complex state parameters to three typical engineering scenarios, enabling the digitization of expert experience. Based on the Comprehensive Health Index (PHI) and combined with the logical matching relationship between static turning torque and dynamic hydraulic efficiency, specific maintenance decision instructions are output. The judgment logic is as follows: Scenario 1 (Mechanical Fault): When the phenomenon of low PHI + low efficiency + high torque occurs, that is, PHI is lower than the alarm threshold, and the characteristics are "low hydraulic efficiency" and "high static mechanical resistance" ( If both "dynamic and static wear" are present, it is determined to be dynamic and static wear.

[0062] At this point, if there is severe friction between moving and stationary parts (such as meshing of the mouth ring or bending of the shaft), the corresponding maintenance decision instruction should be: immediately stop the machine, disassemble and repair it.

[0063] Scenario 2 (Hydraulic soft damage): When the phenomenon of low PHI + low efficiency + normal torque occurs, that is, PHI is lower than the alarm threshold, and the characteristic is "low hydraulic efficiency" but "normal static mechanical resistance", it is judged as overcurrent damage.

[0064] At this point, the flow components suffer hydraulic damage (such as cavitation, silt erosion, and channel scaling), but the mechanical structure remains intact. The corresponding maintenance decision should be: postpone dismantling and prioritize channel repair or anti-wear coating maintenance.

[0065] Scenario 3 (Poor Centering): When the phenomenon of PHI warning + normal torque + oscillation period fluctuation occurs, that is, PHI is in the warning range and static resistance is normal, but the oscillation trend is abnormal. If it exhibits periodic fluctuations, it is determined to be an external coordination problem.

[0066] At this point, the rotor is slightly unbalanced or the coupling is misaligned. The corresponding maintenance decision should be: external adjustment for alignment, without opening the cover or disassembling the machine.

[0067] In summary, this embodiment effectively prevents hydraulic losses from being misdiagnosed as mechanical damage, thereby avoiding unnecessary disassembly and inspection, and saving huge overhaul costs. Once alignment problems are identified, only external adjustments are needed without opening the cover, significantly extending the continuous operating cycle of the main pump. Furthermore, disassembly commands can be issued at the initial stage of mechanical damage, effectively preventing the problem from escalating.

[0068] Please see Figure 2 , Figure 2 This is a schematic diagram of the architecture of the dynamic-static coupled data acquisition and processing system provided in the embodiments of this application.

[0069] This embodiment adopts a layered architecture design, which includes four core modules from bottom to top: the perception layer, the edge computing layer, the decision center layer, and the human-computer interaction terminal.

[0070] The sensing layer, as the data source of the system, is responsible for collecting multi-dimensional status data of equipment operation. This layer is deployed with vibration / temperature sensors for real-time monitoring of the mechanical vibration characteristics and thermodynamic state of the equipment; pressure / flow transmitters for collecting process parameters of the fluid system; and digital torque meters specifically for shutdown detection, ensuring that key mechanical data can still be obtained under special operating conditions such as equipment start-up and shutdown. These various types of sensors constitute a sensing network covering the entire operating state of the equipment.

[0071] The edge computing layer is responsible for data preprocessing, performing real-time processing on the raw data uploaded by the sensing layer. First, signal cleaning and filtering algorithms remove noise interference and outliers to improve data quality. Then, normalization mapping is performed to convert sensor data of different dimensions and ranges into a standardized numerical range, eliminating scale differences between data. Finally, the trend slope k of each parameter is calculated to capture the evolution trend of the device's state, providing dynamic feature input for subsequent evaluation.

[0072] The decision center is the core of the system's evaluation, comprising three key components: a variable weight model engine, a dynamic-static coupled fault knowledge base, and a decision logic unit. The variable weight model engine receives normalized values ​​and trend slope k from the edge computing layer, dynamically calculates the weights w_i of each evaluation indicator and the equipment health index PHI, and adaptively adjusts the evaluation parameters based on the actual operating status of the equipment. The dynamic-static coupled fault knowledge base integrates the static structural characteristics and dynamic operating patterns of the equipment, providing expert experience support for fault diagnosis. The decision logic unit synthesizes the PHI value output by the variable weight model engine and the matching results from the knowledge base to generate the final diagnostic conclusion.

