An automatic adjustment method and system for pump water pumping to prevent disturbance of the river bottom mud

Abstract

The present invention relates to the field of automatic river pumping, and specifically to a method and system for automatically adjusting the pumping of a water pump to prevent the disturbance of the river mud bottom. The method includes obtaining pumping data related to the mud bottom disturbance, evaluating the impact of pumping on the river bottom mud according to the pumping data to obtain the disturbance degree; obtaining a sample set according to the pumping data and the disturbance degree; constructing a prediction model for the water pump inlet, and setting a loss function for the prediction model of the water pump inlet according to the disturbance degree; training and evaluating the prediction model of the water pump inlet by using the sample set; predicting by using the prediction model of the water pump inlet, and automatically adjusting the water inlet and power of the water pump according to the prediction result. The present invention solves the problem of heavy metal pollution of farmland caused by the ineffective control of mud bottom disturbance during pumping in the prior art. It realizes automatic pumping and improves the pumping efficiency through a scientific method.

Description

Technical Field

[0001] The present invention relates to the field of automatic pumping of river channels, and specifically to a method and system for automatic adjustment of water pumping by a water pump to prevent disturbance of the river bottom mud. Background Art

[0002] In agricultural production, river water is one of the important irrigation water sources. The water quality of many river channels can meet the requirements of the "Irrigation Water Quality Standard for Farmland" (GB 5084-2021), providing necessary water support for the growth of crops and ensuring the basic production activities of agriculture. However, the problem of river pollution cannot be ignored, especially heavy metal pollution. After heavy metals enter the river through ways such as wastewater discharge, soil erosion, and rainwater scouring, they will gradually accumulate in the bottom mud through precipitation or particulate adsorption. This creates a situation where the river water can meet the farmland irrigation water quality standard, but the heavy metals in the river bottom mud have seriously exceeded the "Soil Environmental Quality - Risk Control Standards for Soil Pollution of Agricultural Land (Trial)" (GB 15618-2018). Bottom mud pollution is a relatively common environmental problem and one of the main difficulties in the treatment of river and lake pollution. The polluted bottom mud is large in quantity, wide in area, high in cost, and difficult to treat. It is even more impossible to detect or treat all of it in a timely manner. Therefore, it is particularly important to prevent polluted bottom mud from entering farmland.

[0003] When pumping water from a river channel to irrigate farmland, a key problem emerges, that is, how to prevent bottom mud disturbance. On the one hand, once the heavy metals enriched in the bottom mud are disturbed, it is easier for them to re-enter the water body. On the other hand, the disturbed bottom mud will be pumped out along with the irrigation water and enter the farmland during the irrigation process. In the prior art, it is difficult to effectively control bottom mud disturbance during the pumping process. Common pumping equipment, such as water pumps, will generate the suction and stirring effects of water flow during operation. When the water inlet of the water pump is close to the bottom mud, or the pumping flow rate is too large or the flow velocity is too fast, the impact force of the water flow will drive the bottom mud and make it suspended in the water.

[0004] In addition, some traditional pumping methods lack targeted designs for protecting the bottom mud and do not fully consider the potential hazards brought by bottom mud disturbance. For example, when installing a pumping device at the bottom of a river channel, no reasonable protective measures are set, resulting in inevitable flipping of the bottom mud during the pumping process.

[0005] The consequences caused by this bottom mud disturbance are very serious. After the irrigation water containing polluted bottom mud enters the farmland, heavy metals will gradually accumulate in the soil, changing the physical and chemical properties of the soil and reducing soil fertility. At the same time, crops will absorb heavy metals in the soil, resulting in excessive heavy metal content in agricultural products, which not only affects the growth and quality of crops but also harms human health through the food chain.

[0006] Therefore, it is urgent to develop a technology that can effectively control bottom sediment disturbance during river channel pumping irrigation, which is of great significance for ensuring the soil quality of farmland and the safety of agricultural products and realizing the sustainable development of agriculture. Summary of the Invention

[0007] Aiming at the defects in the prior art, the present invention provides a method and system for automatically adjusting the pumping of a water pump to prevent bottom sediment disturbance in a river channel, solving the problem of heavy metal pollution in farmland caused by the inability to effectively control bottom sediment disturbance during pumping in the prior art.

[0008] To achieve the above object, an aspect of the present invention provides a method for automatically adjusting the pumping of a water pump to prevent bottom sediment disturbance in a river channel, the method comprising: obtaining pumping data related to bottom sediment disturbance, and evaluating the impact of pumping on the bottom sediment of the river channel according to the pumping data to obtain the degree of disturbance; obtaining a sample set according to the pumping data and the degree of disturbance; constructing a prediction model for the water pump inlet, and setting a loss function for the prediction model of the water pump inlet according to the degree of disturbance; training and evaluating the prediction model of the water pump inlet by using the sample set; using the prediction model of the water pump inlet to make a prediction, and automatically adjusting the water pump inlet and power according to the prediction result.

[0009] The present invention obtains pumping data related to bottom sediment disturbance, evaluates the impact of pumping on the bottom sediment of the river channel to obtain the degree of disturbance, and then constructs a sample set, providing a key data basis for subsequent research. Constructing a prediction model for the water pump inlet and setting a loss function according to the degree of disturbance enable the model to more accurately reflect the actual situation and improve the prediction accuracy. Using the trained model to make a prediction and automatically adjusting the water pump inlet and power accordingly, realizing the dynamic adjustment of the water pump pumping port and power under the condition of preventing bottom sediment disturbance.

[0010] Optionally, the obtaining of the pumping data related to bottom sediment disturbance includes: conducting a pumping test and detecting the bottom sediment of the river channel to obtain initial data; performing a correlation analysis on the initial data to obtain core parameters of bottom sediment disturbance; screening the initial data by using the core parameters of bottom sediment disturbance to obtain the pumping data related to bottom sediment disturbance.

