Pump station operation regulation device and regulation method

Abstract

The present invention discloses an operation regulation device and method for a water pump pumping station, which relates to the technical field of pumping station operation regulation. A first prediction result is output through the operation data of the water pump pumping station, and it is judged whether the first prediction result needs to be corrected based on environmental characteristics, equipment status data, and water quality data to obtain the regulating parameters of the inlet and outlet valves; a digital model of the water pump pumping station is constructed, the simulated regulation feedback result is received, and the regulating parameters of the inlet and outlet valves are optimized by using the simulated regulation feedback result; the regulating stability threshold of the inlet and outlet valves is obtained, and relationship feedback verification is carried out by using the regulating stability threshold of the inlet and outlet valves. It is judged whether to trigger a protection mechanism through the simulated regulation feedback result and the relationship feedback verification result; when the protection mechanism is triggered, a dynamic flow stabilizing device is started, and the flow stabilizing parameters of the dynamic flow stabilizing device are regulated. It realizes intelligent precise control, active protection, and energy efficiency optimization, improves system stability, and reduces operation and maintenance costs.

Description

Technical Field

[0001] The present invention relates to the technical field of pump station operation regulation, and specifically to a device and method for regulating the operation of a water pump pump station. Background Art

[0002] At present, the operation regulation of water pump pump stations mostly relies on traditional parameters and simple automatic control. The injection or drainage is regulated by controlling the opening degree of the pump outlet valve, and some use a distributed monitoring system based on PLC to achieve remote control of equipment; in terms of energy-saving optimization, the pump is made to work in the efficient area by adjusting the valve, but mostly step-by-step regulation is adopted, with limited accuracy; in terms of stability guarantee, there is a lack of effective monitoring and prediction mechanisms for influencing factors such as pipeline vibration.

[0003] Existing regulation methods are mostly extensive control, unable to smoothly and continuously regulate the valve opening degree, not timely in responding to parameter changes under complex working conditions, with a large regulation error, and it is difficult to achieve efficient and energy-saving operation; at the same time, there is a lack of in-depth analysis of the relationship between water flow characteristics and pipeline stability, and no effective pipeline vibration monitoring and early warning mechanism is established. It is easy to cause pipeline vibration and resonance due to changes in water flow velocity, resulting in pipeline damage or equipment failure; moreover, traditional regulation methods do not fully consider the influence of environmental characteristics, equipment status, and water quality changes on regulation. When seasons, weather, equipment aging, or water quality deteriorates, the regulation strategy cannot be automatically optimized, affecting the operation effect of the pump station.

[0004] Therefore, in view of the above problems, there is an urgent need for a device and method for regulating the operation of a water pump pump station. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides a device and method for regulating the operation of a water pump pump station, which solves the problems of low regulation accuracy and poor safety of traditional pump stations through non-linear dynamic regulation and multi-source data verification.

[0006] To achieve the above object, the present invention is implemented through the following technical solutions: A running adjustment device for a water pump pumping station, comprising: a data acquisition module for real-time monitoring and obtaining the condition parameters of the water pump pumping station, where the condition parameters include operation data, environmental characteristics, equipment status data, water quality data, water flow data, and pipeline acoustic fingerprint data; an adjustment judgment module for outputting a first prediction result through the operation data of the water pump pumping station, and judging whether it is necessary to correct the first prediction result based on the environmental characteristics, equipment status data, and water quality data to obtain the inlet and outlet valve adjustment parameters; an adjustment verification module for inputting the inlet and outlet valve adjustment parameters into the digital model of the water pump pumping station to obtain a simulated adjustment feedback result, and using the simulated adjustment feedback result to optimize the inlet and outlet valve adjustment parameters; a stability threshold verification module for determining the inlet and outlet valve adjustment stability threshold based on the relationship between the water flow data and the pipeline acoustic fingerprint data, using the inlet and outlet valve adjustment stability threshold for relationship feedback verification, and judging whether to trigger a protection mechanism through the simulated adjustment feedback result and the relationship feedback verification result; a protection adjustment module for starting a dynamic flow stabilization device when the protection mechanism is triggered, and adjusting the flow stabilization parameters of the dynamic flow stabilization device according to the water flow data and the pipeline acoustic fingerprint data.

[0007] Further, the environmental characteristics specifically include environmental temperature and rainfall, the equipment status data is specifically the equipment health degree, the water quality data is specifically the chloride ion concentration, turbidity, and hardness, the water flow data is specifically the water flow Reynolds number, and the pipeline acoustic fingerprint data is specifically the pipeline vibration spectrum.

[0008] Further, the specific steps for outputting the first prediction result through the operation data of the water pump pumping station are: obtaining the operation data of the water pump pumping station under different working conditions and the corresponding inlet and outlet valve adjustment parameters under different working conditions, where the inlet and outlet valve adjustment parameters are specifically the inlet and outlet valve adjustment areas, synchronizing the operation data with the inlet and outlet valve adjustment parameters in time, identifying the influence relationship between the operation data and the inlet and outlet valve adjustment parameters, and obtaining the first predicted value of the inlet and outlet valve adjustment area based on the influence relationship between the operation data and the inlet and outlet valve adjustment parameters.

[0009] Further, it is determined whether the first prediction result needs to be corrected, and the specific analysis of the inlet and outlet valve adjustment parameters is as follows: the environmental characteristics, equipment status data and water quality data under different working conditions are obtained, the operation data, environmental characteristics, equipment status data, water quality data and the inlet and outlet valve adjustment parameters are synchronized in time, and the time-synchronized parameters are trained by deep learning to obtain the correction adjustment factors, and the correction adjustment factors include the environmental characteristic correction factor, the equipment status correction factor and the water quality factor correction factor; the ambient temperature threshold, the rainfall threshold, the equipment health threshold, the chloride ion concentration threshold, the turbidity threshold and the hardness threshold are obtained, and the environmental characteristics, the equipment status data and the water quality data are compared with the corresponding thresholds respectively, and it is determined whether the correction demand is triggered according to the comparison results, and the correction demand includes the environmental characteristic correction demand, the equipment status correction demand and the water quality factor correction demand; the correction demand type triggered is counted, and the corresponding correction adjustment factor is integrated into the first prediction value of the inlet and outlet valve adjustment area to obtain the second prediction value of the inlet and outlet valve adjustment area, and the second prediction value of the inlet and outlet valve adjustment area is recorded as the inlet and outlet valve adjustment parameter. If there is no triggering of the correction demand, the first prediction value of the inlet and outlet valve adjustment area is recorded as the inlet and outlet valve adjustment parameter.

