Multi-parameter water quality on-line monitoring system and method

Abstract

The present application relates to the technical field of environmental monitoring, and more particularly to a multi-parameter water quality online monitoring system and method, which covers water grass growth prediction, monitoring equipment damage assessment, water grass interference analysis on detection equipment and sensor installation position selection, etc., predicts water grass growth density through the construction of a long short-term memory neural network model, assesses monitoring equipment damage using a multi-layer perception neural network model, quantifies the interference degree by comprehensively considering water grass density and sensor sensitivity data, and determines the installation position through equipment damage and interference analysis results, which can discover equipment damage risks in advance, reduce the interference of water grass on detection, find the optimal installation position for sensors, and ensure the stable and accurate operation of equipment.

Description

Technical Field

[0001] This invention relates to the field of environmental monitoring technology, and in particular to a multi-parameter online water quality monitoring system and method. Background Technology

[0002] In the field of water environment monitoring and management, accurate and stable monitoring data are crucial for assessing water quality, ecosystem health, and ensuring the sustainable use of water resources. As key equipment for acquiring water environment information, the rationality of sensor installation and operational stability directly affect the quality and reliability of monitoring data. However, in practical applications, many factors pose challenges to the effective operation and rational layout of sensors. Aquatic plants are an important component of aquatic ecosystems, exhibiting complex dynamic changes during their growth. The growth density of aquatic plants fluctuates significantly with changes in environmental factors such as season, water temperature, light, and nutrients. Under suitable environmental conditions, aquatic plants may grow rapidly and reproduce in large quantities, forming dense communities. This growth change not only affects the physical and chemical properties of water bodies, such as water flow velocity and dissolved oxygen content, but also directly interferes with water environment monitoring equipment. When aquatic plants grow too luxuriantly, they can entangle and cover monitoring equipment, hindering effective contact between sensors and water bodies, leading to deviations or even failures in measurement data. For example, aquatic plants may attach to the sensing part of the sensor, affecting its accurate perception of water quality parameters. In addition, the growth of aquatic plants may also change the optical properties of water bodies, affecting the measurement accuracy of optical sensors. The installation location of sensors is crucial for obtaining accurate and representative monitoring data. A reasonable installation location should avoid the influence of external interference factors and ensure that the sensor can truly reflect the actual situation of the water body. However, when selecting an installation location, it is necessary to comprehensively consider many factors, such as the water flow characteristics, the distribution of aquatic plants, and the risk of equipment damage. Currently, the selection of sensor installation locations often lacks scientific basis and systematic methods, and is mostly based on experience and subjective judgment. This approach can easily lead to unreasonable installation locations, making the sensor susceptible to interference from aquatic plants and equipment damage, thereby reducing the quality of monitoring data. In addition, different types of sensors have different requirements for installation locations. How to select the optimal installation location based on the characteristics of the sensor and the monitoring objectives is an urgent problem to be solved in the field of water environment monitoring.

[0003] In view of this, the applicant proposes a multi-parameter online water quality monitoring system and method. Summary of the Invention

[0004] To overcome the defects and shortcomings of existing technologies, this invention provides a multi-parameter online water quality monitoring system and method. This application covers aspects such as aquatic plant growth prediction, monitoring equipment damage assessment, aquatic plant interference analysis on detection equipment, and sensor installation location selection. By constructing a long short-term memory neural network model to predict aquatic plant growth density, using a multilayer perceptron neural network model to assess monitoring equipment damage, quantifying the degree of interference by combining aquatic plant density and sensor sensitivity data, and then determining the installation location based on the equipment damage and interference analysis results, it can detect equipment damage risks in advance, reduce the interference of aquatic plants on detection, find the optimal installation location for sensors, and ensure stable and accurate operation of the equipment.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for online monitoring of multi-parameter water quality, comprising the following steps: S100: Obtain the growth status of aquatic plants and the water flow status at each installation location of the environmental monitoring equipment, and at the same time obtain the operating status of the equipment; S200: Predict the growth of aquatic plants at the corresponding installation location by analyzing the water flow and the growth of aquatic plants at the corresponding location. S300: The damage to the monitoring equipment at the installation location caused by water flow impact is predicted by considering the buffering effect of water flow impact, equipment protection status, and aquatic plant growth at the corresponding installation location. S400. Analyze the interference of aquatic plant growth on detection equipment by using the growth characteristics of aquatic plants at the corresponding location and the detection characteristics of the equipment. S500: The installation location is selected based on the damage analysis results of the monitoring equipment at the installation location caused by water flow impact and the interference analysis results of the detection equipment caused by aquatic plant growth.

