Water pump characteristic curve generation method and device, electronic equipment and storage medium

Abstract

The invention discloses a water pump characteristic curve generation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring multiple groups of water pump operation data of a to-be-detected water pump at multiple different blade angles; according to the multiple sets of water pump operation data corresponding to the target blade angle in the multiple blade angles, a reference characteristic function is determined; for at least one other blade angle except the target blade angle in the plurality of blade angles, determining a characteristic function corresponding to the other blade angles according to a predetermined target transformation parameter and a reference characteristic function corresponding to the other blade angles; and determining a pump characteristic curve corresponding to the water pump to be tested according to the reference characteristic function and the at least one characteristic function. According to the technical scheme, the effect that the smooth characteristic curve corresponding to different blade angles and conforming to the physical law is generated under the condition that the data size of the water pump operation data corresponding to different blade angles is small is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of water pump performance detection, and in particular to a method, device, electronic equipment and storage medium for generating a water pump characteristic curve. Background Art

[0002] At present, large water pumps are widely used in industry, agriculture and municipal engineering. The performance of water pumps directly affects the operating efficiency of the system. Especially for water pumps with adjustable blade angles, the change of blade angle has a significant impact on the flow-head or flow-mechanical efficiency characteristic curve.

[0003] In the related art, the performance analysis of water pumps mainly relies on curve fitting based on experimental data. However, for water pumps with adjustable blade angles, it is difficult to collect experimental data during operation, and the amount of experimental data obtained is relatively small. The existing interpolation fitting method is prone to large fitting errors, and even generates curves that do not conform to physical laws, which in turn leads to low accuracy in water pump performance evaluation, affecting the optimization and application of water pumps. Summary of the invention

[0004] The present invention provides a method, device, electronic device and storage medium for generating a water pump characteristic curve, so as to achieve the effect of generating a smooth characteristic curve corresponding to different blade angles in accordance with physical laws when the amount of water pump operation data corresponding to different blade angles is small.

[0005] According to one aspect of the present invention, a method for generating a water pump characteristic curve is provided, the method comprising:

[0006] Acquire multiple groups of water pump operation data of the water pump to be tested at multiple different blade angles; wherein the water pump operation data is used to indicate data generated during the operation of the water pump to be tested at the corresponding blade angle; the multiple groups of water pump operation data include different water pump flow rates and water pump performance data corresponding to the water pump flow rates; the data volume of the multiple groups of water pump operation data at each of the blade angles is less than a preset data volume threshold;

[0007] determining a reference characteristic function according to a plurality of groups of the water pump operation data corresponding to a target blade angle among the plurality of blade angles;

[0008] For at least one other blade angle among the plurality of blade angles except the target blade angle, determining a characteristic function corresponding to the other blade angle according to a predetermined target transformation parameter corresponding to the other blade angle and the reference characteristic function; wherein the target transformation parameter is determined based on a plurality of groups of the water pump operation data corresponding to the other blade angle;

[0009] A pump characteristic curve corresponding to the water pump to be tested is determined according to the reference characteristic function and at least one of the characteristic functions.

[0010] According to another aspect of the present invention, a device for generating a water pump characteristic curve is provided, the device comprising:

[0011] A data acquisition module, used to acquire multiple groups of water pump operation data of the water pump to be tested at multiple different blade angles; wherein the water pump operation data is used to indicate data generated during the operation of the water pump to be tested at the corresponding blade angle; the multiple groups of water pump operation data include different water pump flow rates and water pump performance data corresponding to the water pump flow rates; the data volume of the multiple groups of water pump operation data at each of the blade angles is less than a preset data volume threshold;

[0012] A reference function determination module, used to determine a reference characteristic function according to a plurality of groups of the water pump operation data corresponding to a target blade angle among the plurality of blade angles;

[0013] a characteristic function determination module, configured to determine, for at least one other blade angle among the plurality of blade angles except the target blade angle, a characteristic function corresponding to the other blade angle according to a predetermined target transformation parameter corresponding to the other blade angle and the reference characteristic function; wherein the target transformation parameter is determined based on a plurality of groups of the water pump operation data corresponding to the other blade angle;

