A Pumping Station Regulation Method, Device and Electronic Equipment Based on Digital Twin

Abstract

The present invention relates to the technical field of information processing, and in particular, to a pumping station regulation method, device and electronic device based on digital twin. The method includes: acquiring real-time data and historical data of the pumping station, and synchronizing the real-time data and historical data to a digital twin platform; acquiring a scheduling strategy generated by the digital twin platform based on the real-time data and historical data; and regulating the operation mode of the pumping station based on the scheduling strategy. This application reproduces the operation process of the pumping station based on digital twin technology, and formulates a scheduling strategy by using the real-time data and historical data of the pumping station, which can realize fine regulation and optimization of the operation state of the pumping station, thereby improving energy efficiency by optimizing the operation parameters of the pumping station, reducing energy consumption, quickly responding to changes in the external environment and urban area demands, and dynamically adjusting the operation mode of the pumping station.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing, and in particular, to a pumping station regulation method, device and electronic device based on digital twin. Background Art

[0002] In the current field of water resource management, as an important part of water conservancy projects, the traditional operation mode of pumping stations mainly relies on manual monitoring and experience control, lacking intelligent and refined management means. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a pumping station regulation method, device and electronic device based on digital twin.

[0004] In a first aspect, an embodiment of the present invention provides a pumping station regulation method based on digital twin, the method comprising:

[0005] Obtaining real-time data and historical data of the pumping station, and synchronizing the real-time data and historical data to a digital twin platform;

[0006] Obtaining a scheduling strategy generated by the digital twin platform based on the real-time data and historical data;

[0007] Adjusting the operation mode of the pumping station based on the scheduling strategy;

[0008] Wherein, the digital twin platform includes an intelligent regulation model, and the intelligent regulation model includes an initial correction model, a pumping station unit evaluation model, an in-pumping-station flow optimization distribution model, and a pumping station real-time optimization scheduling model connected in sequence; the initial correction model includes a water level prediction model and a pump group characteristic curve correction model.

[0009] Combined with the first aspect, the step of obtaining real-time data and historical data of the pumping station, and synchronizing the real-time data and historical data to the digital twin platform includes:

[0010] Obtaining the drawings of the pumping station units, and performing information management to construct an initial digital twin model;

[0011] Correcting the initial digital twin model based on the pumping station to obtain a pumping station digital twin model;

[0012] Integrating the pumping station digital twin model and the intelligent regulation model into the digital twin platform.

[0013] Combined with the first aspect, the step of obtaining the scheduling strategy generated by the digital twin platform based on the real-time data and historical data includes:

[0014] Based on the water level prediction model, a water level prediction sequence plan for the short-term future is obtained. At the same time, based on the pump unit characteristic curve correction model, the corrected device curve of the pump station water pump unit is obtained;

[0015] Based on the pump station unit evaluation model, it is judged whether to optimize in the current period by the pump station operation efficiency / energy unit consumption, and an evaluation plan for the pump station unit is obtained;

[0016] When it is obtained in the evaluation plan of the pump station unit that the current unit state is operating in the non-efficient area, the flow optimization distribution model and the real-time optimization scheduling model in the pump station are called to obtain the corresponding optimal number of operating units and operating flow, and the optimal flow distribution strategy for the units in different periods.

[0017] Combined with the first aspect, the steps of obtaining the corrected device curve of the pump station water pump unit based on the pump unit characteristic curve correction model include:

[0018] Obtain the pump station characteristic curve and the long-sequence operation data during the operation of the pump station unit;

[0019] Use the real-coded genetic algorithm to calibrate and optimize the parameters of the preset formula of the water pump characteristic curve to obtain the optimization result;

[0020] Based on the optimization result, draw the target water pump characteristic curve to update the water pump unit characteristic curve in a rolling manner.

[0021] Combined with the first aspect, the steps of obtaining the evaluation plan for the pump station unit by judging whether to optimize in the current period based on the pump station unit evaluation model include:

[0022] According to the actual engineering scheduling operation conditions at different time scales, process the water regime data and engineering regime data in the real-time monitoring data;

[0023] Determine the evaluation indicators in the pump station unit evaluation index system and quantitatively process the evaluation indicators;

[0024] Use the analytic hierarchy process to determine the evaluation index weights and establish a hierarchical structure;

[0025] Construct a judgment matrix and scale the quantitative relationship of importance between adjacent two levels;

[0026] Based on the judgment matrix, deduce the relative importance order of each element in this level to a certain element in the previous level;

[0027] Combine the scores and weights of each evaluation index for weighted summation to obtain the overall evaluation result.

[0028] Combined with the first aspect, the steps of deducing the relative importance order of each element in this level to a certain element in the previous level based on the judgment matrix also include:

[0029] Calculate the first ratio of the consistency index and the random consistency;

[0030] Determine whether the ratio is less than a preset value;

[0031] If so, determine that the judgment matrix meets the preset requirements;

[0032] If not, adjust and correct the judgment matrix until the second ratio obtained by recalculation is less than the preset value.

[0033] Combined with the first aspect, when it is obtained in the evaluation scheme of the pumping station unit that the current unit state is operating in the non-efficient area, the steps of calling the flow optimization distribution model in the pumping station and the real-time optimization scheduling model of the pumping station to obtain the corresponding optimal number of units to start and the operating flow, and the optimal flow distribution strategy of the units at different times include:

[0034] After processing the characteristic curve of the pump device, calculate the pumping device efficiency of the pump unit;

[0035] Calculate the optimal solution for economic operation in the pumping station;

[0036] The real-time optimization model of the pumping station determines whether it can meet the water transfer requirements corresponding to the optimal solution under the condition of high-area operation;

[0037] If not, with the goal of the lowest unit water lifting cost, combined with the optimal solution, the given scheduling time and the water transfer volume, formulate an optimal unit operation plan that meets the requirements of the water transfer task.

[0038] In the second aspect, the present application provides a pumping station regulating device based on digital twin, and the device includes:

[0039] A data synchronization module for acquiring the real-time data and historical data of the pumping station and synchronizing the real-time data and historical data to the digital twin platform;

[0040] A generation module for acquiring the scheduling strategy generated by the digital twin platform based on the real-time data and historical data;

[0041] An adjustment module for adjusting the operation mode of the pumping station based on the scheduling strategy;

[0042] Among them, the digital twin platform includes an intelligent regulation model, and the intelligent regulation model includes an initial correction model, a pumping station unit evaluation model, a flow optimization distribution model in the pumping station, and a real-time optimization scheduling model of the pumping station connected in sequence; the initial correction model includes a water level prediction model and a pump group characteristic curve correction model.

[0043] In the third aspect, the present application provides an electronic device, which includes a memory and a processor. The memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the above method.

[0044] In a fourth aspect, the present application provides a storage medium storing computer program instructions, which, when read and executed by a processor, execute the above method.

[0045] The embodiments of the present invention bring the following beneficial effects: The embodiments of the present invention provide a method, device and electronic device for regulating a pumping station based on digital twins. The method includes: obtaining real-time data and historical data of the pumping station and synchronizing the real-time data and historical data to a digital twin platform; obtaining a scheduling strategy generated by the digital twin platform based on the real-time data and historical data; adjusting the operation mode of the pumping station based on the scheduling strategy; wherein the digital twin platform includes an intelligent regulation model, and the intelligent regulation model includes an initial correction model, a pumping station unit evaluation model, an internal flow optimization distribution model of the pumping station, and a real-time optimization scheduling model of the pumping station that are connected in sequence; the initial correction model includes a water level prediction model and a pump group characteristic curve correction model.

[0046] Based on digital twin technology, the present application reproduces the operation process of the pumping station and formulates a scheduling strategy using the real-time data and historical data of the pumping station, which can achieve fine regulation and optimization of the operation state of the pumping station, thereby improving energy efficiency by optimizing the operation parameters of the pumping station, reducing energy consumption, quickly responding to changes in the external environment and urban area demands, and dynamically adjusting the operation mode of the pumping station.

[0047] Other features and advantages of the present invention will be described in the following specification, and some of them will become obvious from the specification, or can be understood by implementing the present invention. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification, claims and drawings.

