Depth-keeping layering parameter determination method of multi-channel water sampler, medium and system

By establishing a water base change model and optimizing sampling parameters using multi-layer perceptron and genetic algorithms, the problem of determining the depth-degree stratification parameters of multi-channel water collectors depends on manual experience, and the representativeness of sampling data and the immediacy of monitoring are improved. and intelligence level.

CN119025837AActive Publication Date: 2024-11-26青岛道万科技有限公司
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202410994010.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-26
Estimated Expiration
2044-07-24

AI Technical Summary

Technical Problem

The determination of fixed-depth stratification parameters of existing multi-channel water collectors depends on the experience of the operator, resulting in insufficient representativeness and reliability of the sampling data, which is difficult to meet the immediate and dynamic requirements of water quality monitoring.

Method used

By collecting historical water extraction project data, establishing a basic change model of water body, and using multi-layer perceptron neural network and genetic algorithm to optimize sampling parameters, determine the optimal sampling depth, time interval and volume, and realize automated parameter determination.

Benefits of technology

It improves the representativeness and reliability of sampled data, enhances the immediacy and responsiveness of water quality monitoring, improves the intelligence level of monitoring, and reduces manual intervention and errors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119025837A_ABST
    Figure CN119025837A_ABST
Patent Text Reader

Abstract

The invention provides a depth-keeping layering parameter determination method of a multi-channel water sampler, a medium and a system, and belongs to the technical field of use of multi-channel water samples.The depth-keeping layering parameter determination method comprises the steps that multiple sets of water sampling project data are adopted, a water body basic change model is established, and a multi-layer perceptron neural network model is trained by means of increasing and expanding data to obtain the water body change model. And then on the basis of the water body distribution data, calculating an optimal sampling parameter by adopting a genetic algorithm. And finally, establishing a regression neural network model, and inputting environmental parameters of the current water area to be detected to obtain depth-keeping layering parameters of the multi-channel water sampler. According to the method, historical sampling data is utilized, and through technologies of data expansion, a neural network, a genetic algorithm and the like, refined modeling of a target water body and intelligent optimization of sampling parameters are realized, and effective support is provided for multi-channel water sampling monitoring. The technical problems that in the prior art, depth-keeping layering parameters of the water sampler are determined by means of experience of operators, and the representativeness and reliability of sampling data are not enough are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of use of multi-channel water samplers, and in particular, relates to a method, medium and system for determining fixed-depth stratification parameters of a multi-channel water sampler. Background Art

[0002] Water quality monitoring is an important part of environmental protection and resource management, and is crucial to maintaining ecological balance and ensuring drinking water safety. Traditional water quality monitoring methods mainly include two links: field sampling and laboratory analysis. In the field sampling stage, sampling personnel need to manually determine the sampling point location, sampling depth and sampling time according to the monitoring plan, and take samples on site; in the laboratory analysis stage, the collected water samples are transported back to the laboratory for testing and analysis of physical, chemical and biological indicators. This sampling-transportation-analysis method has some key problems:

[0003] First, the sampling process relies on manual operation, which is subjective and arbitrary. The selection of sampling points, depths and times depends on the experience and judgment of the sampling personnel, which makes it difficult to ensure the representativeness of the entire water body and may lead to deviations in the sampling results. At the same time, the sampling efficiency of manual operation is low and it is difficult to meet the needs of dynamic water quality monitoring.

[0004] Secondly, the collection, transportation and storage of water samples are prone to contamination and measurement errors. Contact contamination during sampling, temperature changes during transportation, and different storage conditions will affect the properties of water samples, thereby affecting the reliability of the final analysis results.

[0005] Furthermore, laboratory analysis usually takes 2-7 days, which cannot provide timely water quality information and makes it difficult to respond quickly to water conditions. In some emergency situations, such as chemical leaks and industrial wastewater discharges, it is impossible to detect and take corresponding measures in time, which can easily cause environmental pollution accidents.

[0006] In order to solve the above problems, automated water quality sampling equipment such as multi-channel water samplers have been developed in recent years, such as the utility model disclosed in the publication number CN202321995114.5, which discloses an intelligent multi-channel water sampling device. This type of equipment can automatically collect water samples and is equipped with online sensors to achieve real-time monitoring of water quality indicators on site. Compared with traditional sampling methods, automated water sampling equipment has the following advantages:

[0007] 1) The sampling points can be set programmably, covering a wide range and can monitor the overall condition of the water body;

[0008] 2) The sampling time interval can be flexibly adjusted to meet the needs of dynamic water quality monitoring;

[0009] 3) On-site instant analysis, no need to transport water samples, can quickly detect water quality abnormalities;

[0010] 4) Data can be transmitted remotely, which is conducive to information management and early warning.

[0011] However, when this device is used, the determination of the depth and stratification parameters of the water sampler often relies on the operator's experience, and the sampling data is not representative and reliable enough. Summary of the invention

[0012] In view of this, the present invention provides a method, medium and system for determining the fixed-depth stratification parameters of a multi-channel water sampler, which can solve the technical problems in the prior art that the determination of the fixed-depth stratification parameters of the water sampler often relies on the experience of the operator, and the representativeness and reliability of the sampling data are not enough.

[0013] The present invention is achieved in that:

[0014] A first aspect of the present invention provides a method for determining depth-determining stratification parameters of a multi-channel water sampler, comprising the following steps:

[0015] S10, collecting multiple groups of historical water collection project data, wherein each group of water collection project data is specifically project data of historical water collection projects that have been successfully collected by multi-channel water collectors in different areas of the same water body;

[0016] S20, for each set of environmental parameters and sampling analysis data in the project data, establishing and fitting the basic change model of the water body;

[0017] S30, based on the basic change model, each set of project data is augmented and expanded to obtain corresponding multiple sets of augmented and expanded project data;

[0018] S40, using each set of water collection project data and its corresponding augmented project data as a training set, using the multiple sets of water collection project data as a validation set, and training a multi-layer perceptron neural network model to obtain a water body change model;

[0019] S50, for each set of water sampling project data in the augmented project data, inputting the environmental parameters and sampling analysis parameters therein into the water body change model to obtain water body distribution data;

[0020] S60, for each group of water sampling project data in the augmented project data, taking the sampling parameters as the initial population, taking maximizing the sampling coverage and minimizing the sampling error as the objective function, using the obtained water body distribution, and using a genetic algorithm to calculate the optimal sampling parameters;

[0021] S70, for all augmented project data, establish a training data set, wherein the input of the training is the environmental parameter, the output of the training is the sampling parameter, and train a regression neural network to obtain a sampling parameter determination model;

[0022] S80, obtaining environmental parameters of the current water area to be tested, and inputting them into the sampling parameter determination model to obtain sampling parameters as depth-determining and stratification parameters of the multi-channel water sampler of the current water area to be tested.