[0014] The curve generating module is used to determine a pump characteristic curve corresponding to the water pump to be tested according to the reference characteristic function and at least one of the characteristic functions.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for generating a water pump characteristic curve described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating a water pump characteristic curve according to any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention obtains multiple groups of water pump operation data of the water pump to be tested at multiple different blade angles, and further determines a benchmark characteristic function based on the multiple groups of water pump operation data corresponding to the target blade angle among the multiple blade angles. Furthermore, for at least one other blade angle among the multiple blade angles except the target blade angle, the characteristic function corresponding to the other blade angles is determined based on the predetermined target transformation parameters corresponding to the other blade angles and the benchmark characteristic function. Furthermore, based on the benchmark characteristic function and at least one pump characteristic function, a pump characteristic curve corresponding to the water pump to be tested is determined, which solves the problem that the characteristic curve generation method in the related art is prone to cause large fitting errors or even generate curves that do not conform to physical laws, and achieves the effect of generating smooth characteristic curves corresponding to different blade angles that conform to physical laws when the amount of water pump operation data corresponding to different blade angles is small, thereby improving the accuracy of curve fitting and, thereby, improving the accuracy of water pump performance analysis.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flow chart of a method for generating a water pump characteristic curve according to Embodiment 1 of the present invention;

[0024] Figure 2 is a flow chart of a method for generating a water pump characteristic curve according to Embodiment 2 of the present invention;

[0025] Figure 3 is a schematic structural diagram of a water pump characteristic curve generating device provided according to Embodiment 3 of the present invention;

[0026] Figure 4 It is a structural schematic diagram of an electronic device for implementing the method for generating a water pump characteristic curve according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 This is a flow chart of a method for generating a water pump characteristic curve provided by the first embodiment of the present invention. This embodiment is applicable to the case of analyzing the performance of a water pump with adjustable blade angle. The method can be executed by a water pump characteristic curve generating device. The water pump characteristic curve generating device can be implemented in the form of hardware and / or software. The water pump characteristic curve generating device can be configured in a terminal and / or a server. Figure 1 As shown, the method includes:

[0031] S110, obtaining multiple groups of water pump operation data of the water pump to be tested at multiple blade angles.

[0032] Among them, the water pump to be tested can be a water pump to be tested for performance. The water pump to be tested can be any type of water pump, optionally, a large adjustable blade angle water pump. It can be understood that the blade angle can be the angle between the blade and the axis of the water pump, also known as the blade installation angle or the blade inclination angle. The water pump operation data can be used to indicate the data generated during the operation of the water pump to be tested at the corresponding blade angle. The water pump operation data can include multiple data associated with the water pump operation performance. In this embodiment, multiple groups of water pump operation data can include different water pump flow rates and water pump performance data corresponding to the water pump flow rates. In other words, multiple groups of water pump operation data can be data constructed by sampling the corresponding water pump performance data under multiple water pump flow rates. The water pump flow rate refers to the amount of liquid (liquid volume or liquid weight) delivered by the water pump per unit time. The water pump performance data can be understood as an important parameter characterizing the performance of the water pump. Optionally, the water pump performance data includes the water pump head and / or the water pump mechanical efficiency. The water pump head refers to the height at which the water pump can lift water, and its unit is meter (m). The mechanical efficiency of a water pump refers to the efficiency that a water pump can convert during operation. Generally, when the blade angle is determined, the water pump to be tested can operate at the blade angle. Furthermore, the water pump flow and water pump performance data generated during the operation of the water pump to be tested can be detected, and data collection can be performed on the water pump flow and water pump performance data to obtain water pump performance data corresponding to multiple different water pump flow rates. Furthermore, the collected data can be used as multiple sets of water pump operation data corresponding to the water pump to be tested at the blade angle, and each set of water pump operation data includes a water pump flow and water pump performance data corresponding to the water pump flow. It should be noted that the multiple sets of water pump operation data corresponding to each blade angle may include key data points within the working range of the water pump to be tested, such as the maximum water pump flow, the maximum water pump head and / or the maximum water pump mechanical efficiency.

[0033] It should be noted that, in this embodiment, the data volume of the multiple groups of water pump operation data at each blade angle may be less than the preset data volume threshold. Furthermore, the water pump performance of the water pump to be tested may be analyzed based on the water pump operation data less than the preset data volume threshold. The preset data volume threshold may be any value, and may be 5 groups, 6 groups, 8 groups, or 10 groups, etc.

[0034] In this embodiment, a plurality of different blade angles can be determined. Furthermore, for each blade angle, the blades in the impeller of the water pump to be tested can be set based on the blade angle, and the water pump to be tested can be controlled to work at the blade angle. Furthermore, the water pump flow and water pump performance data are detected during the operation of the water pump to be tested, and data collection is performed on the water pump flow and the corresponding water pump performance data under the corresponding water pump flow. Furthermore, the collected data can be used as multiple sets of water pump operation data corresponding to the water pump to be tested at the blade angle. Furthermore, when the water pump to be tested works at each blade angle respectively, multiple sets of water pump operation data corresponding to the water pump to be tested at multiple different blade angles can be obtained.

