Pump station group scheduling system and scheduling method based on digital twinning

Abstract

The invention provides a pump station group dispatching system and method based on digital twinning, and relates to the technical field of pump station dispatching.A pump station group digital twinning model is constructed according to a bearing temperature curve, a flow curve and a pump cabin pressure curve during rated power work in history, and a pump station group digital twinning model is established according to the dispatched task load and task time; setting a solving condition I, a solving condition II and a solving condition III, solving the scheduling amount which should be obtained by each pump station in MATLAB, simulating the scheduling amount in a pump station group digital twin model, obtaining a simulated operation state, constructing an operation state score, constructing a health state score according to the data of the pump stations, and obtaining a health state result; the task completion capability of each pump station is judged by analyzing the sequence of the operation state scores and the health state scores, and if the condition that tasks cannot be completed exists, the scheduling amount is redistributed, so that faults possibly caused by overload operation of the pump stations are avoided, and smooth proceeding of the scheduling tasks is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of pumping station scheduling, and particularly to a pumping station group scheduling system and a scheduling method based on digital twin. Background Art

[0002] As the core infrastructure in the fields of water conservancy projects, urban water supply, agricultural irrigation, etc., a pumping station group is usually composed of multiple pumping stations widely distributed, and undertakes key tasks such as flow regulation, pressure control, and water resource allocation. With the development of intelligent technologies, the scheduling requirements of pumping station groups have become increasingly complex, and it is necessary to take into account task efficiency, equipment reliability, and energy consumption optimization. Especially in scenarios such as cross-regional water resource allocation and emergency drainage, the coordinated operation of pumping station groups needs to dynamically adapt to different working conditions and achieve multi-objective optimization. Digital twin technology provides a technical basis for the collaborative interaction between the physical devices and virtual models of pumping station groups through real-time data mapping and simulation modeling, and is applicable to scenarios such as equipment status prediction, scheduling strategy verification, and dynamic optimization, becoming an important direction for improving the intelligent scheduling ability of pumping station groups.

[0003] In the prior art, the published number CN117450050A discloses a smart scheduling system for drainage pumping stations based on digital twin technology, which stores historical data during the scheduling work of pumping stations in the control area through a database; a model training module constructs a digital twin model of the pumping station; a data acquisition module acquires real-time data; and sends the real-time data to the smart scheduling module; the smart scheduling module obtains a scheduling plan according to the real-time data and the digital twin model of the pumping station.

[0004] Although the disclosed technical document realizes the scheduling of pumping stations, it does not consider that the scheduling capabilities of different pumping stations are different, nor does it consider the problem that the scheduling capabilities may be weakened due to the actual working conditions of the pumping stations, which is likely to lead to an unsmooth scheduling process and thus affect normal production activities.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a pumping station group scheduling system and a scheduling method based on digital twin to solve the problems raised in the above background art.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] A pumping station group scheduling method based on digital twin, the specific steps include

[0009] Step 1: Obtain the bearing temperature curve, flow curve, and pump cabin pressure curve of each pumping station when operating at rated power. Taking each pumping station as a unit, train the bearing temperature model, pump cabin pressure model, and flow model of each pumping station respectively. Summarize the models of all pumping stations to obtain the digital twin model of the pumping station group;

[0010] Step 2: According to the task volume and task time of the dispatching, set the dispatching volume of each pumping station, and set Solving Condition I, Solving Condition II, and Solving Condition III, and solve in MATLAB to obtain the dispatching volume of each pumping station;

[0011] Step 3: Each pumping station obtains the operating duration of this pumping station according to the dispatching volume and inputs it into the digital twin model of the pumping station group to obtain the bearing temperature curve, pump cabin pressure curve, and flow curve of each pumping station. Obtain the flow stability according to the flow curve, obtain the pressure stability according to the pump cabin pressure curve, and combine the temperature threshold of each pumping station to obtain the operation status score of each pumping station;

[0012] Step 4: Obtain the equipment duration, operation duration, number of medium repairs, and the duration since the last minor repair of each pumping station, construct the health status score, sort through the operation status score and health status score of each pumping station, and judge whether each pumping station meets the dispatching volume according to the sorting. If there are pumping stations that do not meet the requirements, adjust the task volume of this pumping station and redistribute the task volume of other pumping stations. If there are always pumping stations that cannot meet the dispatching volume, give an alarm.

[0013] Furthermore, through the work logs of each pumping station, obtain the bearing temperature curve, flow curve, and pump cabin pressure curve of each pumping station when operating at rated power in history. The horizontal axis of the curve is the operation duration, the starting point of the operation duration is 0, the ending point is the actual operation duration of the equipment, and the vertical axis is the numerical value of various types of data;

[0014] Taking a single pumping station as a unit, using the starting duration as the training set, and inputting the bearing temperature curve, pump cabin pressure curve, and flow curve corresponding to different starting durations as labels into the convolutional neural network model for training respectively, obtain the bearing temperature model, pump cabin pressure model, and flow model of each pumping station. Summarize the models of all pumping stations to obtain the digital twin model of the pumping station group.