[0023] Wherein, the step S10 specifically includes:

[0024] Step 101, obtain historical project data of successful sampling using a multi-channel water sampler in different areas of the same water body, including environmental parameters, sampling parameters and sampling analysis data; wherein the environmental parameters include water depth, water quality, water temperature and flow rate, etc., the sampling parameters include sampling time interval, sampling depth and sampling volume, and the sampling analysis data include physical indicators, biological indicators and chemical indicators.

[0025] Step 102: sort and classify the collected historical project data to provide basic data for the subsequent establishment of a water body change model.

[0026] The specific implementation of step S20 is as follows:

[0027] Step 201 : Select a suitable mathematical modeling method, such as regression analysis, time series analysis, etc., and establish a basic water body change model based on the environmental parameters and sampling analysis data collected in step S10.

[0028] Step 202: perform parameter fitting and verification on the established water body change model to ensure that the model can accurately describe the intrinsic relationship between the water body environmental parameters and the sampling analysis indicators.

[0029] The specific implementation of step S30 is as follows:

[0030] Step 301 : Select appropriate statistical methods, such as Monte Carlo random simulation, Bootstrap sampling, etc., to augment each set of historical project data collected in step S10 to generate more diverse simulation data.

[0031] Step 302: Use the multiple groups of project data obtained after augmentation as input data for subsequent steps.

[0032] The specific implementation of step S40 is as follows:

[0033] Step 401: Use the original project data of step S10 as a training set and the data augmented in step S30 as a validation set to train a multi-layer perceptron (MLP) neural network model.

[0034] Step 402: repeatedly adjust the structure and training parameters of the neural network, such as the number of layers, the number of nodes, the activation function, etc., so that the model achieves optimal performance on the validation set.

[0035] Step 403: The trained neural network model is a water body change model, which can be used to predict the sampling analysis results under given environmental parameter conditions.

[0036] The specific implementation of step S50 is as follows:

[0037] Step 501: Input the environmental parameters and sampling analysis parameters of each group of project data obtained by the augmentation in step S30 into the water body change model obtained by the training in step S40.

[0038] Step 502: Obtain corresponding water body distribution data based on the model calculation, reflecting the spatial distribution of various water body indicators under given environmental parameter conditions.

[0039] The specific implementation of step S60 is as follows:

[0040] Step 601: Based on the water body distribution data obtained in step S50, a genetic algorithm is used to optimize the sampling parameters of the augmented project data in step S30.

[0041] Step 602: The objective function is to maximize the sampling coverage and minimize the sampling error. The optimal sampling parameter scheme corresponding to each group of project data is obtained through iterative optimization of the genetic algorithm.

[0042] The specific implementation of step S70 is as follows:

[0043] Step 701: Take the optimal sampling parameters obtained by optimization in step S60 as output and the environmental parameters obtained by augmentation in step S30 as input to train a regression neural network model.

[0044] Step 702: Through training, learn the implicit rules between environmental parameters and sampling parameters, and obtain a sampling parameter determination model.

[0045] The specific implementation of step S80 is as follows:

[0046] Step 801: Obtain environmental parameters of the water area to be tested, including water depth, water quality, water temperature, flow rate, etc.

[0047] Step 802: Input the environmental parameters acquired in step 801 into the sampling parameter determination model trained in step S70.

[0048] Step 803: The model outputs the optimal sampling parameters for the water area, including sampling time interval, sampling depth, and sampling volume, etc., as fixed-depth stratification parameters for the multi-channel water sampler.

[0049] Optionally, the optimal sampling parameters output in step 803 meet the requirements that the sampling coverage is not less than 90% and the sampling error does not exceed 5%.

[0050] Optionally, for the specific structure of the water body change model, a hybrid model can be used, combining the advantages of statistical models and deep learning models. Specifically, the model can be divided into the following parts:

[0051] 1. Environmental parameter preprocessing module

[0052] Standardize or normalize the original environmental parameter data to eliminate the dimension effect.

[0053] You can consider performing differential or sliding window processing on time series data to extract time features.

[0054] 2. Statistical model module

[0055] Classic statistical models, such as linear regression, polynomial regression, time series model (ARIMA), etc., are used to fit the basic relationship between environmental parameters and sampling analysis data.

[0056] This module can capture linear and nonlinear trends in data and serve as the basis for deep learning models.

[0057] 3. Deep Learning Module

[0058] Deep neural networks are introduced to capture the complex nonlinear relationship between environmental parameters and sampling analysis data.

[0059] The network structure can adopt a multi-layer perceptron (MLP) or a long short-term memory network (LSTM).

[0060] The input is the preprocessed environmental parameter data, and the output is the corresponding sampling analysis indicators.

[0061] 4. Residual Connection

[0062] The output of the statistical model is used as the residual term of the deep learning model to integrate the linear and nonlinear parts.

[0063] This design can explicitly retain the basic trends captured by the statistical model, while leveraging the residuals learned by the deep model to improve the overall fitting ability.

[0064] 5. Loss Function

[0065] The mean square error (MSE) or mean absolute error (MAE) is used as the loss function to measure the deviation between the model prediction and the true value.

[0066] It is also possible to consider introducing regularization terms to avoid overfitting.

[0067] 6. Model training and optimization

[0068] The model parameters are trained on the training set using optimization algorithms such as stochastic gradient descent.

[0069] The validation set can be used for model selection to prevent overfitting.

[0070] For time series data, rolling forecasting can be used for training and testing.

[0071] Through the design of the above hybrid model structure, the advantages of statistical models and deep learning models can be effectively integrated to capture the linear, nonlinear and time series characteristics of water body change data, thereby improving the overall prediction accuracy. In practical applications, the model structure can be further adjusted and optimized according to the characteristics of the data and task requirements.

[0072] The project data includes environmental parameters, sampling parameters and sampling analysis data.

[0073] Furthermore, the environmental parameters include water depth, water quality, water temperature, and flow rate.

[0074] Furthermore, the sampling parameters are provided by experts based on the environmental parameters, including sampling time interval, sampling depth and sampling volume.

[0075] Furthermore, the sampling and analysis data are physical indicators, biological indicators and chemical indicators of the sampled water.

[0076] Among them, the water body change model includes the following modules: an environmental parameter preprocessing module, a statistical model module, a deep learning module and a residual connection module.

[0077] The environmental parameter preprocessing module is used to standardize or normalize the original environmental parameter data to eliminate the dimension effect.

[0078] Furthermore, the statistical model module adopts a mathematical statistical model to fit the basic relationship between environmental parameters and sampling analysis data.

[0079] Furthermore, the deep learning module adopts a multi-layer perceptron or a long short-term memory network.