[0048] To make the above objectives, features and advantages of the present invention more obvious and understandable, the following preferred embodiments are specifically given below, and in conjunction with the accompanying drawings, the detailed description is as follows. Description of the Drawings

[0049] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required to be used in the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0050] Figure 1 It is a schematic flow chart of the method for regulating a pumping station based on digital twins provided by the embodiments of the present invention;

[0051] Figure 2 It is a schematic principle diagram of the method for regulating a pumping station based on digital twins provided by the embodiments of the present invention;

[0052] Figure 3 Schematic diagram of the connections of the modules in the pump station regulation method based on digital twin provided by the embodiments of the present invention;

[0053] Figure 4 Schematic diagram of the efficiency characteristic curve of the synchronous motor in the pump station regulation method based on digital twin provided by the embodiments of the present invention;

[0054] Figure 5 Schematic diagram of the structure of the pump station regulation device based on digital twin provided by the embodiments of the present invention;

[0055] Figure 6 Schematic diagram of the structure of the electronic device provided by the embodiments of the present invention.

[0056] Reference numerals:

[0057] 10 - Data synchronization module, 20 - Generation module, 30 - Regulation module;

[0058] 130 - Processor, 131 - Memory, 132 - Bus, 133 - Communication interface. Detailed implementation manners

[0059] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0060] To facilitate the understanding of this embodiment, the technical terms designed in this application will be briefly introduced below.

[0061] The concept of digital twin technology is a digital concept and technical means. It is based on and centered around the integrated fusion of data and models. By constructing an accurate digital mapping of a physical object in real time in the digital space, it simulates, verifies, predicts, and controls the entire life cycle process of the physical entity based on data integration and analysis and prediction, and finally forms an optimized closed loop for intelligent decision-making.

[0062] With the rapid development of digital twin technology, this technology has been widely applied in many fields such as industry, urban construction, and smart agriculture. Because it can accurately map the dynamic behavior of physical entities and match a large amount of sensor data, it has greatly improved the operation efficiency and reliability of the system.

[0063] After introducing the technical terms involved in this application, next, the application scenarios and design concepts of the embodiments of this application will be briefly introduced.

[0064] At present, the management of pumping stations mainly relies on manual monitoring and experience-based control, lacking intelligent and refined adjustment methods.

[0065] Based on this, the embodiments of the present application provide a pumping station adjustment method, device, and electronic device based on digital twin.

[0066] Embodiment 1

[0067] The present application provides a pumping station adjustment method based on digital twin, which combines Figure 1 As shown, the method includes:

[0068] S110, obtaining the real-time data and historical data of the pumping station, and synchronizing the real-time data and historical data to the digital twin platform.

[0069] S120, obtaining the scheduling strategy generated by the digital twin platform based on the real-time data and historical data.

[0070] S130, adjusting the operation mode of the pumping station based on the scheduling strategy.

[0071] Among them, the digital twin platform includes an intelligent regulation model, and the intelligent regulation model includes an initial correction model, a pumping station unit evaluation model, an in-pumping-station flow optimization distribution model, and a pumping station real-time optimization scheduling model connected in sequence; the initial correction model includes a water level prediction model and a pump unit characteristic curve correction model.

[0072] The pumping station adjustment method based on digital twin provided by the present application collects the data of the pumping station in real time, combines the collected data with the digital twin model, reproduces the operation process of the pumping station through the digital twin model, and formulates a scheduling strategy using the real-time data and historical data of the pumping station, ensuring the real-time and accuracy of the scheduling of the pumping station group, and can realize the fine regulation and optimization of the operation state of the pumping station, thereby improving energy efficiency by optimizing the operation parameters of the pumping station, reducing energy consumption, quickly responding to changes in the external environment and urban area demands, and dynamically adjusting the operation mode of the pumping station.

[0073] Among them, before step S110, the following steps are specifically included:

[0074] S010, obtaining the drawings of the pumping station units, performing information management, and constructing an initial digital twin model.

[0075] Specifically, the 3DMAX software is used to construct the initial digital twin model of the pumping station units. The modeling process is as follows:

[0076] (1) Organize the drawings: Organize the completed drawings of buildings, structures, water machines, etc. required for the modeling parts such as the pumping station, flood control sluice, and intake sluice.

[0077] (2) Decompose the project: According to the modeling scope, conduct personnel division of labor and decomposition of the twin modeling. Each group independently inversely models each component, and finally conducts model integration and assembly.

[0078] (3) Create a family library: The buildings and equipment components in the pump station project do not have universality. During the twin modeling process, it is necessary to create a family library for the components based on large-scale drawings, etc. The scope of the family library includes doors and windows of the pump station building, mechanical and electrical equipment, etc.

[0079] (4) Graphic management and information management: Before building the model, conduct graphic management and information management. Graphic management mainly includes model color matching, line types, and layer determination, and determine the appearance color matching of the twin model according to the actual decoration plan. Information management mainly includes model geometric information and non-geometric information. Geometric information includes model shape, size, position, etc., and non-geometric information includes project parameters, equipment parameters, manufacturer, etc. Geometric information is determined by the as-built drawings, and non-geometric information is provided by the pump station operation and maintenance unit and input as attributes during the processing of the twin model.

[0080] (5) Software modeling: Use 3DMAX software, and inversely model the twin model strictly in accordance with the design in combination with the drawings of each specialty to ensure the consistency between the twin model and the physical pump station. After inversely modeling each part of each specialty, conduct the general assembly combination of the models to form the initial digital twin model.

[0081] S020, calibrate the initial digital twin model based on the pump station to obtain the pump station digital twin model.

[0082] It can be understood that after the initial digital twin model is established, a quality review is conducted on the initial digital twin model. The review content includes: whether the model meets the initial design accuracy standard; whether the component positioning is accurate; whether the key parts are consistent with the drawings and the actual situation, etc. And when the consistency requirements are not met, timely correction is made, and finally a pump station digital twin model that meets the requirements is obtained.

[0083] S030, integrate the pump station digital twin model and the intelligent control model into the digital twin platform.

[0084] It can be understood that the pump station digital twin model has a communication connection module, which can be connected to the intelligent control model in step S120. The model training of the intelligent control model can be carried out based on the real-time data and historical data of the pump station digital twin model, and a scheduling strategy can be generated based on the model training results. The intelligent control model and the pump station establish a communication connection to obtain real-time data. Specifically: A sensor network is arranged at each key part of the pump station, and real-time data can be collected from each key part of the pump station and synchronized to the digital twin model in real time. The main data is as follows:

[0085] The data collected from the main and auxiliary units at least include: real-time operation data and historical data of water pumps and motors; real-time and historical data of water supply pumps, drainage pumps, vacuum pumps, and fans.

[0086] The data collected from electrical equipment at least include: incoming line, PT, outgoing line interval data of GIS equipment, high-voltage cabinet data, switch cabinet data, and excitation equipment data.

[0087] The data collected from the power generation and transformation system at least include: high- and low-voltage cabinet data of hydropower, various parameters of power generation and transformation equipment such as generators, main substations, and step-up substations.

[0088] The data collected from the vibration and swing monitoring and flow measurement system at least include: vibration monitoring and perception data in various directions of the unit, as well as data such as ultrasonic flow velocity and flow rate in the pump station flow channel.

[0089] Combined with the first aspect, step S120 includes:

[0090] S121, obtaining a water level prediction sequence plan for the short term in the future based on the water level prediction model. At the same time, obtaining the corrected device curve of the pump station water pump unit based on the pump unit characteristic curve correction model.

[0091] S122, based on the pump station unit evaluation model, determining whether to optimize in the current period by the pump station operation efficiency / energy unit consumption, and obtaining the evaluation plan of the pump station unit.

[0092] S123, when it is obtained in the evaluation plan of the pump station unit that the current unit state is operating in the non-efficient area, calling the flow optimization distribution model and the real-time optimization scheduling model in the pump station to obtain the corresponding optimal number of starting units and operating flow rate of the unit, and the optimal flow distribution strategy of the unit in different periods.

