Water pump health state evaluation method, device, equipment and medium

Abstract

This disclosure provides a method, apparatus, equipment, and medium for assessing the health status of a water pump, including: when the measured outlet pressure and measured inlet pressure are included in the field operating point data, the actual head is obtained by converting the measured inlet pressure and measured outlet pressure according to the medium density and gravitational constant; when the measured outlet pressure is included in the field operating point data, the actual head is obtained by converting the measured outlet pressure according to the medium density and gravitational constant; a benchmark performance model of the target water pump is introduced as a constraint condition to construct a comprehensive objective function including a head consistency error term and a power consistency error term; minimizing the comprehensive objective function is used as the optimization objective; and the head degradation characterization parameters and power degradation characterization parameters are solved by measuring the measured active power and the actual head; the health status of the target water pump is assessed based on the head degradation characterization parameters and the power degradation characterization parameters to obtain the health assessment result. This allows for a precise assessment of the water pump's health status.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of water pump health assessment technology, and more specifically, to a method, apparatus, device, and medium suitable for assessing the health status of a water pump. Background Technology

[0002] After long-term operation, water pumps may deviate from their factory performance curves due to factors such as scaling, blockage, wear, internal leakage, cavitation, and deviations from operating conditions. Water pump health assessments can promptly identify potential equipment failures, thereby effectively preventing downtime losses caused by sudden malfunctions.

[0003] In related technologies, traditional water pump health assessment methods mainly rely on periodic manual inspections or offline performance tests, which have limitations such as long detection cycles, poor real-time performance, and strong subjectivity, making it difficult to accurately assess the health status of water pumps. Summary of the Invention

[0004] The embodiments described herein provide a method, apparatus, device, and medium for assessing the health status of a water pump, overcoming the aforementioned problems.

[0005] Firstly, based on the content of this disclosure, a method for assessing the health status of a water pump is provided, including: Collect on-site operating point data of the target water pump; the on-site operating point data includes: measured active power, measured outlet pressure, measured inlet pressure and measured speed; or, measured active power, measured outlet pressure and measured speed; When the field operating point data includes measured active power, measured outlet pressure, measured inlet pressure, and measured rotational speed, the measured inlet pressure and measured outlet pressure are converted according to the medium density and gravity constant to obtain the actual head; when the field operating point data includes measured active power, measured outlet pressure, and measured rotational speed, the measured outlet pressure is converted according to the medium density and gravity constant to obtain the actual head. The reference alignment parameters are determined based on the measured rotational speed and the unified reference rotational speed; the measured active power is aligned based on the reference alignment parameters; and the actual head is aligned based on the reference alignment parameters. The pump flow rate is used as a latent variable, and the benchmark performance model of the target pump is introduced as a constraint. A comprehensive objective function containing head consistency error term and power consistency error term is constructed. The optimization objective is to minimize the comprehensive objective function. The head degradation characterization parameter and the power degradation characterization parameter are solved by jointly using the measured active power and the actual head. A preset rule-based grading strategy / self-learning grading strategy is adopted to assess the health status of the target water pump based on the head degradation characterization parameters and the power degradation characterization parameters, thereby obtaining the health assessment result of the target water pump.

[0006] Secondly, according to the present disclosure, a water pump health status assessment device is provided, comprising: The data acquisition module is used to acquire on-site operating point data of the target water pump; the on-site operating point data includes: measured active power, measured outlet pressure, measured inlet pressure, and measured speed; or, measured active power, measured outlet pressure, and measured speed. The conversion module is used to convert the measured inlet pressure and the measured outlet pressure based on the medium density and the gravitational constant when the field operating point data includes measured active power, measured outlet pressure, measured inlet pressure and measured rotational speed, to obtain the actual head; when the field operating point data includes measured active power, measured outlet pressure and measured rotational speed, the module also converts the measured outlet pressure based on the medium density and the gravitational constant to obtain the actual head. The alignment module is used to determine the reference alignment parameters based on the measured rotational speed and the unified reference rotational speed; and to perform data alignment on the measured active power based on the reference alignment parameters; and to perform data alignment on the actual head based on the reference alignment parameters. The determination module is used to take the pump flow rate as a latent variable, introduce the benchmark performance model of the target pump as a constraint, construct a comprehensive objective function including head consistency error term and power consistency error term, and take minimizing the comprehensive objective function as the optimization objective. The head degradation characterization parameter and power degradation characterization parameter are solved by jointly using the measured active power and the actual head. The evaluation module is used to evaluate the health status of the target water pump by adopting a preset rule-based grading strategy / self-learning grading strategy, based on the head degradation characterization parameters and the power degradation characterization parameters, and obtain the health evaluation result of the target water pump.

