River and lake water quality information internet of things sensing system and control method

Abstract

The application discloses a river and lake water quality information Internet of Things sensing system and a control method, and relates to the technical field of water quality monitoring. The micro water quality automatic monitoring station comprises a flow tank and a control unit; the flow tank is used for collecting water and conveying the water to a spectrum analyzer; the spectrum analyzer is electrically connected with the control unit; the control unit is electrically connected with a communication module; the controller is used for controlling the spectrum analyzer to regularly detect water quality, obtaining spectrum monitoring data and sending the spectrum monitoring data to a server; the server is provided with a water quality correlation model and a fitting error model in advance; the spectrum monitoring data is input into the water quality correlation model to obtain a water quality evaluation initial value, the spectrum monitoring data is input into the fitting error model to obtain a water quality evaluation error, and the water quality evaluation initial value and the water quality evaluation error are superposed to obtain a river and lake water quality sensing result; and the water quality and ecological environment of rivers and lakes can be accurately monitored.

Description

Technical Field

[0001] This invention belongs to the field of river and lake water quality monitoring design, specifically involving a river and lake water quality information Internet of Things sensing system and control method. Background Technology

[0002] As residents pay increasing attention to environmental issues closely related to their health, the monitoring and analysis of river and lake aquatic ecosystems are becoming increasingly important. Currently, regular monitoring of aquatic ecosystems such as rivers, lakes, reservoirs, and ponds generally relies on manual sampling and testing, which is not only time-consuming but also lacks continuous monitoring of water quality and ecological environment conditions in the monitored areas, failing to meet the needs of emergency response and management of water areas. In addition, the large volume, high vector dimension, and multiple attributes of water quality and ecological environment monitoring sample data in rivers and lakes make it difficult for existing water quality monitoring instruments and systems to meet practical needs. Summary of the Invention

[0003] This invention provides an Internet of Things (IoT) sensing system and control method for river and lake water quality information, enabling precise monitoring of water quality and ecological environment in rivers and lakes.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of this invention provides a river and lake water quality information Internet of Things sensing system, including a miniature automatic water quality monitoring station, a communication module, and a server; several miniature automatic water quality monitoring stations are connected to the server through the communication module;

[0006] The miniature automatic water quality monitoring station includes a flow tank and a control unit; the flow tank collects water and then transports it to a spectrometer; the spectrometer is electrically connected to the control unit; the control unit is electrically connected to a communication module.

[0007] The controller controls the spectrometer to periodically detect water quality, obtain spectral monitoring data, and send it to the server. The server has a water quality correlation model and a fitting error model preset in it. The spectral monitoring data is input into the water quality correlation model to obtain the initial value of water quality evaluation, and the spectral monitoring data is input into the fitting error model to obtain the water quality evaluation error. The initial value of water quality evaluation and the water quality evaluation error are superimposed to obtain the river and lake water quality perception result.

[0008] Furthermore, the monitoring point of the micro automatic water quality monitoring station is equipped with a float-type water sampling device, and the water intake pipe of the flow pool is connected to the float-type water sampling device. The water inlet of the water intake pipe of the flow pool is located 0.5m to 1m below the water surface.

[0009] Furthermore, the micro automatic water quality monitoring station is equipped with a sensor group electrically connected to the controller; the sensor group includes a pH sensor, a conductivity sensor, a temperature sensor, and a flow velocity and flow rate sensor; the pH sensor measures the acidity or alkalinity of the river or lake water; the conductivity sensor measures the dissolved salt content in the river or lake water; the temperature sensor measures the water temperature; and the flow velocity and flow rate sensor measures the velocity and flow rate of the river or lake water.

[0010] The server calculates and obtains the river and lake water quality assessment results based on pH, dissolved salt content, water temperature, nitrate nitrogen content, water flow speed and flow rate, and river and lake water quality sensing results.