[0093] Combined with the first aspect, the real-time data of the pump station at least include real-time water regime data; the historical data at least include: historical water regime data.

[0094] The step of obtaining a water level prediction sequence plan for the short term in the future based on the water level prediction model in step S121 includes:

[0095] S1211, training the input layer, hidden layer, and output layer in the water level prediction model based on the BP neural network in turn using real-time water regime data and historical water regime data, and outputting the water level prediction sequence plan.

[0096] It is understandable that, according to the actual requirements of the project and in combination with medium- and long-term measured data, the water level information is processed to establish a suitable water level prediction model for the pumping station, which is of great significance for the regulation of the pumping station, water volume scheduling, and the safety of buildings. In this embodiment, a BP neural network model with strong nonlinear fitting ability and wide application is adopted to establish a complex mapping relationship between the water regime state and the working condition state, so as to accurately perceive the water level and flow velocity.

[0097] Before actual application, the model is built and the model is trained and verified to obtain a water level prediction model that meets the accuracy requirements for application in the test stage.

[0098] It is worth noting that since the water level state of the water diversion project has the characteristic of changing in an annual cycle, the length of the data used in the training stage should be greater than or equal to the water level monitoring data for a complete year.

[0099] A BP neural network refers to an artificial neural network that uses the backpropagation (BP) algorithm. The backpropagation in the BP algorithm actually transmits the calculated prediction error, and then adjusts the weights and thresholds between layers according to the size of the error. Therefore, a complete process includes two parts. First, the input data is forward propagated through the network calculation to obtain a predicted value, and then the error is calculated. The error is then backpropagated to adjust the network parameters.

[0100] Among them, a BP neural network consists of an input layer, an output layer, and an intermediate hidden layer. Specifically, each layer contains a different number of neurons, and there are corresponding weight values, that is, weights, for the connections between neurons in different layers. In addition to the input layer, a certain size of bias, that is, a threshold, is added to the neurons. When the error between the predicted value of the output layer and the target value exceeds the specified range, the error is backpropagated to adjust the weights and thresholds of the previous layers.

[0101] Then, the specific steps for training a three-layer BP neural network with one hidden layer are as follows:

[0102] Combined with Figure 3 As shown, the water regime monitoring data such as the water level and flow rate before and after the pumping station are all typical time series data. After cleaning the above-mentioned water regime data obtained, it is used as the input data set of the above BP neural network. Among them, 70% is used as the training set, 15% is used as the validation set, and 15% is used as the test set. It is understandable that the above BP neural network is trained through the training set; the validation set is used to verify the effect of the trained BP neural network and adjust the parameters to prevent overfitting; the test set is used to finally evaluate the generalization ability of the BP neural network. Specifically, the water regime detection data includes the number of pumping station units started at the previous moment, the average opening of the pumping station units, the pumping station flow rate, the upstream water level of the station, the downstream water level of the station, and the number of pumping station units at the current moment, and the output is the upstream water level (or downstream water level) of the station at the current moment.

[0103] In the process of back-adjusting the weights in the BP neural network, the activation function needs to be differentiated, and the activation function used satisfies the differentiability condition. Commonly used activation functions include sigmoid and tansig functions, etc. The general expression of the S-shaped function is as follows:

[0104]

[0105] When a = 0, b = 1, and k = 1, the above formula can be transformed into

[0106]

[0107] Combined with Figure 2 As shown, the value range of the S function is (0, 1); when net = 0, y = f(net) = 0.5; the slope of y = f(net) is larger when net ∈ (-0.6, 0.6), and changes less in other intervals.

[0108] The specific training process is as follows:

[0109] ① Assign initial values to the weight matrix: Assign a set of non-zero and relatively small initial values to the weights W ji between the input layer and the hidden layer and the weights W kj between the hidden layer and the output layer randomly.

[0110] ② Set the network structure and hyperparameters, such as: set parameters such as the training objective, number of iterations, learning rate, and momentum coefficient, and then perform the following training calculation steps Ⅰ to Ⅵ for each sample in turn until the error convergence condition is reached or the upper limit of the number of training times is reached, and then stop training.

[0111] Ⅰ) Calculate the outputs y i , y j and y k of each layer starting from the input layer. Among them, the BP neural network dataset consists of input data X and output data Y, and generally both are column vectors.

[0112]

[0113]

[0114] In the BP neural network in this embodiment, the linear function is used as the activation function of the input layer, and the sigmoid function is used as the activation function of the hidden layer. The input and output relationship in the network is as follows:

[0115] For the input layer part:

[0116] The input data of the input layer is the water regime data at each moment , due to the use of a linear function, the output .

[0117] For the hidden layer part:

[0118] The input value of a neuron in the hidden layer is equal to the sum of the products of the input values connected to it and the corresponding weights, plus the threshold value added to that neuron, as shown in the following formula:

[0119]

[0120] In the formula, n represents the number of neurons in the input layer, and j represents the number of neurons in the hidden layer.

[0121] The output value of the hidden layer is the value obtained after passing through the sigmoid function, as shown in the following formula:

[0122]

[0123] For the output layer part:

[0124] The input value of a neuron in the output layer is equal to the sum of the products of the input values connected to it and the corresponding weights, plus the threshold value added to that neuron, as shown in the following formula:

[0125]

[0126] Similarly, the output value of the output layer is the value obtained after passing through the sigmoid function, as shown in the following formula:

[0127]

[0128] II) Calculate the error between the predicted value and the true value of each neuron in the output layer, as shown in the following formula:

[0129]

[0130] III) After obtaining the error of the predicted value of the output layer, calculate the error of each neuron in the previous hidden layer according to the following formula:

[0131]

[0132] IV) Use the error to adjust the weights and thresholds of each layer:

[0133]

[0134]

[0135] In the formula, m is the number of iterations, m c is the momentum coefficient, and its general value range is 0.9 - 1; l ris the learning rate, which has a great impact on convergence and the iteration step size. Generally, its value range is 0.1 - 3.

[0136] Ⅴ) After one forward propagation calculation, judge the error obtained from the calculation of the output layer and the set training target for size.

[0137] Ⅵ) If , stop training; otherwise, execute III and IV. After calculating and passing the error forward, adjust the weights and thresholds between each layer, execute I and II, and perform forward propagation again. After meeting the training termination conditions, the training ends.

[0138] After that, perform the performance evaluation of the BP neural network. The evaluation indicators of the neural network model usually select appropriate performance evaluation indicators according to different research problems. For prediction problems, the evaluation indicators usually include mean square error (MSE), root mean square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination (R 2 ), and these four can be selected and used according to actual usage requirements, which are not limited here. Their expressions are respectively:

[0139]

[0140]

[0141]

[0142]

[0143] In the above formulas, n represents the total number of samples, i represents the i-th sample, y i represents the network prediction value of the i-th sample, represents the corresponding true value of the sample.

[0144] Combined with the first aspect, in step S121, the steps of obtaining the corrected device curve of the pump station water pump unit based on the pump unit characteristic curve correction model include:

[0145] S1212, obtain the characteristic curve of the pump station and the long-term operation data during the operation of the pump station unit.

[0146] S1213, use the real-coded genetic algorithm to calibrate and optimize the parameters of the set formula of the water pump characteristic curve to obtain the optimization result.

[0147] S1214, based on the optimization result, draw the water pump characteristic curve to update the characteristic curve of the water pump unit in a rolling manner.

[0148] It is understandable that during the actual operation of the pumping station, due to weather, human operation, emergency events, etc., emergency operations that are uncontrollable for the units are carried out, and blade wear caused by long-term cavitation and vibration of the pumping station units will cause the hydraulic characteristic curve of the actual operation of the units to deviate from the design value. Therefore, by combining the characteristic curve of the pumping station with the long-term operation data during the operation of the pumping station units, the real-coded genetic algorithm is used to calibrate and optimize the preset formula parameters of the water pump characteristic curve, so as to further draw the water pump characteristic curve and realize the rolling update of the characteristic curve relationship of the water pump units.

[0149] In view of the fact that the actual monitoring data are all in the high-efficiency area, different operating points are divided into confidence intervals such as high-efficiency area, non-high-efficiency area, and left and right of the high-efficiency area to increase the calibration accuracy of the curve.