[0010] Furthermore, the inlet and outlet valve adjustment verification module is specifically analyzed as follows: a digital model of a water pump station is constructed based on the status parameters monitored in real time by the data acquisition module, the inlet and outlet valve adjustment parameters are input into the digital model of the water pump station, and the valves in the digital model of the water pump station are adjusted according to the inlet and outlet valve adjustment parameters to simulate the state of the water pump station after valve adjustment in actual operation; during the simulation operation, the output simulation adjustment feedback results are monitored and recorded in real time, the simulation adjustment feedback results include the stable duration of the motor voltage and the pipeline soundprint data, the change value between the motor voltage and the motor voltage obtained by the data acquisition module is identified, the change value is compared with the optimization threshold, and when the change value is lower than the optimization threshold, the inlet and outlet valve adjustment parameters are adjusted using the particle swarm algorithm until the change value is greater than or equal to the optimization threshold to obtain the optimized inlet and outlet valve adjustment parameters.

[0011] Further, the stability threshold verification module is specifically analyzed as follows: The stability threshold verification module further includes constructing a valve-pipeline relationship model, obtaining the opening areas of the inlet and outlet valves of the water pump pumping station, the Reynolds number of the water flow in the pipeline, and the pipeline vibration spectrum under different working conditions, normalizing the obtained data to form a historical data set; using the Reynolds number of the water flow in the pipeline in the historical data set as the independent variable and the pipeline vibration spectrum as the dependent variable, and adopting a machine learning algorithm to obtain a water flow-pipeline relationship model; using the opening areas of the inlet and outlet valves in the historical data set as the independent variable and the corresponding Reynolds number of the water flow in the pipeline as the dependent variable, and adopting a linear regression algorithm to obtain a valve-pipeline relationship model; setting a safe threshold range for the pipeline vibration spectrum, identifying the corresponding Reynolds number of the water flow in the pipeline by using the valve-pipeline relationship model for different opening areas of the inlet and outlet valves, inputting the Reynolds number of the water flow in the pipeline into the water flow-pipeline relationship model to predict the corresponding pipeline vibration spectrum, comparing the predicted pipeline vibration spectrum with the safe threshold range of the pipeline vibration spectrum band by band, when the vibration amplitude of one of the bands first exceeds the corresponding threshold, recording the opening area of the inlet and outlet valves at this time, and determining it as the adjustment stability threshold of the inlet and outlet valves; receiving the adjustment parameters of the inlet and outlet valves output by the non-linear adjustment model, combining the valve-pipeline relationship model and the water flow-pipeline relationship model to obtain the corresponding pipeline vibration spectrum, comparing the pipeline vibration spectrum with the pipeline vibration threshold, if there is any band with a vibration amplitude exceeding the corresponding threshold or the stable duration of the pipeline acoustic fingerprint data is lower than the pipeline acoustic fingerprint stability threshold, sending a protection mechanism trigger signal.

[0012] Further, the protection adjustment module is specifically analyzed as follows: receiving the protection mechanism trigger signal, identifying the Reynolds number distribution and pipeline vibration response of the dynamic flow stabilizer under different flow stabilization parameters, and determining the flow stabilization parameters of the dynamic flow stabilizer with the minimum pipeline vibration amplitude and stable water Reynolds number as the goals, and the flow stabilization parameters are specifically the opening degree of the dynamic flow stabilizer.

[0013] Operation regulation method for a water pump pumping station, applying the operation regulation device for a water pump pumping station as described above, including the following steps: Step S1, monitor and obtain the condition parameters of the water pump pumping station in real time, where the condition parameters include operation data, environmental characteristics, equipment status data, water quality data, water flow data, and pipeline acoustic fingerprint data; Step S2, output a first prediction result through the operation data of the water pump pumping station, and determine whether it is necessary to correct the first prediction result based on environmental characteristics, equipment status data, and water quality data to obtain the inlet and outlet valve regulation parameters; Step S3, input the inlet and outlet valve regulation parameters into the digital model of the water pump pumping station to obtain a simulated regulation feedback result, and optimize the inlet and outlet valve regulation parameters using the simulated regulation feedback result; Step S4, determine the inlet and outlet valve regulation stability threshold based on the relationship between water flow data and pipeline acoustic fingerprint data, perform relationship feedback verification using the inlet and outlet valve regulation stability threshold, and determine whether to trigger the protection mechanism based on the simulated regulation feedback result and the relationship feedback verification result; Step S5, when the protection mechanism is triggered, start the dynamic flow stabilization device, and adjust the flow stabilization parameters of the dynamic flow stabilization device according to the water flow data and pipeline acoustic fingerprint data.

[0014] The present invention has the following beneficial effects:

[0015] The operation regulation device and method for the water pump pumping station realize the calculation of the inlet and outlet valve regulation parameters by dynamically introducing multiple correction factors such as environmental characteristics, equipment status, and water quality data. At the same time, the verification of the inlet and outlet valve regulation parameters avoids the regulation lag or overregulation caused by the traditional linear regulation model ignoring complex working conditions, ensuring the accuracy of regulation, improving the operation efficiency and stability of the pumping station; through the two-layer logic of preliminary screening by a linear relationship formula and precise verification by a non-linear vibration model, it ensures that the valve regulation parameters are within a safe range and avoids mis-triggering the protection mechanism; when the protection mechanism is triggered, the flow stabilization parameters are dynamically adjusted according to real-time water flow data and the acoustic fingerprint library to suppress vibration or pressure shock, avoiding accidents such as pipeline rupture and equipment damage caused by improper valve regulation, and extending the equipment life; through real-time data feedback, the water flow pipeline relationship model is dynamically updated to adapt to changes in the operation conditions of the pumping station and maintain the long-term effectiveness of the regulation strategy. Description of the Drawings

[0016] Figure 1 It is a structural diagram of the operation regulation device for the water pump pumping station of the present invention.

[0017] Figure 2 It is a flow chart of the operation regulation method for the water pump pumping station of the present invention. Detailed Embodiments

[0018] In the embodiments of the present application, through the operation regulation device and method for the water pump pumping station, intelligent precise control, active protection, and energy efficiency optimization are realized, improving the system stability and reducing the operation and maintenance costs.

[0019] The general idea of the embodiments of this application is as follows: Six-dimensional data of the operation of the pump station is collected in real time through a multi-sensor network to construct a digital mirror of the pump station; combined with environmental, equipment, and water quality correction factors, initial valve adjustment parameters are generated, and the adjustment effect is simulated through a digital twin model to verify the rationality of the parameters and optimize them, forming a "prediction-verification-correction" closed loop; an association model between the Reynolds number of the water flow and the pipeline vibration is established, and a stability threshold is set. When the simulation results or actual monitoring data exceed the threshold, the dynamic flow stabilization device is automatically triggered to calculate the optimal flow stabilization parameters to suppress pipeline vibration.