[0035] For example, for multiple blade angles, eight pump flows of the tested pump at the blade angle and the pump performance data corresponding to each pump flow can be collected. Furthermore, the pump flow and its corresponding pump performance data can be used as a set of pump operation data to obtain eight sets of pump operation data corresponding to the tested pump at the blade angle.

[0036] S120 . Determine a reference characteristic function according to multiple groups of water pump operation data corresponding to target blade angles among multiple blade angles.

[0037] Among them, the target blade angle is one of the blade angles among multiple blade angles. The benchmark characteristic function can be a pump characteristic function determined based on multiple groups of water pump operation data corresponding to the target blade angle. It can be understood that the pump characteristic function is used to describe the functional relationship between the important performance parameter values ​​such as head, power, efficiency, flow rate, etc. when the pump is running at a certain speed. Usually the independent variable represents the water pump flow rate, and the dependent variable can represent the water pump head, water pump mechanical efficiency or water pump shaft power, etc. In this embodiment, the benchmark characteristic function may include a flow-head function and / or a flow-efficiency function, that is, reflecting the functional relationship between the water pump flow rate and the water pump head; and / or reflecting the functional relationship between the water pump flow rate and the water pump mechanical efficiency.

[0038] In this embodiment, when multiple sets of pump operation data corresponding to multiple blade angles of the pump to be tested are obtained, the target blade angle can be determined from the multiple blade angles. Further, a reference characteristic function can be generated based on the multiple sets of pump operation data corresponding to the target blade angle.

[0039] Optionally, a benchmark characteristic curve is determined based on multiple sets of water pump operating data corresponding to target blade angles among multiple blade angles, including: randomly determining a blade angle from multiple blade angles as the target blade angle; processing the multiple sets of water pump operating data corresponding to the target blade angle according to a preset spline interpolation method to obtain a benchmark characteristic function.

[0040] Among them, the spline interpolation method is a mathematical method for constructing a smooth curve through a series of points. It is a method of constructing a smooth curve through a series of points using a variable spline. The spline interpolation method can include a variety of spline interpolation types, optionally including a linear spline interpolation method, a quadratic spline interpolation method, and a cubic spline interpolation method. In this embodiment, a cubic spline interpolation method can be used to determine the benchmark characteristic function. It can be understood that the cubic spline interpolation method uses a cubic polynomial as a spline function for interpolation. The cubic spline interpolation method can ensure that the function curve is both continuous and smooth at the connection point.

[0041] As an optional implementation of this embodiment, when multiple sets of water pump operation data corresponding to multiple blade angles of the water pump to be tested are obtained, a blade angle can be randomly determined from the multiple blade angles, and the blade angle is used as the target blade angle. Further, the multiple sets of water pump operation data corresponding to the target blade angle are interpolated and fitted according to a preset cubic spline interpolation method to obtain a fitting function, and the fitting function is used as the reference characteristic function.

[0042] It should be noted that the target blade angle may be determined in other ways, for example, by analyzing multiple sets of water pump operation data corresponding to each blade angle respectively, and determining the target blade angle from multiple blade angles based on the data analysis results. This embodiment does not make any specific limitations on this.

[0043] S130. For at least one other blade angle among the multiple blade angles except the target blade angle, determine a characteristic function corresponding to the other blade angle according to a predetermined target transformation parameter corresponding to the other blade angle and a reference characteristic function.

[0044] Among them, other blade angles are blade angles other than the target blade angle among the multiple blade angles. The target transformation parameter can be understood as a parameter that can transform the function to change the position and / or shape of the function curve. Optionally, the target transformation parameter can include at least a translation parameter and a scaling parameter. The translation parameter can be used to translate the function curve to change the position of the function curve. The scaling parameter can be used to scale the function curve to change the shape of the function curve. In this embodiment, the target transformation parameters corresponding to the other blade angles other than the target blade angle among the multiple blade angles can be determined based on multiple groups of water pump operation data and benchmark characteristic functions corresponding to the other blade angles.

[0045] In practical applications, when the amount of data for multiple sets of water pump operation data corresponding to multiple blade angles of the water pump to be tested is small, multiple sets of water pump operation data are fitted with differences based on conventional fitting interpolation methods to generate multiple characteristic curves. This may result in curves that do not conform to physical laws (such as multiple curves intersecting or discontinuous points appearing).

[0046] In view of the above situation, in this embodiment, for other blade angles except the target blade angle among the multiple blade angles, the target transformation parameters corresponding to the other blade angles can be determined based on the corresponding parameters. Furthermore, the reference characteristic curve and multiple groups of water pump operation data corresponding to the other blade angles can be processed according to the determined target transformation parameters to obtain the characteristic function corresponding to the blade angle. The advantage of such a setting is that it can ensure that the characteristic curves of the water pump to be tested at different blade angles will not intersect, so that the finally generated water pump characteristic curve is a smooth curve that conforms to the laws of physics, which improves the accuracy of curve fitting, and further improves the accuracy of water pump performance analysis.

