A pump station efficiency characteristic surface dynamic updating method and system and a storage medium

Abstract

The application discloses a kind of pump station efficiency characteristic surface dynamic updating method, system and storage medium, method includes:1) pump station data outlier is handled;2) pump station data is data reorganization, in time dimension, division sliding window data set;3) using linear equation to establish original pump station efficiency characteristic curve and measured pump station efficiency characteristic monitoring data relationship, and make linear translation, obtain after correction pump station efficiency characteristic surface;4) according to error minimization principle, select the best learning rate of original pump station efficiency characteristic surface and after correction pump station efficiency characteristic surface, obtain the comprehensive correction pump station efficiency characteristic surface under the best learning rate;5) regularly using historical measured data, pump station efficiency characteristic surface is dynamically updated.The application method is dynamically rolling updated in time dimension, reduce the influence due to data set time span is too long, pump station efficiency characteristic is not obvious, improve the simulation accuracy of pump station efficiency.

Description

Technical Field

[0001] This invention belongs to the field of pump station unit optimization operation technology, specifically involving a method, system and storage medium for dynamic updating of pump station efficiency characteristic surface. Background Technology

[0002] Optimized operation of pumping station units is a crucial component of water resource planning and management. Accurate pumping station efficiency simulation can better support tasks such as water resource management, water allocation, reducing pumping station energy consumption, and lowering water transmission costs. Existing pumping station efficiency simulation technologies focus on data-driven theoretical or conceptual mechanistic models, failing to deeply explore the characteristics of pumping station efficiency and neglecting the hidden time effects. Furthermore, due to the long time span of the datasets, the manifestation of pumping station efficiency characteristics is not obvious, resulting in poor simulation results. Therefore, this paper analyzes the time effects of pumping station efficiency characteristics and proposes a dynamic update method and system for the pumping station efficiency characteristic surface, which can improve simulation accuracy. Summary of the Invention

[0003] The purpose of this invention is to address the shortcomings of existing technologies by providing a method and system for dynamically updating the efficiency characteristic surface of a pumping station, thereby improving simulation accuracy.

[0004] To achieve the above-mentioned technical objectives, the present invention adopts the following technical solution.

[0005] This invention first provides a method for dynamically updating the efficiency characteristic surface of a pumping station, including the following steps:

[0006] Step S1: Process the abnormal values ​​in the collected pump station data;

[0007] Step S2: Compile the pump station data and divide it into sliding window datasets along the time dimension;

[0008] Step S3: Use linear equations to establish the relationship between the original pump station efficiency characteristic curve and the measured pump station efficiency characteristic monitoring data, and perform linear translation on the original pump station efficiency characteristic surface to obtain the corrected pump station efficiency characteristic surface.

[0009] Step S4: Based on the principle of minimizing error, select the optimal learning rate for the original pump station efficiency characteristic surface and the corrected pump station efficiency characteristic surface to obtain the comprehensive corrected pump station efficiency characteristic surface under the optimal learning rate.

[0010] Step S5: Periodically update the efficiency characteristic surface of the pumping station using historical measured data.

[0011] Furthermore, the abnormal values ​​of the collected pump station data described in step S1 are processed as follows:

[0012] The collected pump station data includes: head, flow rate, efficiency, and time;

[0013] Different pumping stations have different limits for head, flow rate, and efficiency data. Outlier data exceeding the threshold is deleted. The mathematical expression for this is:

[0014] H = {H i |H min ≤H i ≤H max};

[0015] Q = {Q i |Q min ≤Q i ≤Q max};

[0016] E = {E i |E min ≤E i ≤E max};

[0017] In the above formula, H represents the effective head data after removing the threshold; H min This represents the lower limit of the pump station head data; H max Q represents the upper limit of the pump station head data; Q is the effective flow rate data after removing the threshold; Q min This represents the lower limit of the pump station flow rate data; Q max E represents the upper limit of the pump station flow rate data; E represents the effective efficiency data after removing the threshold; E min E represents the lower limit of the pump station unit efficiency data. max This represents the upper limit of the pump station unit efficiency data;

[0018] The measured data of the pump station after inspection, troubleshooting, and correction are recorded as follows:

[0019] Head: H' = {H1,H2,...,H} t-1 H t ,...};

[0020] Flow rate: Q' = {Q1, Q2, ..., Q} t-1 Q t ,...};

[0021] Efficiency: E' = {E1, E2, ..., E t-1 E t ,...}.