[0080] A second aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores program instructions, and when the program instructions are executed, they are used to execute the above-mentioned method for determining fixed-depth stratification parameters of a multi-channel water sampler.

[0081] A third aspect of the present invention provides a system for determining fixed-depth stratification parameters of a multi-channel water sampler, which includes the above-mentioned computer-readable storage medium.

[0082] Compared with the prior art, the method, medium and system for determining the fixed depth and stratification parameters of a multi-channel water sampler provided by the present invention have the following beneficial effects:

[0083] 1. Improved the representativeness and reliability of sampling data: This method makes full use of historical water quality monitoring data to establish a mathematical relationship model between water body environmental parameters and sampling analysis indicators. This model can accurately describe the change law of water bodies and provide a basis for the optimization of subsequent sampling parameters. Compared with the manual experience selection of sampling parameters, the automatic optimization based on the model can better cover the overall distribution characteristics of the water body and improve the representativeness of the sampling results. At the same time, the optimized sampling parameters can also reduce the errors in the sampling process, thereby improving the reliability of the data.

[0084] 2. Enhanced the immediacy and responsiveness of water quality monitoring: This method uses machine learning and other technologies to quickly determine the optimal sampling parameter plan. Once the real-time environmental parameters of the water area to be tested are obtained, the pre-trained parameter determination model can be used to quickly output key parameters such as the sampling depth, volume, and time interval required for the water area. Compared with the traditional manual experience selection method, this method greatly shortens the time from obtaining environmental information to completing the sampling plan, providing strong support for the rapid response to abnormal water quality accidents.

[0085] 3. Improved the intelligent level of water quality monitoring: This method integrates advanced technical means such as mathematical modeling and machine learning to achieve automatic optimization of sampling parameters. Compared with traditional methods that rely on manual experience, this method has stronger adaptability and automation capabilities. On the one hand, by establishing a water body change law model, it can adapt to the characteristics of different waters and dynamically adjust sampling parameters; on the other hand, the optimization process based on genetic algorithms can autonomously explore the best sampling plan and reduce manual intervention. This not only improves monitoring efficiency, but also lays a technical foundation for realizing intelligent water quality monitoring.

[0086] Therefore, the solution of the present invention solves the technical problem that the existing technology often relies on the operator's experience to determine the depth and stratification parameters of the water sampler, and the representativeness and reliability of the sampling data are not enough. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0088] Figure 1 A flow chart of the method provided by the present invention. DETAILED DESCRIPTION

[0089] In order to make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0090] like Figure 1 As shown, it is a flow chart of a method for determining the fixed depth and layered parameters of a multi-channel water sampler provided by the present invention. The method comprises the following steps:

[0091] S10, collecting multiple groups of historical water collection project data, wherein each group of water collection project data is specifically project data of historical water collection projects that have been successfully collected by multi-channel water collectors in different areas of the same water body;

[0092] S20. For each set of environmental parameters and sampling analysis data in the project data, establish and fit the basic change model of the water body;

[0093] S30, based on the basic change model, each set of project data is augmented and expanded to obtain corresponding multiple sets of augmented and expanded project data;

[0094] S40, using each set of water collection project data and its corresponding augmented project data as a training set, using multiple sets of water collection project data as a validation set, and training a multi-layer perceptron neural network model to obtain a water body change model;

[0095] S50, for each set of water collection project data in the augmented project data, input the environmental parameters and sampling analysis parameters therein into the water body change model to obtain water body distribution data;

[0096] S60, for each set of water sampling project data in the augmented project data, taking the sampling parameters as the initial population, taking maximizing the sampling coverage and minimizing the sampling error as the objective function, using the obtained water body distribution, and using a genetic algorithm to calculate the optimal sampling parameters;

[0097] S70, for all augmented project data, establish a training data set, wherein the input of the training is the environmental parameter, the output of the training is the sampling parameter, and train a regression neural network to obtain a sampling parameter determination model;

[0098] S80, obtaining environmental parameters of the current water area to be tested, inputting them into a sampling parameter determination model, and obtaining sampling parameters as depth-determining and stratification parameters of the multi-channel water sampler of the current water area to be tested.

[0099] The specific implementation methods of the above steps are described in detail below:

[0100] Step S10: Collect multiple groups of historical water collection project data

[0101] In this step, we first need to collect historical project data of successful sampling using multi-channel water samplers in different areas of the same water body. These data include three categories: environmental parameters, sampling parameters, and sampling analysis data.

[0102] Environmental parameters include water depth, water quality, water temperature and flow rate. Sampling parameters are provided by experts based on environmental parameters, mainly including sampling time interval, sampling depth and sampling volume. Sampling analysis data are the test results of physical, biological and chemical indicators of the collected water samples.

[0103] The purpose of collecting these historical project data is to establish the basic change model of the water body and provide a basis for subsequent parameter optimization. By analyzing the historical data of different areas of the same water body, the intrinsic relationship between the water body environmental parameters and sampling analysis indicators can be obtained.

[0104] Step S20: Establish and fit the basic change model of water body

[0105] Based on the environmental parameters and sampling analysis data collected in step S10, a mathematical modeling method is used to establish and fit the basic change model of the water body. Here, regression analysis, time series analysis and other methods can be used to establish a mathematical relationship model between environmental parameters and sampling analysis indicators.

[0106] By fitting the model, we can describe the changing patterns of the water environment parameters over time and space, and provide a basis for subsequent parameter optimization. The accuracy of the model directly affects the accuracy of the final optimized parameters, so it is necessary to select a suitable modeling method and fully verify the model.

[0107] Step S30: Expand project data

[0108] Based on the basic change model established in step S20, each group of project data collected in step S10 is augmented. More sample data can be obtained through augmentation to provide sufficient training sets for subsequent neural network training.

[0109] The augmentation method can be statistical methods such as Monte Carlo random simulation and Bootstrap sampling. Through these methods, more diverse simulated data can be generated while retaining the original data characteristics. The augmented data set becomes the input for subsequent steps.

[0110] Step S40: Training a multi-layer perceptron neural network model

[0111] Next, a multi-layer perceptron (MLP) neural network model is trained using the original project data of step S10 and the data augmented in step S30. The purpose of this model is to learn the complex nonlinear mapping relationship between environmental parameters and sampled analysis data.

[0112] Specifically, the original project data is used as a training set to input the neural network model for learning, and the augmented data is used as a validation set for model performance evaluation. The structure and training parameters of the neural network, such as the number of layers, number of nodes, activation function, etc., are repeatedly adjusted until the model reaches the optimal performance on the validation set.

[0113] The trained neural network model is the water body change model, which can be used to predict the sampling analysis results under given environmental parameters. This provides an important basis for subsequent parameter optimization.

