Method, apparatus, and storage medium for determining operating conditions of a target pump

Abstract

Embodiments of the present application relate to a method, device and storage medium for determining a working condition of a target pump. The method comprises: obtaining nameplate data of the target pump, so as to obtain a plurality of performance parameters of the target pump based on the obtained nameplate data; calculating a specific speed of the target pump based on the plurality of performance parameters; determining a type of the target pump based on the specific speed of the target pump, so as to match a pump performance curve prediction model based on the type of the target pump; predicting an initial performance curve of the target pump via the matched pump performance curve prediction model based on the plurality of performance parameters; performing shape constraint optimization on the initial performance curve of the target pump, so as to obtain a predicted performance curve of the target pump; and determining the working condition of the target pump based on the predicted performance curve of the target pump. Thus, stable and reliable performance curve prediction and working condition determination results can be obtained for different types of pumps without relying on the factory performance curve of the pump device.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of industrial control, and more specifically to a method, apparatus, and storage medium for determining the operating conditions of a target pump. Background Technology

[0002] The performance curve of a pump determines the accuracy of its operating condition assessment, and accurately determining the operating condition of a water pump is a key prerequisite for implementing energy-saving optimization and predictive maintenance. In industrial sites, such as building water supply systems and renovation projects, complete factory test reports (including performance curves) for water pumps are easily lost or unavailable. At the same time, due to cost or installation limitations, the deployment rate of critical sensors such as flow meters is not high in these projects, leading to a frequent dilemma of "no standard curve, no flow signal" in water supply systems.

[0003] Regarding pump operating condition assessment, existing technologies primarily rely on complete factory performance curves (i.e., standard QH (flow-head), QP (flow-power), and QE (flow-efficiency) curves). For example, operating condition calculations based on standard curve matching and interpolation require accurate pump performance curve data provided by the manufacturer beforehand. This method is highly dependent on complete and accurate factory performance curve data, which is often lacking in actual engineering, especially for a large number of existing or poorly documented pumps. Another example is performance curve estimation methods based on purely data-driven approaches, which employ machine learning models (such as LightGBM and neural networks). These methods directly predict performance curves based on the pump's nameplate parameters (such as rated flow, head, power, and speed). They use purely "black box" fitting data, potentially leading to curves that violate basic physical principles or failing to account for significant performance differences between pumps with different specific speeds. This results in unstable predictions that cannot meet the reliability requirements of engineering applications.

[0004] In summary, the shortcomings of traditional methods for determining the operating conditions of a target pump are that they are highly dependent on the equipment's factory performance curves, lack versatility, and cannot provide stable and reliable results for different types of pumps. Summary of the Invention

[0005] To address the aforementioned problems, this invention provides a method, apparatus, and storage medium for determining the operating conditions of a target pump. This method is independent of the pump's factory performance curve and can obtain stable and reliable performance curve predictions and operating condition judgments for different types of pumps.

[0006] According to a first aspect of the present invention, a method for determining the operating conditions of a target pump is provided, comprising: acquiring nameplate data of the target pump to acquire a plurality of performance parameters of the target pump based on the acquired nameplate data; calculating the specific speed of the target pump based on the plurality of performance parameters; determining the type of the target pump based on the specific speed of the target pump to match a pump performance curve prediction model based on the type of the target pump; predicting an initial performance curve of the target pump based on the plurality of performance parameters via the matched pump performance curve prediction model; performing morphological constraint optimization on the initial performance curve of the target pump to obtain a predicted performance curve of the target pump; and determining the operating conditions of the target pump based on the predicted performance curve of the target pump.

[0007] In some embodiments, determining the type of the target pump based on its specific speed, so as to match a pump performance curve prediction model based on the type of the target pump, includes: if the specific speed of the target pump is less than 80, determining the type of the target pump as a low specific speed pump; if the specific speed of the target pump is greater than 150, determining the type of the target pump as a high specific speed pump; if the specific speed of the target pump is greater than or equal to 80 and less than or equal to 150, determining the type of the target pump as a medium specific speed pump; and matching a target specific speed pump performance curve prediction model based on the type of the target pump, wherein the target specific speed pump performance curve prediction model is any one of the following: a low specific speed pump performance curve prediction model, a medium specific speed pump performance curve prediction model, or a high specific speed pump performance curve prediction model.

[0008] In some embodiments, morphological constraint optimization of the initial performance curve of the target pump to obtain a predicted performance curve of the target pump includes: applying physical constraints to the initial performance curve of the target pump based on predetermined physical rules, wherein the predetermined physical rules include any one of the following: the initial flow-head performance curve is monotonically decreasing, and the initial flow-power performance curve is monotonically increasing.

[0009] In some embodiments, morphological constraint optimization of the initial performance curve of the target pump to obtain a predicted performance curve of the target pump further includes: morphological constraint optimization of the initial flow-head performance curve based on the shut-off head point, rated operating point, and extreme point to obtain a first flow-head performance curve of the target pump; and morphological constraint optimization of the initial flow-power performance curve based on the shut-off head point, rated operating point, and predetermined flow point to obtain a first flow-power performance curve of the target pump.

[0010] In some embodiments, morphological constraint optimization of the initial flow-head performance curve based on the shut-off head point, rated operating point, and extreme point to obtain the first flow-head performance curve of the target pump includes: adjusting the shut-off head point on the initial flow-head performance curve so that the shut-off head point of the initial flow-head performance curve is within a predetermined multiple range of the rated operating point; adjusting the initial flow-head performance curve so that the initial flow-head performance curve passes through the rated operating point; and adjusting the extreme point of the initial flow-head performance curve so that the value of the extreme point of the initial flow-head performance curve is less than or equal to a predetermined multiple of the value of the shut-off head point.

[0011] In some embodiments, morphological constraint optimization of the initial flow-power performance curve based on the shut-off head point, rated operating point, and predetermined flow point to obtain a first flow-power performance curve of the target pump includes: adjusting the shut-off head point on the initial flow-power performance curve such that the power value at the shut-off head point of the initial flow-power performance curve is greater than zero and less than or equal to the rated power; adjusting the initial flow-power performance curve such that the initial flow-power performance curve passes through the rated operating point; and adjusting the predetermined flow point of the initial flow-power performance curve such that the power value at the predetermined flow point of the flow-power performance curve is greater than or equal to the rated power, in order to obtain a first flow-power performance curve of the target pump.

[0012] In some embodiments, morphological constraint optimization of the initial performance curve of the target pump to obtain a predicted performance curve of the target pump further includes: calculating an initial flow efficiency performance curve of the target pump based on a first flow head performance curve and a first flow power performance curve of the target pump; and adjusting the initial flow efficiency performance curve so that the initial flow efficiency performance curve passes through the rated operating point in order to obtain a predicted flow efficiency performance curve.

