A water quality monitoring method and system for surface water

Abstract

The present invention discloses a water quality monitoring method and system for surface water, which relates to the technical field of water quality monitoring; obtaining the water body state data of the target area, and extracting features from the spectral data through a preset algorithm to obtain training data; inputting the training data into the water body evaluation model for evaluation to obtain water body anomaly parameters, obtaining ultrasonic detection data, and determining the water body turbidity parameter of the target area according to the ultrasonic detection data; combining the water body anomaly parameters and the water body turbidity parameter to obtain a water quality evaluation parameter, and evaluating the water quality of the target area according to the water quality evaluation parameter; the preset algorithm extracts features from the spectral data to generate training data, improving the model training efficiency and accuracy. Inputting the training data into the water body evaluation model to automatically evaluate the water body anomaly parameters, combining the turbidity parameters detected by ultrasonic waves to obtain the water quality evaluation parameters, and conducting a comprehensive water quality evaluation. When the threshold is exceeded, an automatic alarm is issued, improving the monitoring efficiency and emergency response speed.

Description

Technical Field

[0001] The present invention belongs to the technical field of water quality monitoring, and particularly relates to a water quality monitoring method and system for surface water. Background Technique

[0002] Surface water is often affected by the discharge of untreated wastewater, resulting in eutrophication, excessive growth of algae, and reduced water transparency. In view of this series of negative impacts, continuous monitoring of the water quality of urban reservoirs has become an essential step in the inland water management system.

[0003] Patent No.: CN118225713A, which discloses a water quality monitoring method and system based on full-spectrum analysis; the first machine learning model is used to predict the influence of environmental factors on the spectrum, and the second machine learning model is used to predict water quality parameters; during the monitoring process, spectral data and environmental data of the water body are collected in real time, and the first model is used to predict the influence of the environment on the spectrum and correct the real-time spectral data; after the corrected spectral data is optimized, it is input into the second model to predict the water quality index value; finally, the predicted water quality index value is compared with a preset threshold, and if it exceeds the threshold, an alarm message is sent. By collecting reference data to train the machine learning model, predicting the influence of the environment on the spectral data and correcting it, the accuracy of the spectral data is improved, and thus the accuracy of water quality monitoring is improved.

[0004] Although the above method solves some problems, there are still some problems, such as: the process of water quality data analysis is too single, analyzing only from spectral data leads to a decrease in the accuracy of water quality data monitoring and an increase in the probability of false alarms and missed reports. Summary of the Invention

[0005] The object of the present invention is to solve the problem that the process of water quality data analysis is too single, analyzing only from spectral data leads to a decrease in the accuracy of water quality data monitoring and an increase in the probability of false alarms and missed reports, and to propose a water quality monitoring method and system for surface water.

[0006] In the first aspect of the implementation of the present invention, a water quality monitoring method for surface water is first proposed. The method includes:

[0007] Obtain the water body state data of the target area, and perform feature extraction on the spectral data through a preset algorithm to obtain training data; the water body state data includes: spectral data and water sample data;

[0008] Input the training data into the water body evaluation model for evaluation to obtain water body anomaly parameters, obtain ultrasonic detection data, and determine the water body turbidity parameter of the target area according to the ultrasonic detection data;

[0009] Combine the water body anomaly parameter and the water body turbidity parameter to obtain a water quality evaluation parameter, and evaluate the water quality of the target area according to the water quality evaluation parameter.

[0010] Optionally, perform feature extraction on the spectral data through a preset algorithm to obtain training data, including:

[0011] Determine the data types of the water sample data, and divide the spectral data of each data type according to a preset division standard to obtain a classification data set; the classification data set includes multiple classification data sets;

[0012] Perform oversampling on the classification data sets in the classification data set to obtain a synthetic data set, and perform mathematical conversion on the spectral data through a preset algorithm to obtain a conversion data set;

[0013] Determine the data types of the conversion data set, and fuse the conversion data with the synthetic data set according to the data types to obtain a fused data set;

[0014] Perform global filtering on the features of each band in the fused data set through a genetic algorithm to obtain initial band features, perform band feature selection on the initial band features through a variance inflation factor to obtain optimal band features, and use the optimal band features as training data.

[0015] Optionally, before inputting the training data into the water body evaluation model for evaluation to obtain the water body anomaly parameter, the method further includes:

[0016] Step 1: Divide the training data according to a preset quantity to obtain a training data set, input the training data set into a first preset model for training according to a preset number of training times to obtain a result set, and vertically merge the result set to obtain a column vector ;

[0017] Step 2: Repeat Step 1 until the number of column vectors is the same as the preset quantity to obtain column vectors , input the training data into a second preset model to obtain a column vector ; the column vector and the column vector have the same number of column vectors;

[0018] Step 3: Obtain a water quality evaluation parameter, input the water quality evaluation parameter, the training data, and the column vector into a third preset model for training to obtain model parameters, and update the third preset model according to the model parameters to obtain a water body evaluation model;

[0019] [[ID=

[0020] Input the column vector into the water body assessment model for assessment to obtain water body anomaly parameters.