[0022] Furthermore, step S2 involves data organization of the pump station data, dividing the dataset into sliding window segments along the time dimension, including the following steps:

[0023] Step S21: Head, data, and efficiency data are collected from different acquisition terminals, and their time information does not correspond one-to-one. The data are arranged chronologically, and a left join is performed on the data tables. Using time as the index, the closest timestamp in each data table is found, and all data are associated into one table. The maximum time difference tolerance is T. max The joined data tables are then reordered using time as the index to obtain the desired data table:

[0024]

[0025]

[0026] In the above formula, D1 represents the pump station unit efficiency data; D2 represents the pump station head data; D3 represents the pump station flow rate data; D represents the data after merging the head, flow rate, and efficiency data and reordering them according to time; the time difference between each group of head, flow rate, and efficiency data is less than the maximum time difference tolerance T. max ;

[0027] Step S22: Reindex the merged dataset, i.e., D = {(t1,x1),(t2,x2),...,(t...} n ,x n The sliding window dataset is denoted as W. k ={(t k ,x k ),(t k+1 ,x k+1 ),...,(t k+W-1 ,x k+W-1 )};

[0028] The sliding window dataset is then represented as:

[0029] W i ={(t i+j ,x i+j )|j=0,1,2,...,m-1};

[0030] i = 1, 1 + S, 1 + 2S, ..., t i+W-1 ≤t n ;

[0031] In the above formula, i is the sliding window dataset number; m is the number of data points in the sliding window dataset; and S is the sliding window time step.

[0032] Furthermore, the process of obtaining the corrected pump station efficiency characteristic surface in step S3 is as follows:

[0033] The actual operating data of the pumping station is interpolated onto the original pumping station efficiency characteristic surface. A linear equation is used to establish a linear relationship between the interpolated original pumping station efficiency characteristic surface data and the actual operating data of the pumping station. The optimal parameters for translating the original pumping station efficiency characteristic surface are found, and the least squares method is selected as the optimization function for the parameters. Based on the optimal parameters, the linear equation for converting the original pumping station efficiency characteristic surface into the corrected pumping station efficiency characteristic surface is derived.

[0034] The interpolation function uses radial basis functions for interpolation, and its mathematical expression is:

[0035]

[0036] In the above formula, f(x) is the interpolation function, and r = ||xx|| i || represents the interpolation point x and the data point x. i The Euclidean distance between them, c i Determined by solving a system of equations or by the least squares method;

[0037] The mathematical expression for the least squares method is:

[0038]

[0039] In the above formula, J1 represents the efficiency-related parameters A and B obtained through the least squares method; The actual observed pump station efficiency; The pump station efficiency is obtained by interpolating the corrected pump station efficiency characteristic surface using radial basis functions.

[0040] The linear equation for converting the original pump station efficiency characteristic surface to the corrected pump station efficiency characteristic surface is:

[0041] The corrected pump station efficiency characteristic surface = A × original pump station efficiency characteristic surface + B.