[0007] Thirdly, a computer device is provided, 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 water pump health status assessment method as described in any of the above embodiments.

[0008] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the water pump health status assessment method as described in any of the above embodiments.

[0009] The pump health status assessment method provided in this application embodiment collects on-site operating point data of the target pump. The on-site operating point data includes: measured active power, measured outlet pressure, measured inlet pressure, and measured rotational speed; or, measured active power, measured outlet pressure, and measured rotational speed. When the on-site operating point data includes measured active power, measured outlet pressure, measured inlet pressure, and measured rotational speed, the measured inlet pressure and measured outlet pressure are converted according to the medium density and gravity constant to obtain the actual head. When the on-site operating point data includes measured active power, measured outlet pressure, and measured rotational speed, the measured outlet pressure is converted according to the medium density and gravity constant to obtain the actual head; the measured rotational speed... A benchmark alignment parameter is determined using a unified reference speed. Based on this parameter, measured active power is aligned to the benchmark alignment parameter, and actual head is aligned to the benchmark alignment parameter. Pump flow rate is used as a latent variable, and the benchmark performance model of the target pump is introduced as a constraint. A comprehensive objective function containing head consistency error terms and power consistency error terms is constructed, with minimizing this comprehensive objective function as the optimization objective. Head degradation characterization parameters and power degradation characterization parameters are jointly solved using measured active power and actual head. A pre-defined rule-based hierarchical strategy / self-learning hierarchical strategy is adopted to assess the health status of the target pump based on the head degradation characterization parameters and power degradation characterization parameters, yielding the target pump's health assessment result. Thus, by introducing pump flow rate as a latent variable into the benchmark performance model and constructing parameterized working models related to actual head and measured power, the actual operating state of the pump can be comprehensively reflected from both hydraulic performance and energy efficiency dimensions, effectively achieving accurate assessment of the pump's health status without relying on direct flow rate measurement.

[0010] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of the embodiments of this application and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of this application more obvious and understandable, specific implementation methods of this application are described below. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments will be briefly described below. It should be understood that the drawings described below only relate to some embodiments of this disclosure and are not intended to limit this disclosure, wherein: Figure 1 This is a flowchart illustrating a method for assessing the health status of a water pump provided in this disclosure.

[0012] Figure 2 This is a schematic diagram of the structure of a water pump health status assessment device provided in this disclosure.

[0013] Figure 3This is a schematic diagram of the structure of a computer device provided in this disclosure.

[0014] It should be noted that the elements in the attached diagram are schematic and not drawn to scale. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure 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 disclosure. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure without creative effort are also within the scope of protection of this disclosure.

[0016] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this subject matter pertains. It will be further understood that terms such as those defined in commonly used dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the specification and in the relevant art, and shall not be interpreted in an idealized or overly formal form unless otherwise explicitly defined herein. As used herein, the statement of “connecting” or “coupling” two or more parts together shall mean that these parts are directly joined together or joined through one or more intermediate components.

[0017] The term "embodiment" as used herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of the phrase "embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0018] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists, A and B exist simultaneously, or B exists. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship. Terms such as "first" and "second" are only used to distinguish one component (or part of a component) from another component (or another part of a component).

[0019] In the description of this application, unless otherwise stated, "multiple" means two or more (including two), and similarly, "multiple groups" means two or more (including two groups).

[0020] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0021] Figure 1 This is a flowchart illustrating a method for assessing the health status of a water pump according to an embodiment of this disclosure, as shown below. Figure 1 As shown, the specific process of the water pump health status assessment method includes: S110. Collect on-site operating point data of the target water pump; the on-site operating point data includes: measured active power, measured outlet pressure, measured inlet pressure and measured speed; or, measured active power, measured outlet pressure and measured speed.

[0022] Among them, the measured active power P_meas is the pump shaft power converted from the input active power. The measured outlet pressure P_out and measured inlet pressure P_in are the fluid pressure values ​​at the outlet and inlet ends of the target pump, respectively, collected by pressure sensors, and can be used to characterize the actual head characteristics of the pump. The measured rotational speed N_meas is the pump shaft rotational speed collected by a speed sensor, which can be used to reflect the pump's operating condition.

[0023] S120. When the field operating point data includes measured active power, measured outlet pressure, measured inlet pressure, and measured speed, the measured inlet pressure and measured outlet pressure are converted according to the medium density and gravity constant to obtain the actual head.

[0024] The actual head H_meas can be obtained by converting the difference between the measured outlet pressure P_out and the measured inlet pressure P_in (combined with the medium density and gravity constant); if there is only outlet pressure and the inlet side is at atmospheric pressure / stable liquid level, the actual head H_meas can be calculated according to the equivalent inlet boundary.