[0021] Optionally, determining the water body turbidity parameter of the target area according to the ultrasonic detection data includes:

[0022] Determine the water body flow rate, transmitted signal and received signal according to the ultrasonic detection data, calculate the water flow according to the water body flow rate, and calculate the signal attenuation amount according to the transmitted signal and the received signal;

[0023] Input the signal attenuation amount into the particle assessment model for training to obtain the particle concentration and the water body particle size; the particle assessment model is trained by historical signal attenuation amount data, particle concentration data and water body particle size data;

[0024] Calculate the water body turbidity parameter according to the water flow, the particle concentration and the water body particle size.

[0025] Optionally, evaluating the water quality of the target area according to the water quality assessment parameter includes:

[0026] If the water quality assessment parameter is greater than the alarm threshold, upload the log and send an alarm instruction to make the system alarm; otherwise, upload the log.

[0027] In the second aspect of the implementation of the present invention, a water quality monitoring system for surface water is proposed, including: a training data acquisition module, a water body parameter acquisition module and a water quality assessment and early warning module:

[0028] The training data acquisition module is used to acquire the water body state data of the target area, and obtain the training data by performing feature extraction on the spectral data through a preset algorithm; the water body state data includes: spectral data and water sample data;

[0029] The water body parameter acquisition module is used to input the training data into the water body assessment model for assessment to obtain water body anomaly parameters, acquire ultrasonic detection data, and determine the water body turbidity parameter of the target area according to the ultrasonic detection data;

[0030] The water quality assessment and early warning module is used to combine the water body anomaly parameter and the water body turbidity parameter to obtain a water quality assessment parameter, and evaluate the water quality of the target area according to the water quality assessment parameter.

[0031] Optionally, the training data acquisition module includes: a data set division module, a data set preprocessing module, a data set fusion module and a band screening module:

[0032] The dataset division module is used to determine the data types of the water sample data, and divide each data type in the spectral data according to a preset division standard to obtain a classification data set; the classification data set includes multiple classification data sets;

[0033] The dataset preprocessing module is used to perform oversampling on the classification data sets in the classification data set to obtain a synthetic data set, and perform mathematical conversion on the spectral data through a preset algorithm to obtain a conversion data set;

[0034] The dataset fusion module is used to determine the data types of the conversion data set, and fuse the conversion data with the synthetic data set according to the data types to obtain a fusion data set;

[0035] The band screening module is used to globally filter each band feature in the fusion data set through a genetic algorithm to obtain an initial band feature, perform band feature selection on the initial band feature through a variance inflation factor to obtain an optimal band feature, and use the optimal band feature as training data.

[0036] Optionally, the system further includes: a column vector acquisition module, a column vector pre-training module, and an evaluation model training module:

[0037] The column vector acquisition module is used to divide the training data according to a preset quantity to obtain a training data set, input the training data set into a first preset model for training according to a preset number of training times to obtain a result set, and vertically merge the result set to obtain a column vector ;

[0038] The column vector pre-training module is used to repeatedly execute the column vector acquisition module until the number of column vectors is the same as the preset quantity to obtain column vectors and input the training data into a second preset model to obtain column vectors ; the column vectors and the column vectors have the same number of column vectors;

[0039] The evaluation model training module is used to obtain water quality evaluation parameters, input the water quality evaluation parameters, the training data, and the column vectors into a third preset model for training to obtain model parameters, and update the third preset model according to the model parameters to obtain a water body evaluation model;

[0040] The water body parameter acquisition module is further used to input the column vectors into the water body evaluation model for evaluation to obtain water body anomaly parameters.

[0041] Optionally, the water body parameter acquisition module includes: a signal attenuation amount acquisition module, a particle evaluation model module, and a water body turbidity parameter module:

[0042] The signal attenuation amount acquisition module is configured to determine the water body flow rate, the transmitted signal, and the received signal according to the ultrasonic detection data, calculate the water flow according to the water body flow rate, and calculate the signal attenuation amount according to the transmitted signal and the received signal;

[0043] The particle evaluation model module is configured to input the signal attenuation amount into the particle evaluation model for training to obtain the particle concentration and the water body particle size; the particle evaluation model is trained by historical signal attenuation amount data, particle concentration data, and water body particle size data;

[0044] The water body turbidity parameter module is configured to calculate the water body turbidity parameter according to the water flow, the particle concentration, and the water body particle size.

[0045] Optionally, the water quality evaluation and early warning module is further configured to, if the water quality evaluation parameter is greater than the alarm threshold, upload a log and send an alarm instruction to cause the system to issue an alarm; otherwise, upload a log.