[0011] The present invention obtains the core parameters of bottom sediment disturbance through a correlation analysis of the initial data, accurately extracts the key elements that play a key role in bottom sediment disturbance, helps to focus on the key research direction, avoids blindly groping in a large amount of data, reduces the data calculation amount, and makes the present invention more scientific, accurate and efficient in the actual application process.

[0012] Optionally, the correlation analysis of the initial data to obtain the core parameters of sediment disturbance includes: obtaining the sediment disturbance parameters according to the initial data; calculating the correlation coefficients between the sediment disturbance parameters, and constructing a theoretical correlation coefficient matrix according to the correlation coefficients; performing eigenvalue decomposition on the theoretical correlation coefficient matrix to obtain eigenvectors and eigenvalues; calculating the contribution degrees of the sediment disturbance parameters on the eigenvectors according to the eigenvectors and the eigenvalues; and screening the sediment disturbance parameters by using the contribution degrees to obtain the core parameters of sediment disturbance.

[0013] By calculating the correlation coefficients and constructing a theoretical correlation coefficient matrix, the present invention can intuitively show the degree of association between parameters, which helps to insight into the internal structure of the data. Using eigenvalue decomposition to obtain eigenvectors and eigenvalues can effectively mine the potential information in the data. By calculating the contribution degrees of the sediment disturbance parameters on the eigenvectors, the influence of each parameter on the overall disturbance situation can be quantified, realizing the accurate extraction of key information from complex data and improving the accuracy of screening the core parameters of sediment disturbance.

[0014] Optionally, the obtaining of the sample set according to the pumping data and the disturbance degree includes: removing outliers and imputing missing values from the pumping data and the disturbance degree to obtain first optimized data; performing normalization processing on the first optimized data to obtain second optimized data; constructing an adversarial network model, and generating enhanced data according to the second optimized data and the adversarial network model; and merging the second optimized data and the enhanced data to obtain the sample set.

[0015] By removing outliers and imputing missing values from the pumping data and the disturbance degree, the present invention can effectively purify the data, avoid misleading of subsequent analysis by abnormal data, fill in the missing information, ensure the integrity and reliability of the data, and provide a solid data basis for the research. Normalization processing converts the first optimized data into a unified scale, making different features in a comparable range, which helps to improve the convergence speed and prediction accuracy of the model and avoid model training deviation caused by data scale differences. Constructing an adversarial network model to generate enhanced data further expands the diversity of samples, alleviates the problems of insufficient sample quantity or uneven distribution, and reduces the cost of the pumping test.

[0016] Optionally, the setting of the loss function for the water pump inlet prediction model according to the disturbance degree includes: sampling and detecting the heavy metal content at the water outlet of the water pump based on the pumping test; evaluating the disturbance of the river bottom sediment according to the results of the sampling and detection to obtain the maximum acceptable sediment disturbance degree when the water pump pumps water; and setting the loss function for the water pump inlet prediction model according to the maximum acceptable sediment disturbance degree and the disturbance degree.

[0017] According to the maximum acceptable heavy metal content in farmland, the heavy metal content at the water outlet of the water pump is detected, the pumping data corresponding to the maximum acceptable heavy metal content is determined, and the maximum sediment disturbance degree corresponding to the pumping data is further calculated. A loss function is set based on the maximum sediment disturbance degree and the actual disturbance degree, enabling the water pump inlet prediction model to be closely combined with the actual environmental requirements. During the training process of the water pump inlet prediction model, the loss function guides the model to optimize in the direction of reducing the deviation between the actual disturbance degree and the maximum acceptable disturbance degree, prompting the prediction result of the water pump inlet prediction model to be more in line with the ecological safety standard, accelerating the training speed of the water pump inlet prediction model, and improving the prediction effect of the water pump inlet prediction model.

[0018] Optionally, the step of using the water pump inlet prediction model to make a prediction and automatically adjusting the water inlet and power of the water pump according to the prediction result includes: obtaining real-time monitoring data, and using the water pump inlet prediction model to make a prediction according to the real-time monitoring data; obtaining the real-time distance from the water inlet to the water surface, and automatically adjusting the water inlet and power of the water pump according to the real-time distance and the prediction result.

[0019] By obtaining real-time monitoring data and making predictions with the aid of a prediction model, the present invention can grasp the relevant states and trends during the operation of the water pump in real time, providing an accurate basis for subsequent adjustment. Combining the distance information from the water inlet to the water surface enables more scientific and reasonable automatic adjustment of the water inlet and power of the water pump, improving the operating efficiency of the water pump.

[0020] Optionally, the step of automatically adjusting the water inlet and power of the water pump according to the real-time distance and the prediction result includes: setting the minimum distance from the water inlet of the water pump to the water surface during normal operation of the water pump as a threshold according to the working conditions of the water pump; automatically adjusting the water inlet and power of the water pump according to the distance and the threshold.

[0021] The present invention incorporates the minimum distance from the water inlet to the water surface when the water pump can operate normally into the adjustment basis of the water inlet, avoiding faults such as cavitation caused by the water inlet being too close to the water surface. At the same time, it can also prevent the water inlet from jumping out of the water surface under the action of automatic adjustment, resulting in ineffective work, prolonging the service life of the water pump, reducing the maintenance cost, and improving the feasibility and applicability of the present invention.

[0022] Optionally, the disturbance degree satisfies the following formula:

[0023] ,

[0024] where is the sediment bottom disturbance degree, is the comprehensive correction coefficient, is the pumping power of the water pump, is the distance from the water inlet of the water pump to the mud bottom, is the water flow velocity in the river channel, is the acceleration due to gravity, is the average diameter of the mud bottom particles, is the density of the mud bottom, is the density of the river water, is the water flow velocity at the water inlet.