[0150] Among them, the water pump characteristic curve specifically refers to the characteristic curves between the flow rate and the head, the flow rate and the power, the flow rate and the efficiency, and the flow rate and the suction height of the water pump at a certain rotational speed. It is understandable that for a water pump, at its fixed frequency, there is a region where the water pump can operate with relatively high efficiency when operating in this region. For the power-frequency pump, its theoretical curve conforms to the following empirical formula:

[0151]

[0152]

[0153] Among them , , , , are the parameters of the characteristic curve, H is the height, and Q is the water flow rate of the pumping station.

[0154] Since the update of the pumping station characteristic curve can be converted into the solution of the parameters in the above formula, the object to find the optimal solution is five coefficient parameters, and each of them has its own different value range. If binary coding is used, difficulties will be encountered during decoding. Therefore, real-coded is used here. The specific implementation steps are as follows:

[0155] ① Determine the search range for each parameter based on the results of the least squares method.

[0156] ② Initialize the population size.

[0157] ③ Develop the corresponding fitness function according to the objective function.

[0158] ④ Select appropriate selection operator, crossover operator and mutation operator.

[0159] ⑤ Iterate the results based on the operators and fitness function in steps ③ and ④, and output the final result.

[0160] In this application, since a genetic algorithm with real - number coding is adopted, the corresponding crossover operator and mutation operator are also different from those in the binary genetic algorithm:

[0161] 1) Crossover operator

[0162] For the traditional crossover operator of the genetic algorithm with real - number coding, a random ratio is taken for the two individuals to be crossed and added, that is:

[0163]

[0164]

[0165] Generally, the value of α is limited to [0, 1]. In this way, the single - point crossover method will limit its global search ability to a certain extent.

[0166] Based on this, a second random quantity β is introduced in the method of this project to enhance the global search ability of the crossover operator, that is:

[0167]

[0168]

[0169] If the value of the new individual exceeds the limited search domain after being calculated by the above formula, the value calculated by the traditional method is used to replace it.

[0170] 2) Mutation operator

[0171] The commonly used mutation operators in the genetic algorithm with real - number coding are: uniform mutation, boundary mutation, non - uniform mutation, Gaussian mutation and other four operators. Uniform mutation means randomly selecting a number in the search domain to directly replace the value of the gene locus to be mutated. This method is the easiest to implement, but it does not consider that the population will get closer to the optimal solution as the iteration progresses. Therefore, in the later stage of iteration, its randomness will affect the speed of the population approaching the optimal solution; boundary mutation is a variation of uniform mutation. Its principle is that when performing boundary mutation operation, one of the two corresponding boundary genes of the gene locus is randomly taken to replace the original gene value, and it has the same problem as uniform mutation. Non - uniform mutation and Gaussian mutation both randomly take values around the current value of the gene locus to be mutated, and as the iteration progresses, the mutation area will be reduced. The method of this project selects non - uniform mutation. The specific mutation operator is as follows. Assume that the value range of the mutation point is X min , X max :

[0172]

[0173] In the formula, △(t,y) is a random number that conforms to a non-uniform distribution within the range of [0, y], and satisfies that as the number of evolutionary generations t increases, the probability that Δ (t,y) is close to 0 also increases, that is:

[0174]

[0175] In the formula, r is a random number that conforms to a uniform distribution within the range of [0, 1], T represents the maximum number of evolutionary generations, and b is a system parameter that determines the dependence of the random number perturbation on the evolutionary generation t.

[0176] 3) Algorithm configuration

[0177] Before using the algorithm to fit the characteristic curve of the water pump, a series of parameter configurations need to be given so that the algorithm can play its role. Different from the algorithm with binary coding, the search interval for each bit in its chromosome is no longer simply 0 and 1. Here, the coefficients to be optimized that make up the chromosome of the polynomial to be fitted each have different search domains. If the search domain is too large, the scale of the population and the number of iterations in the current algorithm may not be able to find the optimal solution; but if the population size and the number of iterations are increased accordingly, it will lead to a significant increase in the solution time of the entire algorithm. Therefore, how to give a reasonable search domain for each coefficient to be solved has become an issue that cannot be ignored in parameter configuration. Specifically, here, since the orders of magnitude of each coefficient of the polynomial are not in the same order, a unified search domain cannot be given. Thus, it is thought to use the least squares method to perform a first fit on the data, and then define 30% above and below the obtained coefficient as the search domain. And in the improved real number coding genetic algorithm, the coefficient obtained by the least squares method is also used as the initial value of the optimal solution, so that it can be ensured that the solution obtained by the algorithm during the optimization process is not worse than the solution obtained by the least squares method.

[0178] In addition, since in actual working conditions, pumps generally operate in the high-efficiency region, the data points collected may not cover the entire operating range of the pump. Moreover, the collected data points vary according to the running time of the pump itself and the changes in external water consumption, and the distribution of data points obtained in a short period is generally uneven. And for different pump units, there will also be situations where they operate in the non-high-efficiency region in a short period. Therefore, if we simply draw curves directly without judgment for all data points, it will have a great deviation impact on the overall curve due to the huge density differences of the data points. So we need to first divide the operating range of the pump into zones and then draw and analyze them. Since the operating condition points of the pump mainly concentrate in the high-efficiency region during operation, the region can be divided accordingly, that is, to the left of the high-efficiency region, the high-efficiency region, and to the right of the high-efficiency region. Naturally, if there are more data points distributed in a region, then the confidence level of this region is higher, which also means that the credibility of the drawn curve is higher. Randomly select the data collected during actual operation, and part of the data is used for effect verification.

[0179] Among them, data collection and processing include: collecting measured data such as long-term flow rate, head, vane setting angle, and unit operation efficiency of the pumping station, and establishing a summary table of historical data of flow rate - head - vane setting angle and a summary table of historical data of flow rate - head - efficiency.

[0180] Rectification of the pumping station characteristic curve includes: using the least squares method to find the shortest distance between the historical data points and the original pumping station characteristic curve, and by moving the characteristic curve, obtaining the pumping station characteristic curve and the corresponding formula that conform to the actual operation situation, obtaining the optimization results of each parameter, and then drawing the characteristic curve of the target pump to update the characteristic curve of the pump unit in a rolling manner.

[0181] Combined with the first aspect, step S122 includes:

[0182] S1221, according to the actual engineering dispatching operation situation at different time scales, process the water regime data and working condition data in the real-time monitoring data.

[0183] S1222, determine the evaluation indicators in the evaluation index system of the pumping station unit and perform quantitative processing on the evaluation indicators.

[0184] S1223, use the analytic hierarchy process to determine the weights of the evaluation indicators and establish a hierarchical structure.

[0185] S1224, construct a judgment matrix and quantify the scale of the importance relationship between two adjacent levels.

[0186] S1225, based on the judgment matrix, deduce the relative importance order of each element in this level to a certain element in the previous level.

[0187] S1226, perform weighted summation by combining the scores and weights of each evaluation index to obtain the overall evaluation result.

[0188] It can be understood that the water conveyance status of the pumping station in each canal pond of the water diversion project is directly related to the project safety. Especially under the real-time scheduling operation, it is necessary to control the water levels upstream and downstream of the pumping station. Therefore, it is necessary to establish a corresponding evaluation model for the pumping station units to characterize the real-time operation status of the pumping station. The evaluation model for the pumping station units should be able to comprehensively consider various scheduling indexes, judge the comprehensive water situation status of the pumping station, and meet the overall control requirements of the scheduling management personnel for the real-time operation status of the pumping station. Specifically, by analyzing the changes of state variables such as water level, flow rate, water volume, energy consumption, and cost during the water diversion period (as shown in Figure 3 ), establish an evaluation index system from aspects such as plan execution, water diversion effect, and operation cost. Based on the analytic hierarchy process, establish a monthly / daily scale water volume scheduling effect evaluation model to meet the quantification of water volume scheduling and the operation situation of the project scheduling, evaluate the scheduling effect from aspects such as plan completion, water supply guarantee degree, water conveyance stability, and water supply efficiency, and provide a reference for the adjustment of the water diversion task in the next stage.