[0042] Furthermore, the process for obtaining the comprehensive corrected pump station efficiency characteristic surface under the optimal learning rate in step S4 is as follows:

[0043] The expression for Mean Absolute Error (MAE) is:

[0044]

[0045] The root mean square error (RMSE) is expressed as follows:

[0046]

[0047] The mean squared error (MSE) is expressed as follows:

[0048]

[0049] The expression for the maximum error MI is:

[0050]

[0051] In the above formula, This refers to the actual operating efficiency of the pumping station; To correct the pump station efficiency;

[0052] The mathematical expression for the learning rate is:

[0053]

[0054] The expression for the multi-objective weighted error function is:

[0055]

[0056] In the above formula, w1, w2, w3, and w4 are the weights of the error term in the error function;

[0057] The mathematical expression for the optimal learning rate is:

[0058]

[0059] The objective of finding the optimal learning rate is to minimize the multi-objective weighted error. J(a) represents the pump station efficiency after comprehensive correction; J(a) represents the optimal learning rate a when the multi-objective weighted error between the actual operating efficiency and the comprehensive corrected pump station efficiency is minimized.

[0060] The comprehensive corrected pump station efficiency characteristic surface is obtained by weighting the original pump station efficiency characteristic surface and the corrected pump station efficiency characteristic surface.

[0061] Furthermore, in step S5, the efficiency characteristic surface of the pumping station is dynamically updated periodically using historical measured data. The update process is as follows:

[0062] The efficiency characteristic curve of the pumping station is updated periodically, with the update time span being the sliding window time step S. For each sliding window dataset W... k Calculate the efficiency characteristic surface E of the pumping station k , denoted as E k =f(W k The efficiency characteristic surface of the pumping station is dynamically updated periodically, with an update time span of S. The mathematical expression is:

[0063]

[0064] In the above formula, E k For the k-th sliding window W k The updated pump station efficiency characteristic surface obtained from the above calculation; W kLet W be the dataset of the k-th sliding window; f is the dataset based on the sliding window dataset W. k A function to calculate and update the efficiency characteristic surface of the pumping station.

[0065] Based on the above technical solutions, the present invention also provides a dynamic updating system for pump station efficiency characteristic surfaces. The system includes a processor, which is used to execute the steps of the dynamic updating method for pump station efficiency characteristic surfaces given in the above technical solutions.

[0066] Furthermore, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the dynamic update method for the pump station efficiency characteristic surface given in the above technical solutions.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] 1. This invention proposes a dynamic update method for the surface of pump station efficiency characteristics. In the time dimension, through dynamic rolling updates, the time effect in the pump station efficiency characteristics is revealed, improving the simulation accuracy of pump station efficiency; it also reduces the influence of the indistinct pump station efficiency characteristics due to the long time span of the dataset, thus improving the simulation accuracy of pump station efficiency.

[0069] 2. The dynamic update method for pump station efficiency characteristic surface proposed in this invention establishes a dynamic update model for pump station efficiency characteristic surface based on the analysis conclusions of dynamic update of pump station efficiency characteristic surface using a short time span pump station dataset, and then outputs the pump station efficiency characteristic surface updated each time; the pump station efficiency simulation accuracy of the dynamic update method for pump station efficiency characteristic surface is higher than that of existing efficiency simulation accuracy. Attached Figure Description

[0070] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this disclosure and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0071] Figure 1 This is a flowchart of a method for dynamically updating the efficiency characteristic surface of a pumping station according to the present invention. Detailed Implementation

[0072] To facilitate understanding and implementation of the present invention by those skilled in the art, the various steps of the method proposed in this invention are described in detail below. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, it should be understood that after reading the teachings of this invention, those skilled in the art can make various modifications or alterations to the invention, and these equivalent forms also fall within the scope defined by the appended claims.

[0073] Example

[0074] like Figure 1 As shown, the present invention provides a method for dynamically updating the efficiency characteristic surface of a pumping station, comprising the following steps:

[0075] Step S1: Process the abnormal values ​​in the collected pump station data;

[0076] Step S2: Compile the pump station data and divide it into sliding window datasets along the time dimension;

[0077] Step S3: Use linear equations to establish the relationship between the original pump station efficiency characteristic curve and the measured pump station efficiency characteristic monitoring data, and perform linear translation on the original pump station efficiency characteristic surface to obtain the corrected pump station efficiency characteristic surface.