[0025] The disturbance degree formula of the present invention comprehensively considers many key factors such as the pumping power of the water pump, the distance from the water inlet to the mud bottom, and the water flow velocity in the river channel, improving the accuracy of calculating the bottom mud disturbance degree.

[0026] Optionally, the loss function satisfies the following formula:

[0027] ,

[0028] wherein, is the loss function, is the number of samples, is the th sample of the bottom mud disturbance degree, is the maximum acceptable bottom mud disturbance degree when the water pump is pumping water.

[0029] By calculating the difference between the sample bottom mud disturbance degree and the maximum acceptable bottom mud disturbance degree, the present invention provides a clear optimization direction for the training of the water pump inlet prediction model. At the same time, the formula structure is simple and easy to calculate.

[0030] Another aspect of the present invention also provides a water pump pumping automatic adjustment system for preventing river channel mud bottom disturbance. The system includes: a processor, an input device, an output device, and a memory. The processor, the input device, the output device, and the memory are interconnected. Among them, the memory is used to store a computer program, and the computer program includes program instructions. The processor is configured to call the program instructions to execute any one of the water pump pumping automatic adjustment methods for preventing river channel mud bottom disturbance provided in the previous aspect of the present invention.

[0031] The water pump pumping automatic adjustment system for preventing river channel mud bottom disturbance of the present invention has a compact structure, stable performance, high integration, and simple composition, and can stably execute the water pump pumping automatic adjustment method for preventing river channel mud bottom disturbance provided in the previous aspect of the present invention, further improving the overall applicability and practical application ability of the present invention. Description of the Drawings

[0032] Figure 1 is a flowchart of a water pump pumping automatic adjustment method for preventing river channel mud bottom disturbance according to an embodiment of the present invention;

[0033] Figure 2 Schematic structural diagram of a pump water extraction automatic regulation system for preventing river mud bottom disturbance according to an embodiment of the present invention. Specific embodiments

[0034] Specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described here are only for illustrative purposes and do not limit the present invention. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to those of ordinary skill in the art that: these specific details need not be employed to practice the present invention. In other instances, well-known circuits, software, or methods have not been specifically described in order to avoid obscuring the present invention.

[0035] Throughout the specification, references to "one embodiment", "an embodiment", "an example", or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Thus, the phrases "in one embodiment", "in an embodiment", "an example", or "an example" appearing throughout the specification do not necessarily all refer to the same embodiment or example. Additionally, the specific features, structures, or characteristics may be combined in any suitable combination and / or sub-combination in one or more embodiments or examples. Further, those of ordinary skill in the art will understand that the diagrams provided herein are for illustrative purposes and are not necessarily drawn to scale.

[0036] Figure 1 Flowchart of a pump water extraction automatic regulation method for preventing river mud bottom disturbance according to an embodiment of the present invention. In order to solve the problem of ineffective control of bottom mud disturbance during water extraction in the prior art, which causes heavy metal pollution in farmland, as Figure 1 The method shown includes the following steps:

[0037] Step S1, obtain pumping data related to mud bottom disturbance, and evaluate the impact of pumping on the river bottom mud according to the pumping data to obtain the disturbance degree.

[0038] Among them, the obtaining of the pumping data related to mud bottom disturbance specifically includes the following sub-steps:

[0039] Step S101, conduct a pumping test and detect the river bottom mud to obtain initial data.

[0040] In this embodiment, to ensure the scientificity and efficiency of the pumping operation, it is necessary to carefully determine the key parameters of the initial data based on the empirical method and data investigation. These parameters cover the river flow velocity, river water temperature, density of river water, density of sediment, average size of sediment particles, pump power, and diameter of the pump inlet, etc. Each parameter plays a crucial role in the subsequent planning and implementation of the pumping operation. They are interrelated and jointly affect the pumping effect and efficiency.

[0041] Currently, the water demand of farmland urgently needs to be alleviated. To meet this urgent need, it is necessary to carefully plan the water diversion channels according to the distribution of farmland and its relative position to the river. And in the process of planning the water diversion channels, comprehensive and detailed preliminary preparation work is essential. For example, conduct a detailed survey of the selected extraction points. Understanding the geological structure helps to judge the bearing capacity of the soil and its impact on the stability of pump installation; clarifying the distribution of aquifers is related to the sustainability of the water source and the water volume recharge situation; mastering the river topography and geomorphology can help planners reasonably layout the pumps and pipelines, avoiding water flow blockage or equipment damage caused by factors such as terrain undulation.

[0042] At the same time, a preliminary assessment of the hydrogeological conditions of the extraction points is also a key link. The water level height determines the installation height of the pump and the pumping head. The quality of the water directly affects the quality of agricultural irrigation and the service life of the pump. Determining the water flow direction helps to reasonably plan the direction of the water diversion channel to ensure that the water source can be smoothly introduced into the farmland. Through the comprehensive consideration and analysis of these factors, a solid foundation is laid for the subsequent stable and efficient pumping operation.

[0043] After in-depth investigation and scientific demonstration by relevant units, fully considering the actual water demand of local farmland, it is finally decided to carefully select 4 most suitable pumping points from the numerous screened pumping points to install pumps. After multiple comparisons and weighings, a centrifugal pump of model IS200-150-315 is selected. This type of centrifugal pump has excellent performance, with a maximum power of up to 110 kilowatts, which can provide strong power support. Its inlet diameter is 0.2 meters, and the flow rate range is between 12.5 cubic meters per hour and 400 cubic meters per hour, and the head range is from 8 meters to 125 meters. It can flexibly adjust the pumping parameters according to different irrigation requirements, fully meeting the diverse water use requirements of farmland.