[0011] Furthermore, the server calculates and obtains river and lake water quality assessment results based on pH, dissolved salt content, water temperature, nitrate nitrogen content, water flow velocity and flow rate, and river and lake water quality sensing results. The process includes:

[0012] pH, dissolved salt content, water temperature, nitrate nitrogen content, water flow velocity, and flow rate are used as water quality monitoring parameters. Anomaly detection ranges are set based on these parameters, expressed by the following formula:

[0013] ;

[0014] ;

[0015] ;

[0016] In the formula, The parameter values ​​that are less than or equal to 25% of the data points in the b-th water quality monitoring parameter set; The parameter value that is less than or equal to 75% of the data points in the b-th water quality monitoring parameter set; The distribution range of the middle 50% of the data in the set of water quality monitoring parameters for type b; The maximum value within the outlier detection range of the b-th water quality monitoring parameter; The minimum value within the outlier detection range of the b-th water quality monitoring parameter;

[0017] Outlier screening is performed on water quality monitoring parameters based on the outlier detection range; noise reduction is then applied to the water quality monitoring parameters, expressed by the following formula:

[0018] ;

[0019] In the formula, This represents the output data after denoising the b-th water quality monitoring parameter at time t. Let b be the water quality monitoring parameter for time k; The moving average window size is t; t represents the current time series.

[0020] The missing data in the water quality monitoring parameters are filled in using a linear interpolation algorithm. Then, the evaluation values ​​of the water quality monitoring parameters and the evaluation values ​​of the river and lake water quality perception results are obtained based on a preset mapping table. The evaluation values ​​of the water quality monitoring parameters and the evaluation values ​​of the river and lake water quality perception results are weighted and summed to obtain the river and lake water quality assessment results.

[0021] Furthermore, it also includes a virtual river and lake display platform, which constructs a three-dimensional scene model based on water system distribution data and terrain data;

[0022] A WebGL scene architecture is established based on the perspective lighting scene and web page architecture. After the 3D scene model is converted and compressed, it is embedded with the WebGL scene architecture to construct a virtual river and lake model. The river and lake water quality assessment results are added to the virtual river and lake model.

[0023] The viewpoint coordinates and target point coordinates are received and input into the river and lake virtual model, which then displays the river and lake water quality assessment results for the target point.

[0024] A second aspect of the present invention provides a method for sensing river and lake water quality information via the Internet of Things, comprising:

[0025] The system controls a spectrometer to periodically detect water quality and obtain spectral monitoring data. The spectral monitoring data is then input into a water quality correlation model to obtain initial values ​​for water quality assessment. The spectral monitoring data is then input into a fitting error model to obtain water quality assessment error. Finally, the initial values ​​for water quality assessment and the water quality assessment error are superimposed to obtain the water quality perception results for rivers and lakes.

[0026] Furthermore, the process of constructing the water quality correlation model and the fitting error model includes:

[0027] A water quality correlation model is obtained by coupling the water quality spectrum-turbidity correlation function, the water quality spectrum-COD correlation function, and the water quality spectrum-nitrogen content correlation function.

[0028] A fitting error model is constructed based on a convolutional neural network, and water quality training data is obtained from a water quality database. The water quality training data includes spectral features, water turbidity, chemical oxygen demand (COD), and water nitrogen content. The true label is obtained by weighted summation of water turbidity, COD, and water nitrogen content.

[0029] The spectral features from the water quality training data are input into the water quality correlation model to obtain the water quality prediction value; the spectral features from the water quality training data are input into the fitting error model to obtain the prediction error training value; the training loss value is calculated based on the water quality prediction value, the prediction error training value, and the true label; the fitting error model is optimized based on the training loss value, and the training process of the neural convolution model is repeated iteratively until the training loss value converges and the trained fitting error model is output.