[0047] Optionally, based on predetermined target transformation parameters corresponding to other blade angles and a baseline characteristic function, characteristic functions corresponding to other blade angles are determined, including: translating the baseline characteristic function according to the translation parameter to obtain the characteristic function to be processed; scaling the characteristic function to be processed according to the scaling parameter to obtain the characteristic functions corresponding to other blade angles.

[0048] As an optional implementation of this embodiment, when the target transformation parameters corresponding to other blade angles are determined, the reference characteristic function can be translated according to the translation parameters in the target transformation parameters to obtain the translated reference characteristic function, and the translated reference characteristic function is used as the characteristic function to be processed. Further, the characteristic function to be processed can be scaled according to the scaling parameters in the target transformation parameters to obtain the scaled characteristic function to be processed, and the scaled characteristic function to be processed can be used as the characteristic function corresponding to other blade angles.

[0049] Exemplarily, the determination method of the characteristic function can be expressed based on the following formula:

[0050] y2(x)=b·y1(xa)

[0051] Among them, y2(x) represents the characteristic function; b represents the scaling parameter; y1(x) represents the reference characteristic function; a represents the translation parameter; x represents the pump flow rate; y1 and y2 represent the pump performance data.

[0052] S140: Determine a pump characteristic curve corresponding to the water pump to be tested according to the reference characteristic function and at least one characteristic function.

[0053] In this embodiment, when a reference characteristic function corresponding to the target blade angle and characteristic functions corresponding to other blade angles are obtained, a pump characteristic curve corresponding to the water pump to be tested can be determined according to the reference characteristic function and each characteristic function.

[0054] Optionally, a pump characteristic curve corresponding to the water pump to be tested is determined based on a benchmark characteristic function and at least one characteristic function, including: generating a benchmark characteristic curve based on the benchmark characteristic function; and generating characteristic curves based on each characteristic function; and using the benchmark characteristic curve and at least one characteristic curve as the pump characteristic curve corresponding to the water pump to be tested.

[0055] As an optional implementation of this embodiment, a curve can be generated according to the reference characteristic function, and the curve can be used as the reference characteristic curve. Also, for the characteristic functions corresponding to other blade angles, a curve can be generated according to the characteristic functions corresponding to other blade angles, and the curve can be used as the characteristic curve corresponding to the other blade angles. Furthermore, the reference characteristic curve and the characteristic curve corresponding to other blade angles can be used as the pump characteristic curve corresponding to the water pump to be tested.

[0056] In this embodiment, in order to analyze the performance of the water pump to be tested more clearly and intuitively based on the pump characteristic curve, this embodiment also includes: generating a pump characteristic analysis diagram based on the pump characteristic curve, and visually displaying the pump characteristic analysis diagram.

[0057] The pump characteristic analysis diagram can be understood as a schematic diagram for reflecting the change trend of the water pump performance of the water pump to be tested. Optionally, the pump characteristic analysis diagram can be a line graph, a bar graph or a pie chart.

[0058] As an optional implementation manner of the first embodiment of the present invention, when a pump characteristic curve corresponding to the water pump to be tested is obtained, a pump characteristic analysis diagram corresponding to the water pump to be tested can be generated based on the pump characteristic curve, and the pump characteristic analysis diagram can be visualized so that relevant staff can understand the water pump performance change trend of the water pump to be tested based on the pump characteristic analysis diagram, so as to promptly discover potential problems in the water pump to be tested and ensure that the water pump to be tested is always maintained in the best working condition.

[0059] The technical solution of the embodiment of the present invention obtains multiple groups of water pump operation data of the water pump to be tested at multiple different blade angles, and further determines a benchmark characteristic function based on the multiple groups of water pump operation data corresponding to the target blade angle among the multiple blade angles. Furthermore, for at least one other blade angle among the multiple blade angles except the target blade angle, the characteristic function corresponding to the other blade angles is determined based on the predetermined target transformation parameters corresponding to the other blade angles and the benchmark characteristic function. Furthermore, based on the benchmark characteristic function and at least one pump characteristic function, a pump characteristic curve corresponding to the water pump to be tested is determined, which solves the problem that the characteristic curve generation method in the related art is prone to cause large fitting errors or even generate curves that do not conform to physical laws, and achieves the effect of generating smooth characteristic curves corresponding to different blade angles that conform to physical laws when the amount of water pump operation data corresponding to different blade angles is small, thereby improving the accuracy of curve fitting and, thereby, improving the accuracy of water pump performance analysis.