[0073] As the system's output interface, the human-machine interface terminal presents the diagnostic results of the equipment's health status to maintenance personnel in a visual manner and provides targeted maintenance suggestions, thereby achieving closed-loop management from status monitoring to maintenance decision-making.

[0074] This embodiment achieves real-time monitoring, intelligent assessment, and accurate diagnosis of the health status of the main pump equipment through a complete technical chain of "data acquisition - edge preprocessing - intelligent evaluation - human-computer interaction".

[0075] Please see Figure 3 , Figure 3 This is a schematic diagram of the dynamic weight change curve based on the variable weight theory provided in the embodiments of this application.

[0076] It can be seen that there is a non-linear mapping relationship between the health index and the dynamic weight.

[0077] The horizontal axis (X-axis) represents the health of the indicator, with a value range of 1.0 to 0.0, representing the evolution of the indicator from a healthy state to a deteriorating state (1.0 is completely healthy, and 0.0 is severely deteriorated / failed); the vertical axis (Y-axis) represents the dynamic weight, with a value range of 0 to 1.0, representing the weight ratio of the indicator in the comprehensive evaluation.

[0078] This contingency mechanism reflects a degradation-sensitive assessment strategy: ① Health Status (Health Score > 0.8): When the indicator performs normally, a lower base weight is assigned to avoid excessive interference from normal fluctuations in the overall assessment. ② Accelerated Deterioration Zone (Health Level 0.6~0.2): As the health level of an indicator decreases, its dynamic weight increases exponentially, ensuring that indicators that are about to fail receive higher attention. ③ Critical Failure Zone (Health < 0.2): When the indicator approaches the danger threshold, the dynamic weight rises sharply to nearly 1.0, making this deterioration indicator dominate the calculation of the comprehensive health index (PHI), realizing the adaptive assessment logic of "the more dangerous, the more attention." This nonlinear variable weighting mechanism effectively solves the problems of "the deterioration of small weight indicators being masked" and "the normal fluctuation of large weight indicators leading to misjudgment" in traditional fixed weight assessment, and significantly improves the sensitivity and accuracy of the health assessment of the main pump equipment.

[0079] Please see Figure 4 , Figure 4 This is a logic matrix diagram for determining dynamic and static coupling faults provided in the embodiments of this application.

[0080] This embodiment is based on a multi-level decision diagnosis method using the comprehensive health index PHI. With the PHI value as the core criterion, it combines multi-dimensional parameters such as hydraulic efficiency, static turning torque, and vibration trend to construct a hierarchical and progressive fault diagnosis logic tree, thereby realizing fully automated decision-making from health status assessment to specific fault location and maintenance strategy generation.

[0081] 1) First-level judgment: PHI interval division.

[0082] First, the calculated Comprehensive Health Index (PHI) is compared with a preset threshold, and the result is divided into three decision branches: ①PHI Normal Range: Determines that the equipment is in a healthy state, outputs the decision suggestion of "equipment is healthy, extend the operation cycle", and allows the equipment to continue to operate and enter the next monitoring cycle; ②PHI is in the warning zone: triggers the secondary refined diagnostic process, focusing on analyzing the temporal characteristics of vibration parameters; ③ When PHI is below the alarm threshold: trigger the in-depth diagnostic process, focusing on investigating hydraulic system and mechanical friction-related faults.

[0083] 2) Second-level judgment: Refined diagnosis of the warning interval (PHI is in the warning interval).

[0084] When PHI falls into the warning range, further determine whether the oscillation trend slope k is greater than 0 and exhibits periodic fluctuation characteristics: ① If the vibration trend k>0 and there are periodic fluctuations, it is diagnosed as a rotor imbalance or misalignment fault. This type of fault is a common externally adjustable fault in rotating machinery. It is recommended to adopt the maintenance strategy of "external adjustment / no need to open the cover". It can be restored by on-site dynamic balancing or alignment adjustment, avoiding unnecessary disassembly operations. ② If the vibration characteristics do not meet the above conditions, it is judged as a general condition deterioration, and a "continue to observe" suggestion can be output to increase the monitoring frequency but not to intervene for the time being.