[0013] In some embodiments, morphological constraint optimization of the initial performance curve of the target pump to obtain a predicted performance curve for the target pump further includes: correcting the first flow-head performance curve based on the predicted flow efficiency performance curve and the efficiency formula to obtain a second flow-head performance curve; and correcting the second flow-head performance curve based on the error value between the rated point of the second flow-head performance curve and the nameplate data to obtain a predicted flow-head performance curve.

[0014] In some embodiments, morphological constraint optimization of the initial performance curve of the target pump to obtain a predicted performance curve of the target pump further includes: calculating a second flow-power performance curve of the target pump based on the predicted flow-efficiency performance curve and the predicted flow-head performance curve of the target pump; and correcting the second flow-power performance curve based on the error value between the rated point of the second flow-power performance curve and the nameplate data, so as to obtain a predicted flow-power performance curve.

[0015] In some embodiments, determining the operating condition of a target pump based on its predicted performance curve includes: acquiring real-time flow data of the target pump, the real-time flow data including: real-time monitored flow or real-time predicted flow; acquiring the real-time operating point of the target pump based on the real-time flow data; determining the optimal efficiency range of the target pump based on its pump type; and comparing the real-time operating point of the target pump with the corresponding optimal efficiency range to determine the operating condition of the target pump.

[0016] In some embodiments, the method for determining the operating conditions of a target pump further includes: calculating first flow data of the target pump based on real-time head data and a predicted flow-head performance curve of the target pump; calculating second flow data of the target pump based on real-time shaft power and a predicted flow-power performance curve of the target pump; and determining a flow calculation weighting coefficient based on the specific speed of the target pump, so as to perform a weighted calculation based on the first flow data and the second flow data to obtain real-time predicted flow data of the target pump.

[0017] According to a second aspect of the present invention, a computing device is provided, the computing device comprising: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the device to perform steps according to the method of the first aspect.

[0018] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a machine, implements the method according to the first aspect.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] The above and other features, advantages, and aspects of the various embodiments of the present invention will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements.

[0021] Figure 1 A schematic diagram of a system for implementing a method for determining the operating conditions of a target pump according to an embodiment of the present invention is shown.

[0022] Figure 2 A flowchart of a method for determining the operating conditions of a target pump according to an embodiment of the present invention is shown.

[0023] Figure 3 A flowchart of a method for morphological constraint optimization of flow-head performance curves according to an embodiment of the present invention is shown.

[0024] Figure 4 A flowchart of a method for morphological constraint optimization of flow-power performance curves according to an embodiment of the present invention is shown.

[0025] Figure 5 An embodiment of the invention is shown for optimizing pump performance curves.

[0026] Figure 6 A flowchart of a method for calculating real-time predicted flow data of a target pump according to an embodiment of the present invention is shown.

[0027] Figure 7 A block diagram of an electronic device according to an embodiment of the present invention is shown.

[0028] Figure 8 An initial flow-head performance curve of a target pump according to an embodiment of the present invention is shown.

[0029] Figure 9 An initial flow-head performance curve of a target pump according to an embodiment of the present invention is shown. .

[0030] Figure 10 An initial flow-head performance curve of a target pump according to an embodiment of the present invention is shown. .

[0031] Figure 11 A first flow-head performance curve of a target pump according to an embodiment of the present invention is shown.

[0032] Figure 12 An initial flow-power performance curve of a target pump according to an embodiment of the present invention is shown.

[0033] Figure 13An initial flow-power performance curve of a target pump according to an embodiment of the present invention is shown. .

[0034] Figure 14 An initial flow-power performance curve of a target pump according to an embodiment of the present invention is shown. .

[0035] Figure 15 A first flow-power performance curve of a target pump according to an embodiment of the present invention is shown.

[0036] Figure 16 An initial flow efficiency performance curve of a target pump according to an embodiment of the present invention is shown.

[0037] Figure 17 A predicted flow efficiency performance curve of a target pump according to an embodiment of the present invention is shown.

[0038] Figure 18 A second flow-head performance curve of a target pump according to an embodiment of the present invention is shown.

[0039] Figure 19 A predicted flow-head performance curve of a target pump according to an embodiment of the present invention is shown.

[0040] Figure 20 A second flow-power performance curve of a target pump according to an embodiment of the present invention is shown.

[0041] Figure 21 A predicted flow-power performance curve of a target pump according to an embodiment of the present invention is shown. Detailed Implementation

[0042] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0043] The term "comprising" and its variations as used herein signify open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "at least partially based on". The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0044] As described above, the shortcomings of traditional methods for determining the operating conditions of a target pump are that they are highly dependent on the equipment's factory performance curves and lack versatility, failing to provide stable and reliable results for different types of pumps.

[0045] To at least partially address one or more of the aforementioned problems and other potential issues, an exemplary embodiment of the present invention proposes a method for determining the operating condition of a target pump. In this invention, nameplate data of the target pump is obtained to acquire multiple performance parameters related to the target pump; the specific speed of the target pump is calculated based on these performance parameters; the type of the target pump is determined based on its specific speed, so as to match a pump performance curve prediction model based on the target pump type; an initial performance curve for the target pump is predicted based on the multiple performance parameters via the matched pump performance curve prediction model; then, morphological constraint optimization is performed on the initial performance curve of the target pump to obtain a predicted performance curve for the target pump; and the operating condition of the target pump is determined based on the predicted performance curve. This allows for stable and reliable performance curve prediction and operating condition judgment results without relying on the factory performance curve of the pump equipment, and for different types of pumps.

[0046] Figure 1 A schematic diagram of a system 100 for implementing a method for determining the operating conditions of a target pump according to an embodiment of the present invention is shown. Figure 1 As shown, system 100 includes a computing device 110 and a target pump 130, a network 140 and a data acquisition device 150. The computing device 110, the target pump 130 and the data acquisition device 150 can interact with each other via the network 140 (e.g., the Internet) and via communication connections (e.g., wireless communication, data cable, etc.).

[0047] The target pump 130 is, for example, but not limited to, a pump device driven by frequency conversion or fixed frequency, such as a pump, water pump, etc.

[0048] Regarding the acquisition device 150, such as a flow acquisition device, it is used to acquire the real-time flow of the target pump 130.

[0049] Regarding the computing device 110, it is used, for example, to calculate the specific speed of the target pump, match a pump performance curve prediction model based on the type of the target pump, predict an initial performance curve for the target pump via the matched pump performance curve prediction model, calculate a predicted performance curve for the target pump, and determine the operating conditions of the target pump.

