Ecological restoration method and system based on river monitoring

Abstract

The invention discloses an ecological restoration method and system based on riverway monitoring, and the method comprises the steps: obtaining the water velocity data of a target riverway, and calculating the trend component and fluctuation component of the water velocity data according to a discrete wavelet transform method; the method comprises the following steps: acquiring dissolved oxygen data, ph value data and turbidity data of a target river channel, and respectively preprocessing the dissolved oxygen data, the ph value data and the turbidity data to obtain a change rate of the dissolved oxygen data, a mapping relation function of a ph value and aeration intensity and a fractal dimension of the turbidity data; constructing a comprehensive adjustment factor according to the trend component, the fluctuation component, the change rate, the mapping relation function and the fractal dimension; and inputting the comprehensive adjustment factor into a pre-constructed LSTM model for prediction to obtain an ideal adjustment factor of the target river channel, and adjusting the aeration intensity of the target river channel according to the ideal adjustment factor to realize ecological restoration of the target river channel. According to the method provided by the invention, the accuracy of ecological monitoring of the river channel is improved.

Description

Technical Field

[0001] The present application relates to the field of environmental monitoring technology, and in particular to an ecological restoration method and system based on river channel monitoring. Background Art

[0002] With the acceleration of urbanization and the increasing requirements for water resources management, river ecological monitoring has become increasingly important. Through river ecological monitoring, potential ecological problems can be discovered and warned in a timely manner to ensure the health and stability of the water ecosystem.

[0003] However, existing water quality monitoring technologies often only focus on a single water quality parameter and lack a comprehensive analysis of the relationship between different parameters. This results in the inability to fully consider the impact of various factors when formulating restoration strategies, thus affecting the formulation and implementation of restoration strategies. Summary of the invention

[0004] The present application aims to provide an ecological restoration method and system based on river monitoring, which solves the technical problem of refined monitoring of river ecology.

[0005] In order to solve the above technical problems, the present application embodiment provides an ecological restoration method based on river monitoring, including:

[0006] Acquire water flow velocity data captured by a plurality of water flow velocity sensors disposed in a target river channel area, and calculate a trend component and a fluctuation component of the water flow velocity data according to a discrete wavelet transform method;

[0007] Obtaining dissolved oxygen data, pH value data and turbidity data captured by a plurality of water quality sensors disposed in the target river channel area, preprocessing the dissolved oxygen data, the pH value data and the turbidity data respectively, to obtain a change rate of the dissolved oxygen data, a mapping relationship function between the pH value and aeration intensity, and a fractal dimension of the turbidity data;

[0008] constructing a comprehensive adjustment factor according to the trend component, the fluctuation component, the change rate, the mapping relationship function and the fractal dimension, wherein the comprehensive adjustment factor reflects the influence of water flow parameters and water quality parameters on the aeration intensity of the target river channel;

[0009] Input the comprehensive adjustment factor into a pre-built LSTM model for prediction to obtain an ideal adjustment factor for the target river channel;

[0010] The aeration intensity of the target river channel is adjusted according to the ideal adjustment factor to achieve ecological restoration of the target river channel.

[0011] As one preferred solution, the method of calculating the trend component and the fluctuation component of the water velocity data according to the discrete wavelet transform method includes:

[0012] Decomposing the water velocity data at a preset scale based on a preset wavelet basis function to obtain an approximate coefficient and a detail coefficient;

[0013] Reconstructing the approximate coefficient of the lowest frequency to obtain a trend component, wherein the trend component reflects the variation trend of the water flow velocity on a long time scale;

[0014] A fluctuation component is calculated according to the trend component, wherein the fluctuation component reflects the fluctuation of the water flow velocity relative to the change trend on a short time scale.

[0015] As one preferred solution, the dissolved oxygen data, the pH value data and the turbidity data are preprocessed respectively to obtain the change rate of the dissolved oxygen data, the mapping relationship function between the pH value and the aeration intensity and the fractal dimension of the turbidity data, including:

[0016] Calculating the long-term change rate and the short-term change rate of the dissolved oxygen data based on the dissolved oxygen data;

[0017] A mapping function between the pH value and the aeration intensity is established through a SVM regression model;

[0018] The fractal dimension of the turbidity data was calculated based on the box counting method.

[0019] As one of the preferred solutions, the comprehensive adjustment factor is input into a pre-built LSTM model for prediction to obtain the ideal adjustment factor of the target river, including:

[0020] Construct a training set based on the acquired historical comprehensive adjustment factor sequence and its corresponding ideal value;

[0021] Inputting the training set into a pre-built initial LSTM model for training to obtain an LSTM model;

[0022] In the actual prediction process, the acquired real-time comprehensive adjustment factor is input into the LSTM model for prediction to obtain the ideal adjustment factor of the target river channel.

[0023] As one preferred solution, adjusting the aeration intensity of the target river channel according to the ideal adjustment factor includes:

[0024] The adjusted aeration intensity is calculated according to the ideal adjustment factor and the aeration intensity adjustment formula, and the aeration intensity adjustment formula is expressed as:

[0025]

[0026] Where I(t) is the adjusted aeration intensity, I0 is the initial aeration intensity, is the Sigmoid function, is the ideal adjustment factor, t0 is the time parameter related to the biological clock of the target river ecosystem, and τ is the time constant.