[0020] Please refer to Figure 1 , an embodiment of the present invention provides a technical solution: a pump station operation adjustment device, including: a data acquisition module for real-time monitoring and obtaining the condition parameters of the pump station, and the condition parameters include operation data, environmental characteristics, equipment status data, water quality data, water flow data, and pipeline acoustic fingerprint data; an adjustment judgment module for outputting a first prediction result through the operation data of the pump station, and judging whether it is necessary to correct the first prediction result based on the environmental characteristics, equipment status data, and water quality data to obtain the inlet and outlet valve adjustment parameters; an adjustment verification module for inputting the inlet and outlet valve adjustment parameters into the pump station digital model to obtain a simulated adjustment feedback result, and using the simulated adjustment feedback result to optimize the inlet and outlet valve adjustment parameters; a stability threshold verification module for determining the inlet and outlet valve adjustment stability threshold based on the relationship between the water flow data and the pipeline acoustic fingerprint data, using the inlet and outlet valve adjustment stability threshold for relationship feedback verification, and judging whether to trigger a protection mechanism through the simulated adjustment feedback result and the relationship feedback verification result; a protection adjustment module for starting the dynamic flow stabilization device when the protection mechanism is triggered, and adjusting the flow stabilization parameters of the dynamic flow stabilization device according to the water flow data and the pipeline acoustic fingerprint data.

[0021] Specifically, the environmental characteristics specifically include environmental temperature and rainfall, the equipment status data is specifically the equipment health, the water quality data is specifically the chloride ion concentration, turbidity, and hardness, the water flow data is specifically the water flow Reynolds number, and the pipeline acoustic fingerprint data is specifically the pipeline vibration spectrum.

[0022] In this implementation plan, the motor voltage represents the operating voltage of the motor driving the water pump, reflecting the motor load and energy consumption status. The voltage at the motor input is directly measured by a voltage sensor and is used to monitor the operating status of the motor. Abnormal voltage fluctuations indicate equipment failures or abnormal loads, optimizing energy consumption management; the ambient temperature represents the external air temperature of the pumping station, which affects the physical properties of water (such as viscosity) and the performance of equipment materials. It is obtained by installing a temperature and humidity sensor in the external environment of the pumping station. Temperature changes affect the viscosity of water, affecting the Reynolds number and pump efficiency, and the valve opening needs to be dynamically adjusted; the rainfall represents the precipitation per unit time, which affects the water source level and water quality turbidity. It is obtained by installing a rain gauge or accessing meteorological data. Heavy rain causes a sudden rise in the water source level and an increase in turbidity, and the pump flow rate and filtration strategy need to be adjusted; the equipment health represents the wear degree and operating status evaluation value of the water pump equipment. The vibration frequency of the water pump equipment is collected by a vibration sensor, and combined with machine learning algorithms to predict the remaining life of the water pump equipment, which is used to early warn of water pump equipment failures, avoid unplanned outages, and optimize the maintenance cycle; the chloride ion concentration represents the chloride ion content in water, evaluating the corrosion risk to stainless steel pumps. It is obtained by on-line detection using an ion-selective electrode (ISE) or colorimetry. When the chloride ion exceeds the standard, the pump flow rate needs to be reduced or corrosion-resistant materials need to be replaced to extend the equipment life; the turbidity represents the concentration of suspended particles in water, reflecting the cleanliness of water quality. It is obtained by measuring the content of particulate matter in water by a turbidimeter using the infrared scattering principle. Excessive turbidity may block the pipeline or accelerate equipment wear, and the filtration system or pump flow rate needs to be adjusted; the hardness represents the concentration of calcium and magnesium ions in water, affecting the scaling risk. It is obtained by on-line detection using the ion exchange resin method or electrode method. Excessive hardness easily causes pipeline scaling and reduces pump efficiency, and the water treatment process or operating parameters need to be adjusted; the flow Reynolds number is a dimensionless number characterizing the fluid flow state (laminar flow / turbulent flow), which affects the pipeline resistance and pump performance. It is calculated by measuring the flow velocity, pipe diameter, and fluid viscosity and is used to judge the water flow state. Under turbulent flow conditions, measures to increase the flow stability need to be added to avoid increased vibration and energy consumption; the pipeline vibration spectrum represents the frequency distribution and amplitude characteristics of pipeline vibration, reflecting the water flow stability and pipeline structure status. The pipeline vibration signal is collected by an acceleration sensor and converted into frequency domain characteristics using Fourier transform. Abnormal vibration spectra (such as resonance frequencies) indicate unstable water flow or structural looseness, triggering a protection mechanism.

[0023] By integrating data on motor operation, environment, equipment, water quality, water flow, and structural status, precise monitoring of the entire life cycle of the pumping station is achieved.

[0024] Specifically, the specific steps to output the first prediction result through the operation data of the water pump pumping station are as follows: Obtain the operation data of the water pump pumping station under different working conditions and the inlet and outlet valve adjustment parameters corresponding to different working conditions. The inlet and outlet valve adjustment parameters are specifically the adjustment area of the inlet and outlet valves. Synchronize the operation data and the inlet and outlet valve adjustment parameters in time, identify the influence relationship between the operation data and the inlet and outlet valve adjustment parameters, and obtain the first predicted value of the adjustment area of the inlet and outlet valves based on the influence relationship between the operation data and the inlet and outlet valve adjustment parameters.

[0025] Judge whether it is necessary to correct the first prediction result. The specific analysis of obtaining the inlet and outlet valve adjustment parameters is as follows: Obtain the environmental characteristics, equipment status data, and water quality data under different working conditions. Synchronize the operation data, environmental characteristics, equipment status data, water quality data, and inlet and outlet valve adjustment parameters in time. Use deep learning to train the synchronized parameters to obtain correction adjustment factors, including environmental characteristic correction factors, equipment status correction factors, and water quality factor correction factors; obtain the environmental temperature threshold, rainfall threshold, equipment health threshold, chloride ion concentration threshold, turbidity threshold, and hardness threshold. Compare the environmental characteristics, equipment status data, and water quality data with the corresponding thresholds respectively, and judge whether to trigger a correction requirement according to the comparison results. The correction requirements include environmental characteristic correction requirements, equipment status correction requirements, and water quality factor correction requirements; count the types of triggered correction requirements, fuse the corresponding correction adjustment factors into the first predicted value of the adjustment area of the inlet and outlet valves to obtain the second predicted value of the adjustment area of the inlet and outlet valves, and record the second predicted value of the adjustment area of the inlet and outlet valves as the inlet and outlet valve adjustment parameters. If no correction requirement is triggered, record the first predicted value of the adjustment area of the inlet and outlet valves as the inlet and outlet valve adjustment parameters.