[0078] Step S4: Based on the principle of minimizing error, select the optimal learning rate for the original pump station efficiency characteristic surface and the corrected pump station efficiency characteristic surface to obtain the comprehensive corrected pump station efficiency characteristic surface under the optimal learning rate.

[0079] Step S5: Periodically update the efficiency characteristic surface of the pumping station using historical measured data.

[0080] Example 1

[0081] In this embodiment, the dynamic updating simulation of the pumping station efficiency characteristic surface is carried out using four units in a certain river section. The specific implementation steps are as follows:

[0082] Step S1: Process the abnormal values ​​in the collected pump station data;

[0083] The pump station data used includes: head, flow rate, efficiency, and time; in this embodiment, the pump station data used includes head, flow rate, efficiency, and time.

[0084] Different pumping stations have different data limits for head, flow rate, and efficiency. Clearly defining these limits for each pumping station is crucial to prevent erroneous data from affecting the model. Due to factors such as aging data acquisition equipment or natural elements, head, flow rate, and unit efficiency data are prone to fluctuations and may exceed data limits. Outlier data exceeding the threshold must be deleted. The mathematical expression for this is:

[0085] H'={H i |H min ≤H i ≤H max};

[0086] Q'={Q i |Q min ≤Q i ≤Q max};

[0087] E'={E i |E min ≤E i ≤E max};

[0088] In the above formula, H' represents the effective head data after removing the threshold; H min This represents the lower limit of the pump station head data; H max Q' represents the upper limit of the pump station head data; Q' represents the effective flow rate data after removing the threshold; Q min This represents the lower limit of the pump station flow rate data; Q max E' represents the upper limit of the pump station flow rate data; E' represents the effective efficiency data after removing the threshold; E min E represents the lower limit of the pump station unit efficiency data. max This represents the upper limit of the pump station unit efficiency data;

[0089] The measured data of the pump station after inspection, troubleshooting, and correction are recorded as follows:

[0090] Head: H' = {H1,H2,...,H} t-1 H t ,...};

[0091] Flow rate: Q' = {Q1, Q2, ..., Q} t-1 Q t ,...};

[0092] Efficiency: E' = {E1, E2, ..., E t-1 E t ,...}.

[0093] The pump station data used in this embodiment is as follows:

[0094] The dataset for Unit 1 consists of actual operating data from November 16, 2022 to March 9, 2024.

[0095] The dataset for Unit 2 consists of actual operating data from November 23, 2022 to March 26, 2024.

[0096] The dataset for Unit 3 consists of actual operating data from November 16, 2022 to March 26, 2024.

[0097] The dataset for Unit 4 consists of actual operating data from December 3, 2022 to March 26, 2024.

[0098] The actual operating data of the pumping station is shown in Table 1 below; the data limitations are as follows: pumping head range: 0 ≤ H ≤ 4.1 m; pumping flow range: 18.5 ≤ Q ≤ 51.4 m³ / h 3 / s; Pump station unit efficiency range: 0≤E≤100%; After removing outliers, the usable data for the pump station are head H', flow rate Q', and efficiency E'.

[0099] Table 1. Actual Operating Data of Pizhou Station

[0100]

[0101] Step S2: Compile the pump station data and divide it into sliding window datasets along the time dimension;

[0102] Head, flow rate, and efficiency data are collected from different acquisition terminals, and their time information is not one-to-one. If the three types of data have different lengths, the data with the smaller data volume will be used as the basis. The data will be arranged chronologically, and a left join will be performed on the data tables. Using time as the index, the closest timestamp in each data table will be found, and all data will be associated into a single table. The maximum time difference tolerance is T. max The joined data tables are then reordered using time as the index to obtain a usable data table. Its mathematical expression is:

[0103]