[0114] Step S50: Predicting water distribution based on water body change model

[0115] After the water body change model obtained by training in step S40 is obtained, for each set of augmented project data obtained in step S30, its environmental parameters and sampling analysis parameters are input into the model to obtain the corresponding water body distribution data.

[0116] The water body distribution data reflects the spatial distribution of various water body indicators under given environmental parameter conditions. This provides an important decision-making basis for subsequent parameter optimization and can guide how to arrange sampling points to cover the spatial distribution of water bodies to the greatest extent.

[0117] Step S60: Optimizing sampling parameters using genetic algorithm

[0118] Based on the water body distribution data obtained in step S50, a genetic algorithm is used to optimize the sampling parameters of each group of augmented project data. The objective function is to maximize the sampling coverage and minimize the sampling error.

[0119] Genetic algorithm is a heuristic optimization algorithm that simulates the biological evolution process. It can find the optimal solution of the objective function through operations such as selection, crossover and mutation. Here, the decision variables of the genetic algorithm are sampling parameters, including sampling time interval, sampling depth and sampling volume.

[0120] Through iterative optimization of genetic algorithms, the optimal sampling parameter scheme corresponding to each group of augmented project data can be obtained, providing a basis for subsequent parameter determination model training.

[0121] Step S70: Training sampling parameters to determine the model

[0122] With the optimal sampling parameters obtained by optimization in step S60, a regression neural network model can be established to fit the mapping relationship between environmental parameters and sampling parameters.

[0123] Specifically, all the project data obtained by step S30 are used as training sets, where the input is the environmental parameters and the output is the optimized sampling parameters. By training the recurrent neural network, the implicit rules between the environmental parameters and the sampling parameters can be learned.

[0124] The regression model obtained through training is the sampling parameter determination model, which can be used to predict the optimal sampling parameters under given environmental parameters. This provides a basis for parameter determination in practical applications.

[0125] Step S80: Determine the sampling parameters of the current water area

[0126] In practical applications, when it is necessary to determine the depth-setting and stratification parameters of a multi-channel water sampler in a certain water area to be tested, the environmental parameters of the water area, including water depth, water quality, water temperature and flow rate, are first obtained.

[0127] Then, these environmental parameters are input into the sampling parameter determination model obtained by training in step S70, and the model can output the optimal sampling parameters for the water area, including sampling time interval, sampling depth, sampling volume, etc.

[0128] These optimized sampling parameters are the fixed depth and stratification parameters of the multi-channel water sampler in this water area, which can guide the actual sampling operations and ensure the accuracy and representativeness of the sampling results.

[0129] Optionally, for the specific structure of the water body change model, its model structure is:

[0130] 1. Input layer:

[0131] The input layer receives environmental parameter data, including water depth, water quality, water temperature, flow rate, etc.

[0132] For time series data, a sliding window approach can be used to take historical data as part of the input.

[0133] For categorical data (such as water quality level), One-Hot encoding is required.

[0134] 2. Embedding Layer:

[0135] For continuous numerical data, a fully connected layer is used for embedding to map the original features into a low-dimensional embedding space.

[0136] For categorical data, an embedding layer is used to map the One-Hot encoding to a low-dimensional embedding vector.

[0137] 3. Statistical model part:

[0138] A multi-layer perceptron (MLP) network is used to perform nonlinear transformation on the embedded input data.

[0139] The output layer uses linear regression or other statistical models to capture linear and nonlinear trends in the data.

[0140] The output of this part serves as the residual term of the deep learning model.

[0141] 4. Deep Learning Module:

[0142] Use recurrent neural network structures such as Long Short-Term Memory (LSTM) or Gated Recurrent Unit (GRU).

[0143] Multiple layers of LSTM or GRU units can be stacked to improve the expressiveness of the model.

[0144] The input is the embedded data, and the output is the corresponding sampling analysis indicator.

[0145] 5. Residual Connection:

[0146] Add the output of the statistical model part to the output of the deep learning module as the final model output.

[0147] This residual connection can explicitly preserve the underlying trends captured by the statistical model while leveraging the residuals learned by the deep model.

[0148] 6. Output layer:

[0149] For regression tasks, the output layer is a fully connected layer that outputs continuous sampling analysis indicator values.

[0150] For classification tasks, the output layer is a Softmax layer that outputs the probability distribution of each category.

[0151] Model training:

[0152] 1. Data preprocessing:

[0153] Standardize or normalize the original data to eliminate the dimension effect.

[0154] The training set, validation set, and test set are divided into fixed proportions.

[0155] For time series data, a sliding window approach can be used to generate samples.

[0156] 2. Loss function:

[0157] For regression tasks, the mean square error (MSE) or mean absolute error (MAE) is used as the loss function.

[0158] For classification tasks, the cross entropy loss function is used.

[0159] You can consider introducing regularization terms (such as L1 or L2 regularization) to prevent overfitting.

[0160] 3. Optimization algorithm:

[0161] Use stochastic gradient descent (SGD), Adam, or other optimization algorithms to calculate the gradient of the parameters based on the loss function.

[0162] Set an appropriate learning rate scheduling strategy, such as exponential decay or cosine annealing.

[0163] 4. Model training:

[0164] Perform multiple epochs of iterative training on the training set and update the parameters using Mini-Batch Gradient Descent (Mini-Batch GD).

[0165] After each epoch, the model performance is evaluated on the validation set, and the model with the best validation metric is selected as the final model.

[0166] For time series data, rolling forecasting can be used for training, that is, using historical data to predict the value of the next time step.

[0167] 5. Early Stopping:

[0168] Monitor the validation set loss or other metrics during training.

[0169] When the validation set indicators do not improve within several consecutive epochs, the training is terminated early to avoid overfitting.

[0170] 6. Model Integration:

[0171] Multiple models can be trained and their outputs can be integrated to improve generalization capabilities.

[0172] Commonly used integration methods include average integration, weighted integration and stacking integration.

[0173] 7. Hyperparameter Optimization:

[0174] For model hyperparameters, such as the number of layers, number of neurons, dropout rate, etc., grid search or Bayesian optimization can be used for automatic tuning.

[0175] Evaluate the model performance under different hyperparameter combinations on the validation set and select the optimal configuration.

[0176] Through the above model structure and training strategy, the advantages of statistical models and deep learning models can be effectively integrated to capture the linear, nonlinear and time series characteristics of water body change data, thereby improving the overall prediction accuracy. In practical applications, the model structure and training process can be further adjusted and optimized according to the characteristics of the data and task requirements to obtain better performance.

[0177] A second aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores program instructions, and when the program instructions are executed, they are used to execute the above-mentioned method for determining fixed-depth stratification parameters of a multi-channel water sampler.

[0178] A third aspect of the present invention provides a system for determining fixed-depth stratification parameters of a multi-channel water sampler, which includes the above-mentioned computer-readable storage medium.