[0027] Another embodiment of the present application provides an ecological restoration system based on river monitoring, including:

[0028] A first acquisition module is used to acquire water flow velocity data captured by a plurality of water flow velocity sensors disposed in a target river channel area, and calculate a trend component and a fluctuation component of the water flow velocity data according to a discrete wavelet transform method;

[0029] A second acquisition module is used to acquire dissolved oxygen data, pH value data and turbidity data captured by a plurality of water quality sensors disposed in the target river channel area, and pre-process the dissolved oxygen data, the pH value data and the turbidity data respectively to obtain a change rate of the dissolved oxygen data, a mapping relationship function between the pH value and the aeration intensity, and a fractal dimension of the turbidity data;

[0030] A construction module, for constructing a comprehensive adjustment factor according to the trend component, the fluctuation component, the change rate, the mapping relationship function and the fractal dimension, wherein the comprehensive adjustment factor reflects the influence of water flow parameters and water quality parameters on the aeration intensity of the target river channel;

[0031] A prediction module, used for inputting the comprehensive adjustment factor into a pre-built LSTM model for prediction to obtain an ideal adjustment factor for the target river channel;

[0032] The adjustment module is used to adjust the aeration intensity of the target river channel according to the ideal adjustment factor to achieve ecological restoration of the target river channel.

[0033] As one preferred solution, the first acquisition module is specifically used to:

[0034] Decomposing the water velocity data at a preset scale based on a preset wavelet basis function to obtain an approximate coefficient and a detail coefficient;

[0035] Reconstructing the approximate coefficient of the lowest frequency to obtain a trend component, wherein the trend component reflects the variation trend of the water flow velocity on a long time scale;

[0036] A fluctuation component is calculated according to the trend component, wherein the fluctuation component reflects the fluctuation of the water flow velocity relative to the change trend on a short time scale.

[0037] As one preferred solution, the second acquisition module is specifically used to:

[0038] Calculating the long-term change rate and the short-term change rate of the dissolved oxygen data based on the dissolved oxygen data;

[0039] A mapping function between the pH value and the aeration intensity is established through a SVM regression model;

[0040] The fractal dimension of the turbidity data was calculated based on the box counting method.

[0041] As one preferred solution, the prediction module is specifically used for:

[0042] Construct a training set based on the acquired historical comprehensive adjustment factor sequence and its corresponding ideal value;

[0043] Inputting the training set into a pre-built initial LSTM model for training to obtain an LSTM model;

[0044] In the actual prediction process, the acquired real-time comprehensive adjustment factor is input into the LSTM model for prediction to obtain the ideal adjustment factor of the target river channel.

[0045] As one preferred solution, the adjustment module is specifically used for:

[0046] The adjusted aeration intensity is calculated according to the ideal adjustment factor and the aeration intensity adjustment formula, and the aeration intensity adjustment formula is expressed as:

[0047]

[0048] Where I(t) is the adjusted aeration intensity, I0 is the initial aeration intensity, is the Sigmoid function, is the ideal adjustment factor, t0 is the time parameter related to the biological clock of the target river ecosystem, and τ is the time constant.

[0049] Compared with the prior art, the beneficial effects of the embodiments of the present application are at least one of the following:

[0050] (1) This application uses the discrete wavelet transform method to decompose the water flow velocity data into trend component and fluctuation component, which can more finely understand the changing trend and short-term fluctuation of the water flow velocity, and provide a more accurate basis for subsequent adjustments; at the same time, the dissolved oxygen content, pH value and turbidity data are pre-processed to extract features such as change rate, mapping relationship function and fractal dimension. These features can more comprehensively reflect the water quality status and its changing trend, and improve the accuracy and sensitivity of water quality assessment.

[0051] (2) The comprehensive adjustment factor constructed in this application integrates multiple key features of water flow parameters and water quality parameters, which can fully reflect the influence of these factors on aeration intensity, avoid the limitations of single parameter adjustment, and improve the accuracy and scientificity of the adjustment. At the same time, by inputting the comprehensive adjustment factor into the pre-built LSTM model for prediction, the ideal adjustment factor of the target river can be obtained. The long and short-term memory capacity of the LSTM model enables it to capture complex patterns in time series data, thereby improving the accuracy of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic diagram of a process of an ecological restoration method based on river channel monitoring in one embodiment of the present application;

[0053] Figure 2 is a three-dimensional schematic diagram of an aerator in one embodiment of the present application;

[0054] Figure 3 It is a schematic diagram of the internal cross-section of an aerator in one embodiment of the present application;

[0055] Figure 4 It is a schematic diagram of an ecological restoration system based on river monitoring in one embodiment of the present application;

[0056] Reference numerals:

[0057] Among them, 1. the air outlet of the micropore; 2. the air inlet pipe; 3. the main ventilation pipe connected to the air inlet pipe. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0059] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0060] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used in this article are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application. The term "and / or" used in this article includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0061] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0062] This application provides an ecological restoration method based on river monitoring. For details, see Figure 1 , Figure 1 The figure shows a flow chart of an ecological restoration method based on river channel monitoring in one embodiment of the present application, which includes steps S1-S5:

[0063] S1: Acquire water velocity data captured by a plurality of water velocity sensors installed in the target river channel area, and calculate the trend component and fluctuation component of the water velocity data according to the discrete wavelet transform method;

[0064] In this step, a water flow velocity sensor based on the Doppler effect principle measures the water flow velocity at fixed time intervals (for example, every 5 minutes), and the measured value is υ(t) (t represents time). The water flow velocity sensor is based on the Doppler frequency shift principle. When sound waves (or other waves) encounter moving objects (particles in the water flow), the frequency of the reflected waves will change. By measuring the frequency change, the water flow velocity can be calculated. The normal range of water flow velocity is [υ min , max ] This range is based on long-term observations of the river or determined according to river design and ecological needs.