[0046] Advantages of the present invention:

[0047] The present invention provides a water quality monitoring method for surface water. By acquiring the water body state data of the target area, feature extraction is performed on the spectral data through a preset algorithm to obtain training data; the training data is input into the water body evaluation model for evaluation to obtain water body anomaly parameters, ultrasonic detection data is acquired, and the water body turbidity parameter of the target area is determined according to the ultrasonic detection data; the water body anomaly parameters and the water body turbidity parameters are combined to obtain a water quality evaluation parameter, and the water quality of the target area is evaluated according to the water quality evaluation parameter; the preset algorithm performs feature extraction on the spectral data to generate training data, improving the model training efficiency and accuracy. The training data is input into the water body evaluation model to automatically evaluate the water body anomaly parameters, and the water quality evaluation parameter is obtained by combining the turbidity parameters detected by ultrasonic waves for comprehensive water quality evaluation. When the threshold is exceeded, an automatic alarm is issued, improving the monitoring efficiency and the emergency response speed. Description of the Drawings

[0048] The present invention will be further described below with reference to the accompanying drawings.

[0049] Figure 1 It is a flowchart of a water quality monitoring method for surface water provided by an embodiment of the present invention;

[0050] Figure 2 It is a framework diagram of another water quality monitoring system for surface water provided by an embodiment of the present invention. Detailed Embodiments

[0051] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The term "and / or" in this article is only a description of the associated relationship of the associated objects, indicating that there can be three relationships. For example, A and B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the descriptions such as "first" and "second" in the present invention are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the fact that those skilled in the art can implement it. When the combination of the technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of the technical solutions does not exist and is not within the scope of protection required by the present invention.

[0052] All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0053] The embodiments of the present invention provide a water quality monitoring method for surface water. See Figure 1 , Figure 1 which is a flowchart of a water quality monitoring method for surface water provided by the embodiments of the present invention. The method includes the following steps:

[0054] S101, obtaining water body state data of the target area, and extracting features from the spectral data through a preset algorithm to obtain training data;

[0055] S102, inputting the training data into a water body evaluation model for evaluation to obtain water body anomaly parameters, obtaining ultrasonic detection data, and determining the water body turbidity parameter of the target area according to the ultrasonic detection data;

[0056] S103, combining the water body anomaly parameters and the water body turbidity parameter to obtain a water quality evaluation parameter, and evaluating the water quality of the target area according to the water quality evaluation parameter;

[0057] The water body state data includes: spectral data and water sample data;

[0058] Based on a water quality monitoring method for surface water provided by an embodiment of the present invention, characteristic extraction is performed on spectral data through a preset algorithm to generate training data, improving the efficiency and accuracy of model training. The training data is input into a water body evaluation model to automatically evaluate water body anomaly parameters, and water quality evaluation parameters are obtained by combining the turbidity parameters detected by ultrasonic waves for comprehensive water quality evaluation. The system monitors water quality in real time and automatically alarms when the threshold is exceeded, improving the monitoring efficiency and emergency response speed.

[0059] In one implementation, the water body state data includes: spectral data and water sample data. Among them, the spectral data is obtained through a detection device installed at the water inlet, and the cross-section at the water inlet is determined by measurement by the staff. The acquisition of spectral data, for example, is obtained through a multi-parameter water quality monitoring spectral analyzer, a water quality spectral detection system, etc.; the acquisition of water sample data, for example, is obtained through an ORP sensor, a pH sensor, a dissolved oxygen sensor, a water temperature sensor, etc.; among them, there is a mapping relationship between the water sample data and the spectral data; training data preset algorithms are obtained by performing characteristic extraction on the spectral data through a preset algorithm (genetic algorithm).

[0060] In one implementation, the data monitoring accuracy can be improved by using water body state data and ultrasonic detection data. Ultrasonic waves: have a high measurement accuracy for the physical properties of fluids (such as flow velocity, suspended particles), but have a weak detection ability for chemical components. Spectrometry: has a high detection accuracy for chemical components, but has a weak measurement ability for physical parameters. The combined use of the two: by measuring physical and chemical parameters simultaneously, the water quality can be more comprehensively evaluated, improving the accuracy and reliability of monitoring; and, ultrasonic waves: can measure the flow velocity, flow rate, suspended solid concentration, etc. of the fluid. Spectrometry: can measure chemical oxygen demand (COD), total organic carbon (TOC), dissolved oxygen (DO), turbidity, chromaticity, etc. The combined use of the two: can monitor multiple parameters simultaneously, provide more comprehensive water quality information, and can achieve more comprehensive, accurate, and reliable water quality monitoring.

[0061] In one implementation, the training data after feature extraction is input into the water body evaluation model, and the model can evaluate the water body anomaly parameters based on these features. By using machine learning or deep learning algorithms, the mapping relationship between the water body state and the anomaly parameters is learned through the existing training data to realize the automatic identification and quantitative evaluation of water body anomalies. Compared with the traditional manual detection method, this method can quickly and accurately identify anomalies in the water body, such as excessive pollutant concentration, algae bloom, etc.