[0085] 3) Third-level judgment: Alarm threshold depth diagnosis (PHI is lower than the alarm threshold).

[0086] When the PHI is below the alarm threshold, first assess whether the hydraulic efficiency is abnormally low: ① If the hydraulic efficiency is normal, it is determined to be another complex fault type. Since it is beyond the scope of the automatic diagnosis knowledge base, a "manual intervention required" prompt can be output and the case can be transferred to a professional engineer for in-depth analysis. ②If the hydraulic efficiency is abnormally low, proceed to the fourth level of judgment to further distinguish the root cause of the fault.

[0087] 4) Fourth-level judgment: root cause localization when hydraulic efficiency is abnormal To address the issue of low hydraulic efficiency, static turning torque can be introduced as a key differentiating indicator: ① If the static turning torque increases significantly (high resistance state), it is diagnosed as a severe friction fault between the moving and stationary components. This type of fault involves mechanical contact between rotating and stationary components, and has a high risk of rapid deterioration and secondary damage. "Immediate disassembly and repair" is recommended, requiring a forced shutdown and a comprehensive disassembly and inspection. ② If the static turning torque is normal (resistance is normal), the diagnosis is hydraulic damage to the flow components. This type of fault mainly manifests as cavitation, wear, or scaling of flow components such as impellers and guide vanes. Although it affects efficiency, there is no urgent mechanical safety risk. "Flow channel repair / temporary non-disassembly" can be recommended. It can be handled by non-disassembly methods such as on-site cleaning and coating repair, reducing maintenance costs and downtime.

[0088] The above embodiment of the process, through a three-layer architecture of "PHI macro-level classification - detailed identification of specific parameters - automatic generation of maintenance strategies", realizes intelligent mapping between equipment health status and fault type, ensuring the scientific nature and operability of diagnostic conclusions and maintenance suggestions.

[0089] Based on the above embodiments, this application deeply integrates dynamic and static data from equipment operation, effectively eliminating monitoring blind spots and realizing a scientific management shift from scheduled maintenance to condition-based maintenance. This application introduces static turning torque as a core physical feature, effectively solving the problem that relying solely on online monitoring data cannot distinguish between soft faults caused by performance degradation and hard faults caused by mechanical friction, significantly reducing unnecessary disassembly and maintenance. This application also completely eliminates the averaging effect in data processing by employing a state-variable weighting algorithm. Experimental results show that the sensitivity of this application in identifying early bearing wear or rubbing is improved by more than 40% compared to traditional weighted methods.

[0090] The following example illustrates a specific application scenario (the main pump unit of a large pumping station): Step 1: Data collection.

[0091] Dynamic operating dataset: Operating data from the past month is acquired through a distributed control system (DCS). The vibration amplitude of the drive-end bearing was detected to be... Rise to (Alarm value) ), hydraulic efficiency from Descending to .

[0092] Static mechanical resistance dataset: During the maintenance window, the coupling pins were removed. The maximum starting static friction torque of the rotor was measured using a digital torque meter. According to the equipment file, the factory-set reference torque for this unit is... The deviation range reached It was determined to be a serious abnormality.

[0093] Step 2: Feature quantification and trend correction.

[0094] Vibration index normalized value .

[0095] Calculate the slope of the vibration trend (Positive degradation), setting .

[0096] Trend penalty factor .

[0097] Corrected vibration evaluation value .

[0098] The introduction of a trend penalty further lowered the health score, reflecting the severity of the deterioration. Step 3: Calculate the variable weights.

[0099] Setting a basic constant weight: vibration ,efficiency torque .

[0100] Setting the variable weight sensitivity coefficient .

[0101] Substitute into the formula to calculate the dynamic weight: due to the static torque ( Extremely low) and vibration ( (Lower) health status, the variable weight algorithm automatically adjusts the weight distribution. Calculation results show that the weight of torque is adjusted by... Rise to The vibration weight is from Rise to Efficiency weights are compressed.

[0102] Calculated (Belongs to the "high-risk" range).

[0103] Step 4: Decision Output.