[0044] After selecting the water pump, connecting the pumping pipeline system becomes an important task. This system includes a suction pipe and a discharge pipe, each with its own function. The suction pipe needs to have good sealing performance to prevent air from entering and affecting the water suction efficiency. At the same time, the pipe diameter should be large enough to ensure the smooth intake of water flow. The discharge pipe, on the other hand, needs to be reasonably set with an appropriate length and pipe diameter according to the actual test requirements to ensure that the water flow can be discharged unobstructed and smoothly transported to the farmland. In addition, necessary valves and connectors need to be installed in the entire pipeline system. The valves are used to flexibly control the on / off and flow rate of the water flow, facilitating adjustment according to the actual irrigation situation. The connectors ensure the stable connection of the pipeline system, facilitating later equipment maintenance and repair work, and ensuring the long-term stable operation of the entire pumping system.

[0045] After all the installation work is completed, a pumping test is carried out. By adjusting the different positions of the water inlet, different pumping parameters are obtained respectively. And the river channel data is detected. Using a propeller-type current meter, the water flow velocity can be calculated by measuring the rotation speed of the propeller and combining relevant formulas. Using an electronic thermometer to measure the temperature of the river water, using a densitometer to measure the density of the river water, using the ring knife method to measure the density of the river bottom mud, and using a laser particle size analyzer to measure the average diameter of the mud bottom particles.

[0046] Finally, all the parameters are integrated to form the initial data.

[0047] Step S102, perform a correlation analysis on the initial data to obtain the core parameters of sediment disturbance.

[0048] Among them, the specific steps of performing a correlation analysis on the initial data to obtain the core parameters of sediment disturbance are as follows:

[0049] Step S10201, obtain the sediment disturbance parameters according to the initial data.

[0050] In this embodiment, according to the type of the initial data, each type corresponds to a parameter, and then the obtained parameters are integrated to form the sediment disturbance parameters.

[0051] Step S10202, calculate the correlation coefficients between the sediment disturbance parameters, and construct a theoretical correlation coefficient matrix according to the correlation coefficients.

[0052] In this embodiment, first calculate the correlation coefficients between the sediment disturbance parameters to obtain the correlation coefficients, and construct a theoretical correlation coefficient matrix according to the correlation coefficients.

[0053] The correlation coefficient satisfies the following formula:

[0054] ,

[0055] Among them, is the sediment disturbance parameter and the sediment disturbance parameter The correlation coefficient between is the number of observations of the sediment disturbance parameter is the sediment disturbance parameter the th observation value is the sediment disturbance parameter the average value is the sediment disturbance parameter the th observation value is the sediment disturbance parameter the average value

[0056] The correlation coefficient reflects the strength and direction of the linear relationship between two sediment disturbance parameter variables, and its value range is , if the correlation coefficient is close to 1, it indicates that the two sediment disturbance parameters are strongly positively correlated; if the correlation coefficient is close to -1, it is strongly negatively correlated; if the correlation coefficient is close to 0, it means that the linear relationship between the two sediment disturbance parameter variables is weak

[0057] According to the calculated correlation coefficients, the correlation coefficients between each sediment disturbance parameter and other sediment disturbance parameters are arranged in sequence to construct a theoretical correlation coefficient matrix. The main diagonal elements of the theoretical correlation coefficient matrix are usually 1, representing the correlation between the sediment disturbance parameter itself and the sediment disturbance parameter. This matrix comprehensively shows the degree of mutual correlation between all sediment disturbance parameters in an intuitive and orderly manner

[0058] Step S10203, perform eigenvalue decomposition on the theoretical correlation coefficient matrix to obtain eigenvectors and eigenvalues

[0059] In this embodiment, eigenvalue decomposition is an important matrix operation method. Its principle is to decompose the theoretical correlation coefficient matrix into the product of three matrices through a specific mathematical algorithm: one is the matrix composed of eigenvectors, one is the diagonal matrix with eigenvalues as the main diagonal elements, and the inverse matrix of the eigenvector matrix

[0060] In an alternative embodiment, the theoretical correlation coefficient matrix is input into MATLAB, which is a powerful mathematical calculation software. MATLAB uses the eig function for eigenvalue decomposition. The eig function is a tool specifically designed for this operation. When the eig function receives the theoretical correlation coefficient matrix, it will perform operations on the matrix according to specific mathematical algorithms. During the operation, MATLAB will search for vectors such that the product of the theoretical correlation coefficient matrix and the vector is equal to the vector multiplied by the eigenvalue, thereby outputting two results. One is a matrix composed of eigenvectors, where each column is an eigenvector corresponding to a certain eigenvalue. These eigenvectors reflect the variation patterns of the data in different directions. The other result is a diagonal matrix, and the elements on its main diagonal are the corresponding eigenvalues. The magnitude of the eigenvalue indicates the degree of data variation in the direction of the corresponding eigenvector. A larger eigenvalue means that the data has more significant variation in that direction.

[0061] Step S10204, calculate the contribution degree of the sediment disturbance parameter on the eigenvector according to the eigenvector and the eigenvalue.

[0062] In this embodiment, since the eigenvectors are obtained by eigenvalue decomposition of the theoretical correlation coefficient matrix, the eigenvectors represent the comprehensive variation directions of the sediment disturbance parameters in different dimensions. Each eigenvector consists of multiple components, which respectively correspond to each sediment disturbance parameter, and the eigenvalues reflect the importance of the information contained in the corresponding eigenvectors.

[0063] Therefore, multiply the square of the eigenvector component corresponding to each sediment disturbance parameter by the eigenvalue corresponding to the eigenvector to obtain the weighted squared component value. Then, calculate the sum of the weighted squared component values corresponding to all sediment disturbance parameters. Finally, divide the weighted squared component value corresponding to each sediment disturbance parameter by the sum of the weighted squared component values to quantify the contribution ratio of the sediment disturbance parameter in the direction of a specific eigenvector. Through this method, for each sediment disturbance parameter and each eigenvector, a clear contribution degree value can be obtained.