[0025] The actual head H_meas can be calculated as the sum of the pressure head and the potential energy term: H_meas = (P_out - P_in) / (ρ·g) + (z_out - z_in), where ρ is the medium density, g is the gravitational constant, z_out is the height at the outlet side, and z_in is the height at the inlet side. In most pumping station sites, if the inlet and outlet pipe diameters are the same and the velocity term is relatively small, the kinetic energy term can be ignored; when it needs to be considered, it can be corrected by (V_out^2 - V_in^2) / (2g), where V_out is the outlet velocity and V_in is the inlet velocity.

[0026] In some embodiments, the measured inlet pressure and measured outlet pressure are converted according to the medium density and gravity constant to obtain the actual head, including: determining the measured pressure difference based on the difference between the measured outlet pressure and the measured inlet pressure; and determining the actual head based on the measured pressure difference, the medium density and gravity constant.

[0027] For example, if the measured outlet pressure P_out = 0.60 MPa (gauge pressure), the measured inlet pressure P_in = 0.10 MPa (gauge pressure), and ρ = 1000 kg / m³, then the measured pressure difference ΔP = 0.50 MPa. At this time, the pressure head is approximately 0.50 × 10^6 / (1000 × 9.81) ≈ 51.0 m. If the outlet is 5 m higher than the inlet, then the actual head H_meas ≈ 51.0 m + 5 m = 56.0 m.

[0028] In some embodiments, the actual head is obtained by converting the measured outlet pressure based on the medium density and gravity constant, including: calculating the inlet pressure based on the medium density and gravity constant to obtain the estimated inlet pressure; and determining the actual head based on the estimated inlet pressure, the measured outlet pressure, the medium density, and the gravity constant.

[0029] For example, if the inlet pressure is missing, and the inlet is an open pool with the inlet pool level 2m higher than the center of the pump inlet flange, then the estimated inlet pressure P_in≈ρ·g·2m (gauge pressure); if the measured outlet pressure P_out=0.60MPa (gauge pressure), then the actual head H_meas≈(0.60×10^6-ρ·g·2) / (ρ·g)≈59.2m (not accounting for the height difference). If the inlet pressure is missing, and it is a closed system, when the inlet side cannot be considered as atmospheric pressure or a stable liquid level, the inlet boundary can be treated as an unknown / prior parameter and incorporated into the confidence mechanism: for example, the inlet pressure range can be estimated using the system static pressure, minimum operating pressure, or other measurable points in the same pumping station, thereby obtaining an interval estimate of the actual head H_meas, which can then be used as an interval constraint or penalty term in subsequent parameter solving.

[0030] S130. Determine the reference alignment parameters based on the measured speed and the unified reference speed; align the measured active power data based on the reference alignment parameters; align the actual head data based on the reference alignment parameters.

[0031] In variable frequency / variable speed scenarios, the operating point is converted to a unified reference frequency / speed condition to align the measured active power and actual head data. For example, conversion can be performed based on similarity / proportional laws to align the operating points at different frequencies / speeds to a unified reference speed N0. Let r = N0 / N_meas, then: the aligned actual head H_meas = H_meas × r^2; Measured active power P_meas after alignment = P_meas × r^3.

[0032] In some embodiments, before determining the reference alignment parameters based on the measured speed and the unified reference speed, the method further includes: performing steady-state screening on the measured speed, actual head, and measured active power respectively; and performing range and saturation checks, rationality checks, and abnormal fluctuation identification on the measured speed, actual head, and measured active power respectively, so as to perform quality control on the measured speed, actual head, and measured active power.

[0033] In steady-state screening, taking 1-second sampling data as an example, a sliding time window can be used for steady-state judgment: Assume a window length of 30s–120s (e.g., 60s), and calculate the fluctuation indices of frequency / speed, head, and power for each window. For example, stable speed: max(f)-min(f) ≤ 0.2Hz or std(f) / mean(f) ≤ 0.5%; stable head: std(H_meas) / mean(H_meas) ≤ 1% (or ≤ 2%); stable power: std(P_meas) / mean(P_meas) ≤ 1% (or ≤ 3%); excluding start-stop: all transitional periods when f rises or falls from 0 (e.g., 60–180s before and after start-stop) are excluded. For windows that pass the screening, the median / mean value within the window can be taken as the "representative steady-state point".