[0006] In one implementation of the present invention, step S100 includes the following specific contents: Step 110: Obtain the density, growth rate, and species of aquatic plants at each location using sensors; Step 120: Obtain the environmental conditions of the water body and the atmospheric environment at the corresponding location through the sensor. The environmental conditions of the water body include the condition of various nutrients in the water body and water body parameters such as water temperature that affect the growth of aquatic plants, as well as water body parameters such as water flow velocity that may damage the sensor. At the same time, the atmospheric environment includes atmospheric parameters such as temperature and humidity that affect the growth of aquatic plants. Step 130: Obtain data on the hardness and elasticity of the equipment surface, reflecting the equipment's protective capabilities, and obtain data on the detection sensitivity of the corresponding sensor probes; store the acquired data into the corresponding storage components.

[0007] In one implementation of the present invention, the prediction of aquatic plant growth at the corresponding position in S200 includes the following specific steps: Step 210: Obtain the density, growth rate, and species of aquatic plants at each location, and simultaneously obtain the environmental conditions of the water body and the atmospheric environment at the corresponding location. Step 220: Based on the initial aquatic plant density, initial aquatic plant growth rate, water environment and atmospheric environment of the corresponding historical aquatic plant species, and the aquatic plant density at each future time, construct a long short-term memory neural network model with the input of initial aquatic plant density, initial aquatic plant growth rate, water environment and atmospheric environment of the corresponding location, and output of aquatic plant density at each future time. Step 230: Import the obtained initial aquatic plant density, initial aquatic plant growth rate, corresponding water environment conditions, and future atmospheric environment conditions of the current aquatic plant species into the constructed long short-term memory neural network model to output the aquatic plant growth density at each time point.

[0008] In one implementation of the present invention, damage to the monitoring device at the installation location specifically includes the following: Step 310: Obtain the average water velocity and water flow density at the corresponding positions for each historical period. At the same time, obtain the data on the surface hardness and elasticity of the corresponding equipment, which reflects the equipment's protective capability. Also, obtain the aquatic plant growth density at the corresponding positions for each historical period. Based on the aquatic plant growth density, water-blocking characteristics of the aquatic plants, and water flow velocity at the corresponding positions, estimate the water velocity of the water flow impacting the corresponding equipment through the aquatic plants. Import the water velocity of the water flow impacting the corresponding equipment through the aquatic plants, the area of ​​the corresponding position, and the water flow density for each historical period into the water flow impact force calculation formula to calculate the water flow impact force at the corresponding position. Divide the water flow impact force at the corresponding time by the safe impact force to obtain the water flow impact anomaly. Step 320: Obtain the hardness and elasticity of the corresponding equipment surface. Divide the hardness of the corresponding equipment surface by the safe hardness to obtain the hardness safety factor. Divide the elasticity of the corresponding equipment surface by the safe elasticity to obtain the elasticity safety factor. Weight the hardness safety factor and the elasticity safety factor to obtain the impact resistance coefficient of the corresponding equipment. Step 330: Divide the water flow impact anomalies at each moment of the future monitoring cycle by the impact resistance coefficient, and then average them over the time range to obtain the damage analysis results of the monitoring equipment at the installation location. By acquiring information such as historical water flow, equipment protection capabilities, and aquatic plant growth density, and combining it with a multilayer perceptron neural network model, the water velocity impacting the equipment is estimated. Then, the water flow impact force and impact anomaly are calculated using formulas. The water flow impact force is related to aquatic plant growth, water velocity, and water flow density. The equipment hardness and elasticity are obtained to calculate the impact resistance coefficient. Taking into account the characteristics of the equipment itself, the damage analysis results can be calculated to comprehensively assess the water flow impact and equipment tolerance, detect potential damage risks to the equipment in advance, and ensure the normal operation of the equipment.