[0050] The computing device 110 may have one or more processing units, including dedicated processing units such as GPUs, FPGAs, and ASICs, and general-purpose processing units such as CPUs. Additionally, one or more virtual machines may run on each computing device 110. In some embodiments, the computing device 110 and the acquisition device 150 may be integrated together or separately configured. In some embodiments, the computing device 110 includes, for example, a performance parameter acquisition module 112, a pump performance curve prediction model matching module 114, an initial performance curve prediction module 116, a predicted performance curve acquisition module 118, and a pump operating condition determination module 120.

[0051] Regarding the performance parameter acquisition module 112, it is used to acquire the nameplate data of the target pump in order to acquire multiple performance parameters of the target pump based on the acquired nameplate data.

[0052] Regarding the pump performance curve prediction model matching module 114, it is used for multiple performance parameters to calculate the specific speed of the target pump; and determines the type of the target pump based on the specific speed of the target pump so as to match the pump performance curve prediction model based on the type of the target pump.

[0053] Regarding the initial performance curve prediction module 116, it is used to predict the initial performance curve of the target pump based on the plurality of performance parameters via a matched pump performance curve prediction model.

[0054] Regarding the predictive performance curve acquisition module 118, it is used to perform morphological constraint optimization on the initial performance curve of the target pump to obtain the predictive performance curve of the target pump.

[0055] Regarding the pump condition determination module 120, it is used to determine the operating condition of the target pump based on the predicted performance curve of the target pump.

[0056] Figure 2 A flowchart of a method 200 for determining the operating conditions of a target pump according to an embodiment of the present invention is shown. Method 200 may be performed by, for example... Figure 1 The computing device 110 shown can be used for execution, and can also be used in Figure 7 The method is performed at the illustrated electronic device 700. It should be understood that method 200 may also include additional steps not shown and / or the steps shown may be omitted, and the scope of the invention is not limited in this respect.

[0057] In step 202, the computing device 110 acquires the nameplate data of the target pump in order to obtain multiple performance parameters of the target pump based on the acquired nameplate data.

[0058] Regarding the acquisition of the target pump's nameplate data, for example, identifying the target pump's nameplate to obtain initial nameplate data, and preprocessing the initial nameplate data to standardize it, thereby obtaining the final nameplate data.

[0059] Nameplate data for the target pump, such as rated flow rate, rated head, rated power, rated speed, and rated efficiency.

[0060] Preprocessing includes unit conversion, outlier detection (such as whether the reference point is self-consistent), etc., to ensure input quality.

[0061] In step 204, the computing device 110 calculates the specific speed of the target pump based on multiple performance parameters.

[0062] Regarding the calculation of specific speed, the specific speed is calculated based on formula (1): Specific speed n s = (1).

[0063] Where Q represents flow rate (unit: m³ / s). 3 / s, cubic meters per second), H represents the head (unit: m, meter; for multi-stage pumps, the head of a single stage is taken), and n represents the rotational speed (unit: r / min, revolutions per minute).

[0064] Specifically, head refers to the highest height a liquid can reach under the action of force in a pump; flow rate refers to the amount of liquid the pump delivers per unit time, such as volumetric flow rate (unit: cubic meters per second, m³ / s). 3 / s), such as mass flow rate (unit: kg / s); speed refers to the number of revolutions per minute of the pump (unit: revolutions per minute, r / min); shaft power refers to the power transmitted from the prime mover to the pump shaft; efficiency refers to the ratio of the pump's useful power to the shaft power (represented by η), which is an indicator of the pump's hydraulic performance.

[0065] In some embodiments, determining the type of the target pump based on its specific speed, so as to match the pump performance curve prediction model based on the type of the target pump, includes: if the specific speed of the target pump is less than 80, determining the type of the target pump as a low specific speed pump; if the specific speed of the target pump is greater than 150, determining the type of the target pump as a high specific speed pump; if the specific speed of the target pump is greater than or equal to 80 and less than or equal to 150, determining the type of the target pump as a medium specific speed pump.

[0066] For example, the specific speed of target pump A is calculated to be 50, the specific speed of target pump B is 170, and the specific speed of target pump C is 100; the type of target pump A is determined to be a low specific speed pump, the type of target pump B is determined to be a high specific speed pump, and the type of target pump C is determined to be a medium specific speed pump.

[0067] In step 206, the computing device 110 determines the type of the target pump based on the specific speed of the target pump, so as to match the pump performance curve prediction model based on the type of the target pump.

[0068] In some embodiments, a target specific speed pump performance curve prediction model is matched to the target pump based on the type of the target pump. The target specific speed pump performance curve prediction model is any one of the following: a low specific speed pump performance curve prediction model, a medium specific speed pump performance curve prediction model, or a high specific speed pump performance curve prediction model.

[0069] For example, a low specific speed pump performance curve prediction model is matched for target pump A (low specific speed pump), a high specific speed pump performance curve prediction model is matched for target pump B (high specific speed pump), and a medium specific speed pump performance curve prediction model is matched for target pump C (medium specific speed pump).

[0070] Different types of pumps have different specific speeds, resulting in different shapes of their performance curves. For example, centrifugal pumps with low specific speeds have relatively flat flow-head (QH) curves and relatively steep flow-power (QP) curves; centrifugal pumps with high specific speeds have relatively steep flow-head (QH) curves and relatively flat flow-power (QP) curves. Even axial flow pumps with even higher specific speeds may exhibit a saddle-shaped flow-head (QH) curve in the low-flow range.

[0071] The pump performance curve prediction model is obtained based on the training of a predetermined model, such as LightGBM (LightGradient Boosting Machine), GBDT (Gradient Boosting Decision Tree), XGBoost (eXtreme Gradient Boosting), and LinearRegression.

[0072] Therefore, by determining the type of the target pump as a low specific speed pump, medium specific speed pump, or high specific speed pump based on the specific speed, it is possible to match the target pump with a model suitable for different performance curve shapes based on different specific speeds. Differentiated prediction models can be selected for different pumps to improve prediction accuracy and adaptability, thereby making the determination results of the performance curve and operating conditions of the target pump more accurate.

[0073] In step 208, the computing device 110 predicts the initial performance curve of the target pump based on the plurality of performance parameters via a matched pump performance curve prediction model.

[0074] In some embodiments, predicting the initial performance curves of the target pump via the matched pump performance curve prediction model includes at least: predicting the initial flow head (QH) performance curve of the target pump and predicting the initial flow power (QP) performance curve of the target pump.