[0060] Embodiment 2

[0061] Figure 2 This is a flow chart of a method for generating a water pump characteristic curve provided by the second embodiment of the present invention. On the basis of the above-mentioned embodiment, target transformation parameters corresponding to other blade angles can be determined according to multiple groups of water pump operation data corresponding to other blade angles and reference characteristic functions, so as to determine characteristic functions corresponding to other blade angles based on the target transformation parameters. The specific implementation method can refer to the technical solution of this embodiment. Among them, the technical terms that are the same or similar to those in the above-mentioned embodiment will not be described in detail here.

[0062] like Figure 2 As shown, the method includes:

[0063] S210, obtaining multiple groups of water pump operation data of the water pump to be tested at multiple different blade angles.

[0064] S220 , determining a reference characteristic function according to multiple groups of water pump operation data corresponding to target blade angles among multiple blade angles.

[0065] S230. For at least one other blade angle among the multiple blade angles except the target blade angle, determine parameters to be optimized corresponding to the other blade angles.

[0066] The parameter to be optimized can be understood as the transformation parameter to be optimized. Optionally, the parameter to be optimized includes a translation parameter and a scaling parameter. It should be noted that before iterative updating, the parameter value of the parameter to be optimized can be an initial value or a default value, and the parameter value of the parameter to be optimized can be manually set or randomly selected. Optionally, the parameter value of the parameter to be optimized can be 0 or any other value.

[0067] S240, iteratively updating the parameters to be optimized based on a preset loss function according to a gradient descent algorithm, so as to determine target transformation parameters corresponding to other blade angles when the loss function reaches a preset convergence condition.

[0068] Among them, the gradient descent algorithm is an algorithm for optimizing and finding the minimum value of a function. The gradient descent algorithm continuously adjusts the parameter values ​​in an iterative manner so that the value of the objective function (loss function or cost function) gradually decreases until it finally reaches a local minimum. In this embodiment, the loss function is constructed based on multiple sets of water pump operation data and benchmark characteristic functions corresponding to other blade angles. The loss function can be used to measure the difference or error between the output obtained based on the benchmark characteristic function and the water pump performance data in multiple sets of water pump operation data. The loss function can be any loss function, and optionally, it is a square error function. The preset convergence conditions may include that the function value of the loss function is less than the preset error value, the function value change trend tends to be stable, or the number of iterative updates reaches a preset number threshold, etc.

[0069] Exemplarily, the loss function can be expressed based on the following formula:

[0070]

[0071] Where i represents the number of groups of pump operation data; x i represents the water pump flow rate in the i-th group of water pump operation data; y i represents the pump performance data in the i-th group of pump operation data; b0 represents the scaling parameter to be optimized; y1 represents the i In the case of , the dependent variable value of the benchmark characteristic function; a0 represents the translation parameter to be optimized.

[0072] In this embodiment, when determining the parameters to be optimized corresponding to other blade angles, a loss function can be constructed based on the reference characteristic function and multiple groups of pump operation data corresponding to other blade angles. Further, the parameters to be optimized can be iteratively updated based on the gradient descent algorithm and the pre-constructed loss function. Then, when the loss function reaches a preset convergence condition, the target transformation parameters corresponding to other blade angles are determined.

[0073] Optionally, the parameters to be optimized are iteratively updated according to the gradient descent algorithm and a preset loss function to determine the target transformation parameters corresponding to other blade angles when the loss function reaches a preset convergence condition, including: for multiple iterative processes, determining the partial derivative of the loss function corresponding to the current iterative process with respect to the parameters to be optimized corresponding to the current iterative process to obtain the gradient corresponding to the current iterative process; updating the parameters to be optimized corresponding to the current iterative process according to the gradient to obtain the parameters to be optimized corresponding to the next iterative update process, and determining the loss function corresponding to the next iterative process according to the parameters to be optimized, the benchmark characteristic function and multiple sets of water pump operation data corresponding to the next iterative process; when it is determined that the loss function corresponding to the next iterative process does not meet the preset convergence condition, taking the next iterative process as the current iterative process, and repeating the steps of determining the gradient and updating the parameters until the loss function corresponding to the next iterative process meets the preset convergence condition, and taking the parameters to be optimized corresponding to the next iterative process as the target transformation parameters corresponding to other blade angles.