[0062] In one implementation, ultrasonic detection data is obtained, and based on these data, the water turbidity parameter of the target area is determined. Ultrasonic detection technology can directly measure the concentration and particle size distribution of suspended particles in water, thus accurately reflecting the turbidity of the water. The water turbidity parameter complements the water anomaly parameter evaluated from spectral data, providing more comprehensive water quality information. The independent measurement of the turbidity parameter ensures the diversity and reliability of the data, helps to more accurately evaluate the overall state of the water body, and can also reflect the flow condition of the water body.

[0063] In one implementation, the water anomaly parameter and the water turbidity parameter are combined to obtain a comprehensive water quality evaluation parameter. The above comprehensive evaluation method takes into account the chemical and physical characteristics of the water body. Through the comprehensive analysis of multiple parameters, it can more comprehensively and accurately evaluate the water quality status of the target area. The comprehensive evaluation parameter not only reflects the pollution degree of the water body, but can also be used as a judgment method for the alarm system. When the water quality evaluation parameter exceeds the preset alarm threshold, the log is uploaded in a timely manner and an alarm instruction is sent.

[0064] In one embodiment, the spectral data is subjected to feature extraction through a preset algorithm to obtain training data, including:

[0065] Determine the data types of the water sample data, and divide each data type in the spectral data according to the preset division standard to obtain a classification data set; the classification data set includes multiple classification data sets;

[0066] Oversample the classification data sets in the classification data set to obtain a synthetic data set, and perform a mathematical transformation on the spectral data through a preset algorithm to obtain a transformed data set;

[0067] Determine the data types of the transformed data set, and fuse the transformed data with the synthetic data set according to the data types to obtain a fused data set;

[0068] Perform global filtering on the features of each band in the fused data set through a genetic algorithm to obtain initial band features, perform band feature selection on the initial band features through a variance inflation factor to obtain optimal band features, and use the optimal band features as training data.

[0069] In one implementation, spectral data undergoes mathematical transformations using preset algorithms, such as reciprocals, logarithms, exponentials, squares, and square roots. The transformed data is then fused with a synthetic dataset to create a fused dataset, using addition, subtraction, multiplication, distribution, and normalization, depending on the data type. The categorized datasets within the categorized dataset are then oversampled to create a synthetic dataset. Oversampling can increase the diversity and quantity of data, particularly in imbalanced data situations, effectively increasing the amount of data in the minority category and making model training more balanced. The generation of synthetic datasets not only enriches the dataset but also improves the model's generalization capabilities, enabling it to better learn and identify features from different data categories.

[0070] In one implementation, the data type of the transformed data set is determined and, based on the data type, the transformed data is fused with the synthesized data set to produce a fused data set. The data fusion process integrates data from different sources and processing methods through operations such as addition, subtraction, multiplication, distribution, and normalization to generate comprehensive features. This process not only preserves the rich information of the original data but also generates new features through the interaction between the data, further improving the data's expressiveness and the model's predictive performance.

[0071] In one implementation, spectral data is mathematically transformed using preset algorithms, such as reciprocals, logarithms, exponentials, squares, and square roots. These mathematical transformations can enhance the data's characteristics, make its distribution more reasonable, and improve the model's sensitivity to the data. The data types of the water sample data are determined, and the spectral data is divided according to preset classification criteria to obtain a classified data set. These steps can classify complex spectral data according to different characteristics or attributes, making the data more organized and easier to manage. Through classification, different types of data can be processed and analyzed in a targeted manner, improving the efficiency and accuracy of data processing.

[0072] In one implementation, a genetic algorithm is used to globally filter the band features in the fused data set to obtain initial band features. As a global optimization algorithm, the genetic algorithm can effectively search and select the most representative and discriminative band features, avoiding the problem of local optimal solutions. The initial band features are then subjected to band feature selection using a variance inflation factor (VIF) to obtain the optimal band features. The VIF can further filter features with low correlation and high information content, reducing redundancy between features and improving model stability and prediction accuracy. The resulting optimal band features serve as training data, providing high-quality input for model training and ensuring that the model can accurately learn and identify changes in water conditions.

[0073] In one embodiment, before inputting the training data into the water body evaluation model for evaluation to obtain water body anomaly parameters, the method further includes:

[0074] Step 1: Divide the training data according to a preset quantity to obtain a training data set, input the training data set into a first preset model for training according to a preset number of training times to obtain a result set, and vertically merge the result set to obtain a column vector ;

[0075] Step 2: Repeat Step 1 until the number of column vectors is the same as the preset quantity to obtain column vectors , input the training data into a second preset model to obtain a column vector ; The column vectors and the column vectors have the same number of column vectors;

[0076] Step 3: Obtain water quality evaluation parameters, input the water quality evaluation parameters, training data, and column vectors into a third preset model for training to obtain model parameters, and update the third preset model according to the model parameters to obtain a water body evaluation model;

[0077] Inputting the training data into the water body evaluation model for evaluation to obtain water body anomaly parameters includes:

[0078] Inputting the column vectors into the water body evaluation model for evaluation to obtain water body anomaly parameters.