[0075] Therefore, the above solution can directly predict the complete pump performance curve based on a small number of nameplate parameters of the target pump, thereby realizing the reconstruction of the pump performance curve.

[0076] In step 210, the computing device 110 performs morphological constraint optimization on the initial performance curve of the target pump to obtain a predicted performance curve for the target pump.

[0077] In some embodiments, morphological constraint optimization of the initial performance curve of the target pump to obtain a predicted performance curve of the target pump includes: applying physical constraints to the initial performance curve of the target pump based on predetermined physical rules, wherein the predetermined physical rules include any one of the following: the initial flow-head performance curve is monotonically decreasing, and the initial flow-power performance curve is monotonically increasing.

[0078] For example, after predicting the preliminary mathematical parameters of the pump performance curve using a data-driven model (such as LightGBM), this invention does not directly use the pump performance curve (initial performance curve) generated by the model. Instead, it uses the initial performance curve as a "candidate solution" and enters a verification and correction closed loop based on physical rules. For example, the first derivative of the target pump's initial performance curve within the operating range is calculated using a computing device, and the performance curve is calibrated and corrected based on physical rules, such as the hard constraints of "initial flow head (QH) performance curve monotonically decreasing" and "initial flow power (QP) performance curve monotonically increasing". If the target pump's initial performance curve does not meet the above physical rules, the initial performance curve shape of the target pump is "calibrated" to a reasonable range that conforms to the physical rules by using a parameter fine-tuning iterative algorithm, while minimizing changes to the original predicted value of the target pump's initial performance curve.

[0079] Therefore, the above solution repairs the performance curve of the target pump through physical constraints, transforming qualitative human experience into an automatically executable algorithm. This fundamentally eliminates the possibility of predictions that do not conform to physical laws (such as the head increasing with flow rate or power decreasing abnormally) that may be generated by purely data-driven methods. It further ensures that the prediction results conform to the basic working principle of the pump, and improves the reliability of the pump performance curve prediction and operating condition determination results.

[0080] In some embodiments, morphological constraint optimization of the initial performance curve of the target pump to obtain a predicted performance curve for the target pump further includes: morphological constraint optimization of the initial flow-head performance curve based on the shut-off head point, rated operating point, and extreme point, in order to obtain a first flow-head performance curve of the target pump. The following will combine... Figure 3 The method for morphological constraint optimization of the flow-head performance curve will not be elaborated here.

[0081] In some embodiments, morphological constraint optimization of the initial performance curve of the target pump to obtain a predicted performance curve for the target pump further includes: morphological constraint optimization of the initial flow-power performance curve based on the shut-off head point, rated operating point, and predetermined flow rate point, in order to obtain a first flow-power performance curve of the target pump. The following will combine... Figure 4 The method for morphological constraint optimization of flow-power performance curves will not be elaborated upon here.

[0082] Therefore, in the absence of a standard performance curve for the target pump, the above solution introduces key operating points for morphological anchoring to optimize the performance curves predicted by the pump performance curve prediction model. This improves the stability of the predicted performance curves, increases noise resistance, and effectively enhances the prediction accuracy of key points.

[0083] In step 212, the calculation device 110 determines the operating conditions of the target pump based on the predicted performance curve of the target pump.

[0084] In some embodiments, step 212, based on the predicted performance curve of the target pump, determines the operating condition of the target pump, including: acquiring real-time flow data of the target pump, the real-time flow data including real-time monitored flow or real-time predicted flow; acquiring the real-time operating point of the target pump based on the real-time flow data of the target pump; determining the optimal efficiency range of the target pump based on the type of the target pump; and comparing the real-time operating point of the target pump with the corresponding optimal efficiency range to determine the operating condition of the target pump.

[0085] For example, if the operating point falls within the optimal efficiency range, the system is considered "normal" and an estimated efficiency value can be added; if the operating point falls outside the optimal efficiency range, an "off-center alarm" is triggered and the direction of deviation can be indicated (e.g., high flow rate or low flow rate); and because it can provide an estimated value for the efficiency of the target pump, it helps to improve spatial judgment and obtain a more accurate operating point location and specific off-center conditions.

[0086] Therefore, the above scheme combines the predicted performance curve of the target pump with real-time operating data, calculates the real-time operating point based on the real-time flow data of the target pump, and compares it with the "optimal efficiency range" for this type of pump that is pre-existing in the knowledge base, thereby realizing a closed loop from "data-model-decision" to complete the real-time operating condition identification and diagnosis of the target pump.

[0087] In the above scheme, multiple performance parameters of the target pump are obtained by acquiring the nameplate data of the target pump. Thus, even in the absence of complete performance curves and parameters, modeling input is achieved based on the limited nameplate data of the pump. The specific speed of the target pump is calculated based on these multiple performance parameters. The type of the target pump is determined based on its specific speed, so that a pump performance curve prediction model can be matched based on the type of the target pump. An initial performance curve for the target pump is predicted based on the multiple performance parameters via the matched pump performance curve prediction model. This allows pumps to be classified based on their specific speed, and differentiated pump performance prediction models are selected for different pump types, improving the adaptability, prediction accuracy, and generalization ability of the pump performance curves, thereby achieving the reconstruction of the target pump performance curve from a small number of parameters.

[0088] Furthermore, the above method also performs morphological constraint optimization on the initial performance curve of the target pump to obtain a predicted performance curve for the target pump, thereby optimizing the initial performance curve of the target pump and further improving the prediction accuracy, rationality, and reliability of the performance curve prediction results. For example, by using monotonic physical constraints, abnormal shapes that violate the pump's working mechanism are effectively avoided in the predicted curve, thereby improving the physical rationality and stability of the model output. By introducing key operating points to constrain the curve's shape, the structural stability of the performance curve and the prediction accuracy of key points are effectively improved.

[0089] Furthermore, the aforementioned method determines the operating condition of the target pump based on its predicted performance curve; by combining the predicted performance curve with real-time operating data, real-time identification and energy efficiency assessment of the pump's operating condition are achieved. Thus, it is possible to obtain stable and reliable performance curve predictions and operating condition judgments for different types of pumps without relying on the pump's factory performance curve.

[0090] Figure 3 A flowchart of a method 300 for morphological constraint optimization of a flow-head performance curve according to an embodiment of the present invention is shown. Method 300 may be performed by, for example... Figure 1 The computing device 110 shown can be used for execution, and can also be used in Figure 7 The method is performed at the illustrated electronic device 700. It should be understood that method 300 may also include additional steps not shown and / or the steps shown may be omitted, and the scope of the invention is not limited in this respect.