[0189] The evaluation model for the pumping station units can review and specifically summarize the operation situation of the pumping station within a year, aggregate and calculate relevant information such as water level, water volume, and unit efficiency, evaluate the health of the pumping station units during a specific scheduling period from aspects such as safety, efficiency, and benefit, determine the starting sequence of the pumping station units, and achieve energy-saving and efficient operation of the pumping station during the water diversion period.

[0190] S1221, according to the actual project scheduling operation situation at different time scales, statistically summarize relevant data such as water situation and project situation.

[0191] S1222, determine the evaluation indexes in the evaluation index system for the pumping station units and perform quantization processing on the evaluation indexes. Specifically, the steps for determining the evaluation indexes include: The evaluation index system for the pumping station units consists of three levels. The first-level indexes include: efficiency, safety, and benefit; the second-level indexes include: plan completion situation, water supply guarantee rate, and water supply efficiency; the third-level indexes include: water supply plan completion situation, water volume diverted at the water diversion outlet, water supply guarantee rate, water supply efficiency, etc. The steps for quantifying the evaluation indexes include: ① Water supply plan completion situation: Evaluate the completion situation of the water supply plan by comparing the planned water diversion volume and the actual water supply volume. The plan completion situation is divided into the monthly / daily plan completion rate, and the calculation method is as follows:

[0192]

[0193] In the formula: PCR is the plan completion rate; AWS is the actual water supply volume; PWS is the planned water supply volume.

[0194] The scoring is directly based on the planned completion index. When the planned completion index is greater than 100%, a score of 100 is given.

[0195] ② Water diversion volume at the water diversion outlets: By comparing the planned and actual water diversion volumes at each water diversion outlet, the compliance of the overall water diversion volume at the water diversion outlets is evaluated. The evaluation objects are mainly individual water diversion outlets, divided into two time scales: monthly / daily. The calculation method is as follows:

[0196]

[0197] In the formula: WOR is the compliance rate of the water diversion volume at the water diversion outlet; AWdg is the actual water diversion volume at each water diversion outlet; PWdg is the planned water diversion volume at each water diversion outlet.

[0198] The scoring uses the average value of the calculation results of each water diversion outlet. When WOR is greater than 100%, a score of 100 is given.

[0199] ③ Water supply guarantee rate: By comparing and analyzing the actual water supply guarantee times and the total times in different periods, the degree of water supply guarantee is evaluated. The actual water supply guarantee times in different periods can be represented by the number of days when the actual water supply volume is equal to the water demand volume. When the actual water supply volume is equal to the water demand volume, it is considered that the water supply is guaranteed. The index is expressed by the monthly / daily water supply guarantee rate. The calculation method is as follows:

[0200]

[0201] In the formula, GR is the water supply guarantee rate; GT is the actual water supply guarantee times for the whole line; AT is the total times; AW is the actual water supply volume; WD is the water demand volume; T is the total number of days. The scoring is directly based on the water supply guarantee index.

[0202] ④ Water supply efficiency: The water supply efficiency index is mainly measured by water volume loss. The water volume loss is obtained by the loss rate, which is the ratio of the water volume loss in the river channel during a period to the inflow volume in the river channel during that period.

[0203] S1223. The analytic hierarchy process is used to determine the weights of the evaluation indicators and establish the hierarchical structure.

[0204] It can be understood that the quantitative representation of the relative importance of each indicator in the entire indicator system, whether the weights are determined reasonably will have a decisive impact on the comprehensive evaluation results and evaluation quality. In this application, the analytic hierarchy process is used to determine the weights of the evaluation indicators. The basic steps are as follows: establishing the hierarchical structure, constructing the judgment matrix, single ranking of the hierarchy, consistency verification, and calculating the evaluation results of the scheme.

[0205] Combined with the first aspect, the steps of establishing the hierarchical structure in step S1223 include:

[0206] According to the results of problem analysis, the elements of the system are divided into the following three levels.

[0207] ① The top level: the goal level. The overall goal to be achieved by the system is at this level.

[0208] ② The middle level: the criterion level. The various criteria to be adopted to achieve the overall goal are at this level.

[0209] ③ The bottom level: the solution level. The various feasible solutions to be selected by the system are at this level.

[0210] S1224. Construct a judgment matrix and quantify the scale for the importance relationship between adjacent two levels.

[0211] Among them, construct the judgment matrix: Analyze the relative importance of the elements in the next level to the element in the previous level, and represent it in the form of a judgment matrix. For example, assume that among the elements in layer C, c is related to P 1 , P 2 …P n . As shown in Table 1.

[0212] Table 1 is a schematic diagram of the judgment matrix.

[0213]

[0214] The element P ij in the matrix represents the estimated value of the relative importance of P i compared with P j . It is obtained by introducing a suitable scale and making pairwise comparisons between P i and P j . The AHP method adopts a scale method to give a quantitative scale for comparisons in different situations:

[0215] 1 - Equally important. It means that two elements have the same importance for a certain attribute.

[0216] 3 - Slightly important. It means that when two elements are compared, one element is slightly more important than the other.

[0217] 5 - Clearly important. It means that when two elements are compared, one element is clearly more important than the other.

[0218] 7 - Very important. It means that when two elements are compared, one element is very more important than the other.

[0219] 9 - Extremely important. It means that when two elements are compared, one element is extremely more important than the other.

[0220] 2, 4, 6, 8 - Represent quantitative scales when a compromise is needed between the above two criteria.

[0221] The reciprocals of the above numbers - representing inverse comparison.

[0222] Obviously, when i = j, there is P ij = 1; when i < j, there is P ij = 1 / P ji

[0223] Step S1425 can usually be calculated by the square root method. Its calculation steps are as follows:

[0224] ① Calculate the product of the elements in each row of the judgment matrix:

[0225]

[0226] ② Calculate the nth root of M i :

[0227]

[0228] ③ Normalize Wi:

[0229] .

[0230] Among them, after S1225, it also includes:

[0231] S1227, calculate the consistency index C.I. and the random consistency ratio C.R.

[0232] S1228, judge whether C.I. is less than 0.1.

[0233] If so, execute step S12281; if not, execute step S12282.

[0234] S12281, determine that the judgment matrix is consistent.

[0235] S1229, determine that the judgment matrix is inconsistent.

[0236] It can be understood that the consistency test is carried out after step S1425, aiming to evaluate the quality of the single sorting and total sorting of the hierarchy. It is mainly completed by calculating the consistency index C.I. and the random consistency ratio C.R.

[0237] Among them, the calculation formula of C.I. is: C.I. = (the maximum eigenvalue of the judgment matrix - the number of elements in this hierarchy) / (the number of elements in this hierarchy - 1).

[0238] The calculation formula of C.R. is: C.R. = C.I. ÷ R.L. R.L. is a coefficient called the random index. Different R.I. values should be taken for judgment matrices of different orders (n). For example, when n = 3, R.I. should be taken as 0.58; when n = 7, R.I. should be taken as 1.32, and so on.

[0239] When C.R. < 0.1, it is considered that the judgment matrix has acceptable satisfactory consistency; otherwise, the judgment matrix needs to be adjusted and corrected to make it satisfy C.R. < 0.1, so as to have satisfactory consistency.

[0240] Before actual application, a pump station unit evaluation model is constructed. Specifically:

[0241] Data collection: According to the real-time engineering scheduling and operation conditions, collect and statistically analyze the scheduling operation data, engineering operation parameters and other information in the pump station project.

[0242] Based on the preset evaluation rules, establish an evaluation index system:

[0243] The real-time evaluation index system of the pump station consists of four parts: the operation safety, operation efficiency, power generation efficiency, and unit comparison selection of the pump station.

[0244] Comprehensively quantify multiple evaluation indicators: In order to construct a real-time state model of the pump station, it is necessary to comprehensively consider the influence of each indicator, quantify each indicator, mainly quantify the evaluation indicators of the pump station, and the quantization process of the remaining building indicators can refer to this example according to the engineering parameter information of each building for evaluation indicator quantization. After all evaluation indicators are quantified, use the calculation formula in the model method to obtain the real-time state evaluation score of the pump station.