[0065] Preferably, in one embodiment of the present application, the trend component and the fluctuation component of the water velocity data are calculated according to the discrete wavelet transform method, including:

[0066] Decomposing the water velocity data at a preset scale based on a preset wavelet basis function to obtain approximate coefficients and detail coefficients;

[0067] The approximate coefficients of the lowest frequency are reconstructed to obtain the trend component, which reflects the changing trend of water velocity on a long time scale;

[0068] The fluctuation component is calculated based on the trend component, which reflects the fluctuation of water flow velocity relative to the change trend on a short time scale.

[0069] That is to say, in order to obtain the dynamic characteristics of water flow velocity, this application uses discrete wavelet transform (DWT) to decompose the water flow velocity data υ(t). Discrete wavelet transform is a mathematical tool that decomposes a signal into different frequency components. Select a suitable wavelet basis function (such as db4 wavelet in Daubechies wavelet system) to decompose the water flow velocity data. For υ(t), this application selects J scales for decomposition, and at each scale j = 1, 2, ..., J, obtains the approximate coefficient a j，k and detail factor d j，k . Where k represents the translation amount, and its value range depends on the length and decomposition scale of the data.

[0070] It should be noted that the approximation coefficient a j，k Represents the low-frequency part of the signal, reflecting the trend information of water velocity; for example, the approximate coefficient at a larger scale may represent seasonal or long-term water velocity trends. j，k It represents the high-frequency part of the signal, reflecting the fluctuation information of water velocity on a shorter time scale, such as changes in water velocity caused by local topography, short-term meteorological changes or other sudden factors. j，k Reconstruct the trend component of water velocity υ trend The trend component describes the change trend of water velocity on a longer time scale, such as the seasonal change trend of water velocity or the long-term change trend of velocity caused by factors such as river topography.

[0071] In order to obtain the trend component υ of the water velocity tend (t), the approximation coefficient for the lowest frequency (i.e. the approximation coefficient a at the maximum scale J) j，k ) is reconstructed. The reconstruction process is based on the inverse transform formula of wavelet transform. j，k Convert back to the time domain signal and get υ trend (t). Trend component υ trend(t) is calculated by approximating the lowest frequency coefficient a j，k (here J = 3) is reconstructed. The reconstruction process is the inverse process of the decomposition process, using the low-pass filter corresponding to the decomposition process and high pass filter

[0072] Specifically, the reconstruction formula is:

[0073] Furthermore, the fluctuation component is the result of subtracting the trend component from the original water velocity data. Calculate the fluctuation component υ of the water velocity fluct (t) = v(t) - v trend The fluctuation component reflects the fluctuation of water velocity relative to the trend on a shorter time scale, such as velocity fluctuations caused by local water flow disturbances or short-term meteorological factors.

[0074] In this step, the fluctuation component and the trend component are normalized. The normalization process makes the changes in water velocity at different time scales and different data points comparable, which facilitates subsequent analysis and comparison. trend (t) and the fluctuation component υ fluct (t) Perform normalization:

[0075] Trend Component trend (t) The normalization formula is: Map it to the interval [0, 1] to facilitate subsequent calculations and comparisons.

[0076] Fluctuation component fluct (t) The normalization formula is: where υ flucr，min and flucr，max It is the lower and upper limits of the volatility component obtained based on historical data statistics. This also maps the volatility component to the [0, 1] interval.

[0077] S2: Obtain dissolved oxygen data, pH value data and turbidity data captured by several water quality sensors installed in the target river area, pre-process the dissolved oxygen data, pH value data and turbidity data respectively, and obtain the change rate of dissolved oxygen data, the mapping relationship function between pH value and aeration intensity, and the fractal dimension of turbidity data;

[0078] In this step, several water quality sensors are set up in the target river area. These sensors should be able to capture water quality parameters, including dissolved oxygen, pH, and turbidity, in real time or periodically. Data is collected from these sensors to ensure the accuracy and integrity of the data. The data can be transmitted to the data collection system via wired or wireless means.

[0079] Preferably, in one embodiment of the present application, the dissolved oxygen data, the pH value data and the turbidity data are preprocessed respectively to obtain the change rate of the dissolved oxygen data, the mapping relationship function between the pH value and the aeration intensity and the fractal dimension of the turbidity data, including:

[0080] Calculate the long-term change rate and short-term change rate of dissolved oxygen data based on dissolved oxygen data;

[0081] The mapping function between pH value and aeration intensity is established through SVM regression model;

[0082] The fractal dimension of turbidity data was calculated based on the box counting method.

[0083] It can be understood that by comparing the dissolved oxygen values ​​at different time points and calculating the change divided by the time interval to measure the dissolved oxygen content to obtain DO(t), the target value DO is set target and normal range [DO min , DO max ], where the time interval for calculating short-term dissolved oxygen is shorter than that for calculating long-term dissolved oxygen.