[0091] In step 302, the computing device 110 adjusts the shut-off head point on the initial flow-head performance curve so that the shut-off head point of the initial flow-head performance curve is within a predetermined multiple range of the rated operating point.

[0092] Please refer to Figure 8 The diagram illustrates an initial flow-head performance curve of the target pump. The orange curve represents the initial flow-head performance curve of the target pump predicted by the pump performance curve prediction model, and the blue curve represents the actual flow-head performance curve of the target pump. The green dots represent the rated operating points of the target pump, i.e., the rated flow and rated head points, which are derived from the data provided on the pump nameplate.

[0093] It is worth noting that, Figure 8 The illustrated initial flow-head performance curve of the target pump is the initial flow-head performance curve after physical constraints have been applied based on physical rules, and it already meets the condition that "the initial flow-head performance curve is monotonically decreasing" in the physical rules. That is, the object optimized in steps 302 to 306 is the initial flow-head performance curve after hard constraints have been applied based on physical rules.

[0094] Continuing with the above example, please refer to... Figure 8 The part circled in red indicates a potential morphological problem in the initial flow-head performance curve: "the shut-off head point of the initial flow-head performance curve is higher than the predetermined ratio range of the rated operating point." For example, the predetermined ratio range is 1.1 to 1.3 (it should be understood that if it does not conform to this range, it does not conform to the laws of physics). To address this, the above solution is based on the constraint condition "shut-off head point ratio (the shut-off head point of the initial flow-head performance curve is within the predetermined ratio range of the rated operating point)", thereby enabling the final obtained first flow-head performance curve to overcome the aforementioned morphological problem.

[0095] In step 304, the calculation device 110 adjusts the initial flow rate and head performance curve so that the initial flow rate and head performance curve passes the rated operating point.

[0096] Please refer to Figure 9 The diagram illustrates an initial flow-head performance curve for the target pump. The orange curve represents the initial flow-head performance curve obtained after optimization using the constraint "closed-off head point ratio". The blue curve represents the actual flow-head performance curve of the target pump, while the green dot represents the rated operating point of the target pump.

[0097] Continuing with the above example, please refer to... Figure 9 The part circled in red represents the initial flow-head performance curve. Another potential issue is the failure to reach the rated operating point. To address this, the aforementioned solution addresses the constraint "reaching the rated operating point" based on the initial flow-head performance curve. Further constraints are applied to ensure that the final first flow head performance curve overcomes the aforementioned morphological problems.

[0098] In step 306, the calculation device 110 adjusts the extreme point of the initial flow-head performance curve so that the value of the extreme point of the initial flow-head performance curve is less than or equal to a predetermined multiple of the value of the shut-off head point.

[0099] Please refer to Figure 10 The diagram illustrates an initial flow-head performance curve for the target pump. The orange curve represents the initial flow-head performance curve obtained after optimization with the constraint "through the rated operating point". The blue curve represents the actual flow-head performance curve of the target pump, while the green dot represents the rated operating point of the target pump.

[0100] Continuing with the above example, please refer to... Figure 10 The part circled in red represents the initial flow-head performance curve. The existing morphological problem is "extreme value anomaly." To address this, the above solution is based on the constraint "extreme value limit (the value of the extreme point of the initial flow-head performance curve is less than or equal to a predetermined multiple of the value of the shut-off head point)" for the initial flow-head performance curve. Constraints are applied to ensure that the final first flow head performance curve overcomes the aforementioned morphological problems.

[0101] Please refer to Figure 11 This illustrates a first flow rate head performance curve (e.g.) Figure 11 (The orange curve in the image) Figure 11 The orange curve shown satisfies multiple constraints of the three key anchor points: "head rate constraint at shut-off point + passing through rated operating point + extreme value limit".

[0102] Therefore, by imposing multiple constraints on the shut-off head point, rated operating point, and extreme point, the above scheme enables the flow-head performance curve of the target pump to control the amplitude range of the curve, avoid abnormal peaks, and ensure a reasonable overall trend. This achieves amplitude control and shape regularity of the head curve, significantly improving the physical consistency of the prediction results.

[0103] It should be understood that the multiple constraints in steps 302 to 306 above are not subject to any sequential restriction, and the initial flow-head performance curve in the above embodiment is consistent with the initial flow-head performance curve. It's just an illustration.

[0104] Figure 4 A flowchart of a method 400 for morphological constraint optimization of a flow-power performance curve according to an embodiment of the present invention is shown. Method 400 may be derived from, for example... Figure 1 The computing device 110 shown can be used for execution, and can also be used in Figure 7 The method is performed at the illustrated electronic device 700. It should be understood that method 400 may also include additional steps not shown and / or the steps shown may be omitted, and the scope of the invention is not limited in this respect.

[0105] In step 402, the calculation device 110 adjusts the shut-off head point on the initial flow power performance curve so that the power value at the shut-off head point of the initial flow power performance curve is greater than zero and less than or equal to the rated power.

[0106] Please refer to Figure 12 The diagram illustrates an initial flow-power performance curve of the target pump. The orange curve represents the initial flow-power performance curve of the target pump predicted by the pump performance curve prediction model, and the blue curve represents the actual flow-power performance curve of the target pump. The green dots represent the rated operating points of the target pump, namely the rated flow and rated head points, which are derived from the data provided on the pump nameplate.

[0107] It is worth noting that, Figure 12 The illustrated initial flow-power performance curve of the target pump is the initial flow-power performance curve after physical constraints have been applied based on physical rules, and it already meets the condition that "the initial flow-power performance curve is monotonically increasing" in the physical rules. That is, the object optimized in steps 402 to 406 is the initial flow-power performance curve after hard constraints have been applied based on physical rules.

[0108] Continuing with the above example, please refer to... Figure 12 The part circled in red indicates a potential morphological problem in the initial flow-power performance curve: "abnormal shut-off power point value". To address this, the above solution uses the constraint "shut-off power point value range (the power value at the shut-off point of the initial flow-power performance curve is greater than zero and less than or equal to the rated power)" to constrain the first flow-power performance curve obtained in the end, thereby overcoming the aforementioned morphological problem.

[0109] In step 404, the computing device 110 adjusts the initial flow-power performance curve so that the initial flow-power performance curve passes the rated operating point.

[0110] Please refer to Figure 13 An initial flow-power performance curve of the target pump is shown. The orange curve represents the initial flow-power performance curve obtained after optimization using the constraint "range of head shut-off points". The blue curve represents the actual flow-power performance curve of the target pump, while the green dot represents the rated operating point of the target pump.