[0074] As an optional implementation of this embodiment, for multiple iterations, the parameters to be optimized corresponding to the current iteration can be obtained, and the parameters to be optimized are input into the loss function to obtain the loss function corresponding to the current iteration. Further, the partial derivative of the loss function with respect to the parameters to be optimized can be determined to obtain the gradient corresponding to the current iteration. Further, the product between the gradient and the preset learning rate can be determined, and the difference between the parameters to be optimized corresponding to the current iteration and the product can be determined, and the difference can be used as the parameters to be optimized corresponding to the next iteration. Further, the parameters to be optimized in the loss function corresponding to the current iteration can be replaced based on the parameters to be optimized corresponding to the next iteration, and the loss function after the parameter replacement can be used as the loss function corresponding to the next iteration. Further, it is determined whether the loss function corresponding to the next iteration meets the preset convergence condition. Further, in the case of determining that the loss function corresponding to the next iteration does not meet the preset convergence condition, the next iteration is used as the current iteration, and the steps of determining the gradient and updating the parameters are repeatedly performed until the loss function corresponding to the next iteration meets the preset convergence condition, and the parameters to be optimized corresponding to the next iteration are used as the target transformation parameters corresponding to other blade angles.

[0075] Exemplarily, the process of finding partial derivatives of the parameters to be optimized can be expressed based on the following formula:

[0076]

[0077] in, represents the gradient corresponding to the translation parameter; represents the gradient corresponding to the scaling parameter.

[0078] The update process of the parameters to be optimized can be expressed based on the following formula:

[0079]

[0080] Among them, a new represents the updated translation parameter; α represents the preset learning rate; a old represents the translation parameter before updating; b new represents the updated scaling parameter; b old Indicates the scaling parameters before updating.

[0081] S250. For at least one other blade angle among the multiple blade angles except the target blade angle, determine a characteristic function corresponding to the other blade angles according to a predetermined target transformation parameter corresponding to the other blade angle and a reference characteristic function.

[0082] S260: Determine a pump characteristic curve corresponding to the water pump to be tested according to the reference characteristic function and at least one characteristic function.

[0083] The technical solution of the embodiment of the present invention determines the parameters to be optimized corresponding to other blade angles for at least one other blade angle among multiple blade angles except the target blade angle; further, the parameters to be optimized are iteratively updated according to the gradient descent algorithm and the preset loss function, so as to determine the target transformation parameters corresponding to the other blade angles when the loss function reaches the preset convergence condition, thereby achieving the effect of quickly determining the target transformation parameters corresponding to each blade angle, thereby improving the generation efficiency and generation effect of the pump characteristic curve.

[0084] Embodiment 3

[0085] Figure 3 Schematic diagram of the structure of a pump characteristic curve generating device provided by the third embodiment of the present invention. Figure 3 As shown, the device includes: a data acquisition module 310, a reference function determination module 320, a characteristic function determination module 330 and a curve generation module 340.

[0086] Among them, the data acquisition module 310 is used to obtain multiple groups of pump operation data of the water pump to be tested at multiple different blade angles; wherein the water pump operation data is used to indicate the data generated during the operation of the water pump to be tested at the corresponding blade angle; the multiple groups of water pump operation data include different water pump flow rates and water pump performance data corresponding to the water pump flow rates; the data volume of the multiple groups of water pump operation data at each of the blade angles is less than the preset data volume threshold; the reference function determination module 320 is used to determine the reference characteristic function according to the multiple groups of water pump operation data corresponding to the target blade angle among the multiple blade angles; the characteristic function determination module 330 is used to determine the characteristic function corresponding to the other blade angle according to the predetermined target transformation parameters corresponding to the other blade angle and the reference characteristic function for at least one other blade angle among the multiple blade angles except the target blade angle; wherein the target transformation parameters are determined based on the multiple groups of water pump operation data corresponding to the other blade angles; the curve generation module 340 is used to determine the pump characteristic curve corresponding to the water pump to be tested according to the reference characteristic function and at least one of the characteristic functions.

[0087] The technical solution of the embodiment of the present invention obtains multiple groups of water pump operation data of the water pump to be tested at multiple different blade angles, and further determines a benchmark characteristic function based on the multiple groups of water pump operation data corresponding to the target blade angle among the multiple blade angles. Furthermore, for at least one other blade angle among the multiple blade angles except the target blade angle, the characteristic function corresponding to the other blade angles is determined based on the predetermined target transformation parameters corresponding to the other blade angles and the benchmark characteristic function. Furthermore, based on the benchmark characteristic function and at least one pump characteristic function, a pump characteristic curve corresponding to the water pump to be tested is determined, which solves the problem that the characteristic curve generation method in the related art is prone to cause large fitting errors or even generate curves that do not conform to physical laws, and achieves the effect of generating smooth characteristic curves corresponding to different blade angles that conform to physical laws when the amount of water pump operation data corresponding to different blade angles is small, thereby improving the accuracy of curve fitting and, thereby, improving the accuracy of water pump performance analysis.