[0104] In the above formula, D1 represents the pump station unit efficiency data; D2 represents the pump station head data; D3 represents the pump station flow rate data; D represents the data after merging the head, flow rate, and efficiency data and reordering them according to time; the time difference between each group of head, flow rate, and efficiency data is less than the maximum time difference tolerance T. max ;

[0105] The merged dataset is reindexed, i.e., D = {(t1,x1),(t2,x2),...,(t...} n ,x n The sliding window dataset is denoted as W. k ={(t k ,x k ),(t k+1 ,x k+1 ),...,(t k+W-1 ,x k+W-1 )};

[0106] The expression for the sliding window dataset is:

[0107] W i ={(t i+j ,x i+j )|j=0,1,2,...,m-1};

[0108] i = 1, 1 + S, 1 + 2S, ..., t i+W-1 ≤t n ;

[0109] In the above formula, i is the sliding window dataset number; m is the number of data points in the sliding window dataset; and S is the sliding window time step.

[0110] In this embodiment, the maximum time difference tolerance for merging pump station data is T. max =10min, the merged dataset is D={(t1,e1,h1,q1),(t2,e2,h2,q2),...(t n ,e n ,h n ,q n The pump station's sliding window dataset is divided into six modes, each with a different time span, as shown in Table 2 below.

[0111] Table 2. Dynamic Update Mode of Pump Station Efficiency Characteristic Surface

[0112]

[0113] Step S3: Use linear equations to establish the relationship between the original pump station efficiency characteristic surface and the measured pump station efficiency characteristic monitoring data, and perform linear translation on the original pump station efficiency characteristic surface to obtain the corrected pump station efficiency characteristic surface.

[0114] The actual operating data of the pumping station is interpolated onto the original pumping station efficiency characteristic surface. A linear equation is used to establish a linear relationship between the interpolated original pumping station efficiency characteristic surface data and the actual operating data. The optimal parameters for translating the original pumping station efficiency characteristic surface are found, and the least squares method is selected as the optimization function for the parameters. Based on the optimal parameters, the linear equation for converting the original pumping station efficiency characteristic surface into the corrected pumping station efficiency characteristic surface is derived.

[0115] The interpolation function uses radial basis function interpolation, and the kernel function is the inverse quadratic kernel function. This kernel function is suitable for data interpolation problems that require smoothing and have good boundary conditions. Its mathematical expression is:

[0116]

[0117] In the above formula, f(x) is the interpolation function, and r = ||xx|| i || represents the interpolation point x and the data point x. iThe Euclidean distance between them is determined by solving a system of equations or by the least squares method.

[0118] The objective function for parameter optimization uses the least squares method, and its mathematical expression is:

[0119]

[0120] In the above formula, J1 represents the efficiency-related parameters A and B obtained through the least squares method; The actual observed pump station efficiency, The pump station efficiency is obtained by interpolating the corrected pump station efficiency characteristic surface using radial basis functions.

[0121] The linear equation for converting the original pump station efficiency characteristic surface to the corrected pump station efficiency characteristic surface is:

[0122] The corrected pump station efficiency characteristic surface = A × original pump station efficiency characteristic surface + B.

[0123] Step S4: Based on the principle of minimizing error, select the optimal learning rate for the original pump station efficiency characteristic surface and the corrected pump station efficiency characteristic surface to obtain the comprehensive corrected pump station efficiency characteristic surface under the optimal learning rate.

[0124] The expression for Mean Absolute Error (MAE) is:

[0125]

[0126] The root mean square error (RMSE) is expressed as follows:

[0127]

[0128] The mean squared error (MSE) is expressed as follows:

[0129]

[0130] The expression for the maximum error MI is:

[0131]

[0132] This refers to the actual operating efficiency of the pumping station; To correct the pump station efficiency;

[0133] The mathematical expression for learning rate is:

[0134] a n+1 =a n +Δa;

[0135]

[0136] The expression for the multi-objective weighted error function is:

[0137]

[0138] The weights of each error term in the multi-objective weighted error function are determined using a normalization method. The expression for the weight of each error term is as follows:

[0139]

[0140] In the above formula, MAE0 is the actual value of the mean absolute error MAE; MSE0 is the actual value of the mean square error MSE; RMSE0 is the actual value of the root mean square error RMSE; and MI0 is the actual value of the maximum error MI.