[0079] In one implementation manner, for example: divide the training data into five training data sets (four for training and one for validation), the mathematical meanings of the preset number of training times and the preset quantity are the same, both are five here, train according to the preset number of training times to obtain a result set ( and ), vertically merge the result set into 1 column to obtain a column vector , repeat Step 1 until the number of column vectors is the same as the preset quantity to obtain a column vector , here the number of column vectors is the same as the preset quantity, both are five, and serve as column vectors a ( , the value of i, i = 1, 2, 3... n), input the training data into the second preset model to obtain a column vector , the column vectors and the column vectors have the same number of columns, input the water quality evaluation parameters, training data (optimal band features), and column vectors Input it into the third model for training to obtain a water body evaluation model, training data (optimal band features) and column vectors are combined. The water quality evaluation parameters are the scores of various chemical components in the water body at various concentrations (score vectors, used to characterize the pollution status of the water body). That is, the water body contains a variety of pollutants, and each pollutant is set with a pollutant concentration range, and each concentration range corresponds to a score. For example: ammonia nitrogen (NH3-N), total phosphorus (TP), chemical oxygen demand (COD), and dissolved oxygen (DO). The "concentration range (mg / L)-score" of ammonia nitrogen: 0 ≤ concentration < 0.5 corresponds to 10 points, 0.5 ≤ concentration < 1.0 corresponds to 7 points, 1.0 ≤ concentration < 1.5 corresponds to 4 points, 1.5 ≤ concentration corresponds to 1 point; the "concentration range (mg / L)-score" of total phosphorus: 0 ≤ concentration < 0.1 corresponds to 10 points, 0.1 ≤ concentration < 0.2 corresponds to 7 points, 0.2 ≤ concentration < 0.3 corresponds to 4 points, 0.3 ≤ concentration corresponds to 1 point; the "concentration range (mg / L)-score" of chemical oxygen demand: 0 ≤ concentration < 10 corresponds to 10 points, 10 ≤ concentration < 20 corresponds to 7 points, 20 ≤ concentration < 30 corresponds to 4 points, 30 ≤ concentration corresponds to 1 point; the "concentration range (mg / L)-score" of dissolved oxygen: 6.0 ≤ concentration corresponds to 10 points, 5.0 ≤ concentration < 6.0 corresponds to 7 points, 4.0 ≤ concentration < 5.0 corresponds to 4 points, 4.0 < concentration corresponds to 1 point; when the detection results are as follows, the ammonia nitrogen concentration of 1.2 is scored 4, the total phosphorus concentration of 0.5 is scored 1, the chemical oxygen demand concentration of 31 is scored 1, and the dissolved oxygen concentration of 5.3 is scored 7. The pollutant score vector of this water body is: [4, 1, 1, 7]. The lower the value of the score vector, the more serious the water body pollution. It can be seen from the score vector that the scores of various pollutants in this water body are all 4, indicating that the water body as a whole is in a medium pollution level and needs further treatment to improve water quality. The above data is for reference only; input the column vector into the water body evaluation model to obtain water body anomaly parameters, column vector contains a variety of chemical components. The water body evaluation model scores according to the concentration of chemical components and assigns weights to each score, and obtains the water body anomaly parameter by weighted summation.

[0080] In one implementation, the first preset model is a basic model, such as: Decision Tree, Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Logistic Regression; the second preset model is an ensemble model, such as: Random Forest, Gradient Boosting Trees (GBT), XGBoost, LightGBM; the third preset model is a meta-model, such as: Linear Regression, Ridge Regression, Least Absolute Shrinkage and Selection Operator (LASSO regression), Neural Network.

[0081] In one embodiment, determining the water turbidity parameter of the target area according to the ultrasonic detection data includes:

[0082] Determining the water flow velocity, transmitted signal, and received signal according to the ultrasonic detection data, calculating the water flow rate according to the water flow velocity, and calculating the signal attenuation amount according to the transmitted signal and the received signal;

[0083] Inputting the signal attenuation amount into the particle evaluation model for training to obtain the particle concentration and water particle size; the particle evaluation model is trained by historical signal attenuation amount data, particle concentration data, and water particle size data;

[0084] Calculating the water turbidity parameter according to the water flow rate, particle concentration, and water particle size.

[0085] In one implementation, determining the water flow velocity according to the ultrasonic detection data, for example: using the time difference method and Doppler effect to measure the flow velocity and flow rate of the fluid. Time difference method: calculating the flow velocity of the fluid by measuring the time difference of ultrasonic wave propagation in the fluid along the flow and against the flow. Let the sound speed in the static fluid be c, the fluid flow velocity be v, the distance between the transducers be L, and the installation angle be θ; the propagation time along the flow is: , the propagation time against the flow is: , the time difference Δt is: , since , so it can be simplified to , the flow velocity v of the fluid can be calculated by measuring the time difference Δt; Doppler effect: the Doppler shift of sound waves is used to measure the movement speed of particles or bubbles in the fluid. The ultrasonic generator emits sound waves with a fixed frequency. When the particles or bubbles in the fluid move at a speed v, the frequency of the reflected sound wave will change. Let the transmitted frequency be f0 and the reflected frequency be f1. The Doppler shift Δf is: , the flow velocity v of the fluid can be calculated by measuring the Doppler shift Δf; the water flow rate is, water flow rate = cross-sectional area × water flow velocity.