[0111] Continuing with the above example, please refer to... Figure 13 The part circled in red represents the initial flow-power performance curve. Another potential issue is the failure to reach the rated operating point. To address this, the aforementioned solution addresses the constraint "reaching the rated operating point" based on the initial flow-power performance curve. Constraints are applied to ensure that the final first flow-power performance curve overcomes the aforementioned morphological problems.

[0112] In step 406, the calculation device 110 adjusts the predetermined flow point of the initial flow-power performance curve so that the power value of the predetermined flow point of the flow-power performance curve is greater than or equal to the rated power, so as to obtain the first flow-power performance curve of the target pump.

[0113] Please refer to Figure 14 An initial flow-power performance curve of the target pump is shown. The orange curve represents the initial flow-power performance curve obtained after optimization with the constraint "passing the rated operating point". The blue curve represents the actual flow-power performance curve of the target pump, while the green dot represents the rated operating point of the target pump.

[0114] Continuing with the above example, please refer to... Figure 14 The part circled in red represents the initial flow-power performance curve. Another potential morphological issue is "abnormal predetermined flow rate point." Regarding the predetermined flow rate point, for example, it could be a high flow rate point (i.e., a point where the flow rate exceeds the rated flow rate). The above solution addresses this by basing the constraint "predetermined flow rate point value range (the power value of the predetermined flow rate point is greater than or equal to the rated power)" on the initial flow-power performance curve. Constraints are applied to ensure that the final first flow-power performance curve overcomes the aforementioned morphological problems.

[0115] Please refer to Figure 15 This illustrates a first flow-power performance curve (e.g.) Figure 15 (The orange curve in the image) Figure 15 The orange curve shown satisfies multiple constraints of three key anchor points: "closed head value range + passing rated operating point + predetermined flow rate value range".

[0116] Therefore, the above scheme, through multiple constraints on the shut-off head point, rated operating point, and predetermined flow rate point, ensures that the flow-power performance curve of the target pump can guarantee a reasonable trend of power change with flow rate, avoid energy relationship distortion, and ensure that the power change trend conforms to the actual load law, thereby improving the reliability of the prediction results.

[0117] It should be understood that the multiple constraints in steps 402 to 406 above are not subject to any sequential restriction, and the initial flow power performance curve in the above embodiment is related to the initial flow power performance curve. It's just an illustration.

[0118] Figure 5 A flowchart of a method 500 for optimizing pump performance curves according to an embodiment of the present invention is shown. Method 500 can be performed by, for example... Figure 1 The computing device 110 shown can be used for execution, and can also be used in Figure 7 The method is performed at the illustrated electronic device 700. It should be understood that method 500 may also include additional steps not shown and / or the steps shown may be omitted, and the scope of the invention is not limited in this respect.

[0119] In step 502, the calculation device 110 calculates the initial flow efficiency performance curve of the target pump based on the first flow head performance curve and the first flow power performance curve of the target pump.

[0120] Please refer to Figure 16 The diagram illustrates an initial flow efficiency performance curve of the target pump. The blue curve represents the initial flow efficiency performance curve obtained by calculation using the first flow head performance curve and the first flow power performance curve. The orange dot represents the rated operating point.

[0121] Regarding the calculation of the initial flow efficiency performance curve of the target pump, for example, the first flow head performance curve derived from the current system (such as Q-). (curve), first flow-power performance curve (such as Q-) (curve) (iterative loop) ), through the efficiency formula Calculate and fit the initial flow efficiency performance curve (e.g., Q-). curve).

[0122] In step 504, the computing device 110 adjusts the initial flow efficiency performance curve so that the initial flow efficiency performance curve passes through the rated operating point in order to obtain the predicted flow efficiency performance curve.

[0123] It should be understood that the rated operating point of a pump should typically be the highest point (or at least close to the highest point) of its flow efficiency performance curve (QE curve), adhering to the principle of optimal efficiency. Therefore, based on the constraint "passing the rated operating point," an optimization algorithm is used to re-optimize the fitted Q-value. The curve is used as the predicted flow efficiency performance curve of the target pump, ensuring that it passes through the rated point and has a reasonable shape.

[0124] Please refer to Figure 17 The diagram illustrates a predicted flow efficiency performance curve for the target pump. The orange curve represents the predicted flow efficiency performance curve (Q-) obtained after optimization with the constraint "passing the rated operating point". The blue curve represents the initial flow efficiency performance curve (Q-) of the target pump. (The curve), where the green dot represents the rated operating point of the target pump.

[0125] In step 506, the computing device 110 corrects the first flow head performance curve based on the predicted flow efficiency performance curve and the efficiency formula in order to obtain the second flow head performance curve.

[0126] For example, using the predicted flow efficiency performance curve (Q- The first flow rate head performance curve (Q-) is further corrected using the efficiency formula. The second flow-head performance curve (Q-) is obtained. curve).

[0127] Please refer to Figure 18 The diagram illustrates a second flow-head performance curve for the target pump. The orange curve represents the flow-efficiency performance curve (Q-) obtained after optimization under the constraint "passing the rated operating point". The blue curve represents the target pump's first flow-head performance curve (Q-). The curve (with green dots representing the rated operating point, i.e., the rated flow and rated head point, is derived from the data provided on the pump nameplate).

[0128] In step 508, the calculation device 110 corrects the second flow head performance curve based on the error value between the rated point of the second flow head performance curve and the nameplate data, so as to obtain the predicted flow head performance curve.

[0129] Continuing with the example above, Figure 18 The ΔH in the figure represents the error value between the rated point and the nameplate data of the second flow rate head performance curve. The error ΔH between the calculated rated point and the nameplate data of the second flow rate head performance curve is calculated, thereby affecting the second flow rate head performance curve (Q-). The curve is shifted and corrected to obtain the predicted flow-head performance curve (Q-) that passes through the rated operating point marked on the nameplate. curve).

[0130] Please refer to Figure 19 This diagram illustrates a predicted flow rate and head performance curve for the target pump. The orange curve represents the predicted flow rate and head performance curve (Q-). The blue curve represents the target pump's first flow-head performance curve (Q-). (The curve), where the green dot represents the rated operating point.

[0131] In step 510, the computing device 110 calculates the second flow-power performance curve of the target pump based on the predicted flow-efficiency performance curve and the predicted flow-head performance curve of the target pump.

[0132] For example, based on the predicted flow efficiency performance curve (Q-) of the target pump (Q-) and predicted flow-head performance curve (Q-) (curve), calculate the second flow-power performance curve (Q-) of the target pump. curve).