[0064] By calculating the contribution degree, the embodiments of the present invention can clearly understand the relative importance of each sediment disturbance parameter in different eigenvector directions. For example, if the contribution degree of a certain sediment disturbance parameter on a certain eigenvector is large, it indicates that this parameter plays a key role in this specific comprehensive variation direction in sediment disturbance. This helps to quickly locate the parameter combinations and directions that have the most significant impact on sediment disturbance among numerous sediment disturbance parameters, thereby providing a strong basis for more accurately screening the core parameters of sediment disturbance in the subsequent process.

[0065] Step S10205, use the contribution degree to screen the sediment disturbance parameters to obtain the core sediment disturbance parameters.

[0066] In this embodiment, a reasonable contribution degree threshold is set according to experience or multiple tests, and the contribution degree of each sediment disturbance parameter is compared with it. The parameter with a contribution degree greater than the threshold is identified as the core sediment disturbance parameter. Screening can avoid the complexity and interference caused by excessive sediment disturbance parameters, not only improving the research efficiency, but also more accurately grasping the essence of sediment disturbance.

[0067] The degree of disturbance satisfies the following formula:

[0068] ,

[0069] where, is the degree of sediment bottom disturbance, is the comprehensive correction coefficient, is the pumping power of the water pump, is the distance from the water inlet of the water pump to the sediment bottom, is the water flow velocity of the river channel, is the acceleration of gravity, is the average diameter of sediment bottom particles, is the density of the sediment bottom, is the density of the river water, is the water flow velocity at the water inlet.

[0070] The water flow velocity at the water inlet satisfies the following formula:

[0071] ,

[0072] where, is the water flow velocity at the water inlet, is the pumping power of the water pump, is the density of the river water, is the diameter of the water inlet of the water pump.

[0073] Step S103, use the core sediment disturbance parameters to screen the initial data to obtain the pumping data related to sediment bottom disturbance.

[0074] In this embodiment, through correlation analysis, the parameters with a relatively large influence on sediment disturbance factors have been clarified. These parameters are used to screen the initial data according to the classification of the initial data. The pumping data screened by this method can fully represent the relevant data of sediment disturbance during river channel pumping.

[0075] Step S2, obtain a sample set according to the pumping data and the degree of disturbance.

[0076] Among them, obtaining the sample set according to the pumping data and the disturbance degree specifically includes the following sub-steps:

[0077] Step S201, eliminate outliers and impute missing values for the pumping data and the disturbance degree to obtain first-optimized data.

[0078] By eliminating outliers, it is possible to eliminate, as much as possible, the outliers caused by equipment failures, measurement errors, or extreme events, thereby improving the reliability of the data and the accuracy of the analysis. The algorithm for eliminating outliers from the pumping data is used to eliminate outliers, and outliers refer to the data that significantly deviates from other pumping data in the pumping data.

[0079] In this embodiment, the K-nearest neighbor distance method is used to eliminate outliers. The principle of the K-nearest neighbor distance method is that for each data point in the pumping data, its Euclidean distance from other data points is calculated. Whether it is an outlier is judged according to the distribution of the K nearest neighbor data points around the data point. If the distance between a data point and its K nearest neighbor data points is significantly greater than the distance between other points, then it may be an outlier.

[0080] The Euclidean distance satisfies the following formula:

[0081] ,

[0082] In the formula, is the Euclidean distance, and are different pumping data, is the position of the data point in the pumping data sequence, is the number of pumping data.

[0083] By imputing missing values, the integrity of the pumping data can be ensured, avoiding analysis biases or insufficient model training caused by missing pumping data, and enhancing the usability of the data.

[0084] Among them, the first-optimized data refers to the data obtained by eliminating outliers and imputing missing values for the pumping data and the disturbance degree.

[0085] In this embodiment, the mean imputation method is used to impute missing values. When there are missing values in the pumping data, the mean value of the variable is used to fill in the missing values. This method is simple and intuitive and is suitable for the case where the data distribution is relatively uniform and the proportion of missing values is relatively small.

[0086] The mean imputation method for imputing missing values satisfies the following formula:

[0087] ,

[0088] In the formula, Indicates the dimensional th parameter of the pumping data, Indicates the dimensional th parameter of the pumping data, Indicates the dimensional th parameter of the pumping data, Indicates the dimension serial number of the parameter.

[0089] Step S202, perform normalization processing on the first optimized data to obtain second optimized data.

[0090] In this embodiment, the essence of the normalization process is to scale the first optimized data proportionally so that it falls within a specific range. From the characteristics of the first optimized data itself, normalization can eliminate the differences in dimension and numerical range between different features. For example, the pumping flow rate has a relatively large numerical range, while the disturbance degree has a relatively small numerical range. Without normalization, in the process of data analysis and modeling, features with a large numerical range like the flow rate will have a greater impact on the model, masking the role of other features. Normalization makes each feature have relatively equal weights in the model, improving the accuracy and stability of the model.

[0091] In terms of model training, normalization helps to accelerate the convergence speed of the model. Many machine learning algorithms, such as the gradient descent method, can find the optimal solution more efficiently when training on normalized data, reducing the number of iterations and saving computational resources and time costs. In addition, the normalized data is more general and comparable, facilitating the comparative analysis between different datasets and the performance evaluation between different models, providing a more reliable data basis for subsequent data analysis and decision-making.

[0092] Step S203, construct an adversarial network model, and generate enhanced data according to the second optimized data and the adversarial network model.