[0030] Furthermore, the process of obtaining the water quality spectrum-turbidity correlation function, the water quality spectrum-COD correlation function, and the water quality spectrum-nitrogen content correlation function includes:

[0031] After obtaining several spectral characteristic curves affected only by turbidity, the least squares regression algorithm is used to fit the water quality turbidity characteristics to obtain the water quality spectrum-turbidity correlation function; after obtaining several spectral characteristic curves affected only by chemical oxygen demand (COD), the least squares regression algorithm is used to fit the COD to obtain the water quality spectrum-COD correlation function; after obtaining several spectral characteristic curves affected only by water nitrogen content, the least squares regression algorithm is used to fit the water nitrogen content to obtain the water quality spectrum-nitrogen content correlation function.

[0032] Furthermore, the fitting error model sequentially includes a first residual layer, a second residual layer, a third residual layer, a dimensionality reduction layer, a first convolutional layer, a first dropout layer, a second convolutional layer, and a second dropout layer.

[0033] Furthermore, the training loss value is calculated based on the predicted water quality value, the training error value, and the true label. The calculation process includes:

[0034] ;

[0035] ;

[0036] ;

[0037] ;

[0038] In the formula, Let represent the fitted water quality value at the i-th monitoring point; n represents the number of monitoring points. This represents the predicted water quality value for the i-th monitoring point. The training value for the prediction error of the i-th monitoring point; This is a real label; This is expressed as the mean squared error of the model training, representing the fitting error. This is represented as the cross-entropy loss value during model training, indicating the fitting error. This represents the training loss value of the fitting error model; It is represented as a weight parameter.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0040] The miniature automatic water quality monitoring station of this invention includes a flow tank and a control unit; the flow tank collects water and transports it to a spectrometer; the spectrometer is electrically connected to the control unit; the control unit is electrically connected to a communication module; the controller controls the spectrometer to periodically detect water quality, obtain spectral monitoring data, and send it to a server; the server generates river and lake water quality sensing results; it provides accurate and real-time monitoring of the water quality and ecological environment of rivers and lakes; simultaneously, the online full-spectrum water quality analysis technology can be directly immersed in water to achieve in-situ water quality detection, which can reduce the number of monitoring samples collected to a certain extent compared with traditional sensor detection.

[0041] The server described in this invention is pre-set with a water quality correlation model and a fitting error model. Spectral monitoring data is input into the water quality correlation model to obtain the initial value of water quality evaluation, and spectral monitoring data is input into the fitting error model to obtain the water quality evaluation error. The initial value of water quality evaluation and the water quality evaluation error are superimposed to obtain the water quality perception result of rivers and lakes. The fitting error model is used to compensate for the water quality prediction error caused by the cross-influence of turbidity, COD and total nitrogen on the spectral characteristic curve. Attached Figure Description

[0042] Figure 1 This is a structural diagram of the Internet of Things sensing system for river and lake water quality information provided in Embodiment 1 of the present invention;

[0043] Figure 2 This is a structural diagram of the micro automatic water quality monitoring station provided in Embodiment 1 of the present invention;

[0044] Figure 3 This is a flowchart of the server evaluating data provided in Embodiment 1 of the present invention;

[0045] Figure 4 This is a flowchart illustrating the construction of a virtual river and lake model in the virtual river and lake display platform provided in Embodiment 1 of the present invention;

[0046] Figure 5 This is a flowchart illustrating the display of the target point river and lake water quality assessment results on the river and lake virtual display platform provided in Embodiment 1 of the present invention.

[0047] Figure 6 This is a flowchart of the Internet of Things (IoT) sensing method for river and lake water quality information provided in Embodiment 2 of the present invention;

[0048] Figure 7 This is a structural diagram of the fitting error model provided in Embodiment 2 of the present invention. Detailed Implementation

[0049] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0050] Example 1

[0051] like Figures 1 to 2 As shown, this embodiment provides a river and lake water quality information Internet of Things sensing system, including a miniature water quality automatic monitoring station, a communication module, and a server; several miniature water quality automatic monitoring stations are connected to the server through the communication module;

[0052] The miniature automatic water quality monitoring station includes a flow tank and a control unit; the flow tank collects water and then transports it to a spectrometer; the spectrometer is electrically connected to the control unit; the control unit is electrically connected to a communication module.