[0104] Logical judgment: (Alarm triggered); "Low hydraulic efficiency" was detected. ); "Static torque maximum" was detected. ).

[0105] Final conclusion: The fault is consistent with the characteristics of "severe friction between moving and stationary parts".

[0106] Operation executed: Issued an "Immediate Disassembly" command. Disassembly revealed severe unilateral metal seizure marks at the impeller mouth ring, verifying the accuracy of the assessment. If only the vibration amplitude is considered according to relevant technologies (…), If the pump continues to operate with the problem, it may eventually lead to a shaft seizure and burnout accident.

[0107] This application also provides a main pump life cycle health assessment device based on dynamic-static coupling. The main pump life cycle health assessment device based on dynamic-static coupling provided in this application is described below. The main pump life cycle health assessment device based on dynamic-static coupling described below can be referred to in correspondence with the main pump life cycle health assessment method based on dynamic-static coupling described above.

[0108] Please see Figure 5 , Figure 5 This is a schematic diagram of the main pump lifecycle health assessment device based on dynamic-static coupling provided in this application embodiment. In this embodiment, the main pump lifecycle health assessment device based on dynamic-static coupling may include a data acquisition module 510, a dynamic evaluation value module 520, and a comprehensive health index module 530.

[0109] The data acquisition module 510 is used to acquire multi-source heterogeneous data of dynamic and static fusion of hydraulic machinery. The multi-source heterogeneous data includes dynamic operation datasets during the operation of the main pump equipment and static mechanical resistance datasets in the shutdown and decoupled state of the main pump equipment. The dynamic evaluation value module 520 is used to perform dimensionless processing on multi-source heterogeneous data and introduce a trend penalty factor to correct the rapid degradation index to obtain the dynamic evaluation value. The Comprehensive Health Index Module 530 is used to calculate the dynamic weights of each indicator based on the state-dependent variable weight model, using dynamic evaluation values, and to determine the comprehensive health index based on the dynamic weights and dynamic evaluation values.

[0110] In some embodiments, the main pump lifecycle health assessment device based on dynamic-static coupling may further include a command output module, which may be used for: Based on the comprehensive health index, and combining the hydraulic efficiency indicators in the static mechanical resistance dataset and the dynamic operation dataset, maintenance decision instructions are output through dynamic-static coupling judgment logic.

[0111] In some embodiments, the rapid degradation index includes the degradation rate slope, and the dynamic evaluation value module 520 can be specifically used for: The initial health index is obtained by dimensionless processing of multi-source heterogeneous data, and the degradation rate slope of the dynamic running dataset is calculated based on time series analysis. A trend penalty factor is introduced to correct the initial health index to obtain a dynamic evaluation value.

[0112] In some embodiments, the dynamic operating dataset includes at least: the bearing temperatures at the drive end and non-drive end, the vibration amplitude of the shaft system in three orthogonal directions, and the inlet and outlet pressure difference and instantaneous flow rate for calculating hydraulic efficiency; the static mechanical resistance dataset includes at least: the maximum starting static friction torque and average dynamic friction torque of the rotor system obtained by the torque measuring device.

[0113] In some embodiments, the calculation process of the trend penalty factor and the dynamic evaluation value is as follows: The degradation rate slope k of each parameter within a preset period is calculated using the least squares method; when k≤0, the trend penalty factor... for: When k>0, the trend penalty factor for: ;in, The preset trend weight coefficient and 0 < <1; Dynamic evaluation value for: ;in, This is the initial health index after dimensionless processing.

[0114] In some embodiments, the calculation formula for the state-dependent variable weight model is as follows: Dynamic weights of each indicator satisfy: ;in, For the first The basic constant weights of each indicator, where exp() is the natural exponential function. α is the variable-weight sensitivity coefficient and α>0, n represents the total number of evaluation indicators, and j represents the traversal sequence number of the indicators; the comprehensive health index is the sum of the products of the corrected dynamic evaluation values ​​of each indicator and the corresponding dynamic weights.