[0034] Quality control can be used to eliminate data from sensors that are malfunctioning, have distorted measurement points, or are unusable due to unforeseen operating conditions. For example, range and saturation checks: points where pressure / power exceeds the sensor's range, shows prolonged fixed values ​​(jamming), or exhibits fluctuations exceeding the physical limit are directly eliminated; rationality checks: unreasonable points such as P_meas≤0, P_meas>k·P_rated (e.g., k=1.2), or H_meas<0 are eliminated; consistency checks: within the same window, the direction of change of H_meas and P_meas should be consistent with the change in rotational speed (e.g., an increase in rotational speed usually leads to an increase in H and P), otherwise the data is considered to have low reliability; abnormal fluctuation identification: if high-frequency oscillations exist within the steady-state window (e.g., the root mean square of dH / dt and dP / dt exceeds the threshold), it can indicate non-steady-state factors such as "potential cavitation / intake / frequent valve operation."

[0035] Therefore, by performing steady-state screening and quality control on the measured speed, actual head, and active power, it is possible to eliminate start-stop, strong fluctuation, and obvious abnormal segments, so as to obtain an effective set of steady-state data points that reflect the true operating characteristics of the water pump.

[0036] S140. The pump flow rate is taken as a latent variable, and the benchmark performance model of the target pump is introduced as a constraint. A comprehensive objective function containing head consistency error term and power consistency error term is constructed. The optimization objective is to minimize the comprehensive objective function. The head degradation characterization parameter and power degradation characterization parameter are solved by combining the measured active power and the actual head.

[0037] The target pump's baseline performance model includes a baseline head model H0(Q) and a baseline power model P0(Q), where Q is the flow rate independent variable. The baseline performance curve can be fitted using discrete curve point data from factory tests, type tests, and acceptance tests. Specifically, a joint consistency objective function can be constructed using the actual head and measured active power to jointly solve for the shared latent variable Q and parameters aH, aP, and optional b; alternatively, during step-by-step solution, shared constraints or iterative methods can be used to ensure consistency between the two models in terms of the latent variable Q and the flow domain offset parameter b.

[0038] The overall objective function includes a head consistency error term: H_work(Q) = aH H0(Q) or H_work(Q) = aH H0(b Q), and the power consistency error term: P_work(Q) = aP P0(Q) or P_work(Q) = aP P0(b Q). Here, aH is the head direction scaling factor (i.e., the head degradation characterization parameter), used to characterize the head offset caused by changes in hydraulic capacity; aP is the power direction scaling factor (i.e., the power degradation characterization parameter), used to characterize the power offset caused by changes in efficiency / loss. b is the flow direction scaling factor, used to describe the overall flow domain offset or equivalent geometric change; when field data is insufficient to identify b, a preset / prior parameter or setting it to 1 can be used and the corresponding confidence level output.

[0039] In the absence of single-pump flow measurement, the flow rate Q is treated as a latent or estimated variable and introduced into the baseline model constraints to align the finite data points with the parameterized working model. Fitting / iteration / optimization methods can be used to simultaneously solve for aH, aP (and optional b), ensuring the model output aligns with {P_meas}. ,H_meas The consistency error is minimized. The fitting method can be least squares, iterative search, data-driven optimization, or a combination thereof; when data coverage is insufficient or latent variables cannot be stably identified, the corresponding confidence level (Conf) is output.

[0040] S150. Using a preset rule-based grading strategy / self-learning grading strategy, the target water pump is evaluated for its health status based on the head degradation characterization parameters and power degradation characterization parameters, and the health evaluation results of the target water pump are obtained.

[0041] During the health status assessment, the target water pump can be evaluated using head degradation characterization parameters and power degradation characterization parameters combined with the flow parameter b. The health assessment results of the target water pump may include: degradation coefficients aH and aP (optional b) and confidence level Conf, degradation mechanism labels (which can be cross-overlaid), health level and trend, and indicator inputs provided for energy-saving assessment, technical upgrades, and maintenance decisions.

[0042] The degradation mechanism label can be obtained by mapping the deviation direction and magnitude of aH and aP. The degradation mechanism label may include, but is not limited to, problems such as decreased hydraulic channel capacity, efficiency or internal leakage / mechanical loss, problems dominated by changes in equivalent geometry / flow domain, and other abnormal operating conditions that need to be indicated (such as cavitation / air intake, etc.).

[0043] Mechanism mapping can be implemented using a pre-defined rule base, statistical discriminant model, fuzzy inference, decision tree, or classification model trained based on historical maintenance labels. Rule parameters can be configured according to pump type, medium, and control method, and can be iteratively updated with new data. The output of mechanism mapping can be a set of candidate mechanism labels and their corresponding scores / probabilities / confidence levels, used to suggest possible causes rather than directly determining the final fault. When the confidence level (Conf) is low, only a prompt of "requires verification / requires additional data collection" can be output. For example, when the relative decrease in aH is more prominent, it can indicate a correlation with a decrease in hydraulic channel capacity; when the deviation of aP is more prominent while aH is relatively stable, it can indicate a correlation with changes in efficiency or losses; when the deviation of b is significant, it can indicate that operating point migration or equivalent geometric changes are dominant.