[0026] In this implementation plan, the correction adjustment factor is specifically obtained based on the construction of a non-linear adjustment model. The specific steps for constructing the non-linear adjustment model are as follows: Collect the motor voltage, ambient temperature, rainfall, equipment health, chloride ion concentration, turbidity, and hardness of the water pump pumping station under different working conditions, and record the adjustment area of the inlet and outlet valves corresponding to each working condition at the same time. Clean the collected data to remove noise and outliers, and unify the data format and range to prepare for subsequent modeling. Select a deep learning model, such as a multi-layer perceptron or a long short-term memory network, to build the framework of the non-linear adjustment model. Determine that the input layer of the model is the processed data features, the hidden layer extracts data features through a multi-layer neuron structure, and the output layer is the predicted value of the adjustment area of the inlet and outlet valves. Use the collected data to train the built model. During the training process, use the mean square error loss function to measure the deviation between the predicted valve adjustment area of the model and the actual value. Through the backpropagation algorithm, transmit the deviation information from the output layer back to each layer of neurons, adjust the model parameters, and continuously reduce the value of the loss function until the model converges, so that the model can accurately predict the valve adjustment area. During the training process, fit the corresponding correction adjustment factors for environmental characteristics, equipment status, and water quality factors respectively. By analyzing the relationship between changes in different factors and the valve adjustment area, construct a correction function so that the non-linear adjustment model can correct the prediction results according to the changes of these factors.

[0027] The environmental characteristic correction factor is used to compensate for the impact of environmental changes on the physical properties of water and the operation of the water pump, so as to adjust the valve opening to maintain stable flow; the equipment status correction factor adjusts the valve adjustment range according to the equipment status. The lower the equipment health, the greater the correction amplitude, reducing equipment wear; the water quality factor correction factor is used to reduce the valve opening to reduce the risks of equipment corrosion, blockage, etc. when the water quality indicators exceed the standard; the environmental temperature threshold is the critical temperature value for triggering environmental characteristic correction. When the ambient temperature changes exceed this value, start the environmental characteristic correction requirement.

[0028] The rainfall threshold is obtained in the following way: Determine the rainfall critical value for judging whether rainstorm emergency adjustment is required. When the value is exceeded, adjust the valve opening to cope with the drainage demand, or set it with reference to the local flood control standard, the drainage capacity of the pumping station and other actual situations.

[0029] The equipment health threshold is obtained in the following way: Determine the critical value for judging whether the water pump equipment needs maintenance. When the equipment health is lower than this value, trigger equipment status correction, or obtain it through the vibration spectrum analysis of the equipment and training of historical fault data combined with machine learning algorithms.

[0030] The chloride ion concentration threshold is obtained in the following way: Identify the chloride ion concentration critical value at which the stainless steel material begins to accelerate corrosion. When the value is exceeded, the valve opening needs to be adjusted to protect the equipment, or determine it with reference to the material industry standard and the technical specifications of the stainless steel material supplier.

[0031] The method for obtaining the turbidity threshold is as follows: identify the turbidity critical value that may cause pipeline blockage. When the value is exceeded, the valve opening should be adjusted or the filtration should be strengthened, or it should be determined through hydrodynamic calculation and combined with actual operation experience based on the pipeline inner diameter and the specifications of the pump inlet filter.

[0032] The method for obtaining the hardness threshold is as follows: identify the critical value at which the risk of scaling significantly increases due to the concentration of calcium and magnesium ions in the water. When the value is exceeded, the operating parameters should be adjusted or water quality treatment should be carried out, or it should be determined through saturation index calculation and combined with experimental verification based on conditions such as pipeline material and water temperature.

[0033] The specific steps for integrating the corresponding correction adjustment factor into the first predicted value of the adjustment area of the inlet and outlet valves to obtain the second predicted value of the adjustment area of the inlet and outlet valves are as follows: calculate the deviation values of environmental characteristics, equipment status, and water quality factors respectively. Compare the environmental temperature and rainfall with the corresponding thresholds to calculate the environmental characteristic deviation. Compare the equipment health with the threshold to calculate the equipment status deviation. Compare the chloride ion concentration, turbidity, and hardness with their respective thresholds to calculate the water quality factor deviation. When the environmental characteristic deviation, equipment status deviation, or water quality factor deviation exceeds the set standard, trigger the corresponding correction requirements respectively; according to the type of triggered correction requirements, extract the corresponding correction factors from the pre-trained correction factor library; on the basis of the first predicted value of the valve adjustment area obtained by the model based on the basic operation data, superimpose the correction terms of each correction factor, combine the correction terms with the first predicted value, and obtain the second predicted value of the adjustment area of the inlet and outlet valves after considering the correction.

[0034] The first predicted value of the adjustment area of the inlet and outlet valves represents the predicted value of the valve opening output by the model only based on basic operation data such as motor voltage, without considering the influence of environmental, equipment status, and water quality factors, and reflects the valve adjustment requirements under ideal conditions.

[0035] The second predicted value of the adjustment area of the inlet and outlet valves represents the final predicted value of the valve opening obtained by compensating and correcting the first predicted value by introducing correction factors of environmental, equipment status, and water quality and other factors on the basis of the first predicted value. It comprehensively considers various influencing factors in the actual working conditions and can more accurately guide the valve adjustment compared with the first predicted value of the adjustment area of the inlet and outlet valves, ensuring the stable operation of the pumping station.

[0036] The system automatically adapts to different working conditions by dynamically introducing correction factors based on data on pump operation, environment, equipment status, and water quality. For example, the valve opening is adjusted in real time when the temperature changes, equipment wears out, or water quality deteriorates. Compared with the traditional fixed parameter adjustment method, the adjustment accuracy is improved, and the actual needs of the pump station can be more accurately matched. With the help of the equipment status correction factor, the valve adjustment amplitude can be adjusted according to the health of the equipment. When the health of the equipment decreases, the valve adjustment frequency and amplitude can be reduced to avoid excessive adjustment and cause additional loss to the equipment, thereby effectively extending the service life of the equipment. At the same time, the water quality correction factor can optimize the adjustment when the water quality deteriorates to reduce the risk of equipment corrosion. The environmental characteristic correction factor can reasonably adjust the valve opening according to changes in ambient temperature, rainfall, etc. For example, in hot weather, the adjustment is optimized to reduce the energy consumption of the pump. In heavy rain, the flow rate is automatically increased to avoid water accumulation, achieving the dual effects of energy saving and functional guarantee. By setting a threshold to determine whether to introduce the correction factor, the model maintains stable operation under normal conditions. When the working condition parameters are abnormal, the corresponding correction is activated, which not only ensures the stability of the model, but also can quickly respond to complex and changeable working conditions, enhancing the robustness of the entire regulation system.