[0115] In some embodiments, the instruction output module can be specifically used for: When the overall health index is lower than the preset alarm threshold, the hydraulic efficiency is lower than the set benchmark, and the static mechanical resistance is greater than the preset reference value, it is determined that there is severe friction between the moving and static components, and an immediate shutdown and disassembly repair command is output. When the overall health index is lower than the preset alarm threshold, the hydraulic efficiency is lower than the set benchmark, but the static mechanical resistance is within the preset reference range, it is determined that there is hydraulic damage to the flow components, and a command to postpone disassembly and prioritize flow channel repair is output. When the overall health index is within the preset warning range, the static mechanical resistance is within the preset reference range, and the slope of the vibration index deterioration rate is greater than zero and shows periodic fluctuations, it is determined that there is slight rotor imbalance or misalignment, and an external adjustment command is output.

[0116] The above-described embodiment of the present application provides a main pump full life cycle health assessment device based on dynamic-static coupling. It introduces a static mechanical resistance dataset of the main pump in a stopped and decoupled state and integrates it with the dynamic operation dataset during operation. This dynamic-static coupling mechanism effectively avoids excessive maintenance and blind disassembly, thereby improving operation and maintenance efficiency and significantly optimizing costs. It also introduces a trend penalty factor to achieve sensitive capture and early warning of weak deterioration trends, and adopts a state-dependent variable weight model to highlight the impact of local faults on overall health, greatly improving the sensitivity of early wear or local failure identification.

[0117] On the other hand, this application also provides an electronic device, please refer to... Figure 6 , Figure 6 This is a schematic diagram of the physical structure of the electronic device provided in the embodiments of this application, such as... Figure 6 As shown, the electronic device may include memory 620, processor 610, and a computer program stored in memory 620 and executable on processor 610. When processor 610 executes the program, it can implement a main pump lifecycle health assessment method based on dynamic-static coupling. This method may include: Multi-source heterogeneous data of hydraulic machinery is collected, including dynamic operation datasets during the operation of the main pump and static mechanical resistance datasets when the main pump is shut down and decoupled. The multi-source heterogeneous data is dimensionless and a trend penalty factor is introduced to correct the rapid deterioration indicators to obtain dynamic evaluation values. Based on a state-dependent variable weight model, the dynamic weights of each indicator are calculated using the dynamic evaluation values, and the comprehensive health index is determined based on the dynamic weights and dynamic evaluation values.

[0118] Optionally, the electronic device may further include a communication bus 630 and a communication interface 640, wherein the processor 610, the communication interface 640, and the memory 620 communicate with each other through the communication bus 630. The processor 610 can call the computer program in the memory 620 to execute the main pump full life cycle health assessment method based on dynamic-static coupling provided by the above methods.

[0119] Furthermore, the logical instructions in the aforementioned memory 620 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the main pump full life cycle health assessment method based on dynamic-static coupling provided by the above methods. The steps and principles of the method have been described in detail in the above methods and will not be repeated here.

[0121] Non-transitory computer-readable storage media can be any available medium or data storage device that can be accessed by a processor, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MOs), etc.), optical storage (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs)).

[0122] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0123] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for full life-cycle health assessment of a main pump based on dynamic-static coupling, characterized in that, include: Collect multi-source heterogeneous data of dynamic and static fusion of hydraulic machinery, wherein the multi-source heterogeneous data includes dynamic operation dataset of the main pump equipment during operation and static mechanical resistance dataset of the main pump equipment in the shutdown and decoupled state. The multi-source heterogeneous data is dimensionless and a trend penalty factor is introduced to correct the rapid degradation index, resulting in a dynamic evaluation value. Based on the state-dependent variable weight model, the dynamic weights of each indicator are calculated using the dynamic evaluation values, and the comprehensive health index is determined based on the dynamic weights and the dynamic evaluation values.

2. The method for full life-cycle health assessment of a main pump based on dynamic-static coupling according to claim 1, characterized in that, The state-dependent variable weighting model, after calculating the dynamic weights of each indicator using the dynamic evaluation values ​​and determining the comprehensive health index based on the dynamic weights and the dynamic evaluation values, further includes: Based on the comprehensive health index, and combined with the hydraulic efficiency index in the static mechanical resistance dataset and the dynamic operation dataset, maintenance decision instructions are output through dynamic-static coupling judgment logic.