[0053] The controller controls the spectrometer to periodically detect water quality, obtain spectral monitoring data, and send it to the server. The server has a water quality correlation model and a fitting error model preset in it. The spectral monitoring data is input into the water quality correlation model to obtain the initial value of water quality evaluation, and the spectral monitoring data is input into the fitting error model to obtain the water quality evaluation error. The initial value of water quality evaluation and the water quality evaluation error are superimposed to obtain the river and lake water quality perception result.

[0054] The monitoring point of the micro automatic water quality monitoring station is equipped with a float-type water sampling device. The water intake pipe of the flow pool is connected to the float-type water sampling device. The water inlet of the water intake pipe of the flow pool is located 0.5m to 1m below the water surface.

[0055] The micro automatic water quality monitoring station is equipped with a sensor group electrically connected to the controller; the sensor group includes a pH sensor, a conductivity sensor, a temperature sensor, and a flow velocity and flow rate sensor; the pH sensor measures the acidity or alkalinity of the river or lake water; the conductivity sensor measures the dissolved salt content in the river or lake water; the temperature sensor measures the water temperature; and the flow velocity and flow rate sensor measures the velocity and flow rate of the river or lake water.

[0056] like Figure 3 As shown, the server calculates and obtains river and lake water quality assessment results based on pH, dissolved salt content, water temperature, nitrate nitrogen content, water flow velocity and flow rate, and river and lake water quality sensing results. The process includes:

[0057] pH, dissolved salt content, water temperature, nitrate nitrogen content, water flow velocity, and flow rate are used as water quality monitoring parameters. Anomaly detection ranges are set based on these parameters, expressed by the following formula:

[0058] ;

[0059] ;

[0060] ;

[0061] In the formula, The parameter values ​​that are less than or equal to 25% of the data points in the b-th water quality monitoring parameter set; The parameter value that is less than or equal to 75% of the data points in the b-th water quality monitoring parameter set; The distribution range of the middle 50% of the data in the set of water quality monitoring parameters for type b; The maximum value within the outlier detection range of the b-th water quality monitoring parameter; The minimum value within the outlier detection range of the b-th water quality monitoring parameter;

[0062] Outlier screening is performed on water quality monitoring parameters based on the outlier detection range; noise reduction is then applied to the water quality monitoring parameters, expressed by the following formula:

[0063] ;

[0064] In the formula, This represents the output data after denoising the b-th water quality monitoring parameter at time t. Let b be the water quality monitoring parameter for time k; The moving average window size is t; t represents the current time series.

[0065] The missing data in the water quality monitoring parameters are filled in using a linear interpolation algorithm. Then, the evaluation values ​​of the water quality monitoring parameters and the evaluation values ​​of the river and lake water quality perception results are obtained based on a preset mapping table. The evaluation values ​​of the water quality monitoring parameters and the evaluation values ​​of the river and lake water quality perception results are weighted and summed to obtain the river and lake water quality assessment results.

[0066] The server communicates with the monitoring terminal via a wireless network. When the water quality assessment results of rivers and lakes are lower than the set threshold, the server retrieves the water system distribution map, adds the water quality assessment results to the water system distribution map to generate early warning information, and sends it to the monitoring terminal.

[0067] like Figure 4 and Figure 5 As shown, the river and lake water quality information Internet of Things sensing system also includes a river and lake virtual display platform, which constructs a three-dimensional scene model based on water system distribution data and terrain data;

[0068] A WebGL scene architecture is established based on the viewpoint, lighting scene, and webpage structure. The 3D scene model is transformed and compressed, and then embedded with the WebGL scene architecture to construct a virtual river and lake model. The river and lake water quality assessment results are added to the river and lake virtual model. The viewpoint coordinates and target point coordinates are received and input into the river and lake virtual model. The river and lake water quality assessment results of the target point are displayed through the river and lake virtual model.