[0009] In one implementation of the present invention, the analysis of interference of aquatic plant growth on the detection equipment includes the following specific aspects: The process involves acquiring data on aquatic plant density and the corresponding sensor probe sensitivity at various points in time during the monitoring period. The aquatic plant density impact value at each point in time is obtained by dividing the aquatic plant density at each point in time by the safe aquatic plant density. The impact anomaly is obtained by multiplying the impact value at each point by the sensor probe sensitivity impact coefficient. The sensor sensitivity anomaly is obtained by dividing the required sensor probe sensitivity by the corresponding sensor probe sensitivity data. The true sensor sensitivity anomaly at each point in time is obtained by multiplying the sum of 1 and the impact anomaly by the sensor sensitivity anomaly. The average of the true sensor sensitivity anomalies over the monitoring period is used to obtain the interference analysis results of aquatic plant growth on the detection equipment. This step accurately assesses the degree of interference of aquatic plant growth on the detection equipment. The process involves acquiring aquatic plant density and sensor probe sensitivity data within the monitoring period, calculating the aquatic plant density impact value, impact anomaly, sensor sensitivity anomaly, and true anomaly. Aquatic plant density affects sensor detection; this impact can be quantified by comparing it with the safe value and calculating coefficients.

[0010] In one implementation of the present invention, the selection of the installation location specifically includes the following: obtaining the damage analysis results of the monitoring equipment at each location and the interference analysis results of aquatic plant growth on the detection equipment; weighting and summing the obtained damage analysis results of the monitoring equipment at each location and the interference analysis results of aquatic plant growth on the detection equipment to obtain the selection anomaly value of the corresponding location; sorting the selection anomaly values ​​in descending order; obtaining the location with the smallest selection anomaly value as the selection location of the corresponding sensor; and sending the selection location of the corresponding sensor to the client. This step can find the optimal installation location for the sensor, obtain the damage analysis results of the monitoring equipment at each location and the interference analysis results of aquatic plant growth on the detection equipment, and weighted sum to obtain the selection anomaly value.

[0011] Secondly, the present invention also provides a multi-parameter online water quality monitoring system, comprising: The data acquisition module acquires the growth of aquatic plants and the water flow at each installation location of the environmental monitoring equipment, and also acquires the operating status of the equipment. The aquatic plant growth prediction module predicts the growth of aquatic plants at the corresponding installation location based on the water flow conditions and the growth of aquatic plants at that location. The damage prediction module predicts the damage to the monitoring equipment at the installation location by considering the water flow impact, equipment protection status, and the buffering effect of aquatic plant growth at the corresponding installation location. The interference analysis module analyzes the interference of aquatic plant growth on the detection equipment by using the growth characteristics of aquatic plants at the corresponding location and the detection characteristics of the equipment. The selection module uses the damage analysis results of water flow impact on the monitoring equipment at the installation location and the interference analysis results of aquatic plant growth on the detection equipment to select the installation location.

[0012] Thirdly, the present invention provides an electronic device comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a multi-parameter online water quality monitoring method by calling the computer program stored in the memory.

[0013] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a multi-parameter online water quality monitoring method.

[0014] Compared with the prior art, the present invention has the following advantages and beneficial effects: This application covers aspects such as aquatic plant growth prediction, monitoring equipment damage assessment, aquatic plant interference analysis of detection equipment, and sensor installation location selection. It predicts aquatic plant growth density by constructing a long short-term memory neural network model, assesses monitoring equipment damage using a multilayer perceptron neural network model, quantifies the degree of interference by combining aquatic plant density and sensor sensitivity data, and determines the installation location based on the equipment damage and interference analysis results. This approach can detect equipment damage risks in advance, reduce aquatic plant interference with detection, find the optimal installation location for sensors, and ensure stable and accurate operation of the equipment. Attached Figure Description

[0015] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the overall process structure of an embodiment of the method of the present invention; Figure 2 This is a schematic diagram of the damage prediction process structure of the monitoring equipment in an embodiment of the method of the present invention; Figure 3This is a schematic diagram of the construction process of the long short-term memory neural network model in an embodiment of the method of the present invention; Figure 4 This is a schematic diagram of the module composition structure of an embodiment of the system of the present invention. Detailed Implementation