[0037] Specifically, the inlet and outlet valve adjustment verification module is specifically analyzed as follows: based on the status parameters monitored in real time by the data acquisition module, a digital model of the water pump station is constructed, the inlet and outlet valve adjustment parameters are input into the digital model of the water pump station, and the valves in the digital model of the water pump station are adjusted according to the inlet and outlet valve adjustment parameters to simulate the state of the water pump station after valve adjustment in actual operation; during the simulation operation, the output simulation adjustment feedback results are monitored and recorded in real time, and the simulation adjustment feedback results include the stable duration of the motor voltage and the pipeline soundprint data, the change value between the motor voltage and the motor voltage obtained by the data acquisition module is identified, and the change value is compared with the optimization threshold. When the change value is lower than the optimization threshold, the particle swarm algorithm is used to adjust the inlet and outlet valve adjustment parameters until the change value is greater than or equal to the optimization threshold to obtain the optimized inlet and outlet valve adjustment parameters.

[0038] In this implementation plan, the steps for constructing the digital model of the pump station are as follows: Based on the CAD drawings of the pump station, use 3D modeling software (such as SolidWorks) to construct the geometric models of equipment such as pumps, valves, pipes, and sensors with an accuracy of up to the millimeter level; define the parameters of key components: the relationship between the valve flow area and the opening degree, the inner diameter and length of the pipe, the impeller size of the pump, etc.; import the real-time parameters of the data acquisition module and establish parameter correlation rules: for example, the ambient temperature affects the water viscosity and corrects the calculation of the Reynolds number; the chloride ion concentration affects the pipeline corrosion rate and adjusts the friction coefficient in the model; according to the adjustment parameters of the inlet and outlet valves, dynamically update the flow area of the valves in the model, integrate the fluid mechanics equation (Navier-Stokes) and the motor characteristic equation (V-I curve) to achieve the coupling simulation of multiple physical fields of electromechanics and hydraulics; input the historical operating condition data, compare the model outputs (such as motor current, vibration spectrum) with the actual monitoring values, and use the orthogonal test method to optimize the model parameters (such as turbulent viscosity coefficient, motor internal resistance) to ensure that the simulation results are consistent with the physical system.

[0039] The method for obtaining the simulation adjustment feedback results is as follows: Input the adjustment parameters of the inlet and outlet valves into the digital model, initialize the boundary conditions, set the simulation time step, and run the model to a steady state; record the simulated values of the motor voltage and the simulated values of the pipeline vibration spectrum in real time, calculate the change value of the motor voltage, and at the same time count the duration from the start of the adjustment to the stabilization of the pipeline vibration spectrum within the safety threshold as the stable duration of the pipeline acoustic fingerprint data.

[0040] The stable duration of the pipeline acoustic fingerprint data represents the time required from the start of the valve adjustment action until the amplitudes of all frequency bands of the pipeline vibration spectrum are stabilized within the safety threshold range, which is used to measure the influence of the adjustment parameters on the pipeline stability. The shorter the stable duration, the faster the pipeline returns to stability after adjustment, and the better the parameters.

[0041] The method for setting the optimization threshold is as follows: Collect the motor voltage fluctuation data under normal operating conditions, calculate the average fluctuation value μ and the standard deviation σ, and set the optimization threshold as μ + 2σ; it is also possible to automatically adjust the threshold when the pump station operating mode switches (such as from the "energy-saving mode" to the "guaranteed supply mode"), relax the threshold to μ + 3σ in the energy-saving mode, and tighten it to μ + σ in the guaranteed supply mode; it is also possible to manually calibrate the threshold in combination with the experience of the pump station engineers. For example, in an old pipeline system, set the threshold to 30% lower than that of the new pipeline system to avoid excessive vibration.

[0042] The specific steps for adjusting the regulation parameters of the inlet and outlet valves using the particle swarm algorithm are as follows: Define the particle position as the regulation parameters of the inlet and outlet valves, and the velocity as the parameter adjustment step size. Randomly generate N particles (e.g., N = 30), calculate the initial fitness value of each particle, and each particle records its own historical optimal position and fitness value. The global optimal position is the position with the minimum fitness value among all particles; Iteratively calculate the particle velocity and update the particle position. When the change value is greater than or equal to the optimization threshold, output the valve opening corresponding to the global optimal position as the optimization parameter.

[0043] Simulate valve regulation through a digital model to avoid equipment damage or operating accidents that may be caused by direct debugging in the physical system, and reduce the debugging risk; Use the particle swarm algorithm to automatically iteratively adjust parameters, which shortens the optimization period and improves the regulation accuracy compared with the manual trial-and-error method; At the same time, verify the motor voltage stability and pipeline acoustic fingerprint data, covering both the electrical performance and mechanical stability dimensions, and avoid the one-sidedness of single-index verification; Update the digital model based on real-time data to adapt to dynamic conditions such as pump station equipment aging and water quality changes, and ensure the long-term effectiveness of the regulation parameters.

[0044] Specifically, the stability threshold verification module is analyzed as follows: The stability threshold verification module also includes constructing a valve-pipeline relationship model, obtaining the opening area of the inlet and outlet valves of the water pump station under different working conditions, the Reynolds number of the water flow in the pipeline, and the pipeline vibration spectrum, and normalizing the obtained data to form a historical data set; Using the Reynolds number of the water flow in the pipeline in the historical data set as the independent variable and the pipeline vibration spectrum as the dependent variable, and using a machine learning algorithm to obtain the water flow-pipeline relationship model; Using the opening area of the inlet and outlet valves in the historical data set as the independent variable and the corresponding Reynolds number of the water flow in the pipeline as the dependent variable, and using a linear regression algorithm to obtain the valve-pipeline relationship model; Set the safety threshold range of the pipeline vibration spectrum. For different opening areas of the inlet and outlet valves, use the valve-pipeline relationship model to identify the corresponding Reynolds number of the water flow in the pipeline, input the Reynolds number of the water flow in the pipeline into the water flow-pipeline relationship model to predict the corresponding pipeline vibration spectrum, and compare the predicted pipeline vibration spectrum with the safety threshold range of the pipeline vibration spectrum band by band. When the vibration amplitude of one of the bands first exceeds the corresponding threshold, record the opening area of the inlet and outlet valves at this time and determine it as the regulation stability threshold of the inlet and outlet valves; Receive the regulation parameters of the inlet and outlet valves output by the non-linear regulation model, combine the valve-pipeline relationship model and the water flow-pipeline relationship model to obtain the corresponding pipeline vibration spectrum, and compare the pipeline vibration spectrum with the pipeline vibration threshold. If there is any band with a vibration amplitude exceeding the corresponding threshold or the stable duration of the pipeline acoustic fingerprint data is lower than the pipeline acoustic fingerprint stability threshold, send a protection mechanism trigger signal.