[0069] The miniature automatic water quality monitoring station is equipped with a surge protector; the internal grounding busbar is connected to the controller and spectrometer inside the miniature automatic water quality monitoring station; a support for the antenna in the fixed communication module is installed outside the miniature automatic water quality monitoring station; the outdoor grounding grid is connected to the antenna support; one end of the surge protector is connected to the power supply through the surge protector lead wire, and the other end is connected to the outdoor grounding grid through the surge protector grounding wire.

[0070] In this embodiment, a number of distributed river and lake monitoring points are used to operate a fully automated miniature water quality automatic monitoring station. This station monitors and records changes in water quality in real time and uploads the monitoring data to a remote big data platform via a communication system, thereby achieving remote monitoring functionality. The miniature water quality automatic monitoring station features modular design, high integration, small footprint, and flexible site selection to meet various field conditions. It also has good scalability and replaceability, allowing users to adjust or change monitoring parameters according to their monitoring needs. Furthermore, the use of online full-spectrum water quality analysis technology allows for in-situ water quality detection by direct immersion in the water.

[0071] Example 2

[0072] like Figures 6 to 7 As shown, this embodiment provides an IoT sensing method for river and lake water quality information. The method is applied to the system described in Embodiment 1, and includes:

[0073] The construction of water quality correlation models and fitting error models includes:

[0074] Several spectral characteristic curves with only turbidity influence are obtained; each spectral characteristic curve is fitted to obtain multiple spectral curve fitting functions; the coefficients of each spectral curve fitting function are fitted with the corresponding turbidity to obtain the correlation function between each coefficient and turbidity; the least squares regression algorithm is used to fit the function to obtain the water quality spectrum-turbidity correlation function.

[0075] Similarly, after obtaining several spectral characteristic curves affected only by chemical oxygen demand (COD), the least squares regression algorithm is used to fit the COD to obtain the water quality spectrum-COD correlation function; after obtaining several spectral characteristic curves affected only by water nitrogen content, the least squares regression algorithm is used to fit the water quality nitrogen content to obtain the water quality spectrum-nitrogen content correlation function.

[0076] A water quality correlation model is obtained by coupling the water quality spectrum-turbidity correlation function, the water quality spectrum-COD correlation function, and the water quality spectrum-nitrogen content correlation function.

[0077] A fitting error model is constructed based on a convolutional neural network. The fitting error model includes, in sequence, a first residual layer, a second residual layer, a third residual layer, a dimensionality reduction layer, a first convolutional layer, a first dropout layer, a second convolutional layer, and a second dropout layer.

[0078] Water quality training data is obtained from a water quality database; the water quality training data includes spectral characteristics, water turbidity, chemical oxygen demand (COD), and water nitrogen content; the water turbidity, COD, and water nitrogen content are weighted and summed to obtain the true label;

[0079] The spectral features from the water quality training data are input into the water quality correlation model to obtain the predicted water quality value; the spectral features from the water quality training data are input into the fitting error model to obtain the prediction error training value. The calculation process includes:

[0080] ;

[0081] ;

[0082] ;

[0083] ;

[0084] In the formula, Let represent the fitted water quality value at the i-th monitoring point; n represents the number of monitoring points. This represents the predicted water quality value for the i-th monitoring point. The training value for the prediction error of the i-th monitoring point; This is a real label; This is expressed as the mean squared error of the model training, representing the fitting error. This is represented as the cross-entropy loss value during model training, indicating the fitting error. This represents the training loss value of the fitting error model; It is represented as a weight parameter.