[0093] In this embodiment, the adversarial network model consists of two parts: a generator and a discriminator. The task of the generator is to learn the distribution of real data and generate as realistic simulated data as possible by inputting random noise or latent vectors. The discriminator is responsible for judging whether the input data is real or generated by the generator.

[0094] Use the second optimized data as a sample of the real data and input it into the adversarial network model. During the training process, the generator learns the features and distribution patterns of the second optimized data. Meanwhile, the generator and the discriminator engage in an adversarial game. The generator strives to generate more realistic data to deceive the discriminator, while the discriminator continuously improves its discrimination ability to accurately distinguish between real data and generated data. In this process of mutual confrontation and optimization, both of them jointly improve their performance.

[0095] Finally, the generator generates new data samples according to the learned patterns. These newly generated data are similar to the original second optimized data in terms of features and distribution, but not exactly the same, thus increasing the diversity of the data.

[0096] The generated enhanced data enriches the original data set and solves the problem of insufficient data volume. In practical applications, especially in the training of machine learning and deep learning models, an adequate data volume is crucial for the model to learn accurate patterns and rules. The enhanced data allows the model to access more samples, improves the generalization ability of the model, and enables it to make more accurate predictions and judgments when facing new and unseen data.

[0097] From the perspective of model performance, the introduction of the adversarial network model prompts the generator to generate high-quality simulated data, which can be used as additional training samples to help the model better learn the complex features and potential relationships of the data. At the same time, the process of adversarial training also enhances the robustness of the model, enabling it to cope with the noise and uncertainty in the data and improving the stability and reliability of the model.

[0098] In addition, the process of generating enhanced data also provides a new perspective for in-depth exploration of the internal structure and variation laws of the data, helping researchers discover hidden information and patterns in the data, and providing a more comprehensive and rich basis for further data analysis, model optimization, and related decision-making.

[0099] Step S204: Merge the second optimized data and the enhanced data to obtain the sample set.

[0100] In this embodiment, the second optimized data and the enhanced data are merged to obtain the sample set. During the merging process, it is necessary to ensure the consistency of the data structure. The second optimized data is the original data that has been normalized, while the enhanced data is the simulated data generated by the adversarial network model. When merging, it is necessary to integrate according to the same data feature dimensions and order to ensure that each data record can accurately correspond to the corresponding features.

[0101] Step S3: Construct a water pump inlet prediction model and set a loss function for the water pump inlet prediction model according to the degree of perturbation.

[0102] Among them, setting the loss function for the water pump inlet prediction model according to the disturbance degree specifically includes the following sub-steps:

[0103] Step S301: Based on the pumping test, sample and detect the heavy metal content at the water outlet of the water pump.

[0104] In this embodiment, during the pumping test, ensure that the pumping power remains unchanged. Adjust the distance from the water inlet of the water pump to the bottom mud from large to small. Using this method, the disturbance to the river bottom mud gradually increases from zero. By disturbing the bottom mud, the bottom mud gradually enters the water inlet of the water pump with the water flow according to the disturbance degree. Detect the heavy metal content at the water outlet of the water pump, and record the heavy metal content at the water outlet of the corresponding water pump when the water inlet of the water pump is at different positions.

[0105] Step S302: According to the results of the sampling and detection, evaluate the disturbance of the river bottom mud to obtain the maximum acceptable bottom mud disturbance degree when the water pump is pumping water.

[0106] In this embodiment, according to the impact of heavy metals on farmland, determine the maximum acceptable heavy metal content in the water during pumping as an index. In a high-standard pumping environment, it is also possible to use zero heavy metal content as an index.

[0107] Determine the distance from the water inlet of the water pump corresponding to this index according to the index, and calculate the disturbance degree by combining this distance with other data.

[0108] It should be additionally noted that preventing bottom mud disturbance during pumping does not strictly mean that the bottom mud cannot be disturbed at all. First of all, not all river bottom mud is pollutants. Only the heavy metals contained in the river bottom mud will have an impact on farmland, and the disturbance coefficients of heavy metals and ordinary sediment are different. Therefore, the detection of the water outlet of the water pump in the present invention only targets the index of heavy metal content.

[0109] Step S303: Set the loss function for the water pump inlet prediction model according to the maximum bottom mud disturbance degree and the disturbance degree.

[0110] The loss function satisfies the following formula:

[0111] ,

[0112] Among them, is the loss function, is the number of samples, is the th bottom mud disturbance degree of the sample, is the maximum acceptable bottom mud disturbance degree when the water pump is pumping water, is the maximum value function.

[0113] In this embodiment, in the above formula, , it indicates that the disturbance degree of the sample is within the acceptable range, which means that no additional penalty will be imposed on the model at this time, reflecting the optimized processing of samples within a reasonable disturbance range. , it indicates that the disturbance degree of the sample exceeds the acceptable range, which will impose a greater penalty on the model, and the greater the degree of exceeding, the heavier the penalty.

[0114] The role of the loss function is to evaluate the prediction result of the water pump inlet prediction model by calculating the difference between the sediment disturbance degree of the sample and the maximum acceptable sediment disturbance degree. It will penalize samples that exceed the maximum acceptable sediment disturbance degree, thereby prompting the model to minimize the occurrence of such situations during the training process, so as to improve the accuracy and reliability of the model prediction and ensure that the sediment disturbance degree is within the acceptable range when the water pump pumps water.

[0115] Step S4, using the sample set, train and evaluate the water pump inlet prediction model.

[0116] In this embodiment, first divide the sample set into a training set and a validation set according to a ratio of 9:1. The training set is used to train the water pump inlet prediction model, and the validation set is used to evaluate the water pump inlet prediction model.