[0045] In this implementation scheme, the opening area of the inlet and outlet valves is collected in real time through an angle sensor or a displacement sensor installed on the valve actuator, and the actual flow area is calculated in combination with the valve geometric parameters (such as valve disc diameter, opening angle); the Reynolds number of the water flow in the pipeline is measured by an ultrasonic flowmeter to measure the water flow velocity, and in combination with the inner diameter of the pipeline and the fluid viscosity (measured by a viscometer) obtained in real time by the water quality detection module, it is obtained according to the Reynolds number calculation formula; the pipeline vibration spectrum is obtained by installing acceleration vibration sensors at key pipeline nodes (such as upstream and downstream of the valve, elbow), collecting the vibration time-domain signal, and using the fast Fourier transform (FFT) to convert it into a frequency-domain feature, and extracting the vibration amplitude of each frequency band as the spectrum data.

[0046] The steps for constructing the water flow pipeline relationship model are as follows: collect the Reynolds number of the water flow in the pipeline and the pipeline vibration spectrum data under historical working conditions, normalize the Reynolds number (map it to the interval [0,1]), perform noise reduction filtering on the vibration spectrum, and extract the vibration amplitude of the key frequency band of 10 - 500Hz as the feature vector; use support vector regression (SVR), random forest regression or convolutional neural network (CNN) to construct a non-linear mapping model, with the Reynolds number as the input layer and the vibration spectrum feature vector as the output layer, and determine the optimal number of layers and nodes of the hidden layer through cross-validation; use the root mean square error (RMSE) as the loss function, and iteratively adjust the model parameters through the gradient descent algorithm to make the prediction errors of the training set and the validation set less than 5%, and finally form an accurate mapping relationship model of "Reynolds number → vibration spectrum".

[0047] The steps for constructing the relationship model between the opening area of the inlet and outlet valves and the Reynolds number are as follows: record the Reynolds number of the water flow in the pipeline at different valve openings, covering the full range of valve openings from 10% to 100%, and collect at least 50 groups of valid data for each opening; use the least squares method to fit the linear relationship between the valve opening area and the Reynolds number, and construct a linear equation, where the slope and intercept are determined through regression calculation; verify the linear model through on-site measured data.

[0048] The safety threshold range of the pipeline vibration spectrum is based on the pipeline material (such as carbon steel, stainless steel), wall thickness, nominal diameter and design specifications, and sets the safety upper limit of the vibration amplitude of each frequency band as the benchmark for judging whether the pipeline is stable. Specifically: under working conditions such as pipeline no-load, rated load, overload, etc., obtain the natural frequency of the pipeline and the safety limit of the vibration amplitude of each frequency band through excitation experiments; or refer to the historical pipeline vibration data of similar pump stations, and combine fatigue life analysis to correct the experimental threshold to form a three-frequency band safety threshold range including 10 - 50Hz (low-frequency vibration, pay attention to structural resonance), 50 - 200Hz (medium-frequency vibration, pay attention to fluid pulsation), 200 - 500Hz (high-frequency vibration, pay attention to cavitation noise).

[0049] The steps for comparing the predicted pipeline vibration spectrum with the safety threshold range of the pipeline vibration spectrum band by band are as follows: decompose the predicted pipeline vibration spectrum into three frequency bands of 10 - 50 Hz, 50 - 200 Hz, and 200 - 500 Hz, and extract the maximum vibration amplitude of each frequency band; compare the amplitude of each frequency band with the corresponding safety threshold range (for example, low frequency band ≤ 0.3g, middle frequency band ≤ 0.5g, high frequency band ≤ 0.8g) point by point; if the amplitude of any frequency band exceeds the corresponding threshold, mark it as "abnormal stability"; if all frequency bands are within the threshold, mark it as "stable".

[0050] The reason why the critical valve adjustment area cannot be directly compared in this implementation plan is that the relationship between the water flow Reynolds number and pipeline vibration is not a simple linear one, but is affected by multiple factors such as the natural frequency of the pipeline, the turbulent characteristics of the fluid, and the flow resistance characteristics of the valve. It is necessary to capture the non - linear mapping relationship through a machine learning model. This implementation plan uses a composite architecture of rapid linear mapping by a linear model and precise prediction by machine learning to solve the one - sidedness of traditional single - linear judgment, constructs a complete risk assessment system covering "adjustment parameters → water flow characteristics → structural response", and improves the scientificity and reliability of pipeline stability judgment.

[0051] By constructing a linear model of "valve opening - Reynolds number" and a machine learning model of "Reynolds number - vibration spectrum", a complete mapping relationship of "valve adjustment → water flow characteristics → pipeline vibration" is formed. Compared with traditional single - linear judgment, it can more comprehensively evaluate the impact of valve adjustment on pipeline stability and avoid misjudgment caused by ignoring the characteristics of the vibration spectrum; based on historical data to train the model, it can identify in advance the pipeline vibration risk when the valve opening exceeds the safety threshold, trigger the protection mechanism before the water flow fluctuation causes pipeline resonance or structural damage, and reduce the accident probability; for different working conditions (such as sudden change in flow rate, change in water quality), the model can continuously optimize the threshold through real - time data update to solve the problem that traditional fixed thresholds cannot adapt to complex working conditions and improve the stability of the system under extreme conditions.

[0052] Specifically, the protection adjustment module is analyzed as follows: receive the protection mechanism trigger signal, identify the water flow Reynolds number distribution and pipeline vibration response under different steady - flow parameters of the dynamic steady - flow device, and determine the steady - flow parameters of the dynamic steady - flow device with the minimum pipeline vibration amplitude and stable water flow Reynolds number as the goals. The steady - flow parameters are specifically the opening of the dynamic steady - flow device.

[0053] In this implementation scheme, based on the Navier-Stokes equations, combined with the topological structure of the pump station pipeline (pipe diameter, elbow, valve position, etc.) and fluid physical property parameters (density, viscosity), a three-dimensional transient flow field model is constructed to simulate the water flow characteristics and pipeline vibration response under different opening degrees of the flow stabilization device. The construction steps are as follows: According to the pump station CAD drawings, a three-dimensional geometric model including pumps, valves, pipelines, and flow stabilization devices is constructed, and the grid is encrypted in key areas (such as the inlet and outlet of valves, elbows); the physical property parameters such as the density and viscosity of the fluid medium (such as water) are set, the boundary conditions (inlet flow rate, outlet pressure) and material properties (pipe elastic modulus, Poisson's ratio) are defined; the Navier-Stokes equations are discretized by the finite volume method, the k-ε turbulence model is used to close the equations, and the time step is set to 0.01 s to capture the transient flow characteristics; the accuracy of the model is verified through experimental data (such as PIV flow velocity measurement, strain gauge vibration monitoring), and the turbulence model parameters are reduced to minimize the error between the simulation results and the measured values.