[0141] The mathematical expression for the optimal learning rate is:

[0142]

[0143] The learning rate 'a' is iteratively increased until the optimal learning rate is found. The comprehensive correction pump station efficiency characteristic surface is a weighted average of the original pump station efficiency characteristic surface and the corrected pump station efficiency characteristic surface. w1, w2, w3, and w4 are the weights of the error term in the error function. The objective of finding the optimal learning rate is to minimize the multi-objective weighted error. J(a) represents the pump station efficiency after comprehensive correction; J(a) represents the optimal learning rate a when the multi-objective weighted error between the actual operating efficiency and the comprehensive corrected pump station efficiency is minimized, thus obtaining the characteristic surface of the comprehensive corrected pump station efficiency.

[0144] In this embodiment, the optimal learning rate was experimentally verified to be a=0, meaning that the multi-objective weighted error was minimized when the corrected pump station efficiency characteristic surface was used to its fullest extent.

[0145] Step S5: Periodically update the efficiency characteristic surface of the pumping station using historical measured data;

[0146] The efficiency characteristic surface of the pumping station is updated periodically, with the update time span being the sliding window time step S; for each sliding window dataset W k Calculate the efficiency characteristic surface E of the pumping station k , denoted as E k =f(W k The efficiency characteristic surface of the pumping station is dynamically updated periodically, with an update time span of S, and the expression is:

[0147]

[0148] In the above formula, E k For the k-th sliding window W k The updated pump station efficiency characteristic surface obtained from the above calculation; W kLet W be the dataset of the k-th sliding window; f is the dataset based on the sliding window dataset W. k A function to calculate and update the efficiency characteristic surface of the pumping station.

[0149] After each round of updates, the sliding window dataset is updated once in the time dimension to achieve dynamic rolling updates, and the pump station efficiency characteristic surface after each update is output.

[0150] In this embodiment, the pump station efficiency simulation method employs dynamic updating of the pump station efficiency characteristic surface, multinomial regression, multiple linear regression, Gaussian process regression, regression tree, support vector regression, and artificial neural network methods. The pump station's sliding window dataset is divided into six modes, each with a different time span. The time range of the dataset used for the dynamic rolling update of the six pump station modes is shown in Table 3 below.

[0151] Table 3. Time range for dynamic rolling update of datasets for six modes at Pizhou Station

[0152]

[0153]

[0154]

[0155]

[0156]

[0157]

[0158] The following evaluation indicators are used to evaluate the simulation results of the dynamic update method for pump station efficiency characteristic surfaces and the results of the traditional efficiency simulation method, so as to obtain an objective analysis.

[0159] Mean Absolute Error (MAE) reflects the average absolute error between simulation efficiency and actual efficiency. Its formula is:

[0160] The root mean square error (RMSE) reflects the dispersion of simulation efficiency, and its formula is:

[0161]

[0162] The mean squared error (MSE) reflects the accuracy level of the model simulation, and its formula is:

[0163]

[0164] The maximum error A reflects the most extreme case of the model simulation results, and its formula is:

[0165] A = max(|Si -0 i |)

[0166] In the above formula, S i For simulation efficiency; O i For actual efficiency; is the average of the actual efficiency; N is the number of simulated efficiency data.

[0167] The simulation results of the six modes of the dynamic update method for the efficiency characteristic surface of the pumping station are compared and analyzed with the simulation results of multinomial regression, multiple linear regression, Gaussian process regression, regression tree, support vector regression and artificial neural network model, as shown in Table 4 below.