[0015] Furthermore, obtain the rated flow and rated power of each pumping station, obtain the task volume and task time of the dispatching of the pumping station group from the superior, distribute the task volume of the dispatching among each pumping station, set the dispatching volume of each pumping station and solve it in MATLAB, and set the solving conditions:

[0016] The formula based on Solving Condition I is as follows:

[0017]

[0018] Among them, V is the amount of tasks to be scheduled, V i represents the scheduling volume of the pumping station numbered i, where i is the retrieval variable of the pumping station number, i ∈ N, 1 ≤ i ≤ M;

[0019] The formula based on which Condition II is solved is as follows:

[0020]

[0021] Among them, MAX represents selecting the maximum value, Q i represents the rated flow of the pumping station numbered i, and T[[ID=- 14]] z is the task time;

[0022] The formula based on which Condition III is solved is as follows:

[0023]

[0024] Among them, MIN is the minimization function, P i represents the rated power of the pumping station numbered i;

[0025] Obtain the scheduling volume of each pumping station after solving.

[0026] Furthermore, each pumping station obtains the operation duration respectively according to the obtained scheduling volume in combination with the rated flow of each pumping station. The formula is as follows:

[0027]

[0028] Among them, T i represents the operation duration of the pumping station numbered i, Q i represents the rated flow of the pumping station numbered i, where i is the retrieval variable of the pumping station number, i ∈ N, 1 ≤ i ≤ M;

[0029] Input the start duration of each pumping station into the corresponding digital twin model of the pumping station group respectively to obtain the bearing temperature curve, pump cabin pressure curve and flow curve of each pumping station, and obtain the flow stability according to the flow curve of each pumping station. The formula is as follows:

[0030]

[0031] Among them, σ Q-i represents the flow stability value when the operation duration of the pumping station numbered i is T i , T i is the operation duration, Q i (t) represents the flow of the pumping station numbered i at time t, Q i represents the average flow of the pumping station numbered i, and t is the retrieval variable of the operation duration, 0 < t ≤ T i , where i is the retrieval variable of the pumping station number, i ∈ N, 1 ≤ i ≤ M;

[0032] The pressure stability is obtained according to the pump cabin pressure curve of each pumping station, and the formula is as follows:

[0033]

[0034] Among them, σ p-i represents the pressure stability value when the operation duration of the pumping station numbered i is T i where T i is the operation duration, p i (t) represents the pressure of the pumping station numbered i at time t, p i represents the average pressure of the pumping station numbered i, i is the operation duration retrieval variable, 0 < t ≤ T i , i is the pumping station number retrieval variable, i ∈ N, 1 ≤ i ≤ M;

[0035] The temperature threshold of each pumping station is obtained. The highest temperature is obtained according to the bearing temperature curve of each pumping station, and the operation status score of each pump is constructed. The formula is as follows:

[0036]

[0037] Among them, SY i represents the operation status score of the pumping station numbered i, σ p-i represents the pressure stability of the pumping station numbered i, σ Q-i represents the flow stability of the pumping station numbered i, T max- i represents the highest temperature of the pumping station numbered i, T th- i represents the temperature threshold of the pumping station numbered i, i is the pumping station number retrieval variable, i ∈ N, 1 ≤ i ≤ M.

[0038] Furthermore, the equipment duration, operation duration, number of medium repairs, and duration since the last minor repair of each pumping station are obtained through the maintenance log. The medium repair and minor repair are the maintenance levels required for equipment maintenance. Among them, the equipment duration is the duration from the commissioning of the pump to the present, and the operation duration is the usage duration after the pump is commissioned. The health status score of each pumping station is constructed. The formula is as follows:

[0039]

[0040] Among them, SJ i represents the health status score of the pumping station numbered i, T equip-i represents the equipment duration of the pumping station numbered i, T run-i represents the operation duration of the pumping station numbered i, N mid-i represents the number of medium repairs of the pumping station numbered i, T last-iIt represents the duration since the last minor repair of the pumping station numbered i, where i is the retrieval variable for the pumping station number, i ∈ N, 1 ≤ i ≤ M, and k1 and k2 are coefficients with k1 < k2.

[0041] Furthermore, sort the health status scores and operation status scores of all pumping stations from high to low respectively. Obtain the pumping stations ranked in the last one-third in the health status score ranking, and obtain the pumping stations ranked in the last one-third in the operation status score ranking. Screen out the pumping stations that are in the last one-third in both rankings, label them as pumping stations that do not meet the current scheduling volume, and redistribute the scheduling volume of all pumping stations.

[0042] Furthermore, the logic for redistributing the scheduling volume is as follows:

[0043] First, adjust the pumping station that does not meet the current scheduling volume. Set its number as j, set the adjusted scheduling volume as half of the scheduling volume before adjustment, and at the same time distribute the remaining task volume among other pumping stations. Re-solve the adjusted scheduling volume of other pumping stations in MATLAB, and modify the solution condition Ⅰ. The formula is as follows:

[0044]

[0045] Among them, V represents the task volume to be scheduled, V j represents the scheduling volume of the pumping station numbered j before adjustment, and V i represents the scheduling volume of the pumping station numbered i, where i is the retrieval variable for the pumping station number, i ∈ N, 1 ≤ i ≤ M;

[0046] Do not modify the solution condition Ⅱ and solution condition Ⅲ, re-obtain the scheduling volume of each pumping station after solution, and send the scheduling volume to the corresponding pumping station.