[0016] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0017] Please see Figures 1 to 3 , Figure 1 This is a schematic diagram of the overall process of the multi-parameter online water quality monitoring method provided in this embodiment of the invention, which specifically includes the following steps: S100: Obtain the growth status of aquatic plants and the water flow status at each installation location of the environmental monitoring equipment, and at the same time obtain the operating status of the equipment; In this step, S100 includes the following specific contents: Step 110: Obtain the density, growth rate, and species of aquatic plants at various locations using sensors. Specifically, this involves: deploying optical sensors (RGB / multispectral cameras), sonar equipment (side-scan sonar), and chlorophyll fluorescence sensors in a grid pattern over the underwater target area; periodically acquiring images, acoustic reflection data, and chlorophyll concentration; secondly, calculating the aquatic plant coverage density through image segmentation (e.g., the U-Net model); distinguishing aquatic plant areas using sonar reflection intensity; and fitting a growth rate model using continuous chlorophyll or laser scanning data; simultaneously, acquiring spectral / DNA information using a hyperspectral imager or eDNA technology; and classifying aquatic plant species through machine learning. This is existing technology in the field and will not be described in detail. Step 120: Obtain the environmental conditions of the water body and the atmospheric environment at the corresponding location through the sensor. The water body environmental conditions include the condition of various nutrients in the water body and water body parameters such as water temperature that affect the growth of aquatic plants, as well as water body parameters such as water flow velocity that may damage the sensor. At the same time, the atmospheric environment conditions include atmospheric parameters such as temperature and humidity that affect the growth of aquatic plants. The atmospheric environment can be obtained through weather forecasts. Step 130: Obtain data on the hardness and elasticity of the equipment surface, reflecting the equipment's protective capability, and obtain data on the detection sensitivity of the corresponding sensor probes; store the acquired data into the corresponding storage components. S200: Predict the growth of aquatic plants at the corresponding installation location by analyzing the water flow and the growth of aquatic plants at the corresponding location. In this step, the prediction of aquatic plant growth at the corresponding location in S200 includes the following specific steps: Step 210: Obtain the density, growth rate, and species of aquatic plants at each location, and simultaneously obtain the environmental conditions of the water body and the atmospheric environment at the corresponding location. Step 220: Based on the historical initial aquatic plant density, initial aquatic plant growth rate, corresponding water environment and atmospheric environment of the corresponding location, and the aquatic plant density at each future time, construct a long short-term memory neural network model with the input of initial aquatic plant density, initial aquatic plant growth rate, corresponding water environment and atmospheric environment, and output of aquatic plant density at each future time. The specific steps are as follows: First, collect historical data, covering the initial aquatic plant density, initial growth rate, corresponding water environment (such as water temperature, dissolved oxygen, pH, etc.) and atmospheric environment (such as light intensity, air temperature, humidity, etc.) of the corresponding aquatic plant species, as well as the aquatic plant density at each future time. Clean the data, handle missing values ​​and outliers, and then perform normalization processing to scale the data to an appropriate range to accelerate the model convergence speed. Then, the layers are constructed: Input layer: The number of neurons in the input layer is determined by the number of input features, i.e., the total number of features such as initial aquatic plant density, initial growth rate, aquatic environment, and atmospheric environment. The input layer is responsible for receiving raw data and passing it to subsequent layers. Its advantage is that it provides a data entry point for the entire model, unifies the data format, and facilitates subsequent processing. LSTM layer: 1-3 LSTM layers can be set. LSTM units have memory cells and gating mechanisms, which can capture long-term dependencies in time series data. In aquatic plant density prediction, the growth of aquatic plants is affected by past environment and growth status. The LSTM layer can remember important information at different time points, avoiding the gradient vanishing or exploding problem in traditional recurrent neural networks, thus better learning the temporal patterns in the data. Fully connected layer: A fully connected layer is added after the LSTM layer. The fully connected layer performs non-linear transformation on the features output by the LSTM layer, integrates the feature information, and enhances the expressive power of the model. It can learn more complex patterns from the temporal features extracted by the LSTM layer, improving the generalization of the model. The output layer has the following characteristics: The number of neurons in the output layer equals the number of predicted aquatic plant density values ​​at each future time point. The output layer maps the features learned by the previous layers to the final prediction result. The number of neurons in the output layer is directly determined by the prediction target; that is, the number of aquatic plant density values ​​to be predicted at each time point determines the number of neurons in the output layer. Finally, the model is trained using prepared data. A suitable loss function (such as mean squared error) and optimization algorithm (such as Adam) are selected to minimize the error between the predicted and true values. After training, the model is evaluated using test data. The model parameters are adjusted based on the evaluation results to improve the model's performance and obtain the final model. The model predicts aquatic plant growth density by acquiring information on aquatic plants and the environment at various locations and constructing a long short-term memory neural network model. Aquatic plant growth is influenced by multiple factors, such as