[0168] Table 4. Simulation results and evaluation results during the validation period for each model method

[0169]

[0170]

[0171] The simulation results based on the dynamic updating method of pump station efficiency characteristic surface show that: ① The simulation results based on the dynamic updating method using measured pump station data, with two months of data simulation and weekly updates, show that most of the four indicators—mean absolute error, mean square error, root mean square error, and maximum error—are superior to the previous traditional simulation method. ② The dynamic updating method of pump station efficiency characteristic surface can significantly reduce the maximum error under the most unfavorable conditions and obtain more ideal simulation results under extreme conditions, making its application to pump station efficiency simulation more feasible and reliable.

[0172] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for dynamically updating the efficiency characteristic surface of a pumping station, characterized in that, Includes the following steps: Step S1: Process the abnormal values ​​in the collected pump station data; Step S2: Compile the pump station data and divide it into sliding window datasets along the time dimension; Step S3: Use linear equations to establish the relationship between the original pump station efficiency characteristic curve and the measured pump station efficiency characteristic monitoring data, and perform linear translation on the original pump station efficiency characteristic surface to obtain the corrected pump station efficiency characteristic surface. The actual operating data of the pumping station is interpolated onto the original pumping station efficiency characteristic surface. A linear equation is used to establish a linear relationship between the interpolated original pumping station efficiency characteristic surface data and the actual operating data of the pumping station. The optimal parameters for translating the original pumping station efficiency characteristic surface are found, and the least squares method is selected as the optimization function for the parameters. Based on the optimal parameters, the linear equation for converting the original pumping station efficiency characteristic surface into the corrected pumping station efficiency characteristic surface is derived. The interpolation function uses radial basis functions for interpolation, and its mathematical expression is: In the above formula, f(x) is the interpolation function, and r = ||xx|| i || represents the interpolation point x and the data point x. i The Euclidean distance between them, c i Determined by solving a system of equations or by the least squares method; The mathematical expression for the least squares method is: In the above formula, J1 represents the efficiency-related parameters A and B obtained through the least squares method; The actual observed pump station efficiency; The pump station efficiency is obtained by interpolating the corrected pump station efficiency characteristic surface using radial basis functions. The linear equation for converting the original pump station efficiency characteristic surface to the corrected pump station efficiency characteristic surface is: Corrected pump station efficiency characteristic surface = A × original pump station efficiency characteristic surface + B; Step S4: Based on the principle of minimizing error, select the optimal learning rate for the original pump station efficiency characteristic surface and the corrected pump station efficiency characteristic surface to obtain the comprehensive corrected pump station efficiency characteristic surface under the optimal learning rate. Step S5: Periodically update the efficiency characteristic surface of the pumping station using historical measured data.

2. The method for dynamically updating the efficiency characteristic surface of a pumping station according to claim 1, characterized in that, The data processing described in step S1 involves processing abnormal values ​​in the collected pump station data. The data processing process is as follows: The collected pump station data includes: head, flow rate, efficiency, and time. Different pumping stations have different limits for head, flow rate, and efficiency data. Outlier data exceeding the threshold is deleted. The mathematical expression for this is: H={H i |H min ≤H i ≤H max }; Q={Q i |Q min ≤Q i ≤Q max }; And={And i |And min ≤E i ≤E max }; In the above formula, H represents the effective head data after removing the threshold; H min This represents the lower limit of the pump station head data; H max Q represents the upper limit of the pump station head data; Q is the effective flow rate data after removing the threshold; Q min This represents the lower limit of the pump station flow rate data; Q max E represents the upper limit of the pump station flow rate data; E represents the effective efficiency data after removing the threshold; E min E represents the lower limit of the pump station unit efficiency data. max This represents the upper limit of the pump station unit efficiency data; The measured data of the pump station after inspection, troubleshooting, and correction are recorded as follows: Head: H' = {H1,H2,...,H} t-1 H t ,...}; Flow rate: Q' = {Q1, Q2, ..., Q} t-1 Q t ,...}; Efficiency: E' = {E1, E2, ..., E t-1 E t ,...}.