[0088] Optionally, the device further includes: a module for determining parameters to be optimized and a module for determining target transformation parameters.

[0089] A module for determining parameters to be optimized, used for determining, for at least one other blade angle among the plurality of blade angles except the target blade angle, a parameter to be optimized corresponding to the other blade angle;

[0090] A target transformation parameter determination module is used to iteratively update the parameters to be optimized according to a gradient descent algorithm and a preset loss function, so as to determine the target transformation parameters corresponding to the other blade angles when the loss function reaches a preset convergence condition; wherein the loss function is constructed based on multiple groups of the water pump operation data corresponding to the other blade angles and the benchmark characteristic function.

[0091] Optionally, the target transformation parameter determination module includes: a gradient determination unit, a parameter updating unit and a target transformation parameter determination unit.

[0092] A gradient determination unit, used to determine, for multiple iterations, a partial derivative of a loss function corresponding to a current iteration process with respect to a parameter to be optimized corresponding to the current iteration process, so as to obtain a gradient corresponding to the current iteration process;

[0093] A parameter updating unit, configured to update the parameters to be optimized corresponding to the current iterative process according to the gradient to obtain the parameters to be optimized corresponding to the next iterative updating process, and determine the loss function corresponding to the next iterative process according to the parameters to be optimized corresponding to the next iterative process and the loss function corresponding to the current iterative process;

[0094] A target transformation parameter determination unit is used to, when it is determined that the loss function corresponding to the next iterative process does not meet the preset convergence condition, use the next iterative process as the current iterative process, and repeatedly execute the steps of determining the gradient and updating the parameters until the loss function corresponding to the next iterative process meets the preset convergence condition, and use the parameters to be optimized corresponding to the next iterative process as the target transformation parameters corresponding to the other blade angles.

[0095] Optionally, the reference function determination module 320 includes: a target blade angle determination unit and a reference function determination unit.

[0096] a target blade angle determination unit, configured to randomly determine one blade angle from the plurality of blade angles as a target blade angle;

[0097] The reference function determination unit is used to process the multiple groups of water pump operation data corresponding to the target blade angle according to a preset spline interpolation method to obtain a reference characteristic function.

[0098] Optionally, the characteristic function determination module 330 includes: a function translation unit and a function scaling unit.

[0099] A function translation unit, used for performing a translation process on the reference characteristic function according to the translation parameter to obtain a characteristic function to be processed;

[0100] A function scaling unit is used to scale the characteristic function to be processed according to the scaling parameter to obtain the characteristic function corresponding to the other blade angles.

[0101] Optionally, the curve generating module 340 includes: a curve generating unit and a characteristic curve determining unit.

[0102] A curve generating unit, configured to generate a reference characteristic curve according to the reference characteristic function; and to generate a characteristic curve according to each of the characteristic functions;

[0103] The characteristic curve determining unit is used to use the reference characteristic curve and at least one of the characteristic curves as pump characteristic curves corresponding to the water pump to be tested.

[0104] Optionally, the device further includes: an analysis chart display module.

[0105] The analysis diagram display module is used to generate a pump characteristic analysis diagram based on the pump characteristic curve and to visually display the pump characteristic analysis diagram.

[0106] The water pump characteristic curve generating device provided in the embodiment of the present invention can execute the water pump characteristic curve generating method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0107] Embodiment 4

[0108] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0109] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0110] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0111] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for generating a water pump characteristic curve.

[0112] In some embodiments, the water pump characteristic curve generation method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the water pump characteristic curve generation method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the water pump characteristic curve generation method in any other appropriate manner (for example, by means of firmware).

[0113] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0114] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0115] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0116] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0117] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0118] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0119] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0120] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating a water pump characteristic curve, characterized in that: include: Acquire multiple groups of water pump operation data of the water pump to be tested at multiple different blade angles; wherein the water pump operation data is used to indicate data generated during the operation of the water pump to be tested at the corresponding blade angle; the multiple groups of water pump operation data include different water pump flow rates and water pump performance data corresponding to the water pump flow rates; the data volume of the multiple groups of water pump operation data at each of the blade angles is less than a preset data volume threshold; determining a reference characteristic function according to a plurality of groups of the water pump operation data corresponding to a target blade angle among the plurality of blade angles; For at least one other blade angle among the plurality of blade angles except the target blade angle, determining a characteristic function corresponding to the other blade angle according to a predetermined target transformation parameter corresponding to the other blade angle and the reference characteristic function; wherein the target transformation parameter is determined based on a plurality of groups of the water pump operation data corresponding to the other blade angle; A pump characteristic curve corresponding to the water pump to be tested is determined according to the reference characteristic function and at least one of the characteristic functions.