[0047] Furthermore, each pumping station executes step 3 and step 4 again according to the re-obtained scheduling volume until the score differences of all pumping stations are greater than zero, then start to execute the scheduling task. When it is impossible to solve such that the score differences of all pumping stations are greater than zero, an alarm is issued.

[0048] The present invention also includes a pumping station group scheduling system based on digital twin for executing the above-mentioned pumping station group scheduling method based on digital twin, including:

[0049] A model construction module for obtaining the bearing temperature curve, flow curve, and pump cabin pressure curve of each pumping station when operating at rated power, training the bearing temperature model, pump cabin pressure model, and flow model of each pumping station respectively in units of pumping stations, summarizing the models of all pumping stations, and obtaining the digital twin model of the pumping station group;

[0050] The scheduling volume solving module is used to set the scheduling volume of each pumping station according to the scheduled task volume and task time, set Solving Condition I, Solving Condition II, and Solving Condition III, and solve in MATLAB to obtain the scheduling volume of each pumping station;

[0051] The operation evaluation module is used for each pumping station to obtain the operation duration of this pumping station according to the scheduling volume and input it into the digital twin model of the pumping station group, obtain the bearing temperature curve, pump cabin pressure curve, and flow curve of each pumping station, obtain the flow stability according to the flow curve, obtain the pressure stability according to the pump cabin pressure curve, and combine the temperature threshold of each pumping station to obtain the operation status score of each pumping station;

[0052] The status analysis module is used to obtain the equipment duration, operation duration, number of medium repairs, and duration since the last minor repair of each pumping station, construct a health status score, sort through the operation status score and health status score of each pumping station, judge whether each pumping station meets the scheduling volume according to the sorting. If there is a pumping station that does not meet the requirements, adjust the task volume of this pumping station and re-allocate the task volume of other pumping stations. If there is always a pumping station that cannot meet the scheduling volume, an alarm will be issued.

[0053] Compared with the prior art, the beneficial effects of the present invention are:

[0054] By constructing a digital twin model of the pumping station group, the present invention simulates the operation of the scheduling volume obtained from each pumping station, constructs an operation status score based on the data of the simulated operation, and then compares and analyzes according to the health status score and operation status score of each pumping station to allocate a suitable scheduling volume for each pumping station, avoiding failures that may be caused by the overload operation of the pumping station and ensuring the smooth progress of the scheduling task. Description of the Drawings

[0055] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0056] Figure 2 It is a schematic diagram of the system structure of the present invention. Detailed Embodiment

[0057] In order to make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the following further elaborates on the present invention in combination with specific embodiments.

[0058] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention pertains. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "comprising" or "including" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0059] Embodiment:

[0060] Please refer to Figure 1 , the present invention provides a technical solution:

[0061] A scheduling method for a pumping station group based on digital twin, the specific steps include:

[0062] Step 1: Obtain the bearing temperature curve, flow curve, and pump cabin pressure curve of each pumping station when operating at rated power. Taking each pumping station as a unit, train the bearing temperature model, pump cabin pressure model, and flow model of each pumping station respectively, and summarize the models of all pumping stations to obtain the digital twin model of the pumping station group;

[0063] The said Step 1 includes the following contents:

[0064] Through the work logs of each pumping station, obtain the bearing temperature curve, flow curve, and pump cabin pressure curve of each pumping station when operating at rated power in history respectively. The horizontal axis of the curve is the operation duration, the starting point of the operation duration is 0, the ending point is the actual operation duration of the equipment, and the vertical axis is the value of various types of data;

[0065] Taking a single pumping station as a unit, using the starting duration as the training set, and inputting the bearing temperature curve, pump cabin pressure curve, and flow curve corresponding to different starting durations as labels into the convolutional neural network model for training respectively, to obtain the bearing temperature model, pump cabin pressure model, and flow model of each pumping station, and summarize the models of all pumping stations to obtain the digital twin model of the pumping station group.

[0066] As a preferred embodiment, a one-dimensional convolutional neural network is adopted in the convolutional neural network, the number of convolutional kernels is 32, the size of the convolutional kernel is 5x5, a max pooling layer is adopted, the pooling window is 2, the stride is 2, and the number of neurons is 128.

[0067] By obtaining the historical operation data of the pumping stations and training the digital twin model, a high-precision simulation foundation is laid for the entire scheduling system. Using a convolutional neural network in combination with the startup duration and actual operation curves of the pumping stations (such as bearing temperature, flow rate, and pressure), the model can dynamically reflect the behavioral characteristics of the pumping stations under different working conditions. This step not only provides key inputs for the subsequent optimal allocation of task volumes but also enables global collaborative analysis by aggregating the models of each pumping station, allowing the solution of multiple constraint conditions in Step 2 to be based on a unified virtual environment, ensuring the rationality and feasibility of the scheduling plan. At the same time, the high fidelity of the model provides reliable data support for the real-time state prediction and score calculation in Step 3.