[0133] Please refer to Figure 20 The diagram illustrates a second flow-power performance curve for the target pump, with the orange curve representing the second flow-power performance curve (Q-). The blue curve represents the first flow-power performance curve (Q-) of the target pump. (The curve), where the green dot represents the rated operating point provided by the nameplate parameters.

[0134] In step 512, the calculation device 110 corrects the second flow power performance curve based on the error value between the rated point of the second flow power performance curve and the nameplate data, so as to obtain the predicted flow power performance curve.

[0135] Continuing with the example above, Figure 20 ΔP in the figure represents the error value between the rated point of the second flow-power performance curve and the nameplate data. The error ΔP between the calculated rated point of the second flow-power performance curve and the nameplate data is calculated, thereby affecting the second flow-power performance curve (Q-). The curve is shifted and corrected to obtain the predicted flow-power performance curve (Q-) that passes through the rated operating point indicated on the nameplate. curve).

[0136] Please refer to Figure 21 This diagram illustrates a predicted flow-power performance curve for the target pump. The orange curve represents the predicted flow-power performance curve (Q-). The blue curve represents the target pump's first flow-head performance curve (Q-). (The curve), where the green dot represents the rated operating point.

[0137] It should be understood that in the above optimization calculation process, if ΔH and ΔP satisfy convergence (i.e., approach 0), the loop is exited; otherwise, let k = k + 1, and Q - Q- As input, the next iteration loop is performed; eventually, the three curves—the flow head performance curve (QH curve), the flow power performance curve (QP curve), and the flow efficiency performance curve (QE curve)—will converge to a stable value.

[0138] Therefore, in the above scheme, when the standard performance curve of the target pump is completely missing, a multi-curve collaborative estimation and optimization closed loop is constructed, with the pump's rated operating point as a fixed point (e.g., obtained from nameplate data) and the basic hydraulic efficiency formula as the link. Starting from the initial predicted performance curve, the efficiency formula is used to establish mutual derivation relationships among the three curves: the flow-head performance curve (QH curve), the flow-power performance curve (QP curve), and the flow-efficiency performance curve (QE curve). Furthermore, with the rated operating point as a strong constraint anchor point, the parameters of each performance curve are continuously adjusted through an iterative algorithm until all three performance curves satisfy the efficiency formula at the rated operating point, and their shapes are reasonable and conform to physical rules and domain knowledge (e.g., the peak of the QE curve is located near the rated operating point). During the iteration process, the head error ΔH and power error ΔP at the rated operating point are calculated and eliminated, causing the entire system to converge to an internally completely self-consistent state.

[0139] Therefore, the above scheme can establish the coupling relationship between multiple physical quantities through a dual correction mechanism based on the efficiency model and nameplate data, thereby improving overall consistency. By introducing the efficiency curve and performing rated point correction, it achieves physical consistency constraints between head, power, and efficiency, improving overall prediction accuracy. It also achieves fine calibration of the performance curve, significantly improving the prediction accuracy of the performance curve. In addition, the above method also uses cross-validation to calibrate the pump performance curve prediction model.

[0140] Figure 6 A flowchart of a method 600 for calculating real-time predicted flow data of a target pump according to an embodiment of the present invention is shown. Method 600 may be derived from, for example... Figure 1 The computing device 110 shown can be used for execution, and can also be used in Figure 7 The method is performed at the illustrated electronic device 700. It should be understood that method 600 may also include additional steps not shown and / or the steps shown may be omitted, and the scope of the invention is not limited in this respect.

[0141] In step 602, the computing device 110 calculates the first flow rate data of the target pump based on the real-time head data and the predicted flow-head performance curve of the target pump.

[0142] For example, when real-time flow data cannot be obtained in the target pump system (e.g., flow meter cannot be installed, flow meter is malfunctioning, etc.), real-time head can be used to monitor the flow rate. The first flow rate data is obtained by solving a system of quadratic equations simultaneously with the flow-head (QH) curve formula (2). ; (2); Where a, b, and c are the coefficients of the formula, and H(Q) represents the head as a function of flow rate.

[0143] In step 604, the calculation device 110 calculates the second flow data of the target pump based on the real-time shaft power and predicted flow power performance curve of the target pump.

[0144] For example, it is also based on real-time shaft power ( Solve the second flow rate data by combining the flow rate power (QP) curve formula (3). ; (3); Where a, b, and c are the coefficients of the formula.

[0145] For example, second traffic data .

[0146] In step 606, the computing device 110 determines the flow calculation weighting coefficient based on the specific speed of the target pump, so as to perform weighted calculation based on the first flow data and the second flow data, in order to obtain the real-time predicted flow data of the target pump.

[0147] In some embodiments, based on the specific speed of the target pump Calculate the weighting factors (e.g.: (where weight represents a coefficient). For example, the flow-power (QP) curve of a high specific speed pump may be relatively flat, resulting in a large error in the flow rate obtained through back calculation. Therefore, the first flow rate data Q_est_H is given a higher weight. For example, the final predicted flow rate Q_final is obtained based on the weighted coefficients, as shown in formula (4): Q_final = Q_est_H weight + Q_est_P (1 - weight) (4); Where Q_est_H represents the first flow data, Q_est_P represents the second flow data, and weight represents the weighting coefficient.

[0148] Therefore, when determining the real-time operating condition of a target pump, in the case of missing flow signals, the above scheme, based on the performance curves of real-time head and predicted flow-head (QH), and real-time power and predicted flow-power (QP), solves for two flow estimates in reverse. Furthermore, it assigns dynamic weights to the two flow estimates according to the pump's specific speed type. This transforms the inherent characteristics of the pump type (specific speed) into prior knowledge for optimizing real-time estimation. Through multi-source flow estimation and weighted fusion mechanisms, it effectively improves the stability and robustness of flow prediction under complex operating conditions.

[0149] Figure 7 A schematic step diagram of an example electronic device 700 that can be used to implement embodiments of the contents of this specification is shown. For example, as Figure 1 The computing device 110 shown can be implemented by an electronic device 700. As shown, the electronic device 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) 702 or loaded from storage unit 708 into random access memory (RAM) 703. The random access memory 703 can also store various programs and data required for the operation of the electronic device 700. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0150] Multiple components in electronic device 700 are connected to input / output interface 705, including: input unit 706, such as keyboard, mouse, microphone, etc.; output unit 707, such as various types of monitors, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows electronic device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0151] The various processes and procedures described above, such as methods 200 to 500, can be executed by the central processing unit 701. For example, in some embodiments, methods 200 to 500 may be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via read-only memory 702 and / or communication unit 709. When the computer program is loaded into random access memory 703 and executed by the central processing unit 701, one or more actions of methods 200 to 500 described above can be performed.