[0086] In one implementation, the method for determining the particle concentration and water body particle size further includes: Acoustic backscatter signal analysis: By analyzing the intensity and frequency changes of the reflected signal, the concentration and particle size of the suspended particles can be determined. The intensity of the reflected signal is proportional to the concentration of the suspended particles, and the frequency change of the reflected signal is proportional to the movement speed of the particles. Doppler shift measurement: By measuring the Doppler shift of the reflected signal, the movement speed of the suspended particles can be determined, and thus the concentration of the suspended particles can be deduced. The Doppler shift is proportional to the movement speed of the particles, and the frequency shift can be converted into concentration through a calibration curve.

[0087] In one implementation, by setting an ultrasonic transmitter and a receiver, allowing the ultrasonic wave to pass through the water body containing suspended particles, measuring the intensity of the ultrasonic wave emitted by the transmitter and the intensity of the reflected signal received by the receiver, by comparing these two intensity values, the energy loss of the ultrasonic wave during propagation can be calculated, and then the signal attenuation amount can be obtained. By establishing a relationship model between the signal attenuation amount and the particle concentration. This model is obtained through experimental measurement, that is, measuring the signal attenuation amount of the ultrasonic wave in the water body with a known particle concentration, and using it as the training data of the particle evaluation model (which can be a machine learning model, a neural network model, etc.), so as to establish the mapping relationship between the signal attenuation amount and the particle concentration and particle size; the water body turbidity parameter is calculated according to the water flow rate, particle concentration and water body particle size, that is , where is the water body turbidity parameter, gc is the particle concentration, wp is the water body particle size, wf is the water flow rate, α, β and γ are constant proportionality coefficients, all of which are not zero; the numerical values of gc, wp and wf have been dimensionless processed, and numerically represent that the larger the value, the more turbid the water body.

[0088] In one embodiment, the water quality of the target area is evaluated according to the water quality evaluation parameter, including:

[0089] If the water quality evaluation parameter is greater than the alarm threshold, upload the log and send an alarm instruction to make the system alarm; otherwise, upload the log.

[0090] In one implementation, before evaluating the water quality of the target area according to the water quality evaluation parameters, the water quality evaluation parameters are obtained by combining the water body anomaly parameters and the water body turbidity parameters. That is, , where is the water quality evaluation parameter, is the water body anomaly parameter, is the water body turbidity parameter, and are both constant proportionality coefficients and are not zero.

[0091] In one implementation, upload logs: The collected data is transmitted in real time to the database and cloud server of the monitoring center through a wireless network (or wired transmission) to ensure the timeliness and accuracy of the data. The system automatically records the detailed information of the alarm event, including time, location, alarm parameters, alarm level, etc., and generates an alarm log. Alarm threshold: Set the alarm threshold. When the water quality evaluation parameter exceeds (greater than and not equal to) this threshold, the system automatically triggers an alarm. For example: turbidity exceeds 100 NTU, COD exceeds 20 mg / L, etc. Alarm method: The alarm method includes multiple forms such as text messages, APP push, e-mails, etc. to ensure that relevant personnel can receive the alarm information in a timely manner.

[0092] Based on the same inventive concept, the embodiments of the present invention also provide a water quality monitoring system for surface water. Refer to Figure 2 , Figure 2 which is a schematic structural diagram of a water quality monitoring system for surface water provided by the embodiments of the present invention, including: a training data acquisition module, a water body parameter acquisition module, and a water quality evaluation and warning module:

[0093] The training data acquisition module is used to acquire the water body state data of the target area, and extract features from the spectral data through a preset algorithm to obtain training data; the water body state data includes: spectral data and water sample data;

[0094] The water body parameter acquisition module is used to input the training data into the water body evaluation model for evaluation to obtain the water body anomaly parameter, acquire the ultrasonic detection data, and determine the water body turbidity parameter of the target area according to the ultrasonic detection data;

[0095] The water quality evaluation and warning module is used to combine the water body anomaly parameter and the water body turbidity parameter to obtain the water quality evaluation parameter, and evaluate the water quality of the target area according to the water quality evaluation parameter.

[0096] A water quality monitoring system for surface water provided by an embodiment of the present invention extracts features from spectral data through a preset algorithm to generate training data, improving the training efficiency and accuracy of the model. The training data is input into a water body evaluation model to automatically evaluate water body anomaly parameters, and combined with the turbidity parameters detected by ultrasonic waves to obtain water quality evaluation parameters for comprehensive water quality evaluation. The system monitors water quality in real time and automatically alarms when the threshold is exceeded, improving the monitoring efficiency and emergency response speed.