[0054] The steps to identify the water flow Reynolds number distribution and pipeline vibration response under different flow stabilization parameters of the dynamic flow stabilization device are as follows: Set the opening degree of the dynamic flow stabilization device as a variable parameter, and establish a parameterized fluid dynamics model library; for each opening degree of the flow stabilization device, input the real-time measured water flow Reynolds number and vibration spectrum as boundary conditions, run the fluid dynamics model, and obtain the distribution of the flow velocity field and pressure field in the pipeline; through the fluid-structure interaction algorithm, map the fluid pressure load to the pipeline structure model, calculate the pipeline vibration frequency and amplitude at each opening degree, and extract the vibration response characteristics in the frequency band of 10 - 500 Hz; establish a three-dimensional mapping relationship between the opening degree of the flow stabilization device, the Reynolds number distribution, and the vibration spectrum to form an "opening degree - Reynolds number - vibration response" database.

[0055] The opening degree of the dynamic flow stabilization device represents the ratio of the flow area of the flow stabilization device to the maximum flow area, which is controlled by an electric actuator and directly affects the fluid flow resistance and flow field distribution. The actual opening degree of the valve is obtained in real time through an angle encoder or a linear displacement sensor installed on the actuator, or the opening degree command value is read from the PLC control system through the Modbus / TCP protocol, and cross-verified with the sensor measurement value to ensure accuracy.

[0056] Calculating the optimal opening degree of the flow stabilization device through the fluid dynamics model can reduce the pipeline vibration amplitude compared with traditional empirical regulation, and reduce the pipeline fatigue damage caused by unstable water flow; the model can analyze the changing trends of the water flow Reynolds number and vibration spectrum in real time, and can adjust the parameters of the flow stabilization device when the working conditions change suddenly (such as rapid opening and closing of valves, flow rate fluctuations), improving the response speed compared with traditional PID control; minimizing the vibration amplitude and stabilizing the Reynolds number can not only ensure the safety of the pipeline structure, but also maintain the fluid transportation efficiency, avoiding the system imbalance caused by traditional methods only focusing on a single index.

[0057] Please refer toFigure 2 , a method for regulating the operation of a water pump pumping station, which applies the above-mentioned device for regulating the operation of a water pump pumping station, includes the following steps: Step S1, monitor and obtain the condition parameters of the water pump pumping station in real time. The condition parameters include operation data, environmental characteristics, equipment status data, water quality data, water flow data, and pipeline acoustic fingerprint data; Step S2, output a first prediction result through the operation data of the water pump pumping station, and judge whether it is necessary to correct the first prediction result based on the environmental characteristics, equipment status data, and water quality data to obtain the inlet and outlet valve regulation parameters; Step S3, input the inlet and outlet valve regulation parameters into the digital model of the water pump pumping station to obtain a simulated regulation feedback result, and use the simulated regulation feedback result to optimize the inlet and outlet valve regulation parameters; Step S4, determine the inlet and outlet valve regulation stability threshold based on the relationship between the water flow data and the pipeline acoustic fingerprint data, use the inlet and outlet valve regulation stability threshold for relationship feedback verification, and judge whether to trigger the protection mechanism based on the simulated regulation feedback result and the relationship feedback verification result; Step S5, when the protection mechanism is triggered, start the dynamic flow stabilization device, and adjust the flow stabilization parameters of the dynamic flow stabilization device according to the water flow data and the pipeline acoustic fingerprint data.

[0058] In summary, the present application has at least the following effects:

[0059] By constructing a digital model of the water pump pumping station and simulating the valve regulation effect in a virtual environment, compared with traditional physical tests, the rationality of the regulation parameters can be verified in advance, the trial-and-error cost can be reduced, and the regulation optimization cycle can be shortened; by combining the simulated regulation feedback result and the stability threshold verification, both the economy and safety of the valve regulation are taken into account, achieving a balance between the two goals. On the premise of ensuring that the pipeline vibration amplitude is lower than the safety threshold, the energy efficiency of the pumping station is improved; based on the correlation analysis of real-time water flow data and pipeline acoustic fingerprint data, when potential risks are detected, the system timely triggers the protection mechanism to improve the response speed; the digital model continuously absorbs actual operation data for iterative optimization, enabling the regulation strategy to adaptively adjust with the aging of the pumping station equipment and environmental changes, and extending the service life of the equipment.

[0060] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods and systems. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0061] The present invention is described with reference to the flowcharts and block diagrams of methods and systems according to embodiments of the present invention. It should be understood that each combination of the processes and modules in the flowcharts and block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in one process Figure 1 one process or multiple processes and architectures Figure 1 or multiple modules.

[0062] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one process Figure 1 one process or multiple processes and architectures Figure 1 or multiple modules.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operating steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and architectures Figure 1 or multiple modules.

[0064] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0065] Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A running regulation device for a water pump pumping station, characterized in that, Including: A data acquisition module for real-time monitoring and obtaining the condition parameters of the water pump pumping station, where the condition parameters include operation data, environmental characteristics, equipment status data, water quality data, water flow data, and pipeline acoustic fingerprint data; An adjustment judgment module for outputting a first prediction result through the operation data of the water pump pumping station, and judging whether the first prediction result needs to be corrected based on the environmental characteristics, equipment status data, and water quality data to obtain the inlet and outlet valve adjustment parameters; An adjustment verification module that inputs the inlet and outlet valve adjustment parameters into the digital model of the water pump pumping station to obtain a simulated adjustment feedback result, and uses the simulated adjustment feedback result to optimize the inlet and outlet valve adjustment parameters; A stability threshold verification module for determining the inlet and outlet valve adjustment stability threshold based on the relationship between the water flow data and the pipeline acoustic fingerprint data, using the inlet and outlet valve adjustment stability threshold for relationship feedback verification, and judging whether to trigger the protection mechanism through the simulated adjustment feedback result and the relationship feedback verification result; The stability threshold verification module further includes constructing a valve-pipeline relationship model, obtaining the opening area of the inlet and outlet valves of the water pump pumping station, the Reynolds number of the water flow in the pipeline, and the pipeline vibration spectrum under different working conditions, and normalizing the obtained data to form a historical data set; Using the Reynolds number of the water flow in the pipeline in the historical data set as the independent variable and the pipeline vibration spectrum as the dependent variable, and adopting a machine learning algorithm to obtain a water flow-pipeline relationship model; Using the opening area of the inlet and outlet valves in the historical data set as the independent variable and the corresponding Reynolds number of the water flow in the pipeline as the dependent variable, and adopting a linear regression algorithm to obtain a valve-pipeline relationship model; Setting a safety threshold range for the pipeline vibration spectrum, identifying the corresponding Reynolds number of the water flow in the pipeline using the valve-pipeline relationship model for different opening areas of the inlet and outlet valves, inputting the Reynolds number of the water flow in the pipeline into the water flow-pipeline relationship model to predict the corresponding pipeline vibration spectrum, comparing the predicted pipeline vibration spectrum with the safety threshold range of the pipeline vibration spectrum band by band, and when the vibration amplitude of one of the bands first exceeds the corresponding threshold, recording the opening area of the inlet and outlet valves at this time and determining it as the inlet and outlet valve adjustment stability threshold; Receiving the inlet and outlet valve adjustment parameters output by the non-linear adjustment model, combining the valve-pipeline relationship model and the water flow-pipeline relationship model to obtain the corresponding pipeline vibration spectrum, comparing the pipeline vibration spectrum with the pipeline vibration threshold, and if there is any band with a vibration amplitude exceeding the corresponding threshold or the stable duration of the pipeline acoustic fingerprint data is lower than the pipeline acoustic fingerprint stability threshold, sending a protection mechanism trigger signal; A protection adjustment module that starts the dynamic flow stabilization device when the protection mechanism is triggered, and adjusts the flow stabilization parameters of the dynamic flow stabilization device according to the water flow data and the pipeline acoustic fingerprint data.