[0179] In order to better understand and implement the present invention, the following provides a specific embodiment 1 of the present invention in a computer-readable storage medium or a computer for use in a computer program: For this embodiment 1, in step S10, it is necessary to collect historical project data of successful sampling using a multi-channel water sampler in different areas of the same water body. These data include three categories: environmental parameters, sampling parameters, and sampling analysis data.

[0180] Environmental parameters include water depth D, water quality Q, water temperature T and flow velocity V. These environmental parameters can be expressed as a vector E:

[0181] E = [D, Q, T, V]

[0182] The sampling parameters are provided by experts based on environmental parameters, mainly including sampling time interval Δt, sampling depth Δz and sampling volume V s Etc. These sampling parameters are composed into a vector S:

[0183] S=[Δt,Δz,V s ]

[0184] The sampling and analysis data are the test results of the physical index P, biological index B and chemical index C of the collected water samples. These sampling and analysis data can be composed into a vector A to represent:

[0185] A=[P,B,C]

[0186] In summary, each set of historical water extraction project data can be expressed as:

[0187] X=[E,S,A]

[0188] In step S20, it is necessary to establish and fit the basic change model of the water body. Based on the historical project data X, the mathematical relationship model between the environmental parameter E and the sampling analysis data A can be established using the regression analysis method:

[0189] A=f(E)+∈

[0190] Among them, f(·) represents the unknown functional relationship, and ∈ is the random error term. By fitting the training sample data, the specific form of the function f(·) can be obtained, thereby establishing a basic water body change model. Commonly used fitting methods include linear regression, polynomial regression, neural network, etc.

[0191] In step S30, each set of historical project data collected in step S10 needs to be augmented to obtain more sample data. Here, the Monte Carlo random simulation method can be used to generate more diverse environmental parameters E and sampling analysis data A based on the water body change model f(·) established in step S20. Specifically, the probability distribution p(E) of the environmental parameter E can be set, and then a random number generator can be used to sample according to the distribution to obtain multiple realization values ​​of E, and then substitute them into the model f(·) to calculate the corresponding A value. By iterating repeatedly in this way, a large amount of augmented project data can be obtained.

[0192] In step S40, a multi-layer perceptron (MLP) neural network model needs to be trained. The input of the model is the environmental parameter E, and the output is the sampled analysis data A. Its structure can be expressed as:

[0193]

[0194] in, represents the nonlinear mapping function of the neural network, and Θ is the parameter of the network. The back propagation algorithm can be used to minimize the mean square error between the training sample and the network output, optimize the network parameter Θ, and thus train the water body change model.

[0195] In step S50, the water body change model trained in step S40 is required Predict the water body distribution corresponding to each set of data in the augmented project data. Specifically, for the i-th augmented project data X i =[E i , S i , A i ], the environmental parameter E i Input to model In the above example, we get the predicted sampling analysis data. Then, you can With the actual A i Compare and analyze the distribution characteristics of water bodies under the environmental parameter conditions.

[0196] In step S60, it is necessary to use a genetic algorithm to optimize the sampling parameter S of each group of augmented project data. Genetic algorithm is a heuristic optimization algorithm that simulates the biological evolution process. Its basic idea is to iteratively optimize and solve the optimal solution of the objective function through operations such as selection, crossover and mutation. Here, the objective function includes two indicators:

[0197] 1. Sampling coverage R c , which represents the proportion of sampling points in the water distribution area. The larger the value, the better.

[0198] 2. Sampling error E s , which represents the root mean square error between the actual sampling data and the predicted water body distribution. The smaller the value, the better.

[0199] These two indicators can be combined into the objective function J and optimized using the genetic algorithm:

[0200] minJ=-R c +λE s

[0201] Among them, λ is the weight coefficient, which is used to balance the importance of the two indicators. Through the iteration of the genetic algorithm, the optimal sampling parameter S* corresponding to each group of augmented project data can be obtained.

[0202] In step S70, a recurrent neural network model needs to be trained to learn the mapping relationship between the environmental parameter E and the optimized sampling parameter S*. The input of the model is E, and the output is S*, which can be expressed as:

[0203]

[0204] in, represents the nonlinear mapping function of the regression neural network, and Φ is the network parameter. The back propagation algorithm can also be used to minimize the mean square error between the training sample and the network output, optimize the network parameter Φ, and thus train the sampling parameter determination model.

[0205] In step S80, when it is necessary to determine the depth-determining and stratification parameters of a multi-channel water sampler in a certain water area to be tested, the environmental parameters E0 of the water area are first obtained, including water depth D0, water quality Q0, water temperature T0 and flow rate V0, etc. Then, E0 is input into the sampling parameter determination model trained in step S70. The optimal sampling parameters for this water area can be obtained

[0206]

[0207] These optimized sampling parameters That is, the fixed depth and stratification parameter of the multi-channel water sampler in this water area, which can guide the actual sampling operation and ensure the accuracy and representativeness of the sampling results.

[0208] Specifically, the principle of the present invention is:

[0209] 1. Establish a water body change law model based on historical sampling data: In actual water quality monitoring, the historical sampling data of different areas of the same water body contain the inherent laws of the water body environment change. The present invention first collects these historical data, including environmental parameters (water depth, water quality, water temperature, flow rate, etc.), sampling parameters (sampling time interval, sampling depth, sampling volume, etc.) and sampling analysis results (physical and chemical indicators, biological indicators, etc.).

[0210] By analyzing and modeling these historical data, we can obtain a mathematical relationship model between water body environmental parameters and sampling analysis indicators. Commonly used modeling methods include regression analysis, time series analysis, etc. Establishing such a water body change law model can more accurately describe the overall condition of the water body under different environmental conditions and provide a basis for subsequent parameter optimization.

[0211] 2. Optimize sampling parameters based on machine learning: After having a water body change law model, the present invention further uses machine learning technology to optimize sampling parameters. First, the historical data is expanded and augmented to generate more diverse simulation data. Then, a multi-layer perceptron neural network model is trained to learn the complex mapping relationship between environmental parameters and sampling analysis data. Next, based on the trained neural network model, the sampling parameters (sampling depth, sampling volume, sampling time interval, etc.) are optimized in combination with a genetic algorithm. A genetic algorithm is a heuristic optimization algorithm that simulates the process of biological evolution to find the optimal solution of the objective function. In the present invention, the objective function includes two indicators: maximizing the sampling coverage rate and minimizing the sampling error. Through the iterative optimization of the genetic algorithm, the optimal sampling parameter scheme under various environmental conditions can be obtained to meet the maximum coverage and minimum measurement error of the overall distribution of the water body. These optimized parameters are the fixed depth and stratification parameters of the multi-channel water sampler, which can guide the actual water quality sampling work and improve the representativeness of the sampling results.