[0068] Step 2: According to the task volume and task time of the scheduling, set the scheduling volume of each pumping station, and set Solving Condition I, Solving Condition II, and Solving Condition III, and solve in MATLAB to obtain the scheduling volume of each pumping station;

[0069] The said Step 2 includes the following contents:

[0070] Obtain the rated flow rate and rated power of each pumping station, obtain the task volume and task time of the scheduling of the pumping station group from the superior, allocate the task volume of the scheduling among each pumping station, set the scheduling volume of each pumping station and solve in MATLAB, and set the solving conditions:

[0071] The formula based on Solving Condition I is as follows:

[0072]

[0073] Among them, V is the task volume of the scheduling, V i represents the scheduling volume of the pumping station numbered i, i is the pumping station number retrieval variable, i ∈ N, 1 ≤ i ≤ M;

[0074] Among them, by ensuring that the sum of the scheduling volumes of each pumping station is equal to the task volume of the scheduling, it is ensured that the work of the pumping station group can meet the task volume of the scheduling.

[0075] The formula based on Solving Condition II is as follows:

[0076]

[0077] Among them, MAX represents selecting the maximum value, Q i represents the rated flow rate of the pumping station numbered i, T z is the task time;

[0078] Among them, by judging the longest pumping station working time, it is judged that this scheduling task can be completed within the specified time.

[0079] The formula based on Solving Condition III is as follows:

[0080]

[0081] Among them, MIN is the minimization function, and P i represents the rated power of the pumping station numbered i;

[0082] Among them, by multiplying the working time of each pumping station by the corresponding power, the power consumption of each pumping station can be judged, and the minimum power consumption can be obtained through the minimization function, so as to achieve the purpose of energy conservation.

[0083] As a preferred embodiment, the scheduling volume of each pumping station is solved by the interior point method, the maximum number of iterations is set to 1000, and the optimality tolerance is set to 10 -6 to ensure accuracy. If the problem has no solution, a world alarm will be issued.

[0084] Obtain the scheduling volume of each pumping station after solving.

[0085] By setting triple constraint conditions for task volume allocation (total task volume, time limit, and minimum energy consumption), the scientificity and economy of the scheduling scheme are balanced. The MATLAB solving tool is used to quickly process complex constraint problems to ensure that the scheduling volume of each pumping station can meet the task requirements and conform to the operation efficiency and energy-saving goals. The solution result of this step provides direct parameters for the operation duration calculation and digital twin model input in step 3, laying a foundation for subsequent state prediction and the construction of the scoring system. In addition, the dynamic allocation logic of the task volume implicitly considers the preliminary differences in the potential performance of the pumping stations, prepares for the determination of the scoring difference and the reallocation mechanism in step 4, and forms a prerequisite for scheduling optimization.

[0086] Step 3: Each pumping station obtains the operation duration of this pumping station according to the scheduling volume and inputs it into the digital twin model of the pumping station group, obtains the bearing temperature curve, pump cabin pressure curve, and flow curve of each pumping station, obtains the flow stability according to the flow curve, obtains the pressure stability according to the pump cabin pressure curve, and combines the temperature threshold of each pumping station to obtain the operation status score of each pumping station;

[0087] The said step 3 includes the following contents:

[0088] Each pumping station obtains the operation duration respectively according to the obtained scheduling volume and combines the rated flow of each pumping station. The formula is as follows:

[0089]

[0090] Among them, T i represents the operation duration of the pumping station numbered i, Q i represents the rated flow of the pumping station numbered i, i is the pumping station number retrieval variable, i ∈ N, 1 ≤ i ≤ M;

[0091] Among them, the operating duration required for the pump is determined by dividing the task volume of each pumping station by the rated flow rate. The larger the scheduling volume, the longer the operating duration; the larger the rated flow rate, the shorter the operating duration.

[0092] The startup durations of each pumping station are respectively input into the digital twin models of the corresponding pumping station groups to obtain the bearing temperature curves, pump cabin pressure curves, and flow curves of each pumping station. The flow stability is obtained based on the flow curves of each pumping station. The formula is as follows:

[0093]

[0094] Among them, σ Q-i represents the flow stability value when the operating duration of the pumping station numbered i is T i , T i is the operating duration, Q i (t) represents the flow rate of the pumping station numbered i at time t, represents the average flow rate of the pumping station numbered i, t is the operating duration retrieval variable, 0 < t ≤ T i , i is the pumping station number retrieval variable, i ∈ N, 1 ≤ i ≤ M;

[0095] Among them, the stability of the flow is judged by the standard deviation of the flow curve. The flow stability represents the operating state of the pump. The smaller the standard deviation of the pump, the better the operating state. For pumps with a larger standard deviation, the flow may be unstable due to problems such as corrosion or sealing. These unstable factors indicate that problems may occur during the future operation of the pump. Therefore, they need to be considered in the assessment of the operating state score.