2. The operation adjustment device for a water pump pumping station according to claim 1, characterized in that The operation data of the water pump pumping station is specifically the motor voltage, the environmental characteristics specifically include the environmental temperature and rainfall, the equipment status data is specifically the equipment health, the water quality data is specifically the chloride ion concentration, turbidity, and hardness, the water flow data is specifically the Reynolds number of the water flow, and the pipeline acoustic fingerprint data is specifically the pipeline vibration spectrum.

3. The operation regulation device of the water pump pumping station according to claim 1, characterized in that, The specific steps of outputting the first prediction result through the operation data of the water pump station are: obtaining the operation data of the water pump station under different working conditions and the inlet and outlet valve adjustment parameters corresponding to the different working conditions, the inlet and outlet valve adjustment parameters are specifically the inlet and outlet valve adjustment areas, synchronizing the operation data with the inlet and outlet valve adjustment parameters in time, identifying the influence relationship between the operation data and the inlet and outlet valve adjustment parameters, and obtaining the first prediction value of the inlet and outlet valve adjustment area based on the influence relationship between the operation data and the inlet and outlet valve adjustment parameters.

4. The operation regulation device for a water pump pumping station according to claim 3, characterized in that, Determine whether it is necessary to correct the first prediction result, and obtain the specific analysis of the inlet and outlet valve adjustment parameters as follows: obtain environmental characteristics, equipment status data and water quality data under different working conditions, synchronize the operation data, environmental characteristics, equipment status data, water quality data and the inlet and outlet valve adjustment parameters, and use deep learning to train the time-synchronized parameters to obtain correction adjustment factors, wherein the correction adjustment factors include environmental characteristic correction factors, equipment status correction factors and water quality factor correction factors; Obtaining the ambient temperature threshold, rainfall threshold, equipment health threshold, chloride ion concentration threshold, turbidity threshold, and hardness threshold, respectively comparing the environmental characteristics, equipment status data, and water quality data with the corresponding thresholds, and judging whether to trigger correction requirements based on the comparison results, the correction requirements include environmental characteristics correction requirements, equipment status correction requirements, and water quality factor correction requirements; Statistically trigger the correction demand type, integrate the corresponding correction adjustment factor into the first predicted value of the inlet and outlet valve regulating area to obtain the second predicted value of the inlet and outlet valve regulating area, record the second predicted value of the inlet and outlet valve regulating area as the inlet and outlet valve regulating parameter, if there is no triggering of the correction demand, record the first predicted value of the inlet and outlet valve regulating area as the inlet and outlet valve regulating parameter.

5. The operation regulation device of the water pump pumping station according to claim 2, characterized in that The inlet and outlet valve adjustment verification module is specifically analyzed as follows: a water pump station digital model is constructed based on the status parameters monitored in real time by the data acquisition module, the inlet and outlet valve adjustment parameters are input into the water pump station digital model, and the valves in the water pump station digital model are adjusted according to the inlet and outlet valve adjustment parameters to simulate the state of the water pump station after valve adjustment in actual operation; During the simulation operation, the output simulation adjustment feedback results are monitored and recorded in real time, including the stable duration of the motor voltage and the pipeline soundprint data, and the change value between the motor voltage and the motor voltage obtained by the data acquisition module is identified. The change value is compared with the optimization threshold. When the change value is lower than the optimization threshold, the particle swarm algorithm is used to adjust the inlet and outlet valve adjustment parameters until the change value is greater than or equal to the optimization threshold to obtain the optimized inlet and outlet valve adjustment parameters.

6. The operation adjustment device for a water pump pumping station according to claim 5, wherein The protection adjustment module is specifically analyzed as follows: receiving a protection mechanism trigger signal, identifying the water flow Reynolds number distribution and pipeline vibration response of the dynamic flow stabilizing device under different flow stabilizing parameters, and determining the flow stabilizing parameters of the dynamic flow stabilizing device with the minimum pipeline vibration amplitude and stable water flow Reynolds number as the goal. The flow stabilizing parameters are specifically the opening of the dynamic flow stabilizing device.

7. Method for regulating the operation of a water pump pumping station, applying the water pump pumping station operation regulating device according to any one of claims 1-6, characterized in that, The following steps are involved: Step S1, monitor and obtain the condition parameters of the water pump pumping station in real time, where the condition parameters include operation data, environmental characteristics, equipment status data, water quality data, water flow data, and pipeline acoustic fingerprint data; Step S2, output a first prediction result based on the operation data of the water pump pumping station, and determine whether it is necessary to correct the first prediction result based on the environmental characteristics, equipment status data, and water quality data to obtain the inlet and outlet valve adjustment parameters; Step S3, input the inlet and outlet valve adjustment parameters into the digital model of the water pump pumping station to obtain a simulated adjustment feedback result, and use the simulated adjustment feedback result to optimize the inlet and outlet valve adjustment parameters; Step S4, determine the inlet and outlet valve adjustment stability threshold based on the relationship between the water flow data and the pipeline acoustic fingerprint data, perform relationship feedback verification using the inlet and outlet valve adjustment stability threshold, and determine whether to trigger the protection mechanism based on the simulated adjustment feedback result and the relationship feedback verification result; Step S5, when the protection mechanism is triggered, start the dynamic flow stabilization device, and adjust the flow stabilization parameters of the dynamic flow stabilization device according to the water flow data and the pipeline acoustic fingerprint data.

Images