[0212] 3. Realize adaptive sampling parameter determination: Finally, the present invention trains a regression neural network model to learn the mapping relationship between environmental parameters and optimized sampling parameters. In this way, as long as the real-time environmental parameters of the water area to be tested are obtained, the optimal sampling parameter scheme can be quickly predicted through the regression model.

[0213] This adaptive parameter determination method does not require human experience intervention and can automatically adjust the sampling plan according to the actual conditions of the water body. Compared with the traditional method that relies on manual judgment, this method has stronger adaptability and automation capabilities, which not only improves the monitoring efficiency, but also ensures the scientificity and representativeness of the sampling results.

[0214] In order to better understand the present invention, the following provides Example 2 of the present invention in a specific scenario: A reservoir in a certain city has long been responsible for the drinking water supply task of the city, so its water quality has always been highly valued. In order to better grasp the dynamic changes in the water quality of the reservoir, the environmental protection department decided to deploy a set of multi-channel water samplers in the reservoir to monitor water quality indicators in real time.

[0215] According to the analysis of water quality monitoring data in previous years, this reservoir has some typical characteristics of water quality changes:

[0216] 1) The water temperature changes significantly with the seasons, with higher water temperatures in summer and lower temperatures in winter. The average annual water temperature is about 15°C;

[0217] 2) The reservoir has obvious stratification phenomenon, and there is a large difference in water quality between the surface and bottom layers, especially the dissolved oxygen content;

[0218] 3) Affected by the agricultural non-point source pollution from upstream, the water quality of the reservoir varies between the wet season and the dry season, and the nitrogen and phosphorus indicators fluctuate greatly;

[0219] 4) Affected by weather factors, reservoir water level and flow rate have certain daily and monthly variations.

[0220] In order to effectively monitor these dynamic characteristics of water quality, the environmental protection department requires that the multi-channel water sampler needs to meet the following technical indicators:

[0221] 1) The sampling depth covers the entire water layer of the reservoir and can reflect the water quality conditions of the surface, middle and bottom layers;

[0222] 2) The sampling interval should not exceed 4 hours, which can capture short-term changes in water quality;

[0223] 3) The single sampling volume should not exceed 2 liters to minimize disturbance to the water body;

[0224] 4) The entire monitoring system can realize remote monitoring and automatic data upload.

[0225] According to these technical requirements, the environmental protection department decided to use the multi-channel water sampler fixed depth layer parameter determination method proposed in this invention to design the monitoring plan for the reservoir. The specific implementation steps are as follows:

[0226] Step S10: Collect multiple groups of historical water collection project data

[0227] First, the environmental protection department collected the historical water quality monitoring data of the reservoir for the past five years. These data include:

[0228] 1) Environmental parameters: water depth (3-25m), water temperature (10-25℃), dissolved oxygen (4-12mg / L), pH value (6.5-8.5), turbidity (5-50NTU), nutrients (nitrogen and phosphorus index, 0.1-2.0mg / L), flow rate (0.1-0.6m / s), etc.;

[0229] 2) Sampling parameters: sampling depth (surface, middle, bottom), sampling time interval (1h, 2h, 4h, 8h), sampling volume (1L, 1.5L, 2L), etc.;

[0230] 3) Sampling and analysis data: physical and chemical indicators (pH value, dissolved oxygen, turbidity, conductivity, etc.), biological indicators (chlorophyll a, number of plankton, etc.), nutrient indicators (ammonia nitrogen, nitrate, phosphate, etc.).

[0231] These historical data cover the sampling conditions of different periods and water layers in the reservoir, laying the foundation for the subsequent establishment of a water body change law model.

[0232] Step S20: Establish and fit the basic change model of water body

[0233] Based on the historical data collected in step S10, the environmental protection department used the multivariate linear regression method to establish a relationship model between reservoir water quality indicators and environmental parameters. Taking dissolved oxygen (DO) as an example, the regression model can be expressed as:

[0234] DO = 9.82-0.15×water temperature+0.24×flow rate-0.36×turbidity+0.41×pH value

[0235] Through model fitting, R^2 reached 0.78, indicating that the model can better describe the law of reservoir DO changes with environmental parameters. Similarly, regression models between other water quality indicators (such as ammonia nitrogen, total phosphorus, etc.) and environmental parameters were also established.

[0236] In addition, the environmental protection department has also tried to establish a time series model of water quality indicators to describe the dynamic changes of water quality over time. For example, the ARIMA model is used to fit the time series of dissolved oxygen, and the model parameters are obtained as follows:

[0237]

[0238] Through this model, the changing trend of dissolved oxygen in the future can be predicted, providing a basis for the optimization of sampling parameters.

[0239] In general, these water body change models established based on historical data provide important reference information for subsequent parameter determination and can more accurately describe the laws of changes in the reservoir water quality with environmental changes.

[0240] Step S30: Expand the project data

[0241] Based on the water body change model established in step S20, the environmental protection department uses the Monte Carlo simulation method to expand and augment the historical project data.

[0242] Specifically, they first performed distribution fitting on historical observation data of environmental parameters (water temperature, flow rate, turbidity, etc.) to obtain the probability density function of each parameter. Then, they used a random number generator to simulate a large number of environmental parameters according to these probability distributions, and obtained more diverse combinations of environmental parameters.

[0243] Next, these simulated environmental parameters are substituted into the water quality index regression model and time series model established in step S20 to calculate the corresponding water quality analysis data. This simulation is repeated many times, and a large amount of augmented project data is finally generated, providing rich samples for subsequent neural network training.

[0244] Through this augmentation method, the environmental protection department obtained a total of 3,000 sets of simulated project data, which is 6 times the original historical data. These data not only retain the statistical characteristics of real data, but also cover a wider range of environmental conditions, providing a good foundation for subsequent optimization.

[0245] Step S40: Training the multi-layer perceptron neural network model

[0246] With abundant training samples, the environmental protection department set out to train a multi-layer perceptron (MLP) neural network model to learn the complex nonlinear mapping relationship between environmental parameters and water quality indicators.

[0247] The specific network structure is set as follows:

[0248] - Input layer: 7 nodes, corresponding to environmental parameters such as water temperature, flow rate, turbidity, pH value, ammonia nitrogen, nitrate, phosphate, etc.

[0249] -Hidden layer 1: 64 nodes, using ReLU activation function

[0250] -Hidden layer 2: 32 nodes, using ReLU activation function

[0251] - Output layer: 9 nodes, corresponding to water quality indicators such as dissolved oxygen, chemical oxygen demand, total nitrogen, total phosphorus, chlorophyll a, and plankton quantity

[0252] The standard back propagation algorithm is used for network training, and the mean absolute error (MAE) is used as the loss function to optimize the network parameters. During the training process, the 2000 sets of data generated in step S30 are used as the training set, and the remaining 1000 sets of data are used as the validation set. By adjusting the network structure and hyperparameters, the performance index of the mean absolute error less than 5% is finally achieved on the validation set.