[0096] The pressure stability is obtained based on the pump cabin pressure curve of each pumping station. The formula is as follows:

[0097]

[0098] Among them, σ p-i represents the pressure stability value when the operating duration of the pumping station numbered i is T i , T i is the operating duration, p i (t) represents the pressure of the pumping station numbered i at time t, represents the average pressure of the pumping station numbered i, t is the operating duration retrieval variable, 0 < t ≤ T i , i is the pumping station number retrieval variable, i ∈ N, 1 ≤ i ≤ M;

[0099] Among them, the pressure in the pump compartment is an important factor affecting the normal operation of the pump. The normal pump compartment pressure should be stable, and stability means that the pump has strong sustainable working ability. If the standard deviation of the pump compartment pressure is large, it indicates that the pump may have problems with sealing and blockage, resulting in an unsmooth scheduling process. Therefore, it needs to be considered in the operation status scoring.

[0100] Obtain the temperature threshold for each pumping station. The temperature threshold is obtained from the merchant that supplies the pumps. Based on the bearing temperature curve of each pumping station, obtain the maximum temperature, and construct the operation status score for each pump. The formula is as follows:

[0101]

[0102] Among them, SY i represents the operation status score of the pumping station numbered i, σ p-i represents the pressure stability of the pumping station numbered i, σ Q-i represents the flow stability of the pumping station numbered i, T max-i represents the maximum temperature of the pumping station numbered i, T th-i represents the temperature threshold of the pumping station numbered i. i is the retrieval variable for the pumping station number, i ∈ N, 1 ≤ i ≤ M.

[0103] Among them, the operating condition of the pump is judged by subtracting the maximum temperature from the temperature threshold. During the continuous operation of the pump, the bearing temperature will increase. However, under the condition of the heat dissipation system and its own stable heat generation, the maximum temperature generally does not exceed the temperature threshold. However, when the pump is in an abnormal state, such as problems like eccentric rotation shaft and corroded ball bearings, it will continuously increase the bearing temperature, resulting in the temperature exceeding the temperature threshold. Temperature is also an important factor for judging the normal operation of the pump. Incorporate pressure stability, flow stability, and maximum temperature into the consideration of the status score at the same time. Considering these three factors simultaneously can avoid misjudgment caused by local factors. The higher the value of pressure stability, the higher the operation status score; the higher the value of flow stability, the higher the operation status score; when the maximum temperature exceeds the temperature threshold, the more the excess amount, the operation status score will increase exponentially.

[0104] Based on the digital twin model, predict the bearing temperature, pump compartment pressure, and flow curve of the pumping station. By quantifying the flow stability (and pressure stability), convert the dynamic operation status into a measurable scoring index. Combine the comparison between the temperature threshold and the maximum temperature to identify the equipment overheating risk in advance and avoid equipment damage caused by abnormal working conditions. The operation status scoring formula synthesizes multi-dimensional data of flow, pressure, and temperature, providing a basis for the comparison of the health status score in step 4 from the dimension of real-time operation. The prediction result of this step is directly related to the short-term performance of the pumping station, providing a key criterion for subsequent dynamic adjustment.

[0105] Step 4: Obtain the equipment duration, operation duration, medium repair times, and the duration since the last minor repair for each pumping station, construct a health status score, sort based on the operation status score and health status score of each pumping station, and determine whether each pumping station meets the dispatching volume according to the sorting. If there is a pumping station that does not meet the requirement, adjust the task volume of this pumping station and reallocate the task volume of other pumping stations. If there is always a pumping station that cannot meet the dispatching volume, issue an alarm.

[0106] The said Step 4 includes the following contents:

[0107] Step 401: Obtain the equipment duration, operation duration, medium repair times, and the duration since the last minor repair for each pumping station through the maintenance log. The medium repair and minor repair are the maintenance levels required for equipment maintenance. Among them, the equipment duration is the duration from the commissioning of the pump to the current time, the operation duration is the usage duration after the pump is commissioned, and construct the health status score for each pumping station. The basis formula is as follows:

[0108]

[0109] Among them, SJ i represents the health status score of the pumping station numbered i, T equip-i represents the equipment duration of the pumping station numbered i, T run-i represents the operation duration of the pumping station numbered i, N mid-i represents the medium repair times of the pumping station numbered i, T last-i represents the duration since the last minor repair of the pumping station numbered i. i is the pumping station number retrieval variable, i ∈ N, 1 ≤ i ≤ M, k1 and k2 are coefficients, and k1 < k2.

[0110] Among them, the equipment duration, operation duration, medium repair times, and the duration since the last minor repair all affect the health status of the pump. The longer the equipment duration, the lower the health status score; the longer the operation duration, the lower the health status score; the more medium repair times, it means the more failure times of this pump, indicating that the pump is less healthy and the health status score is lower; the longer the duration since the last minor repair, it means the pump has not been maintained for a long time and the health status score is also lower. k1 < k2 means that the influencing factor of the operation duration is greater than the equipment duration, to avoid the influence of the health status score of some pumping stations due to long equipment time and low working intensity.