[0084] In some embodiments, the short-term rate of change ΔDO is calculated s (t) = DO(t) - DO(t - Δt), where Δt = 10 minutes, is used to capture changes in dissolved oxygen content in a short period of time, such as fluctuations in dissolved oxygen caused by local biological activity or short-term water quality changes.

[0085] Calculate the long-term rate of change ΔDO l (t) = DO(t) - DO(tT), where T = 12 hours. This rate of change reflects the changing trend of dissolved oxygen over a longer period of time, such as when it is affected by circadian rhythms or large-scale water quality changes.

[0086] In this step, the dissolved oxygen content DO(t) is normalized. Through normalization, the dissolved oxygen content, short-term change rate and long-term change rate are converted to the same scale to facilitate subsequent data analysis and comparison. The formula is expressed as

[0087] Specifically, for the short-term change rate ΔDO s (t) is normalized, and the formula is expressed as Where ΔDO s，min and ΔDO s，max It is the lower and upper limits of the short-term rate of change determined based on historical data.

[0088] Long-term change rate ΔDO l (t) is normalized, and the formula is expressed as Where ΔDO l，min and ΔDOl，max It is the lower and upper limits of the long-term rate of change determined based on historical data.

[0089] In this step, the SVM regression model is used to establish the relationship between the value and the aeration intensity. SVM is a machine learning model based on statistical learning theory and has good generalization ability. This application uses a pH sensor based on the principle of a glass electrode or an ion selective electrode to measure the pH value of the water body at fixed time intervals (such as every 5 minutes). The normal range of pH value is set according to the type of water body, water quality standards and treatment objectives. For example, for some freshwater ecosystems, the normal range of pH value may be set to 6.5 to 8.5.

[0090] Collect historical pH data and corresponding aeration intensity adjustment values ​​from previous experiments, monitoring or manual experience records. Ensure that the correspondence between the data timestamp, pH value and aeration intensity adjustment value is accurate, and remove outliers or noise data to ensure data accuracy and reliability.

[0091] In some embodiments, the pH value is used as an input feature (independent variable) and the aeration intensity adjustment value is used as an output label (dependent variable). Since only the original pH value is used as a feature, no additional feature conversion or feature engineering is required. However, in some complex cases, feature expansion or dimensionality reduction may be required.

[0092] The SVM regression model selects a suitable kernel function. Commonly used kernel functions include linear kernel, polynomial kernel, radial basis function (RBF), etc.

[0093] In some embodiments, an RBF kernel function can be selected, which can handle nonlinear relationships. Other parameters of the model, such as the penalty coefficient and the width parameter of the RBF kernel function, are determined by cross-validation and other methods. The selection of these parameters has an important impact on the performance and generalization ability of the model. The SVM model is trained using the prepared historical data. The goal of the training is to minimize the error between the predicted aeration intensity adjustment value and the actual value. Commonly used error metrics include mean square error (MSE) and the like. The mean square error is expressed as:

[0094] where y i is the actual aeration intensity adjustment value, is the predicted value, n is the number of data points. Use the test data set to evaluate the performance of the model, including prediction accuracy, generalization ability, etc. If the model performance is poor, it can be optimized by adjusting parameters, increasing the amount of data, or improving feature selection.

[0095] After training, the mapping function between pH value and aeration intensity is obtained. This function can predict a suitable aeration intensity adjustment value based on the current pH value, taking into account the complex nonlinear effect of pH value on aeration intensity. For example, when pH(t) = 7, f pH (7) may return a value indicating the proportional adjustment required to aeration intensity at this pH value.

[0096] In this step, the box counting method is used to calculate the fractal dimension D of the turbidity data. T (t). Fractal dimension is an indicator that describes the complexity and irregularity of geometric objects. For turbidity data, fractal dimension can reflect the complexity of turbidity changes, such as the mixing of pollutants from different sources or the complex impact of water flow on turbidity.

[0097] Specifically, the turbidity sensor measures the turbidity at a time interval of 5 minutes to obtain the measured value T(t). The turbidity sensor is based on the principle of light scattering or transmission, and measures the degree of light scattering or transmission of suspended particles in water to determine the turbidity. The box counting method is used to calculate the fractal dimension D of the turbidity data. T (t). The basic steps of the box counting method are as follows:

[0098] 1) Determine the range of turbidity data and divide it into "boxes" of different sizes. Initially, you can choose a smaller box size (such as a box side length of a small positive number), and then gradually increase the box size. For example, for data with turbidity values ​​in the range of [0, 100], you can start with a smaller box size (such as a box side length of 1).

[0099] 2) For each box size, count the number of boxes that contain turbidity data points. As the box side length increases, the number of boxes that contain data points generally decreases. For example, count the number of boxes that contain turbidity data points N(∈), where ∈ is the side length of the box. As the box side length ∈ changes, N(∈) will also change.

[0100] 3) Perform logarithmic processing on the number of boxes under different box side lengths, that is, calculate log(number of boxes) and log(box side length). Use linear regression or other fitting methods to fit log(number of boxes) and log(box side length) to obtain the slope of the fitted line. This slope is the fractal dimension D of the turbidity data. In two-dimensional space, the fractal dimension D is usually between 1 and 2, where D = 1 represents a completely regular geometric shape and D = 2 represents a completely filled plane.