[0117] Input the data in the training set into the water pump inlet prediction model one by one. Based on these data characteristics, the model gradually learns the internal relationship between each parameter at the inlet and the operating state of the water pump by continuously adjusting its own parameters and weights. Through repeated iterative training, the water pump inlet prediction model can more accurately capture the complex relationship between the parameters in the training set, so that when facing new pumping data, it can give a reliable prediction result based on the input parameters, providing strong support for the efficient and stable operation of the water pump.

[0118] After the training is completed, it enters the evaluation stage. Use the validation set data to test the prediction effect of the model. By calculating a series of evaluation indicators, such as mean square error, mean absolute error, coefficient of determination, etc., comprehensively measure the deviation degree and goodness of fit between the model prediction value and the actual value. If the evaluation result is not ideal, it is necessary to readjust the model structure, parameters or optimize the sample set, and then perform training and evaluation again until the model reaches a satisfactory performance, can accurately predict the operating condition of the water pump inlet, and provide a reliable basis for the stable operation and fault warning of the water pump.

[0119] The mean absolute error satisfies the following formula:

[0120] ,

[0121] where, represents the mean absolute error, Represents the number of samples in the validation set, Represents the true value of the distance from the water pump inlet to the bottom mud of the th sample in the validation set, and represents the predicted value of the distance from the water pump inlet to the bottom mud of the

[0122] The root mean square error expression satisfies the following formula:

[0123] ,

[0124] where, represents the root mean square error, represents the number of samples in the validation set, represents the true value of the distance from the water pump inlet to the bottom mud of the th sample in the validation set, and represents the predicted value of the distance from the water pump inlet to the bottom mud of the

[0125] The coefficient of determination expression satisfies the following formula:

[0126] ,

[0127] where, represents the coefficient of determination, represents the number of samples in the validation set, represents the true value of the distance from the water pump inlet to the bottom mud of the th sample in the validation set, and represents the predicted value of the distance from the water pump inlet to the bottom mud of the th sample in the validation set, and represents the average value of the true values of the distances from the water pump inlets to the bottom mud in the validation set.

[0128] The smaller the data in the mean absolute error and the root mean square error, the better the prediction effect of the model.

[0129] In the coefficient of determination, when , it means that the fitting of the model to the data is completely accurate. In the regression model, the predicted value is exactly equal to the true value, and all data points are on the regression line or regression plane. This is an ideal fitting state, indicating that the model can perfectly explain the change of the dependent variable. When , it means that there is an error between the model prediction result and the true value, which is normal. The closer the coefficient of determination is to 1, the better the prediction effect of the model.

[0130] Step S5: Use the water pump inlet prediction model to make a prediction, and automatically adjust the inlet and power of the water pump according to the prediction result.

[0131] Among them, the process of using the water pump inlet prediction model to make a prediction and automatically adjusting the inlet and power of the water pump according to the prediction result specifically includes the following sub-steps:

[0132] Step S501: Obtain real-time monitoring data, and use the water pump inlet prediction model to make a prediction based on the real-time monitoring data.

[0133] In this embodiment, the trained and evaluated water pump inlet prediction model is deployed in the pumping system for pumping operations. To achieve automated data collection, an automatic detection device is deployed in the pumping system to automatically collect data such as river water flow, pumping power, and the distance from the inlet to the bottom mud, and automatically send the collected data to the large pumping system.

[0134] The density and particle diameter of the bottom mud at the river bottom are relatively less likely to change. Although it is also possible to monitor the density and particle diameter of the bottom mud at the river bottom in the prior art, the equipment cost is expensive and not cost-effective. Therefore, a method of taking regular samples is adopted to collect these two data, namely the density and particle diameter of the bottom mud at the river bottom.

[0135] The obtained real-time monitoring data is normalized. The water pump inlet prediction model uses the normalized real-time monitoring data to predict the distance from the inlet of the water pump to the bottom mud. The reason for normalizing the monitoring data is that for better training of the model, the samples for training the model have been normalized. Therefore, the water pump inlet prediction model uses the normalized real-time monitoring data to predict the distance from the inlet of the water pump to the bottom mud, improving the prediction accuracy.

[0136] Step S502: Obtain the real-time distance from the inlet to the water surface, and automatically adjust the inlet and power of the water pump according to the real-time distance and the prediction result.

[0137] Among them, the process of automatically adjusting the inlet and power of the water pump according to the distance and the prediction result specifically includes the following sub-steps:

[0138] Step S50201: According to the working conditions of the water pump, set the minimum distance from the inlet of the water pump to the water surface when the water pump is working normally as the threshold.

[0139] In this embodiment, setting the minimum distance from the inlet to the water surface when the water pump is working normally as the threshold is a key measure to ensure the stable, efficient, and reasonable operation of the water pump.

[0140] On the one hand, setting this threshold is aimed at ensuring that the water pump is always in good working condition. The normal operation of the water pump depends on sufficient and stable water intake. If the distance from the water inlet to the water surface is too large, it may cause the water pump to suck in air, forming cavitation, damaging key components such as the impeller of the water pump, reducing the working efficiency and service life of the water pump. At the same time, it may also cause unstable water output of the water pump, affecting the normal operation of the entire pumping system. By setting the minimum distance threshold, these problems can be effectively avoided, ensuring the continuous and reliable operation of the water pump.

[0141] On the other hand, since the water inlet of the water pump is adjusted according to the prediction result of the water pump water inlet prediction model, however, when there is no rain for a long time or the rainfall is small, and the river water level drops abruptly, without setting constraint conditions, the water inlet of the water pump may be forced to jump out of the water surface according to the prediction result.

[0142] Step S50202, automatically adjust the water inlet and power of the water pump according to the distance and the threshold.