[0097] In one embodiment, the training data acquisition module includes: a data set division module, a data set preprocessing module, a data set fusion module, and a band screening module:

[0098] The data set division module is used to determine the data types of water sample data, and divide each data type in the spectral data according to a preset division standard to obtain a classification data set; the classification data set includes multiple classification data sets;

[0099] The data set preprocessing module is used to perform oversampling on the classification data sets in the classification data set to obtain a synthetic data set, and perform mathematical conversion on the spectral data through a preset algorithm to obtain a conversion data set;

[0100] The data set fusion module is used to determine the data types of the conversion data set, and fuse the conversion data with the synthetic data set according to the data types to obtain a fusion data set;

[0101] The band screening module is used to perform global filtering on the band features in the fusion data set through a genetic algorithm to obtain initial band features, perform band feature selection on the initial band features through a variance inflation factor to obtain optimal band features, and use the optimal band features as training data.

[0102] In one embodiment, the system further includes: a column vector acquisition module, a column vector pre-training module, and an evaluation model training module:

[0103] The column vector acquisition module is used to divide the training data according to a preset quantity to obtain a training data set, input the training data set into a first preset model for training according to a preset number of training times to obtain a result set, and vertically merge the result set to obtain a column vector ;

[0104] The column vector pre-training module is used to repeatedly execute the column vector acquisition module until the number of column vectors is the same as the preset quantity to obtain column vectors and input the training data into a second preset model to obtain column vectors ; the column vectors and the column vectors have the same number of column vectors;

[0105] An evaluation model training module for obtaining water quality evaluation parameters, and inputting the water quality evaluation parameters, training data, and column vector into a third preset model for training to obtain model parameters, and updating the third preset model according to the model parameters to obtain a water body evaluation model;

[0106] The water body parameter acquisition module is further configured to input the column vector into the water body evaluation model for evaluation to obtain water body anomaly parameters.

[0107] In one embodiment, the water body parameter acquisition module includes: a signal attenuation amount acquisition module, a particle evaluation model module, and a water body turbidity parameter module:

[0108] The signal attenuation amount acquisition module is configured to determine the water body flow rate, transmitted signal, and received signal according to ultrasonic detection data, calculate the water flow rate according to the water body flow rate, and calculate the signal attenuation amount according to the transmitted signal and the received signal;

[0109] The particle evaluation model module is configured to input the signal attenuation amount into the particle evaluation model for training to obtain the particle concentration and the water body particle size; the particle evaluation model is trained by historical signal attenuation amount data, particle concentration data, and water body particle size data;

[0110] The water body turbidity parameter module is configured to calculate the water body turbidity parameter according to the water flow rate, particle concentration, and water body particle size.

[0111] In one embodiment, the water quality evaluation and warning module is further configured to upload a log and send an alarm instruction to cause the system to alarm if the water quality evaluation parameter is greater than the alarm threshold; otherwise, upload the log.

[0112] The above has described an embodiment of the present invention in detail, but the content is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the application of the present invention shall still fall within the scope covered by the patent of the present invention.

Claims

1. A water quality monitoring method for surface water, characterized in that, The method includes: Obtaining water body state data of a target area, and extracting features from spectral data through a preset algorithm to obtain training data; the water body state data includes: spectral data and water sample data; Inputting the training data into a water body evaluation model for evaluation to obtain water body anomaly parameters, obtaining ultrasonic detection data, and determining the water body turbidity parameter of the target area according to the ultrasonic detection data; Combining the water body anomaly parameter and the water body turbidity parameter to obtain a water quality evaluation parameter, and evaluating the water quality of the target area according to the water quality evaluation parameter; Determining the water body turbidity parameter of the target area according to the ultrasonic detection data, including: Determining the water body flow rate, transmitted signal, and received signal according to the ultrasonic detection data, calculating the water flow rate according to the water body flow rate, and calculating the signal attenuation amount according to the transmitted signal and the received signal; Inputting the signal attenuation amount into a particle evaluation model for training to obtain the particle concentration and the water body particle size; the particle evaluation model is trained by historical signal attenuation amount data, particle concentration data, and water body particle size data; Calculating the water body turbidity parameter according to the water flow rate, the particle concentration, and the water body particle size.

2. The water quality monitoring method for surface water according to claim 1, wherein Extracting features from the spectral data through a preset algorithm to obtain training data, including: Determining the data types of the water sample data, and dividing each data type in the spectral data according to a preset division standard to obtain a classification data set; the classification data set includes multiple classification data sets; Performing oversampling on the classification data sets in the classification data set to obtain a synthetic data set, and performing a mathematical transformation on the spectral data through a preset operation rule to obtain a transformed data set; Determining the data types of the transformed data set, and fusing the transformed data with the synthetic data set according to the data types to obtain a fused data set; Performing global filtering on the features of each band in the fused data set through a genetic algorithm to obtain initial band features, performing band feature selection on the initial band features through a variance inflation factor to obtain optimal band features, and using the optimal band features as training data.