[0101] Specifically, according to the definition of fractal dimension By performing logarithmic fitting on N(∈) under different ∈, the fractal dimension D of the turbidity data at each time t is calculated. T(t). The fractal dimension can reflect the complexity of turbidity changes. For example, if turbidity is caused by a mixture of suspended particles of different sizes, its fractal dimension may be high.

[0102] 4) Based on historical data, determine the lower limit D_min and upper limit D_max of the fractal dimension. These values ​​can be obtained by analyzing the fractal dimension distribution of historical turbidity data. Use the normalization formula to map the fractal dimension to a specified interval (such as 0 to 1) for calculation in the comprehensive adjustment factor. The formula is expressed as:

[0103]

[0104] S3: A comprehensive adjustment factor is constructed based on the trend component, fluctuation component, change rate, mapping relationship function and fractal dimension. The comprehensive adjustment factor reflects the influence of water flow parameters and water quality parameters on the aeration intensity of the target river;

[0105] In this step, the comprehensive adjustment factor C(t) is an indicator that comprehensively considers the influence of multiple factors such as water flow rate, dissolved oxygen content, pH value and turbidity on aeration intensity. The formula is:

[0106] C(t)=w1×υ n1 (t)×(1+ω2Xυ n2 (t))+ω3×DO n1 (t)×(1+w4XDO n2 (t)+ω5×DO n3 (t)+w6×f pH (pH(t))+w7×D T，n (t)

[0107] Among them, ω1×υ n1 (t)×(1+w2×υ n2 (t)) represents the trend component of water velocity v n1 (t) and its fluctuation component υ n2 (t) on the comprehensive adjustment factor C(t), w3×DO n1 (t)×(1+w4×DO n2 (t)+w5×DO n3 (t)) represents the dissolved oxygen content DO n1 (t) and its short-term rate of change DO n2 (t) and long-term rate of change DO n3 (t), w1×υ n1 (t)×(1+w2×υn2(t)) represents the trend component υ of the water flow velocity n1 (t) and its fluctuation component υ n2 (t) on the comprehensive adjustment factor C(t), w3×DOn1 (t)×(1+w4×DO n2 (t)+w5×DO n3 (t)) represents the dissolved oxygen content DO n1 (t) and its short-term rate of change DO n2 (t) and long-term rate of change DO n3 (t), w6×f pH (pH(t)) represents the contribution of the mapping relationship between pH value and aeration intensity obtained by SVM regression to the comprehensive adjustment factor, w7×D T，n (t) represents the influence of the fractal dimension of turbidity on the comprehensive adjustment factor. The weight coefficients w1-w7 are determined based on experiments and actual river conditions.

[0108] S4: Input the comprehensive adjustment factor into the pre-built LSTM model for prediction to obtain the ideal adjustment factor of the target river;

[0109] Preferably, in one embodiment of the present application, the comprehensive adjustment factor is input into a pre-built LSTM model for prediction to obtain an ideal adjustment factor of the target river channel, including:

[0110] Construct a training set based on the acquired historical comprehensive adjustment factor sequence and its corresponding ideal value;

[0111] Input the training set into the pre-built initial LSTM model for training to obtain the LSTM model;

[0112] In the actual prediction process, the real-time comprehensive adjustment factor obtained is input into the LSTM model for prediction to obtain the ideal adjustment factor of the target river.

[0113] In related technologies, LSTM is a special recurrent neural network (RNN) suitable for processing time series data. The LSTM network processes sequence information through a special gate structure (forget gate, input gate, and output gate) to effectively capture long-term dependencies in time series. For example, it can learn the impact pattern of past comprehensive adjustment factors on the current aeration intensity adjustment, such as the cumulative impact of the changing trends of parameters such as water flow rate and dissolved oxygen content over a period of time on the current aeration intensity adjustment.

[0114] Specifically, the LSTM network consists of multiple LSTM units, each of which contains an input gate i t 、Forget gate t , output gate o t and cell state C t . Input gate i t =σ(W xi x t +W hi ht-1 +b i ) determines the current input x t (Here x t =C(t)) how much information can update the cell state, where W xi and W hi is the weight matrix, b i is the bias term, σ is the Sigmoid function, which maps the value to the (0, 1) interval. t =σ(W xf x t +W hf h t-1 +b f ) determines the cell state C at the previous moment t-1 How much information can be forgotten in . The cell state is represented by ,here Represents element-wise multiplication. The cell state is updated through the forget gate and input gate, and the tanh function maps the value to the (-1, 1) interval. The output gate o t =σ(W xo x t +W ho h t-1 +b o ) determines the cell state C t How much information can be output. The hidden state is represented by , hidden state h t As the output of the LSTM unit, it also serves as the input h of the next LSTM unit t-1 .

[0115] In this step, the historical comprehensive adjustment factor sequences of the target river and their corresponding ideal values ​​are collected. These historical data should contain sufficient time spans to capture long-term dependencies in the time series. The historical data are cleaned, denoised, and standardized to ensure the accuracy and consistency of the data. Based on the obtained historical comprehensive adjustment factor sequences and their corresponding ideal values, a training set for training the LSTM model is constructed. Generally, the data needs to be divided into input sequences and output labels. The input sequence is a continuous comprehensive adjustment factor value, and the output label is the corresponding ideal adjustment factor value.