density, growth rate, water body, and atmospheric environment. Collecting historical data can comprehensively reflect the relationship between these factors. Data cleaning and normalization ensure the quality of the model input. LSTM... The layer can capture the long-term dependence of aquatic plant growth and avoid gradient problems. The fully connected layer enhances the model's expressive power, and the output layer provides the prediction results. The training and evaluation adjust the parameters so that the model can accurately predict the future aquatic plant growth density. Step 230: Import the obtained initial aquatic plant density, initial aquatic plant growth rate, corresponding water environment conditions, and future atmospheric environment conditions of the current aquatic plant species into the constructed long short-term memory neural network model to output the aquatic plant growth density at each time point. S300: The damage to the monitoring equipment at the installation location caused by water flow impact is predicted by considering the buffering effect of water flow impact, equipment protection status, and aquatic plant growth at the corresponding installation location. In this step, damage to the monitoring equipment at the installation location specifically includes the following: Step 310: Obtain the average water velocity and water flow density at the corresponding positions for each historical period. At the same time, obtain the data on the surface hardness and elasticity of the corresponding equipment, which reflects the equipment's protective capability. Also, obtain the aquatic plant growth density at the corresponding positions for each historical period. Based on the aquatic plant growth density, water-blocking characteristics of the aquatic plants, and water flow velocity at the corresponding positions, estimate the water velocity of the water flow impacting the corresponding equipment through the aquatic plants. Import the water velocity of the water flow impacting the corresponding equipment through the aquatic plants, the area of ​​the corresponding position, and the water flow density for each historical period into the water flow impact force calculation formula to calculate the water flow impact force at the corresponding position. The water flow impact force calculation formula is a conventional technical method. The water flow impact anomaly is obtained by dividing the water flow impact force at the corresponding time by the safe impact force. It should be noted that the water velocity passing through the aquatic plants and impacting the corresponding equipment can be estimated using a multilayer perceptron neural network model based on the aquatic plant growth density and water flow velocity at the corresponding location. The specific steps are as follows: the number of neurons in the input layer depends on the number of input features (such as aquatic plant growth density, aquatic plant water-blocking characteristics (including leaf size and shape, as well as stem thickness and flexibility), water flow velocity, etc.), and the number of neurons in the output layer is 1, representing the estimated water velocity passing through the aquatic plants and impacting the equipment. The number of hidden layers and neurons needs to be adjusted according to specific circumstances, preferably 4 layers. In the hidden layers, a suitable activation function, the ReLU function, can be selected. In the output layer, no activation function is used because the water velocity is a continuous value and does not require nonlinear transformation. For regression problems, the commonly used loss function is mean squared error (MSE), which is the average of the squares of the differences between the predicted and actual values. A suitable optimization algorithm is chosen to update the weights and biases of the neural network. The preferred algorithm is Adam, which combines the advantages of momentum and adaptive learning rate, typically achieving good training results. The training data is input into the neural network model, and forward propagation is performed to calculate the predicted values. Then, the error between the predicted and actual values ​​is calculated based on the loss function. The optimization algorithm is used to update the model's weights and biases based on the error through backpropagation. This training process is iterated until the loss function converges or a preset number of training rounds is reached. The trained model is then evaluated using validation data, and evaluation metrics such as mean squared error (MSE), mean absolute error (MAE), and coefficient of determination (R²) are calculated. 2 These indicators can reflect the model's prediction accuracy and fitting effect, so the model with the highest prediction accuracy is selected as the final layer perceptron neural network model, and the water velocity of the equipment impacted by the aquatic plants is predicted through the final model. Step 320: Obtain the hardness and elasticity of the corresponding equipment surface. Divide the hardness of the corresponding equipment surface by the safe hardness to obtain the hardness safety factor, and divide the elasticity of the corresponding equipment surface by the safe elasticity to obtain the elasticity safety factor. Calculate the impact resistance coefficient of the corresponding equipment by weighted summation of the hardness safety factor and the elasticity safety factor. When calculating the impact resistance coefficient of the corresponding equipment by weighted summation of the hardness safety factor and the elasticity safety factor, the weights can be set according to the actual situation of the equipment and experience. For example, if the hardness of the equipment has a greater impact on the impact resistance, a higher weight can be assigned to the hardness safety factor; conversely, a higher weight can be assigned to the elasticity safety factor. Alternatively, experiments can be conducted to evaluate the impact resistance performance of the equipment under different weight combinations, and the weight corresponding to the optimal performance can be selected. Step 330: Divide the water flow impact anomalies at each moment of the future monitoring cycle by the impact resistance coefficient, and then average them over the time range to obtain the damage analysis results of the monitoring equipment at the installation location. By acquiring information such as historical water flow, equipment protection capability, and aquatic plant growth density, and combining it with a multilayer