[0253] The trained MLP model is a water body change model, which can accurately predict the distribution of various water quality indicators of the reservoir under given environmental conditions. This model provides an important basis for subsequent parameter optimization.

[0254] Step S50: Predicting water distribution based on water body change model

[0255] After having the water body change model trained in step S40, the environmental protection department inputs the environmental parameters of the 3000 sets of augmented project data in step S30 into the model and calculates the corresponding water quality index distribution.

[0256] Taking dissolved oxygen as an example, the model's prediction results show that under the environmental conditions of water temperature 15°C, flow velocity 0.3m / s, and turbidity 20NTU, the dissolved oxygen in the surface layer of the reservoir is about 9.5mg / L, in the middle layer about 7.2mg / L, and in the bottom layer about 5.8mg / L. Similarly, the distribution of other water quality indicators in different water layers was also obtained.

[0257] By analyzing these water distribution data, we can find that:

[0258] 1) Water temperature, flow rate and other factors have a significant impact on the spatial distribution of dissolved oxygen in the entire water body, and the dissolved oxygen in the bottom layer is generally low;

[0259] 2) Nutrient indicators (ammonia nitrogen, phosphate) differ greatly between the surface and bottom layers, reflecting the stratification characteristics of the reservoir;

[0260] 3) The plankton indicator (chlorophyll a) is relatively abundant in the middle and upper layers of the water, but less in the bottom layer.

[0261] These water quality distribution characteristics provide a basis for the optimization of subsequent sampling parameters and can guide how to reasonably arrange sampling points to cover the overall conditions of the water body.

[0262] Step S60: Optimizing sampling parameters using genetic algorithm

[0263] Based on the water distribution data predicted in step S50, the environmental protection department uses genetic algorithms to optimize the sampling parameters. The objective function includes two indicators:

[0264] 1) Sampling coverage R c: Reflects the proportion of water distribution area covered by the sampling point, the value range is [0,1], the larger the better.

[0265] 2) Sampling error E s : Reflects the error between the actual sampling data and the water body distribution prediction. The smaller the value, the better.

[0266] These two indicators are combined into the following objective function:

[0267] J=-R c +0.2E s

[0268] Among them, R c The calculation formula is:

[0269]

[0270] Among them, A i is the water distribution area covered by the i-th sampling point, V j is the total volume of the water body. Sampling error E s The root mean square error between the predicted value and the actual observed value is used.

[0271] The genetic algorithm is encoded as:

[0272] Decision variables: sampling depth (0-25m), sampling time interval (1h, 2h, 4h), sampling volume (1L, 1.5L, 2L)

[0273] Population size: 100

[0274] Evolutionary Algebra:200

[0275] Through iterative optimization of genetic algorithm, the optimal sampling parameter scheme is finally obtained:

[0276] Sampling depth: 2m for surface layer, 10m for middle layer, 20m for bottom layer

[0277] Sampling time interval: 4 hours

[0278] Sampling volume: 1.5L

[0279] Under this scheme, the sampling coverage R c Reach 92%, sampling error E s It is controlled within 3%, meeting the technical requirements of the environmental protection department.

[0280] Step S70: Training sampling parameters to determine the model

[0281] With the optimal sampling parameter solution obtained by optimization in step S60, the environmental protection department then trained a regression neural network model to learn the mapping relationship between environmental parameters and sampling parameters.

[0282] The input of the regression model is: 7 environmental parameters such as water temperature, flow rate, turbidity, pH value, and nutrients; the output is: 3 sampling parameters: sampling depth, sampling time interval, and sampling volume. The network structure is set as follows:

[0283] - Input layer: 7 nodes

[0284] -Hidden layer 1: 32 nodes, using ReLU activation function

[0285] -Hidden layer 2: 16 nodes, using ReLU activation function

[0286] -Output layer: 3 nodes

[0287] The back propagation algorithm is also used for training, with mean absolute error (MAE) as the loss function. After 200 epochs of training, the model achieved a performance indicator of less than 5% mean absolute error on the validation set.

[0288] The trained regression model is the sampling parameter determination model, which can quickly predict the optimal sampling parameter plan required for the water area based on the environmental parameters obtained in real time.

[0289] Step S80: Determine the sampling parameters of the current water area

[0290] When actual sampling of the reservoir is required, the multi-channel water sampler equipment first obtains the current environmental parameters, including water temperature (15°C), flow rate (0.4m / s), turbidity (25NTU), pH value (7.2), nutrients (ammonia nitrogen 0.5mg / L, nitrate 1.2mg / L, phosphate 0.3mg / L), etc.

[0291] Then, these environmental parameters are input into the sampling parameter determination model trained in step S70, and the model can output the optimal sampling scheme:

[0292] - Sampling depth: 2m for surface layer, 10m for middle layer, 20m for bottom layer

[0293] - Sampling time interval: 4 hours

[0294] -Sampling volume: 1.5L

[0295] These optimized sampling parameters can not only cover the overall distribution of water bodies (coverage rate of 92%), but also control the measurement error at a low level (within 3%), meeting the technical requirements of environmental protection departments.

[0296] The multi-channel water sampler automatically completed the regular sampling of the reservoir based on these parameter settings. After the collected water samples were transported back to the laboratory, the test results showed:

[0297] -Dissolved oxygen in the surface layer is 9.3mg / L, in the middle layer is 7.5mg / L, and in the bottom layer is 6.1mg / L

[0298] - Ammonia nitrogen 0.48mg / L, nitrate 1.1mg / L, phosphate 0.28mg / L

[0299] -Chlorophyll a concentration 12μg / L, plankton count 3500 / L

[0300] These monitoring results are basically consistent with the water quality distribution predicted in step S50, indicating that the sampling parameters determined by this method are reasonable and feasible, and can effectively reflect the actual water quality of the reservoir.

[0301] In order to further verify the effectiveness of the method of the present invention, the environmental protection department has operated the multi-channel water sampler in the reservoir for a long time and collected a large amount of water quality monitoring data. Through the analysis of these data, it is found that the method performs well in practical applications, which is specifically reflected in the following aspects:

[0302] 1. The representativeness and reliability of the sampling results are greatly improved: The sampling parameters determined by the method of the present invention can better cover the overall water quality distribution of the reservoir. Taking dissolved oxygen as an example, the monitoring results of the surface, middle and bottom layers reflect obvious stratification characteristics, which are consistent with the distribution predicted in step S50. At the same time, the discrete degree of the monitoring data of different water layers is also small, indicating that the error in the sampling process has been effectively controlled.

[0303] Compared with the previous situation of selecting sampling parameters based on manual experience, the sampling scheme determined by this method can better represent the overall water quality of the reservoir and provide reliable basic data for subsequent water quality evaluation.