[0152] This invention relates to methods, apparatus, systems, electronic devices, computer-readable storage media, and / or computer program products. The computer program product may include computer-readable program instructions for performing various aspects of the invention.

[0153] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0154] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge computing devices. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to computer-readable storage media within the respective computing / processing device.

[0155] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0156] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or step diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each step in the flowchart illustrations and / or step diagrams, as well as combinations of steps in the flowchart illustrations and / or step diagrams, can be implemented by computer-readable program instructions.

[0157] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more steps of the flowchart and / or diagram of steps. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more steps of the flowchart and / or diagram of steps.

[0158] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more steps of a flowchart and / or a diagram of steps.

[0159] The flowcharts and step diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each step in the flowchart or step diagram may represent a module, segment, or part of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the step may occur in a different order than those indicated in the drawings. For example, two consecutive step steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each step in the step diagram and / or flowchart, and combinations of steps in the step diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0160] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for determining the operating conditions of a target pump, characterized in that, include: Obtain the nameplate data of the target pump in order to obtain multiple performance parameters of the target pump based on the obtained nameplate data; Based on the aforementioned performance parameters, the specific speed of the target pump is calculated; The type of target pump is determined based on the specific speed of the target pump, so that the pump performance curve prediction model can be matched based on the type of target pump; Based on the aforementioned performance parameters, an initial performance curve for the target pump is predicted via a matched pump performance curve prediction model. The initial performance curve of the target pump is subjected to shape constraint optimization to obtain a predicted performance curve for the target pump. This includes: performing shape constraint optimization on the initial flow-head performance curve based on the shut-off head point, rated operating point, and extreme point to obtain a first flow-head performance curve for the target pump; performing shape constraint optimization on the initial flow-power performance curve based on the shut-off head point, rated operating point, and predetermined flow point to obtain a first flow-power performance curve for the target pump; calculating the initial flow efficiency performance curve of the target pump based on the first flow-head performance curve and the first flow-power performance curve; and adjusting the initial flow efficiency performance curve so that it passes through the rated operating point to obtain a predicted flow efficiency performance curve. The operating conditions of the target pump are determined based on the predicted performance curve of the target pump.

2. The method according to claim 1, characterized in that, The target pump type is determined based on its specific speed, and a pump performance curve prediction model is matched based on the target pump type, including: If the specific speed of the target pump is less than 80, the type of the target pump is determined to be a low specific speed pump; If the specific speed of the target pump is greater than 150, the type of the target pump is determined to be a high specific speed pump; If the specific speed of the target pump is greater than or equal to 80 and less than or equal to 150, the type of the target pump is determined to be a medium specific speed pump; and Based on the type of the target pump, a target specific speed pump performance curve prediction model is matched to the target pump. The target specific speed pump performance curve prediction model is any one of the following: a low specific speed pump performance curve prediction model, a medium specific speed pump performance curve prediction model, or a high specific speed pump performance curve prediction model.

3. The method according to claim 1, characterized in that, The morphological constraint optimization of the initial performance curve of the target pump to obtain the predicted performance curve of the target pump includes: The initial performance curve of the target pump is physically constrained based on predetermined physical rules, which include any of the following: the initial flow-head performance curve is monotonically decreasing, and the initial flow-power performance curve is monotonically increasing.

4. The method according to claim 3, characterized in that, Based on the shut-off head point, rated operating point, and extreme point, morphological constraint optimization is performed on the initial flow-head performance curve to obtain the first flow-head performance curve of the target pump, including: Adjust the shut-off head point on the initial flow-head performance curve so that the shut-off head point of the initial flow-head performance curve is within a predetermined multiple range of the rated operating point. Adjust the initial flow rate-head performance curve so that it passes through the rated operating point; and Adjust the extreme point of the initial flow-head performance curve so that the value of the extreme point of the initial flow-head performance curve is less than or equal to a predetermined multiple of the value of the shut-off head point.

5. The method according to claim 3, characterized in that, Based on the shut-off head point, rated operating point, and predetermined flow rate point, morphological constraint optimization is performed on the initial flow-power performance curve to obtain the first flow-power performance curve of the target pump, including: Adjust the shut-off head point on the initial flow power performance curve so that the power value at the shut-off head point of the initial flow power performance curve is greater than zero and less than or equal to the rated power. Adjust the initial flow-power performance curve so that it passes through the rated operating point; and Adjust the predetermined flow point of the initial flow-power performance curve so that the power value at the predetermined flow point of the flow-power performance curve is greater than or equal to the rated power, in order to obtain the first flow-power performance curve of the target pump.

6. The method according to claim 3, characterized in that, The morphological constraint optimization of the initial performance curve of the target pump to obtain the predicted performance curve of the target pump also includes: Based on the predicted flow efficiency performance curve and efficiency formula, the first flow head performance curve is corrected to obtain the second flow head performance curve; and Based on the error value between the rated point of the second flow head performance curve and the nameplate data, the second flow head performance curve is corrected in order to obtain the predicted flow head performance curve.

7. The method according to claim 6, characterized in that, The morphological constraint optimization of the initial performance curve of the target pump to obtain the predicted performance curve of the target pump also includes: Based on the predicted flow efficiency performance curve and predicted flow head performance curve of the target pump, the second flow power performance curve of the target pump is calculated; and Based on the error value between the rated point of the second flow-power performance curve and the nameplate data, the second flow-power performance curve is corrected in order to obtain the predicted flow-power performance curve.

8. The method according to any one of claims 1 to 6, characterized in that, Based on the predicted performance curve of the target pump, the operating conditions of the target pump are determined as follows: Acquire real-time flow data of the target pump, wherein the real-time flow data includes: real-time monitored flow or real-time predicted flow; Based on the real-time flow data of the target pump, the real-time operating point of the target pump is obtained; Based on the type of the target pump, determine the optimal efficiency range of the target pump; and The real-time operating point of the target pump is compared with the corresponding optimal efficiency range to determine the operating condition of the target pump.

9. The method according to claim 8, characterized in that, Also includes: Based on the real-time head data and predicted flow-head performance curve of the target pump, the first flow data of the target pump is calculated. Based on the real-time shaft power and predicted flow power performance curves of the target pump, the second flow data of the target pump is calculated; as well as The flow rate weighting coefficient is determined based on the specific speed of the target pump, so that a weighted calculation can be performed based on the first flow rate data and the second flow rate data to obtain the real-time predicted flow rate data of the target pump.

10. A computing device, comprising: At least one processing unit; At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the device to perform the steps of the method according to any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, the computer program implementing the method according to any one of claims 1 to 9 when executed by a machine.

Images