[0111] Extract the equipment duration, operation duration, medium repair times, and the duration since the last minor repair of the pumping stations from the maintenance logs. Combine with the exponential decay function to construct a health status score to quantify the long-term health status of the pumping stations. This score reflects the combined impact of equipment aging, usage frequency, and maintenance history on reliability. The setting of k1 < k2 highlights that the operation duration has a much greater negative impact on the health status than the equipment duration. Step 401 provides static health dimension data for the score difference calculation in Step 402, complementing the dynamic operation status score in Step 3 to ensure that the scheduling decision considers both real-time performance and the long-term reliability of the equipment. At the same time, the formula design of the health score implies guidance for the maintenance strategy, indirectly optimizing the subsequent operation and maintenance management.

[0112] Step 402: Sort the health status scores and operation status scores of all pumping stations from high to low. Obtain the pumping stations ranked in the last one-third of the health status score ranking, and obtain the pumping stations ranked in the last one-third of the operation status score ranking. Screen out the pumping stations that are in the last one-third in both rankings, and label them as pumping stations that do not meet the current scheduling volume. Redistribute the scheduling volume of all pumping stations.

[0113] Sort the two scores and screen out the pumping stations that are in the last one-third in both rankings, indicating that the selected pumping stations are the most unstable ones during operation among all pumping stations and need to be considered emphatically. To avoid unexpected situations in actual work, adjust their scheduling volume to improve their stability in the scheduling task.

[0114] Step 403: The logic for redistributing the scheduling volume is as follows:

[0115] First, adjust the pumping stations that do not meet the current scheduling volume. Set their number as j, and set their adjusted scheduling volume to half of the scheduling volume before adjustment. At the same time, distribute the remaining task volume among other pumping stations. Resolve the adjusted scheduling volume of other pumping stations in MATLAB, and modify the solution condition Ⅰ. The formula is as follows:

[0116]

[0117] Among them, V is the scheduled task volume, V j represents the scheduling volume of the pumping station numbered j before adjustment, V i represents the scheduling volume of the pumping station numbered i, where i is the pumping station number retrieval variable, i ∈ N, 1 ≤ i ≤ M;

[0118] Optimize the pumping stations that cannot complete the current scheduling volume in the new round of task allocation so that they only complete half of the original planned task volume, and distribute the remaining task volume among other pumping stations.

[0119] Without modifying Solution Condition II and Solution Condition III, re-obtain the scheduling volume of each pumping station after solution, and send the scheduling volume to the corresponding pumping station.

[0120] For non-compliant pumping stations, halve their scheduling volume, re-solve the scheduling volume of other pumping stations, and update the total task volume constraint at the same time. This step dynamically adjusts the task allocation to prevent faulty pumping stations from dragging down the overall task. At the same time, MATLAB is used for rapid re-optimization to ensure that the remaining pumping stations efficiently fill the task gap under time constraints and energy consumption constraints. The re-allocation logic reflects the elasticity and fault tolerance of the system, which not only repairs local problems but also maintains the priority of global goals. In addition, the adjusted scheduling volume provides new inputs for the re-prediction in Step 3 and the iterative determination in Step 4, forming a key part of the closed-loop feedback.

[0121] Step 404: Each pumping station executes Steps 3 and 4 again according to the re-obtained scheduling volume until the score differences of all pumping stations are greater than zero, then start to execute the scheduling task. When it is impossible to solve such that the score differences of all pumping stations are greater than zero, an alarm is issued.

[0122] By repeatedly executing Steps 3 and 4, continuously update the scheduling volume and re-evaluate the status of the pumping stations until all pumping stations G i ≥0 or an alarm is triggered. The iterative process realizes the gradual optimization of the scheduling scheme, ensuring that the system approaches the optimal solution in dynamic changes. If all conditions cannot be met finally, the alarm mechanism prompts manual intervention to avoid task interruption caused by collective equipment failure. This step not only strengthens the self-healing ability of the system but also feeds back the problems that cannot be automatically solved to the operation and maintenance side, promoting equipment maintenance or replacement, and indirectly optimizing the health status of the pumping station group (feeding back the data update in Step 401). The iterative logic and the alarm mechanism jointly ensure the ultimate feasibility of the scheduling and provide data support for long-term operation and maintenance decisions.

[0123] Please refer to Figure 2 The present invention also includes a pumping station group scheduling system based on digital twin for executing the above-mentioned pumping station group scheduling method based on digital twin, including:

[0124] A model construction module for obtaining the bearing temperature curve, flow curve, and pump cabin pressure curve of each pumping station when operating at rated power, training the bearing temperature model, pump cabin pressure model, and flow model of each pumping station respectively with the pumping station as a unit, and summarizing the models of all pumping stations to obtain a digital twin model of the pumping station group;

[0125] A scheduling volume solving module for setting the scheduling volume of each pumping station according to the scheduled task volume and task time, setting Solution Condition I, Solution Condition II, and Solution Condition III, and solving in MATLAB to obtain the scheduling volume of each pumping station;

[0126] An operation evaluation module is used for each pumping station to obtain the operation duration of this pumping station according to the scheduling volume and input it into the digital twin model of the pumping station group, obtain the bearing temperature curve, pump cabin pressure curve and flow curve of each pumping station, obtain the flow stability according to the flow curve, obtain the pressure stability according to the pump cabin pressure curve, and combine the temperature threshold of each pumping station to obtain the operation status score of each pumping station;

[0127] A status analysis module is used to obtain the equipment duration, operation duration, number of medium repairs and the duration since the last minor repair of each pumping station, construct a health status score, sort through the operation status score and health status score of each pumping station, judge whether each pumping station meets the scheduling volume according to the sorting. If there is a pumping station that does not meet the requirement, adjust the task volume of this pumping station and reallocate the task volume of other pumping stations. If there is always a pumping station that cannot meet the scheduling volume, an alarm will be issued.