[0116] Constructing an initial LSTM model includes setting the network structure (such as the number of hidden layers, the number of neurons, etc.), activation function, optimizer, etc. In some embodiments, assuming that the time window size n=10, that is, the length of the input sequence is 10, select a suitable LSTM network structure, for example, set the number of hidden layer neurons to 20.

[0117] After the initial model is built, the training set is input into the LSTM model for training, and the model parameters are adjusted through the back propagation algorithm to minimize the prediction error. During the training process, strategies such as cross-validation and early stopping can be used to prevent overfitting.

[0118] Specifically, the historical sequence of comprehensive adjustment factors {C(tn), C(t-n+1), ..., C(t-1)} is used as the input x of the LSTM network. t After being processed by the LSTM network, the output is the ideal adjustment factor that takes into account the impact of historical data It not only includes the comprehensive impact of various parameters on aeration intensity at the current moment, but also integrates useful information in historical data, making the aeration intensity adjustment more in line with the dynamic change law of the river ecosystem. By inputting the historical sequence of the comprehensive adjustment factor C(t) into the trained LSTM network, the output is obtained. When training the LSTM network, a supervised learning method is used to convert the historical comprehensive adjustment factor sequence and its corresponding ideal value obtained through actual verification or simulation. As training data. For example, the sequence C(t) of the past 1000 time points and its corresponding ideal value Divided into training set, validation set and test set, the ratio is 7:2:1.

[0119] In the actual prediction process, the comprehensive adjustment factor data of the target river is obtained in real time. The preprocessed real-time comprehensive adjustment factor data is input into the trained LSTM model for prediction to obtain the ideal adjustment factor of the target river.

[0120] S5: Adjust the aeration intensity of the target river channel according to the ideal adjustment factor to achieve ecological restoration of the target river channel.

[0121] Preferably, in one embodiment of the present application, the aeration intensity of the target river channel is adjusted according to the ideal adjustment factor, including:

[0122] The adjusted aeration intensity is calculated based on the ideal adjustment factor and the aeration intensity adjustment formula. The aeration intensity adjustment formula is expressed as:

[0123]

[0124] Where I(t) is the adjusted aeration intensity, I0 is the initial aeration intensity, is the Sigmoid function, which Mapped to the interval (0, 1), is the ideal adjustment factor, t0 is the time parameter related to the biological clock of the target river ecosystem, and τ is the time constant.

[0125] In this step, the Sigmoid function is used to map Converted into a proportional factor suitable for adjusting aeration intensity, making the adjustment smoother and more reasonable. This section considers the effect of time factors on aeration intensity adjustment. t0 is a time parameter related to the biological clock of the river ecosystem. For example, if the biological activity in the river peaks in the morning or evening, t0 can be set to the corresponding time. τ is a time constant used to control the time scale of adjustment. For example, when τ is small, the aeration intensity is more sensitive to the time factor and the adjustment speed is faster; when τ is large, the response is relatively slow and the adjustment is more gentle.

[0126] Through the above scheme, the effects of multiple factors such as water flow velocity, dissolved oxygen content, value and turbidity on aeration intensity are comprehensively, meticulously and creatively considered. By using a variety of novel modeling technologies and reasonable mathematical formulas, the aeration intensity can be adjusted more intelligently and accurately according to the actual situation and ecological needs of the river, so as to better achieve the goal of river ecological restoration.

[0127] In some embodiments of the present application, the ecological restoration equipment of the present application selects an aerator, and the aeration head of the aerator is made of a special microporous ceramic material. This material has an extremely high porosity and a uniform microporous structure, and can produce extremely small bubbles. The tiny bubbles rise slowly in the water and have a large contact area with the water, thereby greatly increasing the solubility of oxygen in the water and improving the aeration efficiency. The structural diagram of the aeration head is shown in the figure below: Figure 2 and Figure 3 As shown. Figure 2 is a three-dimensional schematic diagram of an aerator in one embodiment of the present application, Figure 3 It is a schematic diagram of the internal cross-section of an aerator in one embodiment of the present application, wherein each micro pore is connected to the main ventilation pipe through an pore channel.

[0128] In order to enable the aeration head to automatically adjust the aeration intensity according to the water flow velocity and water quality, the present application installs a series of sensors on the aeration head. Among them, the water flow velocity sensor uses the Doppler effect principle to accurately measure the speed and direction of the water flow. The water quality sensors include dissolved oxygen sensors, pH sensors, turbidity sensors, etc., which can monitor the changes in water quality in real time.

[0129] Specifically, the intelligent control system automatically adjusts the aeration intensity of the aeration head according to the sensor data. When the water flow rate is fast, the system will increase the ventilation volume of the aeration head to ensure that the bubbles can be fully mixed with the water; when the water flow rate is slow, the system will appropriately reduce the ventilation volume of the aeration head to avoid excessive aeration. At the same time, when the water quality is poor and the dissolved oxygen content is low, the system will increase the aeration intensity to improve the oxygen supply; when the water quality is good and the dissolved oxygen content reaches the set value, the system will reduce the aeration intensity to save energy. In this way, the intelligent aerator can always maintain the best aeration effect and provide strong support for river ecological restoration.