[0085] The training loss value is calculated based on the water quality prediction value, the prediction error training value, and the true label. The fitting error model is optimized based on the training loss value. The training process of the neural convolution model is repeated iteratively until the training loss value converges and the trained fitting error model is output.

[0086] The system controls a spectrometer to periodically detect water quality and obtain spectral monitoring data. The spectral monitoring data is then input into a water quality correlation model to obtain initial values ​​for water quality assessment. The spectral monitoring data is also input into a fitting error model to obtain water quality assessment errors. The initial values ​​and water quality assessment errors are then superimposed to obtain the water quality perception results for rivers and lakes. The fitting error model is used to compensate for the water quality prediction errors caused by the cross-influence of turbidity, COD, and total nitrogen on the spectral characteristic curves.

[0087] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0088] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0089] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0090] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0091] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A river and lake water quality information Internet of Things sensing system, characterized in that, The system comprises a micro water quality automatic monitoring station, a communication module and a server; the micro water quality automatic monitoring stations are connected to the server through the communication module; The micro water quality automatic monitoring station comprises a flow cell and a control unit; the flow cell collects water and then delivers the water to a spectral analyzer; the spectral analyzer is electrically connected to the control unit; the control unit is electrically connected to the communication module; The control unit controls the spectral analyzer to regularly detect water quality to obtain spectral monitoring data and send the data to the server; the server is preconfigured with a water quality correlation model and a fitting error model; the spectral monitoring data is input into the water quality correlation model to obtain a water quality evaluation initial value, the spectral monitoring data is input into the fitting error model to obtain a water quality evaluation error, and the water quality evaluation initial value and the water quality evaluation error are superimposed to obtain a river and lake water quality perception result; The server calculates a river and lake water quality evaluation result according to the pH value, the content of dissolved salts, the water temperature, the content of nitrate nitrogen, the speed and flow of water flow and the river and lake water quality perception result, and the process comprises: The pH value, the content of dissolved salts, the water temperature, the content of nitrate nitrogen, the speed and flow of water flow are used as water quality monitoring parameters, and an abnormal value detection range is set based on the water quality monitoring parameters, and the expression formula is: ； ； ； In the formula, is the parameter value that is less than or equal to 25% of the data points in the bth set of water quality monitoring parameters; is the parameter value that is less than or equal to 75% of the data points in the bth set of water quality monitoring parameters; is the distribution range of the middle 50% of data in the bth set of water quality monitoring parameters; is the minimum value in the outlier detection range of the bth water quality monitoring parameter; is the maximum value in the outlier detection range of the bth water quality monitoring parameter; The water quality monitoring parameters are subjected to abnormal value screening based on the abnormal value detection range; the water quality monitoring parameters are denoised, and the expression formula is: ； In the formula, denotes the output data after denoising of the bth water quality monitoring parameter in time t; is the bth water quality monitoring parameter in time k; is the moving average window size; t is the current time series; The missing data in the water quality monitoring parameters is filled by using a linear interpolation algorithm, and then the evaluation value of the water quality monitoring parameters and the evaluation value of the river and lake water quality perception result are obtained based on a preconfigured mapping relationship table; the evaluation value of the water quality monitoring parameters and the evaluation value of the river and lake water quality perception result are subjected to weighted summation to obtain the river and lake water quality evaluation result.

2. The river-lake water quality information Internet of Things sensing system according to claim 1, characterized in that, A floating ball type water sampling device is arranged on the monitoring point of the micro water quality automatic monitoring station, a water inlet pipe of the flow cell is connected to the floating ball type water sampling device, and a water inlet hole of the water inlet pipe is located 0.5-1 m below the water surface. 3.The river-lake water quality information Internet of Things sensing system according to claim 1, characterized in that, A sensor group electrically connected to the controller is arranged in the micro water quality automatic monitoring station; the sensor group comprises a pH sensor, a conductivity sensor, a temperature sensor and a flow rate and flow sensor; the pH sensor measures the pH value of the river and lake water quality; the conductivity sensor measures the content of dissolved salts in the river and lake water quality; the temperature sensor measures the water temperature; and the flow rate and flow sensor measures the speed and flow of the river and lake water flow.