[0304] 2. The response efficiency of abnormal water quality events is greatly improved: During the operation of the reservoir, an accident occurred in which chemical wastewater entered the lake, causing the water quality to change dramatically in a short period of time. Since the sampling time interval determined by the method of the present invention is short (4 hours), the multi-channel water sampler can quickly capture this water quality abnormality and upload the abnormal alarm information within 2 hours after the accident. The environmental protection department quickly organized emergency disposal and quickly identified the source of pollution and took effective measures by retrieving recent water quality monitoring data, minimizing environmental losses. If the traditional daily sampling plan is adopted, it is likely to take 1-2 days to discover the problem and miss the best time for disposal.

[0305] Therefore, the method of the present invention greatly improves the timeliness and response capability of the water quality monitoring system, and plays an important role in responding to sudden events in the water environment.

[0306] 3. The operating cost is significantly reduced, and the operation and maintenance are more intelligent and efficient: First, the method of the present invention makes full use of historical monitoring data, and there is no need to invest additional manpower for on-site sampling. At the same time, the optimized sampling parameters can cover the water body conditions to the maximum extent, reduce unnecessary repeated sampling, and greatly reduce consumables and labor costs. Secondly, the adaptive adjustment function of the sampling parameters enables the multi-channel water sampler to autonomously optimize the sampling plan according to water body changes without human intervention. This not only improves the level of automation of monitoring, but also reduces dependence on professional and technical personnel, greatly alleviating the pressure of operation and maintenance. In addition, the system realizes the remote automatic uploading of water quality data, which greatly facilitates the information management and early warning analysis work of the environmental protection department. Compared with traditional manual inspections and on-site recording methods, this intelligent water quality monitoring mode has greatly improved work efficiency.

[0307] In summary, the environmental protection department has fully verified the excellent performance of the method of the present invention in the application of multi-channel water samplers through long-term practice. This method not only improves the scientific nature and response capability of water quality monitoring, but also significantly reduces the operating cost, providing strong support for the realization of intelligent water environment monitoring. In the future, the environmental protection department plans to promote the application of this technology in more water bodies to better protect the regional water environment quality.

[0308] In order to further demonstrate the performance of the method of the present invention, the long-term monitoring data of the reservoir are organized into a table and Table 1 as follows:

[0309] Table 1 Statistics of reservoir dissolved oxygen monitoring results

[0310] Water layer Average value (mg / L) Standard Deviation surface layer 9.1 0.4 Middle level 7.4 0.6 Bottom Layer 6.0 0.5

[0311] As can be seen from Table 1, the sampling parameters determined by the method of the present invention can better reflect the differences in the vertical stratification of the reservoir dissolved oxygen. The surface dissolved oxygen is higher, and the bottom layer is relatively low, which is consistent with the reservoir stratification characteristics. The standard deviation of the monitoring results of each water layer is also small, indicating that the sampling data is more stable and reliable.

[0312] The 4-hour sampling interval determined by the method of the present invention can better capture this short-term dynamic change and provide valuable data support for water quality early warning.

[0313] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for determining depth-determining stratification parameters of a multi-channel water sampler, characterized in that: The following steps are involved: S10, collecting multiple groups of historical water collection project data, wherein each group of water collection project data is specifically project data of historical water collection projects that have been successfully collected by multi-channel water collectors in different areas of the same water body; S20, for each set of environmental parameters and sampling analysis data in the project data, establishing and fitting the basic change model of the water body; S30, based on the basic change model, each set of project data is augmented and expanded to obtain corresponding multiple sets of augmented and expanded project data; S40, using each set of water collection project data and its corresponding augmented project data as a training set, using the multiple sets of water collection project data as a validation set, and training a multi-layer perceptron neural network model to obtain a water body change model; S50, for each set of water collection project data in the augmented project data, inputting the environmental parameters and sampling analysis parameters therein into the water body change model to obtain water body distribution data; S60, for each group of water sampling project data in the augmented project data, taking the sampling parameters as the initial population, taking maximizing the sampling coverage and minimizing the sampling error as the objective function, using the obtained water body distribution, and using a genetic algorithm to calculate the optimal sampling parameters; S70, for all augmented project data, establish a training data set, wherein the input of the training is the environmental parameter, the output of the training is the sampling parameter, and train a regression neural network to obtain a sampling parameter determination model; S80, obtaining environmental parameters of the current water area to be tested, and inputting them into the sampling parameter determination model to obtain sampling parameters as depth-determining and stratification parameters of the multi-channel water sampler of the current water area to be tested.

2. The method for determining the depth-setting stratification parameters of a multi-channel water sampler according to claim 1, characterized in that: The project data includes environmental parameters, sampling parameters and sampling analysis data.

3. The method for determining the depth-determining stratification parameters of a multi-channel water sampler according to claim 2, characterized in that: The environmental parameters include water depth, water quality, water temperature and flow rate.

4. The method for determining the depth-setting stratification parameters of a multi-channel water sampler according to claim 2, characterized in that: The sampling parameters are provided by experts according to the environmental parameters, including sampling time interval, sampling depth and sampling volume.

5. The method for determining the depth-setting stratification parameters of a multi-channel water sampler according to claim 2, characterized in that: The sampling and analysis data include physical indicators, biological indicators and chemical indicators of the sampled water.

6. The method for determining the depth-setting stratification parameters of a multi-channel water sampler according to claim 1, characterized in that: The water body change model includes the following modules: an environmental parameter preprocessing module, a statistical model module, a deep learning module and a residual connection module.

7. A method for determining depth-determining stratification parameters of a multi-channel water sampler according to claim 6, characterized in that: The statistical model module adopts a mathematical statistical model to fit the basic relationship between environmental parameters and sampling analysis data.

8. The method for determining the depth-setting stratification parameters of a multi-channel water sampler according to claim 6, characterized in that: The deep learning module uses a multi-layer perceptron or a long short-term memory network.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program instructions, and when the program instructions are executed, they are used to execute the method for determining the fixed-depth stratification parameters of a multi-channel water sampler according to any one of claims 1 to 8.

10. A system for determining depth and stratification parameters of a multi-channel water sampler, characterized in that: A computer-readable storage medium comprising the computer-readable storage medium of claim 9.

Citation Information

Patent Citations

  • Method for predicting water area where water bloom of blue algae occurs first next year in large shallow lake

    CN102141517A

  • Water supplement and algae control method for large-scale shallow lake water bloom agglomeration water area

    CN105973207A

  • Long-term sampling equipment of shallow groundwater from polluted areas

    CN107894350A

  • River water quality predicting method

    CN108053054A

  • Methods and systems for detection in industrial internet of things data collection environment with large data sets

    CN110073301A