perceptron neural network model, the water velocity impacting the equipment is estimated. Then, the water flow impact force and impact anomaly are calculated using formulas. The water flow impact force is related to aquatic plant growth, water velocity, and water flow density. The equipment hardness and elasticity are obtained to calculate the impact resistance coefficient. Taking into account the characteristics of the equipment itself, the damage analysis results are finally calculated to comprehensively consider the water flow impact and equipment tolerance, detect potential damage risks to the equipment in advance, and ensure the normal operation of the equipment. S400. Analyze the interference of aquatic plant growth on detection equipment by using the growth characteristics of aquatic plants at the corresponding location and the detection characteristics of the equipment. In this step, the analysis of the interference of aquatic plant growth on the detection equipment includes the following specific aspects: The process involves acquiring data on aquatic plant density and the corresponding sensor probe sensitivity at each moment of the monitoring period. The influence value of aquatic plant density at each moment is obtained by dividing the aquatic plant density at each moment by the safe aquatic plant density. The influence anomaly is obtained by multiplying this influence value by the sensor probe sensitivity influence coefficient. The sensor sensitivity anomaly is obtained by dividing the required sensor probe sensitivity by the corresponding sensor probe sensitivity data. The true sensor sensitivity anomaly at the corresponding moment is obtained by multiplying the sum of 1 and the influence anomaly by the sensor sensitivity anomaly. Finally, the average of the true sensor sensitivity anomalies over the monitoring period is calculated to obtain the interference analysis results of aquatic plant growth on the detection equipment. This step accurately assesses the impact of aquatic plant growth on the detection equipment. The degree of interference was assessed by obtaining data on aquatic plant density and sensor probe detection sensitivity during the monitoring period. The impact values ​​of aquatic plant density, impact anomalies, sensor sensitivity anomalies, and actual anomalies were calculated. Aquatic plant density affects sensor detection. By comparing with safety values ​​and calculating coefficients, this impact can be quantified. The average value over the monitoring period is used to obtain the interference analysis results, which comprehensively reflect the interference of aquatic plant growth on the detection equipment throughout the entire monitoring period. This helps to take timely measures to reduce interference and ensure the accuracy of the detection equipment. The sensor probe detection sensitivity impact coefficient can be obtained experimentally. Under different aquatic plant density environments, the changes in sensor probe detection sensitivity are measured, and the relationship between aquatic plant density and detection sensitivity changes is analyzed. The coefficient between the two is fitted using methods such as linear regression. S500: The installation location is selected based on the damage analysis results of the monitoring equipment at the installation location caused by water flow impact and the interference analysis results of the detection equipment caused by aquatic plant growth. In this step, the selection of the installation location specifically includes the following: obtaining the damage analysis results of the monitoring equipment at each location and the interference analysis results of aquatic plant growth on the detection equipment; weighting and summing the obtained damage analysis results of the monitoring equipment at each location and the interference analysis results of aquatic plant growth on the detection equipment to obtain the selection anomaly value for the corresponding location; sorting the selection anomaly values ​​in descending order, and selecting the location with the smallest selection anomaly value as the selection location for the corresponding sensor; and sending the selection location of the corresponding sensor to the client. This step can find the optimal installation location for the sensor. The steps involve obtaining the damage analysis results of the monitoring equipment at each location and the interference analysis results of aquatic plant growth on the detection equipment, and weighting and summing them to obtain the selection anomaly value, based on the factors of equipment damage and water... Both plant interference and sensor interference can affect the normal operation of sensors. Taking both into account allows for a more comprehensive evaluation of the location's merits. Selecting outliers in descending order and choosing the location with the smallest outlier can minimize the risk of equipment damage and interference, enabling the sensor to operate stably and accurately. The results are then sent to the client for user understanding and decision-making. The determination of weights requires a comprehensive consideration of the impact of both equipment damage and plant interference on the sensor's normal operation (i.e., its impact on lifespan). If equipment damage has a greater impact on the sensor, the damage analysis results of the monitoring equipment can be assigned a higher weight; conversely, the interference analysis results of plant growth on the detection equipment should be assigned a higher weight. Weights can also be determined through expert evaluation, historical data statistical analysis, and other methods. The advantages of the above embodiments are as follows: they cover aspects such as aquatic plant growth prediction, monitoring equipment damage assessment, aquatic plant interference analysis on detection equipment, and sensor installation location selection. By constructing a long short-term memory neural network model to predict aquatic plant growth density, using a multilayer perceptron neural network model to assess monitoring equipment damage, quantifying the degree of interference by combining aquatic plant density and sensor sensitivity data, and then determining the installation location based on the equipment damage and interference analysis results, the risk of equipment damage can be detected in advance, the interference of aquatic plants on detection can be reduced, the optimal installation location for the sensor can be found, and the stable and accurate operation of the equipment can be guaranteed.