2. The method for generating a water pump characteristic curve according to claim 1, characterized in that: Also includes: For other blade angles among the plurality of blade angles except the target blade angle, determining parameters to be optimized corresponding to the other blade angles; The parameters to be optimized are iteratively updated according to the gradient descent algorithm and the preset loss function to determine the target transformation parameters corresponding to the other blade angles when the loss function reaches the preset convergence conditions; wherein the loss function is constructed based on multiple groups of the water pump operation data corresponding to the other blade angles and the benchmark characteristic function.

3. The method for generating a water pump characteristic curve according to claim 2, characterized in that: The iterative updating of the parameters to be optimized according to the gradient descent algorithm and the preset loss function, so as to determine the target transformation parameters corresponding to the other blade angles when the loss function reaches a preset convergence condition, includes: For multiple iterations, determine the partial derivative of the loss function corresponding to the current iteration with respect to the parameter to be optimized corresponding to the current iteration to obtain the gradient corresponding to the current iteration; Performing parameter updating on the parameter to be optimized corresponding to the current iterative process according to the gradient to obtain the parameter to be optimized corresponding to the next iterative update process, and determining the loss function corresponding to the next iterative process according to the parameter to be optimized corresponding to the next iterative process and the loss function corresponding to the current iterative process; When it is determined that the loss function corresponding to the next iterative process does not meet the preset convergence conditions, the next iterative process is used as the current iterative process, and the steps of determining the gradient and updating the parameters are repeated until the loss function corresponding to the next iterative process meets the preset convergence conditions, and the parameters to be optimized corresponding to the next iterative process are used as the target transformation parameters corresponding to the other blade angles.

4. The method for generating a water pump characteristic curve according to claim 1, characterized in that: The generating of the reference characteristic function according to the plurality of groups of the water pump operation data corresponding to the target blade angle among the plurality of blade angles comprises: Randomly determine one of the blade angles from the plurality of blade angles as a target blade angle; The plurality of groups of the water pump operation data corresponding to the target blade angles are processed according to a preset spline interpolation method to obtain a reference characteristic function.

5. The method for generating a water pump characteristic curve according to claim 1, characterized in that: The target transformation parameters include translation parameters and scaling parameters; and determining the characteristic function corresponding to the other blade angles according to the predetermined target transformation parameters corresponding to the other blade angles and the reference characteristic function includes: Performing translation processing on the reference characteristic function according to the translation parameter to obtain a characteristic function to be processed; The characteristic function to be processed is scaled according to the scaling parameter to obtain a characteristic function corresponding to the other blade angles.

6. The method for generating a water pump characteristic curve according to claim 1, characterized in that: Determining a pump characteristic curve corresponding to the water pump to be tested according to the reference characteristic function and at least one of the characteristic functions comprises: generating a reference characteristic curve according to the reference characteristic function; and generating a characteristic curve according to each of the characteristic functions; The reference characteristic curve and at least one of the characteristic curves are used as pump characteristic curves corresponding to the water pump to be tested.

7. The method for generating a water pump characteristic curve according to claim 1, characterized in that: Also includes: A pump characteristic analysis diagram is generated based on the pump characteristic curve, and the pump characteristic analysis diagram is visualized.

8. A water pump characteristic curve generating device, characterized in that: include: A data acquisition module, used to acquire multiple groups of water pump operation data of the water pump to be tested at multiple different blade angles; wherein the water pump operation data is used to indicate data generated during the operation of the water pump to be tested at the corresponding blade angle; the multiple groups of water pump operation data include different water pump flow rates and water pump performance data corresponding to the water pump flow rates; the data volume of the multiple groups of water pump operation data at each of the blade angles is less than a preset data volume threshold; A reference function determination module, used to determine a reference characteristic function according to a plurality of groups of the water pump operation data corresponding to a target blade angle among the plurality of blade angles; a characteristic function determination module, configured to determine, for at least one other blade angle among the plurality of blade angles except the target blade angle, a characteristic function corresponding to the other blade angle according to a predetermined target transformation parameter corresponding to the other blade angle and the reference characteristic function; wherein the target transformation parameter is determined based on a plurality of groups of the water pump operation data corresponding to the other blade angle; The curve generating module is used to determine a pump characteristic curve corresponding to the water pump to be tested according to the reference characteristic function and at least one of the characteristic functions.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the water pump characteristic curve generating method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for generating a water pump characteristic curve according to any one of claims 1 to 7 when executed.

Images