[0044] In some embodiments, a pre-defined rule-based hierarchical strategy is employed to assess the health status of the target water pump based on head degradation characterization parameters and power degradation characterization parameters, thereby obtaining a health assessment result for the target water pump. This includes: predicting the rate of change of the degradation trend of the target water pump based on the head degradation characterization parameters and power degradation characterization parameters; determining the steady-state prediction score of the target water pump based on the head degradation characterization parameters and power degradation characterization parameters; and determining the health assessment result of the target water pump based on the rate of change of the degradation trend, the steady-state prediction score, the deviation magnitude and direction of the head degradation characterization parameters, the deviation magnitude and direction of the power degradation characterization parameters, the confidence level of the head degradation characterization parameters, and the confidence level of the power degradation characterization parameters.

[0045] The system can perform weighted scoring on the target pump's degradation trend change rate, steady-state prediction score, deviation magnitude and direction of head degradation characterization parameters, deviation magnitude and direction of power degradation characterization parameters, confidence level of head degradation characterization parameters, and confidence level of power degradation characterization parameters. After segmented mapping, fuzzy inference, hierarchical decision tree, or rule base matching, the health assessment result of the target pump is obtained. Thresholds, weights, and level boundaries are configurable parameters that can be set according to pump type, operating condition, medium, and control method. For example, when the deviation magnitude is small and the trend is stable with high Conf, a higher level (e.g., A) is output; when the deviation magnitude or trend deterioration increases, a medium level (e.g., B / C) is output; when the deviation magnitude is significant, the trend deteriorates rapidly, or the abnormal duration is long, a lower level (e.g., D) is output, along with maintenance / review suggestions.

[0046] In some embodiments, a self-learning grading strategy is adopted to assess the health status of the target water pump based on the head degradation characterization parameters and power degradation characterization parameters, and to obtain the health assessment result of the target water pump. This includes: performing anomaly detection on the head degradation characterization parameters and power degradation characterization parameters based on the historical operating distribution of other water pumps related to the target water pump, and obtaining the anomaly detection level; and determining the health assessment result of the target water pump based on the anomaly detection level of the head degradation characterization parameters and power degradation characterization parameters.

[0047] Among them, pumps of the same model or category can be regarded as other pumps that are related to the target pump. Based on their historical operation distribution, quantile division, clustering or anomaly detection of aH, aP (optional b) and their rate of change are performed to automatically form the boundaries of each level. The classification model is iteratively updated in combination with the conclusions of manual maintenance to adapt to different pump types and field differences.

[0048] In some embodiments, the method further includes: determining the degradation risk value of the target water pump based on the health assessment results of the target water pump; if the degradation risk value of the target water pump exceeds a preset risk threshold, generating a degradation warning prompt corresponding to the target water pump.

[0049] The health assessment results can be quantified using health assessment levels, degradation trend rates, and operating condition weights to obtain degradation risk values. For example, the health status is divided into four levels: normal, attention, abnormal, and dangerous, corresponding to risk ranges of 0-0.3, 0.3-0.6, 0.6-0.85, and 0.85-1.0, respectively. Head degradation rate and power degradation rate are introduced as dynamic correction factors. When the degradation rate exceeds the historical statistical threshold, the baseline risk score is weighted upwards by a preset coefficient. Simultaneously, an operating condition influence coefficient is set to reflect the accelerating effect of actual operating intensity on the degradation process. Finally, a continuous degradation risk value in the 0-1 range is obtained through multi-factor fusion calculation. When the degradation risk value exceeds the preset risk threshold, a graded early warning prompt can be automatically triggered, and the prompt method can be configured according to the difference in risk severity, thereby realizing closed-loop monitoring and proactive maintenance of the pump's health status.