3. The method for dynamically updating the efficiency characteristic surface of a pumping station according to claim 2, characterized in that, Step S2 involves organizing the pump station data and dividing the dataset into sliding window segments along the time dimension. This includes the following steps: Step S21: Head, data, and efficiency data are collected from different acquisition terminals, and their time information does not correspond one-to-one. The data are arranged chronologically, and a left join is performed on the data tables. Using time as the index, the closest timestamp in each data table is found, and all data are associated into one table. The maximum time difference tolerance is T. max The joined data tables are then reordered using time as the index to obtain the desired data table: Step S22: Reindex the merged dataset, i.e., D = {(t1,x1),(t2,x2),...,(t...} n ,x n The sliding window dataset is denoted as W. k ={(t k ,x k ),(t k+1 ,x k+1 ),...,(t k+W-1 ,x k+W-1 )}; The sliding window dataset is then represented as: W i ={(t i+j ,x i+j )∣j=0,1,2,...,m-1}; i=1,1+S,1+2S,...,t i+W-1 ≤t n ; In the above formula, t i+j x is the timestamp of the j-th data point in the i-th sliding window; i+j Let be the multivariate data vector of the j-th data point in the i-th sliding window; j is the relative position index within the sliding window; i is the dataset number of the sliding window; m is the number of data points in the dataset of the sliding window; and S is the time step of the sliding window.

4. The method for dynamically updating the efficiency characteristic surface of a pumping station according to claim 1, characterized in that, The process of obtaining the comprehensive correction pump station efficiency characteristic surface under the optimal learning rate in step S4 is as follows: The expression for the mean absolute error (MAE) is: The root mean square error (RMSE) is expressed as follows: The mean squared error (MSE) is expressed as follows: The expression for the maximum error MI is: In the above formula, This refers to the actual operating efficiency of the pumping station; To correct the pump station efficiency; The mathematical expression for the learning rate is: The expression for the multi-objective weighted error function is: In the above formula, w1, w2, w3, and w4 are the weights of the error term in the error function; The mathematical expression for the optimal learning rate is: The objective of finding the optimal learning rate is to minimize the multi-objective weighted error. J(a) represents the pump station efficiency after comprehensive correction; J(a) represents the optimal learning rate a when the multi-objective weighted error between the actual operating efficiency and the comprehensive corrected pump station efficiency is minimized. The comprehensive corrected pump station efficiency characteristic surface is obtained by weighting the original pump station efficiency characteristic surface and the corrected pump station efficiency characteristic surface.

5. The method for dynamically updating the efficiency characteristic surface of a pumping station according to claim 1, characterized in that, Step S5 describes the periodic dynamic updating of the pump station efficiency characteristic surface using historical measured data. The updating process is as follows: The efficiency characteristic curve of the pumping station is updated periodically, with the update time span being the sliding window time step S. For each sliding window dataset W... k Calculate the efficiency characteristic surface E of the pumping station k , denoted as E k =f(W k The efficiency characteristic surface of the pumping station is dynamically updated periodically, with an update time span of S. The mathematical expression is: In the above formula, E k For the k-th sliding window W k The updated pump station efficiency characteristic surface obtained from the above calculation; W k Let W be the dataset of the k-th sliding window; f is the dataset based on the sliding window dataset W. k A function to calculate and update the efficiency characteristic surface of the pumping station.

6. A dynamic updating system for the efficiency characteristic surface of a pumping station, characterized in that, Includes a processor, the processor being configured to perform the steps of the dynamic update method for the pump station efficiency characteristic surface as described in claims 1-5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the dynamic updating method for the efficiency characteristic surface of a pumping station as described in any one of claims 1-6.

Images