[0128] All the above formulas are dimensionless and take their numerical values for calculation. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0129] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or by the combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0130] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all of them should be covered within the protection scope of this application.

Claims

1. A scheduling method for a pumping station group based on digital twin, characterized in that, The specific steps include: Step 1: Obtain the bearing temperature curve, flow curve, and pump cabin pressure curve of each pumping station when operating at rated power. Taking each pumping station as a unit, train the bearing temperature model, pump cabin pressure model, and flow model of each pumping station respectively. Summarize the models of all pumping stations to obtain the digital twin model of the pumping station group. Step 2: According to the task volume and task time of the dispatch, set the dispatch volume of each pumping station, and set Solving Condition I, Solving Condition II, and Solving Condition III, and solve in MATLAB to obtain the dispatch volume of each pumping station. Step 3: Each pumping station obtains the operation duration of this pumping station according to the dispatch volume and inputs it into the digital twin model of the pumping station group to obtain the bearing temperature curve, pump cabin pressure curve, and flow curve of each pumping station. Obtain the flow stability according to the flow curve, obtain the pressure stability according to the pump cabin pressure curve, and combine the temperature threshold of each pumping station to obtain the operation status score of each pumping station. Step 4: Obtain the equipment duration, operation duration, number of medium repairs, and duration since the last minor repair of each pumping station, construct the health status score, sort through the operation status score and health status score of each pumping station, and judge whether each pumping station meets the dispatch volume according to the sorting. If there is a pumping station that does not meet the requirements, adjust the task volume of this pumping station and redistribute the task volume of other pumping stations. If there is always a pumping station that cannot meet the dispatch volume, give an alarm.

2. The method for scheduling a pumping station group based on digital twin according to claim 1, wherein: Through the work logs of each pumping station, obtain the bearing temperature curve, flow curve, and pump cabin pressure curve of each pumping station when operating at rated power in history. The horizontal axis of the curve is the operation duration, the starting point of the operation duration is 0, the end point is the actual operation duration of the equipment, and the vertical axis is the value of various types of data. Taking a single pumping station as a unit, using the starting duration as the training set, and inputting the bearing temperature curve, pump cabin pressure curve, and flow curve corresponding to different starting durations as labels into the convolutional neural network model for training respectively, obtain the bearing temperature model, pump cabin pressure model, and flow model of each pumping station. Summarize the models of all pumping stations to obtain the digital twin model of the pumping station group.

3. A dispatching method for a pumping station group based on digital twin according to claim 1, characterized in that: Obtain the rated flow and rated power of each pumping station, obtain the task volume and task time of the dispatch of the pumping station group from the superior, distribute the task volume of the dispatch among each pumping station, set the dispatch volume of each pumping station and solve in MATLAB. The logic for setting the solving conditions is as follows: The formula based on Solving Condition I is as follows: Among them, V is the amount of tasks scheduled, and V i represents the scheduling volume of the pumping station numbered i, where i is the retrieval variable of the pumping station number, i ∈ N, and 1 ≤ i ≤ M; The formula based on Solving Condition II is as follows: Among them, MAX represents selecting the maximum value, and Q i represents the rated flow rate of the pumping station numbered i, and T z is the mission time; The formula based on Solving Condition III is as follows: where MIN is the minimization function, and P i represents the rated power of the pumping station numbered i; Obtain the dispatch volume of each pumping station after solving.

4. A dispatching method for a pumping station group based on digital twin according to claim 1, characterized in that: Each pumping station obtains the operation duration according to the obtained dispatch volume in combination with the rated flow of each pumping station. The formula is as follows: Among them, T i represents the operation duration of the pumping station numbered i, and Q i represents the rated flow rate of the pumping station numbered i. Here, i is the retrieval variable for the pumping station number, i ∈ N, and 1 ≤ i ≤ M; Input the starting duration of each pumping station into the corresponding digital twin model of the pumping station group respectively to obtain the bearing temperature curve, pump cabin pressure curve, and flow curve of each pumping station. Obtain the flow stability according to the flow curve of each pumping station. The formula is as follows: Among them, σ Q-i represents the flow stability value when the operation duration of the pumping station numbered i is T i , T i is the operation duration, Q i (t) represents the flow rate of the pumping station numbered i at time t, represents the average flow rate of the pumping station numbered i, t is the operation duration retrieval variable, 0 < t ≤ T i , i is the pumping station number retrieval variable, i ∈ N, 1 ≤ i ≤ M; Obtain the pressure stability according to the pump cabin pressure curve of each pumping station. The formula is as follows: Among them, σ p-i represents the pressure stability value when the operation duration of the pumping station numbered i is T i , T i is the operation duration, and p i (t) represents the pressure of the pumping station numbered i at time t, represents the average pressure of the pumping station numbered i, t is the operation duration retrieval variable, 0 < t ≤ T i , i is the pumping station number retrieval variable, i ∈ N, 1 ≤ i ≤ M; Obtain the temperature threshold of each pumping station, obtain the highest temperature according to the bearing temperature curve of each pumping station, and construct the operation status score of each pump. The formula is as follows: Among them, SY i represents the operation status score of the pumping station numbered i, and σ p-i represents the pressure stability of the pumping station numbered i, and σ Q-i represents the flow stability of the pumping station numbered i, and T max-i represents the highest temperature of the pumping station numbered i, and T th-i represents the temperature threshold of the pumping station numbered i. i is the retrieval variable of the pumping station number, i ∈ N, 1 ≤ i ≤ M.