[0050] In this embodiment, on-site operating point data of the target water pump is collected. This data includes: measured active power, measured outlet pressure, measured inlet pressure, and measured rotational speed; or, measured active power, measured outlet pressure, and measured rotational speed. When the on-site operating point data includes measured active power, measured outlet pressure, measured inlet pressure, and measured rotational speed, the measured inlet pressure and measured outlet pressure are converted based on the medium density and gravity constant to obtain the actual head. Similarly, when the on-site operating point data includes measured active power, measured outlet pressure, and measured rotational speed, the measured outlet pressure is converted based on the medium density and gravity constant to obtain the actual head. The measured rotational speed and a unified reference rotational speed are then used to calculate the actual head. The process involves determining benchmark alignment parameters; aligning measured active power data with these parameters; aligning actual head data with these parameters; introducing pump flow rate as a latent variable and using the target pump's benchmark performance model as a constraint; constructing a comprehensive objective function containing head consistency error terms and power consistency error terms; minimizing this comprehensive objective function as the optimization objective; and jointly solving for head degradation and power degradation characterization parameters using measured active power and actual head. A pre-defined rule-based hierarchical strategy / self-learning hierarchical strategy is employed to assess the target pump's health status based on these parameters, yielding the target pump's health assessment results. Thus, by introducing pump flow rate as a latent variable into the benchmark performance model and constructing parameterized working models related to actual head and measured power, the actual operating state of the pump can be comprehensively reflected from both hydraulic performance and energy efficiency dimensions, effectively achieving accurate pump health status assessment without relying on direct flow rate measurement.

[0051] In summary, this embodiment presents a general degradation quantification framework for "limited power and pressure data, without single-pump flow rate," which can be directly implemented in large-scale pumping station sites. It uniformly characterizes degradation using parametric curve scaling factors aH / aP (optional b), ensuring interpretability and transferability. Even without flow rate measurement, degradation parameters can still be solved through baseline model constraints, significantly reducing sensor dependence and expert costs. The aH / aP combination maps degradation mechanisms and outputs health grading, forming a manageable degradation profile. The confidence mechanism adapts to different data coverage and identifiability, ensuring engineering usability and clearly defining confidence boundaries. Thus, degradation quantification and trend tracking are achieved even without single-pump flow rate; it is low-cost, easily replicable, and suitable for rapid coverage of existing pumps at the group level; it supports energy-saving technological upgrade assessments, optimal scheduling, and predictive maintenance.

[0052] Figure 2 This is a schematic diagram of a water pump health status assessment device provided in this embodiment. The water pump health status assessment device may include: The data acquisition module 210 is used to acquire field operating point data of the target water pump; the field operating point data includes: measured active power, measured outlet pressure, measured inlet pressure and measured speed; or, measured active power, measured outlet pressure and measured speed.

[0053] The conversion module 220 is used to convert the measured inlet pressure and measured outlet pressure based on the medium density and gravity constant when the field operating point data includes measured active power, measured outlet pressure, measured inlet pressure and measured speed, to obtain the actual head; when the field operating point data includes measured active power, measured outlet pressure and measured speed, it converts the measured outlet pressure based on the medium density and gravity constant to obtain the actual head.

[0054] Alignment module 230 is used to determine the reference alignment parameters based on the measured speed and the unified reference speed; and to perform data alignment of the measured active power based on the reference alignment parameters; and to perform data alignment of the actual head based on the reference alignment parameters.

[0055] The determination module 240 is used to take the pump flow rate as a latent variable, introduce the benchmark performance model of the target pump as a constraint, construct a comprehensive objective function including head consistency error term and power consistency error term, and take minimizing the comprehensive objective function as the optimization objective. The head degradation characterization parameter and power degradation characterization parameter are solved by jointly using measured active power and actual head.

[0056] The evaluation module 250 is used to evaluate the health status of the target water pump by adopting a preset rule-based grading strategy / self-learning grading strategy, based on the head degradation characterization parameters and power degradation characterization parameters, and obtain the health evaluation result of the target water pump.

[0057] In some embodiments, the evaluation module 250 is specifically used for: The rate of change of the deterioration trend of the target water pump is predicted based on the head deterioration characterization parameters and the power deterioration characterization parameters; the steady-state prediction score of the target water pump is determined based on the rate of change of the deterioration trend of the target water pump, the steady-state prediction score, the deviation magnitude and direction of the head deterioration characterization parameters, the deviation magnitude and direction of the power deterioration characterization parameters, the confidence level of the head deterioration characterization parameters, and the confidence level of the power deterioration characterization parameters.

[0058] In some embodiments, the evaluation module 250 is specifically used for: Based on the historical operating distribution of other pumps related to the target pump, anomaly detection is performed on the head degradation characterization parameters and power degradation characterization parameters to obtain the anomaly detection level; based on the anomaly detection level of the head degradation characterization parameters and power degradation characterization parameters, the health assessment result of the target pump is determined.

[0059] In some embodiments, a screening module is also included.

[0060] The screening module is used to perform steady-state screening of measured speed, actual head, and measured active power respectively; and to perform range and saturation checks, rationality checks, and abnormal fluctuation identification on measured speed, actual head, and measured active power respectively, so as to perform quality control on measured speed, actual head, and measured active power.