[0143] In this embodiment, in order to ensure the irrigation work of the farmland, the pumping power of the water pump is generally adjusted to the maximum value under normal operation. However, in the case of a gradually decreasing water level, the distance from the water inlet of the water pump to the bottom mud will also gradually decrease. When the distance reaches the maximum value of the acceptable bottom mud disturbance level, the water inlet cannot continue to drop. Also due to the limitation of the threshold, the pumping system can only adjust the power of the water pump, by reducing the power of the water pump to meet the threshold limitation, and at the same time not further increasing the impact on the bottom mud disturbance, so as to realize the automatic adjustment of the water inlet and power of the water pump.

[0144] As Figure 2 shown, on the other hand, the present invention also provides a water pump pumping automatic adjustment system for preventing river bottom mud disturbance, including: a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are interconnected, wherein, the memory is used for storing computer programs, the computer programs include program instructions, and the processor is configured to call the program instructions to execute the relevant steps of the relevant embodiments in a method for automatically adjusting the pumping of a water pump for preventing river bottom mud disturbance according to the present invention.

[0145] For the water pump pumping automatic adjustment system for preventing river bottom mud disturbance provided by the present invention, each functional component can be integrated in a processing component, or each component can exist physically alone, or two or more components can be integrated in one component. The above integrated components can be implemented in the form of hardware or in the form of software functions, further improving the overall applicability and practical application ability of the present invention.

[0146] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present invention, and they should all be covered by the scope of the claims and the specification of the present invention.

Claims

1. A method for automatically adjusting water pumping to prevent disturbance of muddy bottom in a river channel, characterized in that: The method comprises: Acquiring pumping data related to mud bottom disturbance, and evaluating the impact of pumping on riverbed mud based on the pumping data to obtain the degree of disturbance; The acquisition of pumping data related to mud bottom disturbance includes: Conducting pumping tests and testing the sediments of the riverbed to obtain initial data; Performing correlation analysis on the initial data to obtain core parameters of sediment disturbance; The correlation analysis of the initial data to obtain the core parameters of sediment disturbance includes: According to the initial data, obtaining sediment disturbance parameters; Calculating the correlation coefficients between the sediment disturbance parameters, and constructing a theoretical correlation coefficient matrix based on the correlation coefficients; Performing eigenvalue decomposition on the theoretical correlation coefficient matrix to obtain eigenvectors and eigenvalues; Calculating the contribution of the sediment disturbance parameter to the eigenvector according to the eigenvector and the eigenvalue; Using the contribution degree to screen the sediment disturbance parameters, and obtain the sediment disturbance core parameters; Using the sediment disturbance core parameter to screen the initial data, and obtain the pumping data related to the sediment disturbance; The disturbance degree satisfies the following formula: Where I is the disturbance degree of mud bottom, k is the comprehensive correction coefficient, P is the pumping power of the water pump, H is the distance from the water inlet of the water pump to the mud bottom, V w is the velocity of the river flow, g is the acceleration of gravity, d is the average diameter of the mud bottom particles, ρ s is the density of the mud bottom, ρ w is the density of river water, V p is the water flow velocity at the water inlet; Obtaining a sample set according to the pumping data and the disturbance degree; Constructing a water pump inlet prediction model, and setting a loss function for the water pump inlet prediction model according to the disturbance degree; The water pump water inlet prediction model is trained and evaluated using the sample set; the water pump water inlet prediction model is used to perform predictions, and the water inlet and power of the water pump are automatically adjusted according to the prediction results.

2. A method for automatically adjusting water pumping to prevent muddy bottom disturbance in a river according to claim 1, characterized in that: The obtaining of a sample set according to the pumping data and the disturbance degree comprises: Eliminate outliers and interpolate missing values ​​from the pumping data and the disturbance degree to obtain first optimized data; Normalizing the first optimized data to obtain second optimized data; Constructing an adversarial network model, and generating enhanced data according to the second optimized data and the adversarial network model; The second optimized data and the enhanced data are combined to obtain the sample set.

3. The method for automatically adjusting water pumping to prevent muddy bottom disturbance in a river according to claim 1, characterized in that: The setting of a loss function for the water pump inlet prediction model according to the disturbance degree comprises: Based on the water pumping test, sampling and testing the heavy metal content at the water outlet of the water pump; According to the sampling test results, the disturbance of the riverbed sediment is evaluated to obtain the maximum acceptable degree of sediment disturbance when the water pump is pumping water; A loss function is set for the water pump inlet prediction model according to the maximum sediment disturbance degree and the disturbance degree.

4. The method for automatically adjusting water pumping to prevent muddy bottom disturbance in a river according to claim 1, characterized in that: The method of using the water pump water inlet prediction model to make predictions and automatically adjusting the water inlet and power of the water pump according to the prediction results includes: Acquire real-time monitoring data, and make predictions using the water pump inlet prediction model based on the real-time monitoring data; The real-time distance from the water inlet to the water surface is obtained, and the water inlet and power of the water pump are automatically adjusted according to the real-time distance and the predicted result.

5. The method for automatically adjusting water pumping to prevent muddy bottom disturbance in a river according to claim 4, characterized in that: The automatic adjustment of the water inlet and power of the water pump according to the real-time distance and the predicted result includes: According to the working condition of the water pump, the minimum distance from the water inlet of the water pump to the water surface when the water pump works normally is set as a threshold; The water inlet and power of the water pump are automatically adjusted according to the real-time distance and the threshold.

6. The method for automatically adjusting water pumping to prevent muddy bottom disturbance in a river according to claim 3, characterized in that: The loss function satisfies the following formula: Among them, L is the loss function, N is the number of samples, and I i is the sediment disturbance degree of the i-th sample, I max The maximum acceptable level of sediment disturbance when pumping water.

7. A water pump automatic regulating system for preventing muddy bottom disturbance in a river channel, characterized in that: include: A processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute a method for automatically adjusting water pumping to prevent muddy bottom disturbance in a river channel as described in any one of claims 1 to 6.

Images