5. The scheduling method for a pumping station group based on digital twin according to claim 4, characterized in that: Obtain the equipment duration, operation duration, medium repair times, and duration since the last minor repair of each pumping station through the maintenance log. The medium repair and minor repair are the maintenance levels required for equipment maintenance. Among them, the equipment duration is the duration from the commissioning of the pump to the present, and the operation duration is the usage duration after the pump is commissioned. Construct the health status score of each pumping station, and the basis formula is as follows: Among them, SJ i represents the health status score of the pumping station numbered i, T equip-i represents the equipment duration of the pumping station numbered i, T run-i represents the operation duration of the pumping station numbered i, N mid-i represents the number of medium repairs of the pumping station numbered i, T last-i represents the duration since the last minor repair of the pumping station numbered i. i is the retrieval variable of the pumping station number, i ∈ N, 1 ≤ i ≤ M, and k1 and k2 are coefficients, where k1 < k2.

6. The method for scheduling a pumping station group based on digital twin according to claim 1, characterized in that: Sort the health status scores and operation status scores of all pumping stations from high to low respectively. Obtain the pumping stations ranked in the last one-third in the health status score ranking, and obtain the pumping stations ranked in the last one-third in the operation status score ranking. Screen out the pumping stations that are in the last one-third in both rankings, label them as pumping stations that do not meet the current scheduling volume, and reallocate the scheduling volume of all pumping stations.

7. A dispatching method for a pumping station group based on digital twin according to claim 1, characterized in that: The logic for reallocating the scheduling volume is as follows: First, adjust the pumping stations that do not meet the current scheduling volume. Set its number as j, and set the adjusted scheduling volume as half of the scheduling volume before adjustment. At the same time, allocate the remaining task volume among other pumping stations, and re-solve the adjusted scheduling volume of other pumping stations in MATLAB. At the same time, modify the solution condition Ⅰ, and the basis formula is as follows: Among them, V is the amount of tasks scheduled, and v j represents the scheduling amount of the pumping station numbered j before adjustment, and V i represents the scheduling amount of the pumping station numbered i, where i is the retrieval variable of the pumping station number, i ∈ N, 1 ≤ i ≤ M; Do not modify the solution condition Ⅱ and solution condition Ⅲ, re-obtain the scheduling volume of each pumping station after solution, and send the scheduling volume to the corresponding pumping station.

8. A dispatching method for a pumping station group based on digital twin according to claim 1, characterized in that: Each pumping station executes steps 3 and 4 again according to the re-obtained scheduling volume until the score differences of all pumping stations are greater than zero, then start to execute the scheduling task. When it is impossible to make the score differences of all pumping stations greater than zero, an alarm is issued.

9. A pumping station group scheduling system based on digital twin, which is used to execute the method for scheduling a pumping station group based on digital twin described in the above claims 1-8, and is characterized in that, Include: A model construction module, which is used to obtain the bearing temperature curve, flow curve, and pump cabin pressure curve of each pumping station when operating at the rated power. Taking the pumping station as a unit, train the bearing temperature model, pump cabin pressure model, and flow model of each pumping station respectively, and summarize the models of all pumping stations to obtain the digital twin model of the pumping station group; A scheduling volume solving module, which is used to set the scheduling volume of each pumping station according to the scheduling task volume and task time, and set the solution condition Ⅰ, solution condition Ⅱ, and solution condition Ⅲ, and solve in MATLAB to obtain the scheduling volume of each pumping station; An operation evaluation module, which is used for each pumping station to obtain the operation duration of this pumping station according to the scheduling volume and input it into the digital twin model of the pumping station group, obtain the bearing temperature curve, pump cabin pressure curve, and flow curve of each pumping station, obtain the flow stability according to the flow curve, obtain the pressure stability according to the pump cabin pressure curve, and combine the temperature threshold of each pumping station to obtain the operation status score of each pumping station; A status analysis module, which is used to obtain the equipment duration, operation duration, medium repair times, and duration since the last minor repair of each pumping station, construct the health status score, sort through the operation status score and health status score of each pumping station, and judge whether each pumping station meets the scheduling volume according to the sorting. If there are pumping stations that do not meet the requirements, adjust the task volume of this pumping station and reallocate the task volume of other pumping stations. If there are always pumping stations that cannot meet the scheduling volume, an alarm is issued.

Images