3. A water quality monitoring method for surface water according to claim 1, characterized in that, Before inputting the training data into a water body evaluation model for evaluation to obtain water body anomaly parameters, the method further includes: Step 1: Divide the training data according to a preset quantity to obtain a training data set. Input the training data set into a first preset model and train it according to a preset number of training times to obtain a result set. Vertically merge the result set to obtain a column vector ; Step 2: Repeat Step 1 until the number of column vectors is the same as the preset number to obtain column vectors , and input the training data into a second preset model to obtain column vectors ; the column vectors and the column vectors have the same number of column vectors; Step 3: Obtain water quality assessment parameters, and input the water quality assessment parameters, the training data, and the column vector into the third preset model for training to obtain model parameters, and update the third preset model according to the model parameters to obtain a water body assessment model; Inputting the training data into a water body evaluation model for evaluation to obtain water body anomaly parameters, including: Input the column vector into the water body assessment model for assessment to obtain water body anomaly parameters.

4. A water quality monitoring method for surface water according to claim 1, characterized in that, Evaluating the water quality of the target area according to the water quality evaluation parameter, including: If the water quality evaluation parameter is greater than the alarm threshold, uploading a log and sending an alarm instruction to cause the system to issue an alarm; otherwise, uploading a log.

5. A water quality monitoring system for surface water, characterized in that, The system includes: a training data acquisition module, a water body parameter acquisition module, and a water quality evaluation and warning module: The training data acquisition module is used to obtain water body state data of a target area, and extract features from spectral data through a preset algorithm to obtain training data; the water body state data includes: spectral data and water sample data; The water body parameter acquisition module is used to input the training data into a water body evaluation model for evaluation to obtain water body anomaly parameters, obtain ultrasonic detection data, and determine the water body turbidity parameter of the target area according to the ultrasonic detection data; The water quality assessment and early warning module is used to combine the water body anomaly parameters and the water body turbidity parameters to obtain water quality assessment parameters, and evaluate the water quality of the target area according to the water quality assessment parameters; The water body parameter acquisition module includes: a signal attenuation amount acquisition module, a particle evaluation model module, and a water body turbidity parameter module: The signal attenuation amount acquisition module is used to determine the water body flow rate, the transmitted signal, and the received signal according to the ultrasonic detection data, calculate the water flow according to the water body flow rate, and calculate the signal attenuation amount according to the transmitted signal and the received signal; The particle evaluation model module is used to input the signal attenuation amount into the particle evaluation model for training to obtain the particle concentration and the water body particle size; the particle evaluation model is trained by historical signal attenuation amount data, particle concentration data, and water body particle size data; The water body turbidity parameter module is used to calculate the water body turbidity parameter according to the water flow, the particle concentration, and the water body particle size.

6. The water quality monitoring system for surface water according to claim 5, characterized in that, The training data acquisition module includes: a data set division module, a data set preprocessing module, a data set fusion module, and a band screening module: The data set division module is used to determine the data types of the water sample data, and divide each data type in the spectral data according to a preset division standard to obtain a classification data set; the classification data set includes multiple classification data sets; The data set preprocessing module is used to perform oversampling on the classification data sets in the classification data set to obtain a synthetic data set, and perform mathematical conversion on the spectral data through a preset algorithm to obtain a conversion data set; The data set fusion module is used to determine the data types of the conversion data set, and fuse the conversion data with the synthetic data set according to the data types to obtain a fusion data set; The band screening module is used to perform global filtering on the band features in the fusion data set through a genetic algorithm to obtain initial band features, perform band feature selection on the initial band features through a variance inflation factor to obtain optimal band features, and use the optimal band features as training data.

7. A water quality monitoring system for surface water according to claim 5, characterized in that, The system further includes: a column vector acquisition module, a column vector pre-training module, and an evaluation model training module: The column vector obtaining module is configured to divide the training data according to a preset quantity to obtain a training data set, input the training data set into a first preset model to be trained according to a preset number of training times to obtain a result set, and vertically merge the result set to obtain a column vector ; The column vector pre-training module is used to repeatedly execute the column vector acquisition module until the number of column vectors is the same as the preset number to obtain column vectors , and input the training data into a second preset model to obtain column vectors ; the column vectors and the column vectors have the same number of column vectors; The evaluation model training module is used to obtain water quality evaluation parameters, and input the water quality evaluation parameters, the training data, and the column vector into a third preset model for training to obtain model parameters, and update the third preset model according to the model parameters to obtain a water body evaluation model; The water body parameter acquisition module is further configured to input a column vector into the water body evaluation model for evaluation to obtain water body anomaly parameters.

8. A water quality monitoring system for surface water according to claim 5, characterized in that, The water quality assessment and early warning module is further used to, if the water quality assessment parameter is greater than the alarm threshold, upload the log and send an alarm instruction to cause the system to issue an alarm; otherwise, upload the log.

Images