4. The river-lake water quality information Internet of Things sensing system according to claim 3, characterized in that, The system further comprises a river and lake virtual display platform; the river and lake virtual display platform constructs a three-dimensional scene model according to water system distribution data and terrain data; A WebGL scene architecture is established according to a view angle light scene and a webpage architecture, the three-dimensional scene model is converted and compressed, and then model scene data of the three-dimensional scene model is embedded into the WebGL scene architecture to construct a river and lake virtual model; the river and lake water quality evaluation result is added to the river and lake virtual model; The received view point coordinates and target point coordinates are input into the river and lake virtual model, and the river and lake water quality evaluation result of the target point is displayed through the river and lake virtual model.

5. A control method of the river and lake water quality information Internet of Things perception system according to any one of claims 1 to 4, comprising: The control spectrum analyzer detects water quality periodically to obtain spectrum monitoring data, inputs the spectrum monitoring data into a preset water quality correlation model to obtain a water quality evaluation initial value, inputs the spectrum monitoring data into a preset fitting error model to obtain a water quality evaluation error, and superimposes the water quality evaluation initial value and the water quality evaluation error to obtain a river and lake water quality sensing result.

6. The control method according to claim 5, characterized by The water quality correlation model and the fitting error model are constructed by: coupling a water quality spectrum-turbidity correlation function, a water quality spectrum-COD correlation function and a water quality spectrum-nitrogen content correlation function to obtain the water quality correlation model; constructing the fitting error model based on a convolutional neural network, and obtaining water quality training data from a water quality database; the water quality training data includes spectrum features, water quality turbidity, chemical oxygen demand and water quality nitrogen content; and performing weighted summation on the water quality turbidity, the chemical oxygen demand and the water quality nitrogen content to obtain a true label; inputting the spectrum features in the water quality training data into the water quality correlation model to obtain a water quality prediction value; inputting the spectrum features in the water quality training data into the fitting error model to obtain a prediction error training value, and calculating a training loss value according to the water quality prediction value, the prediction error training value and the true label; optimizing the fitting error model according to the training loss value, repeating the training process of the neural convolutional model until the training loss value converges, and outputting the trained fitting error model.

7. The control method according to claim 6, characterized by, The water quality spectrum-turbidity correlation function, the water quality spectrum-COD correlation function and the water quality spectrum-nitrogen content correlation function are obtained by: after obtaining a plurality of spectrum feature curves affected only by turbidity, fitting the water quality turbidity features by using a least square method regression algorithm to obtain the water quality spectrum-turbidity correlation function; after obtaining a plurality of spectrum feature curves affected only by chemical oxygen demand, fitting the chemical oxygen demand by using a least square method regression algorithm to obtain the water quality spectrum-COD correlation function; and after obtaining a plurality of spectrum feature curves affected only by water quality nitrogen content, fitting the water quality nitrogen content by using a least square method regression algorithm to obtain the water quality spectrum-nitrogen content correlation function.

8. The control method according to claim 6, characterized by The fitting error model sequentially includes a first residual layer, a second residual layer, a third residual layer, a dimension reduction layer, a first convolutional layer, a first dropout layer, a second convolutional layer and a second dropout layer.

9. The control method according to claim 6, characterized by, The training loss value is calculated according to the water quality prediction value, the prediction error training value and the true label, and the calculation process includes: ； ； ； ； In the formula, represents the water quality fitting value of the ith monitoring point; n represents the number of monitoring points; is the water quality prediction value of the ith monitoring point; is the prediction error training value of the ith monitoring point; is the true label; represents the mean square error of the fitting error model training; represents the cross-entropy loss value of the fitting error model training; is the training loss value of the fitting error model; represents the weight parameter.

Images