[0130] Another embodiment of the present application provides an ecological restoration system based on river monitoring. For details, see Figure 4 , Figure 4 The figure shows a schematic diagram of an ecological restoration system based on river monitoring provided in one embodiment of the present application. It includes: a first acquisition module 11, a second acquisition module 12, a construction module 13, a prediction module 14, and an adjustment module 15, wherein:

[0131] The first acquisition module 11 is used to acquire water flow velocity data captured by a plurality of water flow velocity sensors disposed in the target river channel area, and calculate the trend component and the fluctuation component of the water flow velocity data according to the discrete wavelet transform method;

[0132] The second acquisition module 12 is used to acquire dissolved oxygen data, pH value data and turbidity data captured by a plurality of water quality sensors installed in the target river channel area, and pre-process the dissolved oxygen data, pH value data and turbidity data respectively to obtain the change rate of dissolved oxygen data, the mapping relationship function between pH value and aeration intensity and the fractal dimension of turbidity data;

[0133] A construction module 13 is used to construct a comprehensive adjustment factor according to the trend component, the fluctuation component, the change rate, the mapping relationship function and the fractal dimension, wherein the comprehensive adjustment factor reflects the influence of the water flow parameter and the water quality parameter on the aeration intensity of the target river channel;

[0134] The prediction module 14 is used to input the comprehensive adjustment factor into the pre-built LSTM model for prediction to obtain the ideal adjustment factor of the target river channel;

[0135] The adjustment module 15 is used to adjust the aeration intensity of the target river channel according to the ideal adjustment factor to achieve ecological restoration of the target river channel.

[0136] Preferably, in one embodiment of the present application, the first acquisition module is specifically used to:

[0137] Decomposing the water velocity data at a preset scale based on a preset wavelet basis function to obtain approximate coefficients and detail coefficients;

[0138] The approximate coefficients of the lowest frequency are reconstructed to obtain the trend component, which reflects the changing trend of water velocity on a long time scale;

[0139] The fluctuation component is calculated based on the trend component, which reflects the fluctuation of water flow velocity relative to the change trend on a short time scale.

[0140] Preferably, in one embodiment of the present application, the second acquisition module is specifically used to:

[0141] Calculate the long-term change rate and short-term change rate of dissolved oxygen data based on dissolved oxygen data;

[0142] The mapping function between pH value and aeration intensity is established through SVM regression model;

[0143] The fractal dimension of turbidity data was calculated based on the box counting method.

[0144] Preferably, in one embodiment of the present application, the prediction module is specifically used for:

[0145] Construct a training set based on the acquired historical comprehensive adjustment factor sequence and its corresponding ideal value;

[0146] Input the training set into the pre-built initial LSTM model for training to obtain the LSTM model;

[0147] In the actual prediction process, the real-time comprehensive adjustment factor is input into the LSTM model for prediction to obtain the ideal adjustment factor of the target river.

[0148] Preferably, in one embodiment of the present application, the adjustment module is specifically used to:

[0149] The adjusted aeration intensity is calculated based on the ideal adjustment factor and the aeration intensity adjustment formula. The aeration intensity adjustment formula is expressed as:

[0150]

[0151] Where I(t) is the adjusted aeration intensity, I0 is the initial aeration intensity, is the Sigmoid function, is the ideal adjustment factor, t0 is the time parameter related to the biological clock of the target river ecosystem, and τ is the time constant.

[0152] Compared with the prior art, the embodiments of the present application have the following advantages:

[0153] (1) This application uses the discrete wavelet transform method to decompose the water flow velocity data into trend component and fluctuation component, which can more finely understand the changing trend and short-term fluctuation of the water flow velocity, and provide a more accurate basis for subsequent adjustments; at the same time, the dissolved oxygen content, pH value and turbidity data are pre-processed to extract features such as change rate, mapping relationship function and fractal dimension. These features can more comprehensively reflect the water quality status and its changing trend, and improve the accuracy and sensitivity of water quality assessment.

[0154] (2) The comprehensive adjustment factor constructed in this application integrates multiple key features of water flow parameters and water quality parameters, which can fully reflect the influence of these factors on aeration intensity, avoid the limitations of single parameter adjustment, and improve the accuracy and scientificity of the adjustment. At the same time, by inputting the comprehensive adjustment factor into the pre-built LSTM model for prediction, the ideal adjustment factor of the target river can be obtained. The long and short-term memory capacity of the LSTM model enables it to capture complex patterns in time series data, thereby improving the accuracy of the prediction.

[0155] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An ecological restoration method based on river monitoring, characterized in that: include: Acquire water flow velocity data captured by a plurality of water flow velocity sensors disposed in a target river channel area, and calculate a trend component and a fluctuation component of the water flow velocity data according to a discrete wavelet transform method; Obtaining dissolved oxygen data, pH value data and turbidity data captured by a plurality of water quality sensors disposed in the target river channel area, preprocessing the dissolved oxygen data, the pH value data and the turbidity data respectively, to obtain a change rate of the dissolved oxygen data, a mapping relationship function between the pH value and aeration intensity, and a fractal dimension of the turbidity data; constructing a comprehensive adjustment factor according to the trend component, the fluctuation component, the change rate, the mapping relationship function and the fractal dimension, wherein the comprehensive adjustment factor reflects the influence of water flow parameters and water quality parameters on the aeration intensity of the target river channel; Input the comprehensive adjustment factor into a pre-built LSTM model for prediction to obtain an ideal adjustment factor for the target river channel; The aeration intensity of the target river channel is adjusted according to the ideal adjustment factor to achieve ecological restoration of the target river channel.