[0061] In some embodiments, the conversion module 220 is specifically used for: The measured pressure difference is determined by the difference between the measured outlet pressure and the measured inlet pressure; and the actual head is determined by the measured pressure difference, the medium density, and the gravity constant.

[0062] In some embodiments, the conversion module 220 is specifically used for: The inlet pressure is calculated based on the medium density and gravity constant to obtain the estimated inlet pressure; the actual head is determined based on the estimated inlet pressure, the measured outlet pressure, the medium density, and the gravity constant.

[0063] In some embodiments, a generation module is also included.

[0064] The generation module is used to determine the degradation risk value of the target water pump based on the health assessment results of the target water pump; if the degradation risk value of the target water pump exceeds the preset risk threshold, a corresponding degradation warning prompt is generated for the target water pump.

[0065] The water pump health status assessment device provided in this disclosure can perform the above-described method embodiments. Its specific implementation principle and technical effects can be found in the above-described method embodiments, and will not be repeated here.

[0066] This application also provides a computer device. Please refer to the following for details. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0067] The computer device includes a memory 310 and a processor 320 that are interconnected via a system bus. It should be noted that only a computer device with memory 310 and processor 320 is shown in the figure; however, it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented alternatively. Those skilled in the art will understand that the computer device described herein is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0068] Computer devices can include desktop computers, laptops, handheld computers, and cloud servers. These devices allow for human-computer interaction with users through keyboards, mice, remote controls, touchpads, or voice-activated devices.

[0069] The memory 310 includes at least one type of readable storage medium, including non-volatile memory or volatile memory, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. RAM may include static RAM or dynamic RAM. In some embodiments, the memory 310 may be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the memory 310 may also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, or flash card equipped on the computer device. Of course, the memory 310 may include both internal storage units and external storage devices of the computer device. In this embodiment, the memory 310 is typically used to store the operating system and various application software installed on the computer device, such as the program code of the method described above. In addition, the memory 310 can also be used to temporarily store various types of data that have been output or will be output.

[0070] Processor 320 is typically used to perform overall operations of a computer device. In this embodiment, memory 310 is used to store program code or instructions, including computer operation instructions, and processor 320 is used to execute the program code or instructions stored in memory 310 or process data, such as program code that runs the methods described above.

[0071] In this article, the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus system can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0072] Another embodiment of this application also provides a computer-readable medium, which may be a computer-readable signal medium or a computer-readable medium. A processor in a computer reads computer-readable program code stored in the computer-readable medium, enabling the processor to execute the functional actions specified in each step or combination of steps in the above method; and to generate means for implementing the functional actions specified in each block or combination of blocks in the block diagram.

[0073] Computer-readable media include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared memory or semiconductor systems, devices or apparatuses, or any suitable combination thereof, wherein the memory is used to store program code or instructions, the program code including computer operation instructions, and the processor is used to execute the program code or instructions of the above-described methods stored in the memory.

[0074] The definitions of memory and processor can be found in the description of the foregoing computer device embodiments, and will not be repeated here.

[0075] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0076] In the various embodiments of this application, the functional units or modules can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0077] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it 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 all or 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.) or processor to execute all or part of the steps of the methods of 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.

[0078] In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" as described in this application does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims listing several means, several units of these means may be embodied by the same item of hardware. The use of "first," "second," and "third," etc., does not indicate any order and these words should be interpreted as names. Unless otherwise specified, the steps in the above embodiments should not be construed as limiting the order of execution.

[0079] 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 water pump health condition evaluation method, characterized by, include: Collect on-site operating data of the target water pump; The field operation point data includes: measured active power, measured outlet pressure, measured inlet pressure, and measured rotational speed; or, measured active power, measured outlet pressure, and measured rotational speed. When the field operating point data includes measured active power, measured outlet pressure, measured inlet pressure, and measured rotational speed, the measured inlet pressure and measured outlet pressure are converted according to the medium density and gravity constant to obtain the actual head; when the field operating point data includes measured active power, measured outlet pressure, and measured rotational speed, the measured outlet pressure is converted according to the medium density and gravity constant to obtain the actual head. The reference alignment parameters are determined based on the measured rotational speed and the unified reference rotational speed; the measured active power is aligned based on the reference alignment parameters; and the actual head is aligned based on the reference alignment parameters. The pump flow rate is used as a latent variable, and the benchmark performance model of the target pump is introduced as a constraint. A comprehensive objective function containing head consistency error term and power consistency error term is constructed. The optimization objective is to minimize the comprehensive objective function. The head degradation characterization parameter and the power degradation characterization parameter are solved by jointly using the measured active power and the actual head. A preset rule-based grading strategy / self-learning grading strategy is adopted to assess the health status of the target water pump based on the head degradation characterization parameters and the power degradation characterization parameters, thereby obtaining the health assessment result of the target water pump.