3. The method for full life-cycle health assessment of a main pump based on dynamic-static coupling according to claim 1, characterized in that, The rapid degradation index includes a degradation rate slope. The process of dimensionless processing of the multi-source heterogeneous data and the introduction of a trend penalty factor to correct the rapid degradation index yields a dynamic evaluation value, including: The multi-source heterogeneous data is dimensionless to obtain an initial health index. The degradation rate slope of the dynamic running dataset is calculated based on time series analysis. A trend penalty factor is introduced to correct the initial health index to obtain the dynamic evaluation value.

4. The method for full life-cycle health assessment of a main pump based on dynamic-static coupling according to claim 1, characterized in that, The dynamic operation dataset includes at least: bearing temperatures at the drive end and non-drive end, vibration amplitudes of the shaft system in three orthogonal directions, and inlet and outlet pressure differences and instantaneous flow rates used to calculate hydraulic efficiency; The static mechanical resistance dataset includes at least the maximum starting static friction torque and average dynamic friction torque of the rotor system obtained by a torque measuring device.

5. The method for full life-cycle health assessment of a main pump based on dynamic-static coupling according to claim 1, characterized in that, The calculation process for the trend penalty factor and the dynamic evaluation value is as follows: The slope k of the degradation rate of each parameter within a preset period is calculated using the least squares method. When k≤0, trend penalty factor for: ; When k>0, the trend penalty factor for: ; in, The preset trend weight coefficient and 0 < <1; The dynamic evaluation value for: ; in, This is the initial health index after dimensionless processing.

6. The method for full life-cycle health assessment of a main pump based on dynamic-static coupling according to claim 5, characterized in that, The calculation formula for the state-dependent variable weight model is as follows: No. Dynamic weights of each indicator satisfy: ； in, For the first The basic constant weights of each indicator, where exp() is the natural exponential function. α is the variable-weight sensitivity coefficient and α>0, n represents the total number of evaluation indicators, and j represents the traversal sequence number of the indicators; The comprehensive health index is the sum of the products of the corrected dynamic evaluation values ​​of each indicator and their corresponding dynamic weights.

7. The method for full life-cycle health assessment of a main pump based on dynamic-static coupling according to claim 2, characterized in that, Based on the comprehensive health index, and combining the hydraulic efficiency indicators from the static mechanical resistance dataset and the dynamic operation dataset, the maintenance decision command is output through a dynamic-static coupling judgment logic, including: When the comprehensive health index is lower than the preset alarm threshold, the hydraulic efficiency is lower than the set benchmark, and the static mechanical resistance is greater than the preset reference value, it is determined that there is severe friction between the moving and static parts, and an immediate shutdown and disassembly repair command is output. When the comprehensive health index is lower than the preset alarm threshold, the hydraulic efficiency is lower than the set benchmark, but the static mechanical resistance is within the preset reference range, it is determined that the flow component is hydraulically damaged, and a command to postpone disassembly and prioritize the flow channel repair is output. When the comprehensive health index is in the preset warning range, the static mechanical resistance is in the preset reference range, and the slope of the vibration index deterioration rate is greater than zero and fluctuates periodically, it is determined that the rotor is slightly unbalanced or misaligned, and an external adjustment command is output.

8. A main pump life-cycle health assessment device based on dynamic-static coupling, characterized in that, include: The data acquisition module is used to collect multi-source heterogeneous data of dynamic and static fusion of hydraulic machinery. The multi-source heterogeneous data includes dynamic operation datasets during the operation of the main pump equipment and static mechanical resistance datasets in the shutdown and decoupled state of the main pump equipment. The dynamic evaluation value module is used to perform dimensionless processing on the multi-source heterogeneous data and introduce a trend penalty factor to correct the rapid degradation index to obtain a dynamic evaluation value. The comprehensive health index module is used to calculate the dynamic weights of each indicator based on the state-dependent variable weight model and the dynamic evaluation value, and to determine the comprehensive health index based on the dynamic weights and the dynamic evaluation value.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the main pump full life cycle health assessment method based on dynamic-static coupling as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the main pump full life cycle health assessment method based on dynamic-static coupling as described in any one of claims 1 to 7.

Images