[0245] Among them, the evaluation indicators include multiple preset grade evaluation indicators corresponding to the water levels in front of the pump station as shown in Table 2, so that the water levels in front of the pump station can be used to evaluate the current operation state with seven grades.

[0246] Table 2 is a schematic table for the grade division of the water levels in front of the pump station.

[0247]

[0248] It also includes: the evaluation indicator for the grade division of the warning time. As shown in Table 3, the grade division of the warning time is used to evaluate the current operation state with six grades.

[0249] Table 3 is the grade division table of the warning time.

[0250]

[0251] It also includes: the evaluation indicator of the water level amplitude. As shown in Table 4, the grade division of the water level amplitude can be used to evaluate the current operation state with eight grades.

[0252] Table 4 is the classification table of water level fluctuation levels.

[0253]

[0254] It also includes: evaluation indicators for water level high / low limit warning values. As shown in Table 5, the classification of water level high / low limit warning values can be used to evaluate the current operating status with eight levels.

[0255] Table 5 is the evaluation index for the classification of water level high / low limit levels.

[0256]

[0257] The evaluation indicators for the pump station efficiency warning value. As shown in Table 6, the classification of the pump station efficiency warning value can be used to evaluate the current operating status with four levels.

[0258] Table 6 is the evaluation index table for the classification of pump station efficiency levels.

[0259]

[0260] The evaluation indicators for the pump station operating temperature. As shown in Table 7, the classification of the pump station temperature warning value can be used to evaluate the current operating status with five levels.

[0261] Table 7 is the evaluation index for the classification of the station operating temperature.

[0262]

[0263] Combined with the first aspect, step S123 includes:

[0264] S1231, after processing the characteristic curve of the pump device, calculate the pumping device efficiency of the pump unit.

[0265] S1232, calculate the optimal solution for the economic operation in the pump station.

[0266] S1233, the pump station real-time optimization model determines whether it can meet the water transfer requirements corresponding to the optimal solution under the condition of high zone operation.

[0267] If not, execute step S1234.

[0268] With the goal of the lowest unit water lifting cost, combined with the optimal solution, the given scheduling time and water transfer volume, formulate the optimal unit operation plan that meets the requirements of the water transfer task.

[0269] It is understandable that the operation of the pumping station needs to consider how to reasonably distribute the total flow among the units in the station to ensure the economic and reasonable operation of the pumping station under the existing equipment conditions, improve the operation efficiency of the pumping station, and reduce the water lifting cost. Therefore, it is necessary to construct an optimal flow distribution model in the pumping station to carry out optimization work at the unit level and the pumping station level, so as to achieve the goal of maximizing the project benefit on the premise of ensuring the safe operation and scheduling of the project.

[0270] The optimal flow distribution model in the pumping station is actually an optimal problem of space for flow distribution among the units in the pumping station. The units that can be put into operation in the pumping station are numbered artificially in sequence, and each unit is abstracted as a stage. In this way, the flow optimization problem becomes an optimal problem of a multi-stage decision-making process, and the optimization algorithm can be used for solution. Since the unit selection in the design stage is carried out for the design conditions of the pumping station, there are often some unfavorable operating conditions that cannot be realized in the actual operation process. For the operable operating conditions of each pumping station, when the flow is certain, how to distribute the flow to each unit to ensure that each pumping station can operate within the high-efficiency range. According to the design data and operating characteristics, an optimal flow distribution model in the pumping station is constructed to analyze the distribution results of the corresponding different flows of the units in the station when the pumping station operates at the highest efficiency under different combinations of flow and head during operation, so as to provide a basis for the operation and scheduling when the upstream flow changes during the actual water transfer process.

[0271] The solution process of the optimal flow distribution model in the pumping station is as follows:

[0272] (1) Objective function

[0273] The objective of the first-layer model is to distribute the flow of the units in the pumping station to maximize its total efficiency while satisfying various equality and inequality constraints. The objective function of a pumping station with n units is expressed as:

[0274]

[0275] In the formula, is the total efficiency of the jth pumping station at a flow rate of and a head of ; is the total flow of the pumping station at the kth time period, is the head of the jth pumping station; and are the flow rate and efficiency of the ith unit of the jth pumping station respectively.

[0276] (2) Decision variables

[0277] The flow rate of each unit in the pumping station is used as the decision variable. For the discretization of the decision variables of the pumping station, the smaller the discretization step size, the higher the calculation accuracy, but the calculation amount increases significantly.

[0278] (3) Constraints

[0279] The constraints include the total flow constraint and the over-flow capacity constraint of the unit, and their mathematical representation forms are shown in the following formulas respectively.

[0280]

[0281]

[0282] In the formula, and are the minimum and maximum allowable flows corresponding to the i-th unit respectively.

[0283] The model is based on a deterministic algorithm such as the dynamic programming algorithm that does not involve random variables. When developing the model, the test reports of the pump device corresponding to the actually installed units in the project and the test reports of the supporting motors are used. Considering the parameter deviation caused by the wear of the pump unit, the relevant parameters of the model are summarized in the configuration file, which is easy for humans to read, write and modify.

[0284] Step S143, if it is obtained in the evaluation scheme of the pump station unit in step S142 that the current unit state is operating in the non-efficient area, when calling the flow optimization distribution model in the pump station, first, the processing of the pump device characteristic curve includes the fitting and discretization processing of flow-head-efficiency and the fitting and discretization processing of flow-head-vane setting angle / speed; secondly, calculate the pumping device efficiency of the pump unit; then, calculate the optimal solution of the economic operation in the pump station.

[0285] Among them, the steps of the fitting and discretization processing of flow-head-efficiency are specifically as follows: extract the corresponding working condition points of flow-head-efficiency from the prototype characteristic curve diagram of the pump station, fit the extracted working condition points into a third-order surface by using Matlab, and at the same time obtain the flow-head-efficiency relationship formula. Use the fitted formula to discretize the flow-head-efficiency curve with a step size of 0.1.

[0286] The steps of the fitting and discretization processing of flow-head-vane setting angle / speed are specifically as follows: extract the corresponding working condition points of flow-head-vane setting angle from the prototype characteristic curve diagram, fit the extracted working condition points into a second-order surface by using Matlab, and at the same time obtain the flow-head-vane setting angle relationship formula. Use the fitted formula to discretize the flow-head-vane setting angle curve with a step size of 0.1.

[0287] The steps of calculating the pumping device efficiency of the unit include: it is known that the main carrier for completing the pumping task during the operation of the pump station is the pumping device, and the pumping device is composed of a pump, a prime mover, a transmission device, a pipeline and its accessories. The pumping device efficiency is used as the actual operation efficiency in the pump station calculation. The calculation formula for the pumping device efficiency of the pump station is:

[0288]

[0289] In the formula respectively represent the efficiency of the pumping device, represents the efficiency of the pump device, represents the transmission efficiency, represents the motor efficiency, represents the frequency conversion efficiency.

[0290] For the mechanical transmission with the motor directly connected to the pump, . The frequency conversion efficiency of the PWM high-voltage frequency converter is about 96%. When the pumping station is not frequency-modulated, take = 1. It is known that the motor efficiency value of large motors is about 94%, that is = 94%. When the load is greater than 50%, it can be considered that the motor efficiency is basically unchanged.

[0291] For the motor efficiency at different operating points of specific units, the efficiency output at different operating points of a single unit in the pumping station can be calculated according to the following formula:

[0292]

[0293]

[0294] In the formula, is the motor output power, kW; is the density of water ; is the acceleration due to gravity, m / s²; is the flow rate of the i-th unit, m 3 / s; is the head of the i-th unit, m; is the rated power of the motor, kW.

[0295] When the obtained ≥ 50%, the motor efficiency is calculated by taking 94%; when < 50%, the motor efficiency is calculated according to Figure 4 taking its slope.

[0296] After determining the transmission efficiency, motor efficiency and frequency conversion efficiency under the operating conditions of each pumping station, the operating condition feasible region of the pumping station can be discretized with a step size of 0.1, and the pumping device efficiency of each pumping station can be calculated according to the formula.