2. The ecological restoration method based on river monitoring according to claim 1, characterized in that: The method of calculating the trend component and the fluctuation component of the water velocity data according to the discrete wavelet transform method includes: Decomposing the water velocity data at a preset scale based on a preset wavelet basis function to obtain an approximate coefficient and a detail coefficient; Reconstructing the approximate coefficient of the lowest frequency to obtain a trend component, wherein the trend component reflects the variation trend of the water flow velocity on a long time scale; A fluctuation component is calculated according to the trend component, wherein the fluctuation component reflects the fluctuation of the water flow velocity relative to the change trend on a short time scale.

3. The ecological restoration method based on river monitoring according to claim 1, characterized in that: The preprocessing of the dissolved oxygen data, the pH value data and the turbidity data respectively to obtain the change rate of the dissolved oxygen data, the mapping relationship function between the pH value and the aeration intensity and the fractal dimension of the turbidity data includes: Calculating the long-term change rate and the short-term change rate of the dissolved oxygen data based on the dissolved oxygen data; A mapping function between the pH value and the aeration intensity is established through a SVM regression model; The fractal dimension of the turbidity data was calculated based on the box counting method.

4. The ecological restoration method based on river monitoring according to claim 1, characterized in that: The comprehensive adjustment factor is input into the pre-built LSTM model for prediction to obtain the ideal adjustment factor of the target river, including: Construct a training set based on the acquired historical comprehensive adjustment factor sequence and its corresponding ideal value; Inputting the training set into a pre-built initial LSTM model for training to obtain an LSTM model; In the actual prediction process, the acquired real-time comprehensive adjustment factor is input into the LSTM model for prediction to obtain the ideal adjustment factor of the target river channel.

5. The ecological restoration method based on river monitoring according to claim 1, characterized in that: The adjusting the aeration intensity of the target river channel according to the ideal adjustment factor includes: The adjusted aeration intensity is calculated according to the ideal adjustment factor and the aeration intensity adjustment formula, and the aeration intensity adjustment formula is expressed as: Where I(t) is the adjusted aeration intensity, I0 is the initial aeration intensity, is the Sigmoid function, is the ideal adjustment factor, t0 is the time parameter related to the biological clock of the target river ecosystem, and τ is the time constant.

6. An ecological restoration system based on river monitoring, characterized in that: include: A first acquisition module is used to acquire water flow velocity data captured by a plurality of water flow velocity sensors disposed in a target river channel area, and calculate a trend component and a fluctuation component of the water flow velocity data according to a discrete wavelet transform method; A second acquisition module is used to acquire dissolved oxygen data, pH value data and turbidity data captured by a plurality of water quality sensors disposed in the target river channel area, and pre-process the dissolved oxygen data, the pH value data and the turbidity data respectively to obtain a change rate of the dissolved oxygen data, a mapping relationship function between the pH value and the aeration intensity, and a fractal dimension of the turbidity data; A construction module, for constructing a comprehensive adjustment factor according to the trend component, the fluctuation component, the change rate, the mapping relationship function and the fractal dimension, wherein the comprehensive adjustment factor reflects the influence of water flow parameters and water quality parameters on the aeration intensity of the target river channel; A prediction module, used for inputting the comprehensive adjustment factor into a pre-built LSTM model for prediction to obtain an ideal adjustment factor for the target river channel; The adjustment module is used to adjust the aeration intensity of the target river channel according to the ideal adjustment factor to achieve ecological restoration of the target river channel.

7. The ecological restoration system based on river monitoring according to claim 6, characterized in that: The first acquisition module is specifically used to: Decomposing the water velocity data at a preset scale based on a preset wavelet basis function to obtain an approximate coefficient and a detail coefficient; Reconstructing the approximate coefficient of the lowest frequency to obtain a trend component, wherein the trend component reflects the variation trend of the water flow velocity on a long time scale; A fluctuation component is calculated according to the trend component, wherein the fluctuation component reflects the fluctuation of the water flow velocity relative to the change trend on a short time scale.

8. The ecological restoration system based on river monitoring according to claim 6, characterized in that: The second acquisition module is specifically used for: Calculating the long-term change rate and the short-term change rate of the dissolved oxygen data based on the dissolved oxygen data; A mapping function between the pH value and the aeration intensity is established through a SVM regression model; The fractal dimension of the turbidity data was calculated based on the box counting method.

9. The ecological restoration system based on river monitoring according to claim 6, characterized in that: The prediction module is specifically used for: Construct a training set based on the acquired historical comprehensive adjustment factor sequence and its corresponding ideal value; Inputting the training set into a pre-built initial LSTM model for training to obtain an LSTM model; In the actual prediction process, the acquired real-time comprehensive adjustment factor is input into the LSTM model for prediction to obtain the ideal adjustment factor of the target river channel.

10. The ecological restoration system based on river monitoring according to claim 6, characterized in that: The adjustment module is specifically used for: The adjusted aeration intensity is calculated according to the ideal adjustment factor and the aeration intensity adjustment formula, and the aeration intensity adjustment formula is expressed as: Where I(t) is the adjusted aeration intensity, I0 is the initial aeration intensity, is the Sigmoid function, is the ideal adjustment factor, t0 is the time parameter related to the biological clock of the target river ecosystem, and τ is the time constant.

Images