2. The method of claim 1, wherein, A pre-defined rule-based classification strategy is adopted to assess the health status of the target water pump based on the head degradation characterization parameters and the power degradation characterization parameters, resulting in a health assessment result for the target water pump, including: The rate of change of the degradation trend of the target water pump is predicted based on the head degradation characterization parameters and the power degradation characterization parameters; the steady-state prediction score of the target water pump is determined based on the head degradation characterization parameters and the power degradation characterization parameters. The health assessment result of the target water pump is determined based on the rate of change of the deterioration trend, the steady-state prediction score, the deviation magnitude and direction of the head deterioration characterization parameter, the deviation magnitude and direction of the power deterioration characterization parameter, the confidence level of the head deterioration characterization parameter, and the confidence level of the power deterioration characterization parameter.

3. The method according to claim 1, characterized in that, A self-learning classification strategy is adopted to assess the health status of the target water pump based on the head degradation characterization parameters and the power degradation characterization parameters, resulting in a health assessment result for the target water pump, including: Based on the historical operating distribution of other pumps associated with the target pump, anomaly detection is performed on the head degradation characterization parameter and the power degradation characterization parameter to obtain the anomaly detection level. The health assessment result of the target water pump is determined based on the abnormal detection level of the head degradation characterization parameter and the power degradation characterization parameter.

4. The method according to claim 1, characterized in that, Before determining the reference alignment parameters based on the measured rotational speed and the unified reference rotational speed, the following steps are also included: Steady-state screening is performed on the measured rotational speed, the actual head, and the measured active power, respectively. The measured rotational speed, actual head, and measured active power are respectively subjected to range and saturation checks, rationality checks, and abnormal fluctuation identification in order to perform quality control on the measured rotational speed, actual head, and measured active power.

5. The method according to claim 1, characterized in that, The actual head is obtained by converting the measured inlet pressure and the measured outlet pressure based on the medium density and the gravitational constant, including: The measured pressure difference is determined based on the difference between the measured outlet pressure and the measured inlet pressure; and the actual head is determined based on the measured pressure difference, the medium density, and the gravity constant.

6. The method according to claim 1, characterized in that, The actual head is obtained by converting the measured outlet pressure based on the medium density and gravitational constant, including: The inlet pressure is calculated based on the medium density and the gravitational constant, and the estimated inlet pressure is obtained. The actual head is determined based on the estimated inlet pressure, the measured outlet pressure, the medium density, and the gravity constant.

7. The method according to claim 1, characterized in that, Also includes: The degradation risk value of the target water pump is determined based on the health assessment results of the target water pump; If the degradation risk value of the target water pump exceeds a preset risk threshold, a degradation warning message corresponding to the target water pump will be generated.

8. A water pump health status assessment device, characterized in that, include: The data acquisition module is used to collect on-site operating data of the target water pump; The field operation point data includes: measured active power, measured outlet pressure, measured inlet pressure, and measured rotational speed; or, measured active power, measured outlet pressure, and measured rotational speed. The conversion module is used to convert the measured inlet pressure and the measured outlet pressure based on the medium density and the gravitational constant when the field operating point data includes measured active power, measured outlet pressure, measured inlet pressure and measured rotational speed, to obtain the actual head; when the field operating point data includes measured active power, measured outlet pressure and measured rotational speed, the module also converts the measured outlet pressure based on the medium density and the gravitational constant to obtain the actual head. The alignment module is used to determine the reference alignment parameters based on the measured rotational speed and the unified reference rotational speed; and to perform data alignment on the measured active power based on the reference alignment parameters; and to perform data alignment on the actual head based on the reference alignment parameters. The determination module is used to take the pump flow rate as a latent variable, introduce the benchmark performance model of the target pump as a constraint, construct a comprehensive objective function including head consistency error term and power consistency error term, and take minimizing the comprehensive objective function as the optimization objective. The head degradation characterization parameter and power degradation characterization parameter are solved by jointly using the measured active power and the actual head. The evaluation module is used to evaluate the health status of the target water pump by adopting a preset rule-based grading strategy / self-learning grading strategy, based on the head degradation characterization parameters and the power degradation characterization parameters, and obtain the health evaluation result of the target water pump.

9. A computer device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the water pump health status assessment method as described in 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 the processor, it implements the pump health status assessment method as described in any one of claims 1 to 7.

Images