[0297] After that, based on the calculated efficiency of the pumping device, one-dimensional and two-dimensional characteristic curves of the pumping device can be plotted. Furthermore, after determining the efficiency surface of the pumping device in the pumping station based on the one-dimensional and two-dimensional characteristic curves of the pumping device, the calculation of the optimal solution for the economic operation within the pumping station can be started.

[0298] Among them, the calculation within the pumping station specifically includes two parts: the analysis of the operable flow range and the optimization calculation.

[0299] Analysis of the operable flow range of each pumping station: First, based on the characteristic curves of each unit of the pumping station and the design head range, the operable flow range of a single unit is deduced. Then, the operable flow range of each pumping station when different numbers of units in the pumping station are put into operation is preliminarily determined, and the "flow-head feasible region" analysis is carried out.

[0300] After the actual operation of the project, there will be certain differences in the performance between different pump units, resulting in that the operation flow range and head range of different units cannot be simply added up. The above-mentioned flow range needs to be delimited again according to a similar method.

[0301] Optimization calculation within a single-stage pumping station: The efficiency of each pump unit in the pumping station at discrete flow and head operating points is used as the input of the flow optimization distribution model of the pumping station, and the optimized efficiency of the pumping station at all operating points and the optimized distribution of the flow within the station are calculated. According to the calculation results of the model, an optimized distribution plan for the number of operating units and the flow of the units in the pumping station is generated to meet the optimal operation within the pumping station during the water transfer process.

[0302] Due to the influence of factors such as water level fluctuations and operating condition changes, the pumping station does not always operate under the optimal operating conditions optimized by the flow optimization distribution model within the pumping station. Therefore, it is necessary to construct a real-time optimization scheduling model for the pumping station. Based on the real-time water conditions and operating conditions of the project, with the goal of maximizing the comprehensive benefit of the project, the operation of the pumping station is optimized in real time.

[0303] Specifically, in the case where S1232 provides the optimal solution, the real-time optimization scheduling model of the pumping station needs to judge whether it can meet the water transfer requirements and operate in the high-efficiency area in step S1233. If it cannot be met, then in step S1234, according to the optimal solution of the economic operation model within the pumping station, under the conditions of a given scheduling time and water transfer volume task, with the goal of the lowest unit water lifting cost, the optimal unit operation plan that meets the requirements of the water transfer task can be obtained.

[0304] Among them, step S1234 specifically identifies information such as the water level boundary sequence upstream and downstream of the pumping station, the initial operating flow, and the start calculation time of the model plan. Under the condition of meeting the actual operation requirements during the scheduling process, the objective function, decision variables, and constraint conditions adopted in the calculation of the model plan are as follows:

[0305] 1) Objective function

[0306]

[0307] Among them, is the total cost of the pumping device, unit: yuan; W is the total water transfer volume during the scheduling period, unit: m 3 . is the flow rate of each time period of a single new station, unit: m 3 / h; is the operation time at different pumping station flow rates of a single station, unit: h; is the number of segmented regulation stages during the scheduling period.

[0308] 2) Decision variables

[0309] Since it involves the segmented operation time during the scheduling period, the operation flow rate of each unit of the pumping station, the starting state of the pumping station, the operation duration of the pumping station, and the number of operation stages of the pumping station are used as decision variables to calculate the in-station economic operation model with the lowest unit water lifting cost as the goal.

[0310] 3) Constraint conditions

[0311] ① River channel constraint

[0312]

[0313] In the formula, is the lower limit water level of the river channel, m; is the upper limit water level of the river channel, m.

[0314] ② Meet the water transfer volume task

[0315]

[0316] In the formula, is the actual water transfer volume; is the water transfer volume task during the scheduling time of the model calculation scheme.

[0317] ③ Resonance constraint

[0318] Collect the working condition points where resonance occurs during the operation of the pumping station unit, and exclude such working conditions.

[0319] Among them, before actual application, the real-time optimal scheduling model of the pumping station is constructed, including: data collection, model constraints, simulating the change process of the channel water level, real-time optimal regulation, and regulation failure handling.

[0320] Specifically, data collection includes: collecting and sorting out the real-time water level below the station, real-time water level above the station, real-time flow rate of the pumping station to be regulated, and the water level below the station or lake water level of the next pumping station from the database, and making them into model input data.

[0321] The model constraints include: taking the water diversion volume requirements within the scheduling time generated by the ten-day scheduling model received by the real-time optimization scheduling model or issued by the flood control and drought relief command unit as the model constraint conditions.

[0322] The simulation of the channel water level change process includes: First, calculate the change process of the storage volume between pumping stations by using the storage volume model through the flow imbalance between adjacent pumping stations or river channels. Then, calculate the channel water level change process according to the change process of the storage volume between adjacent pumping stations by methods such as the water level-storage volume relationship and channel water body generalization:

[0323] ① The water level-storage volume results calculated by the one-dimensional hydrodynamic numerical simulation model are used to calculate the change process of the water level from the change process of the storage volume between adjacent pumping stations;

[0324] ② According to the basic parameters of the channel, the channel water body is generalized, and the change process of the water body height is simulated and calculated from the change process of the water volume of the water body to obtain the change process of the channel water level.

[0325] The real-time optimization regulation includes: obtaining the change process of the head of the pumping stations to be regulated according to the simulated channel water level change process. According to the flow rate, head sequence of the pumping stations, and the flow rate-head-efficiency result table of the pumping stations, conduct an efficient area inspection for each level of pumping station. If it can ensure that the pumping station operates within the efficient area during the scheduling time, the pumping station will not be regulated during the scheduling time.

[0326] If it cannot be ensured that the pumping stations to be regulated always operate within the efficient area, then optimize the scheduling decision. Set the flow rate and regulation time after the regulation of each level of pumping station as optimization parameters, use the particle swarm optimization algorithm (PSO), and carry out the real-time optimization regulation process with the goal of minimizing the unit water lifting cost of the pumping station, output the regulation time and the flow rate before and after the regulation, and obtain a scheduling plan that meets the constraint conditions.

[0327] The regulation failure handling includes: If a scheduling decision that can operate under the water diversion volume task given by the ten-day scheduling model cannot be generated, or the generated scheduling decision cannot operate within the efficient area, then give feedback to the ten-day scheduling model, and the ten-day scheduling model modifies the water diversion volume task according to the feedback content. If the generated scheduling decision suggestion can meet the water diversion volume requirements given by the ten-day scheduling model and operate within the efficient area, then send the generated scheduling decision suggestion to the dispatcher for confirmation.

[0328] In a second aspect, the present application provides a pumping station regulation device based on digital twin, combined with Figure 5 As shown, the device includes: a data synchronization module 10, a generation module 20, and a regulation module 30.

[0329] The data synchronization module 10 is used to obtain the real-time data and historical data of the pumping station and synchronize the real-time data and historical data to the digital twin platform.

[0330] The generation module 20 is configured to obtain the scheduling strategy generated by the digital twin platform based on real-time data and historical data.

[0331] The adjustment module 30 is configured to adjust the operation mode of the pumping station based on the scheduling strategy.

[0332] Among them, the intelligent control terminal includes a digital twin platform including an intelligent control model, and the intelligent control model includes an initial correction model, a pumping station unit evaluation model, an in-pumping-station flow optimal distribution model, and a pumping station real-time optimal scheduling model connected in sequence; the initial correction model includes a water level prediction model and a pump group characteristic curve correction model.

[0333] In a third aspect, an embodiment of the present application provides an electronic device. In combination with Figure 6 as shown, the electronic device includes a memory 131 and a processor 130. The memory 131 is used to store a computer program, and the processor 130 runs the computer program to enable the electronic device to execute the above method.

[0334] Further, in combination with Figure 6 the electronic device shown also includes a bus 132 and a communication interface 133. The processor 130, the communication interface 133, and the memory 131 are connected through the bus 132.

[0335] Among them, the memory 131 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 133 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The bus 132 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 6 only a bidirectional arrow is used in [description] but it does not mean that there is only one bus or one type of bus.

[0336] The processor 130 may be an integrated circuit chip with the ability to process signals. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 130 or the instructions in the form of software. The above-mentioned processor 130 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 131, and the processor 130 reads the information in the memory 131 and combines its hardware to complete the steps of the method in the foregoing embodiments.

[0337] In a fourth aspect, an embodiment of the present application provides a storage medium, in which computer program instructions are stored. When the computer program instructions are read and run by a processor, the above-mentioned method is executed.

[0338] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems and devices described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0339] In addition, in the description of the embodiments of the present invention, unless otherwise clearly defined and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediate medium, and it may be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0340] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0341] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0342] Finally, it should be noted that the above embodiments are only specific implementation manners of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A pump station regulation method based on digital twin, characterized in that: The method comprises: Acquire real-time data and historical data of the pump station, and synchronize the real-time data and historical data to the digital twin platform; Obtaining a scheduling strategy generated by the digital twin platform based on the real-time data and historical data; Based on the scheduling strategy, adjusting the operation mode of the pump station; The digital twin platform includes an intelligent control model, which includes an initial correction model, a pump station unit evaluation model, a flow optimization distribution model within the pump station, and a pump station real-time optimization scheduling model connected in sequence; the initial correction model includes a water level prediction model and a pump unit characteristic curve correction model; Wherein, obtaining the scheduling strategy generated by the digital twin platform based on the real-time data and historical data includes: Based on the water level prediction model, a water level prediction sequence scheme in the short term in the future is obtained. At the same time, based on the pump unit characteristic curve correction model, a corrected pump station water pump unit device curve is obtained; Based on the evaluation model of pump station units, the hierarchical analysis method is used to integrate multi-dimensional evaluation indicators, generate dynamic weight allocation to determine whether the current period is optimized based on the pump station operation efficiency / energy consumption, and obtain the evaluation plan of the pump station units; When the evaluation scheme of the pump station unit shows that the current unit state is operating in the non-efficient area, the flow optimization allocation model in the pump station and the real-time optimization scheduling model of the pump station are called to obtain the corresponding optimal number of units to be started and the operating flow, and the optimal flow allocation strategy for the units in different time periods; The step of obtaining a corrected pump station water pump unit device curve based on the pump unit characteristic curve correction model includes: Acquire the pump station characteristic curve and the long-sequence operation data during the operation of the pump station unit, and establish a flow-head-blade placement angle historical data summary table and a flow-head-efficiency historical data summary table; the long-sequence operation data at least includes the measured flow, head, blade placement angle, and unit efficiency of the pump station; Using the least square method to fit the long sequence running data to obtain a least square method fitting result; The coefficients in the least squares fitting result are used as the center values ​​of the initial population of the genetic algorithm, and 30% above and below the coefficients are defined as the search domain; According to the objective function, the corresponding fitness function is formulated, and double random quantities (α, β) are introduced to select the crossover operator, and non-uniform mutation is used to select the mutation operator; Iterate the least squares fitting result by combining the fitness function and the selection operator, the crossover operator and the mutation operator, and output the optimization result; Based on the optimization result, a target water pump characteristic curve is drawn to roll over and update the water pump unit characteristic curve.

2. The method according to claim 1, characterized in that: Before the step of obtaining the real-time data and historical data of the pump station and synchronizing the real-time data and historical data to the digital twin platform, the steps include: Obtain drawings of pump station units, manage information, and build an initial digital twin model; Correcting the initial digital twin model based on the pump station to obtain a digital twin model of the pump station; The pump station digital twin model and the intelligent control model are integrated into the digital twin platform.

3. The method according to claim 1, characterized in that Based on the evaluation model of the pump station unit, the steps of determining whether the current period is optimized by the pump station operation efficiency / energy consumption and obtaining the evaluation plan of the pump station unit include: According to the actual project scheduling and operation conditions at different time scales, the water situation data and construction situation data in the real-time monitoring data are statistically summarized; Determine the evaluation index in the evaluation index system of the pump station unit and quantify the evaluation index; The analytic hierarchy process is used to determine the weights of evaluation indicators and establish a hierarchical structure; Construct a judgment matrix and quantify the scale of the importance relationship between two adjacent levels; Based on the judgment matrix, the relative importance order of each element in the current level to an element in the previous level is calculated; The scores and weights of the evaluation indicators are combined and weighted to obtain an overall evaluation result.

4. The method according to claim 3, characterized in that The step of calculating the relative importance order of each element in the current level to an element in the previous level based on the judgment matrix also includes: Calculate the first ratio of the consistency index and the random consistency; Determining whether the ratio is less than a preset value; If so, determine that the judgment matrix meets the preset requirements; If not, the judgment matrix is ​​adjusted and corrected until the second ratio calculated again is smaller than the preset value.

5. The method according to claim 1, characterized in that When the evaluation scheme of the pump station unit shows that the current unit status is operating in the non-efficient area, the flow optimization allocation model in the pump station and the real-time optimization scheduling model of the pump station are called to obtain the corresponding optimal number of units to be started and the operating flow, and the optimal flow allocation strategy for units in different time periods, including: After processing the characteristic curve of the water pump device, calculate the efficiency of the water pump unit pumping device; Calculate the optimal solution for economic operation within the pumping station; The real-time optimization model of the pump station determines whether the water diversion requirements corresponding to the optimal solution can be met under high-zone operation; If not, with the goal of minimizing the unit water extraction cost, combined with the optimal solution, the given scheduling time and water transfer volume, formulate the optimal unit operation plan that meets the water transfer task requirements.

6. A pump station regulating device based on digital twin, characterized in that: The device includes: A data synchronization module, used to obtain real-time data and historical data of the pump station, and synchronize the real-time data and historical data to the digital twin platform; A generation module, used to obtain a scheduling strategy generated by the digital twin platform based on the real-time data and historical data; A regulating module, used for regulating the operation mode of the pump station based on the scheduling strategy; The digital twin platform includes an intelligent control model, which includes an initial correction model, a pump station unit evaluation model, a flow optimization distribution model within the pump station, and a pump station real-time optimization scheduling model connected in sequence; the initial correction model includes a water level prediction model and a pump unit characteristic curve correction model; Wherein, obtaining the scheduling strategy generated by the digital twin platform based on the real-time data and historical data includes: obtaining a water level prediction sequence plan in the short term in the future based on the water level prediction model, and obtaining a corrected pump station water pump unit device curve based on the pump unit characteristic curve correction model; Based on the evaluation model of pump station units, the hierarchical analysis method is used to integrate multi-dimensional evaluation indicators, generate dynamic weight allocation to determine whether the current period is optimized based on the pump station operation efficiency / energy consumption, and obtain the evaluation plan of the pump station units; When the evaluation scheme of the pump station unit shows that the current unit state is operating in the non-efficient area, the flow optimization allocation model in the pump station and the real-time optimization scheduling model of the pump station are called to obtain the corresponding optimal number of units to be started and the operating flow, and the optimal flow allocation strategy for the units in different time periods; The step of obtaining a corrected pump station water pump unit device curve based on the pump unit characteristic curve correction model includes: Acquire the pump station characteristic curve and the long sequence operation data during the operation of the pump station unit; the long sequence operation data at least includes the measured pump station flow, head, blade placement angle, unit efficiency, and establish a flow-head-blade placement angle historical data summary table and a flow-head-efficiency historical data summary table; The long sequence running data is first fitted once using the least squares method to obtain the least squares fitting result; The coefficients in the least squares fitting result are used as the center values ​​of the initial population of the genetic algorithm, and 30% above and below the coefficients are defined as the search domain; According to the objective function, the corresponding fitness function is formulated, and the double random (α, β) is introduced to select the crossover operator and the non-uniform mutation is used to select the mutation operator; Iterate the least squares fitting result by combining the fitness function and the selection operator, the crossover operator and the mutation operator, and output the optimization result; Based on the optimization result, a target water pump characteristic curve is drawn to roll over and update the water pump unit characteristic curve.

7. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the method according to any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the method according to any one of claims 1 to 5 is executed.

Images