[0018] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of the multi-parameter online water quality monitoring system provided in an embodiment of the present invention, including: The data acquisition module acquires the growth of aquatic plants and the water flow at each installation location of the environmental monitoring equipment, and also acquires the operating status of the equipment. The aquatic plant growth prediction module predicts the growth of aquatic plants at the corresponding installation location based on the water flow conditions and the growth of aquatic plants at that location. The damage prediction module predicts the damage to the monitoring equipment at the installation location by considering the water flow impact, equipment protection status, and the buffering effect of aquatic plant growth at the corresponding installation location. The interference analysis module analyzes the interference of aquatic plant growth on the detection equipment by using the growth characteristics of aquatic plants at the corresponding location and the detection characteristics of the equipment. The selection module uses the damage analysis results of water flow impact on the monitoring equipment at the installation location and the interference analysis results of aquatic plant growth on the detection equipment to select the installation location.

[0019] The steps for implementing the corresponding functions of each parameter and each unit module in the multi-parameter online water quality monitoring system of the present invention can be referred to the parameters and steps in the embodiments of the multi-parameter online water quality monitoring method described above, and will not be repeated here.

[0020] Embodiments of the present invention also provide an electronic device, including a memory, a processor, and a communication bus; the memory and the processor are connected via the communication bus. The memory stores a multi-parameter online water quality monitoring method that can be loaded by the processor and executed as provided in the above embodiments.

[0021] The memory can be used to store instructions, programs, code, code sets, or instruction sets. The memory may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the multi-parameter online water quality monitoring method provided in the above embodiments, etc.; the data storage area may store data involved in the multi-parameter online water quality monitoring method provided in the above embodiments, etc.

[0022] A processor may include one or more processing cores. The processor executes instructions, programs, code sets, or instruction sets stored in memory, and calls data stored in memory to perform various functions and process data according to the present invention. The processor may be at least one of a specific application-specific integrated circuit, digital signal processor, digital signal processing device, programmable logic device, field-programmable gate array, central processing unit, controller, microcontroller, and microprocessor. It is understood that, for different devices, the electronic devices used to implement the above-described processor functions may also be other types, and the embodiments of the present invention do not specifically limit this.

[0023] A communication bus may include a pathway for transmitting information between the aforementioned components. The communication bus can be a PCI bus or an EISA bus, etc. Communication buses can be categorized into address buses, data buses, control buses, etc.

[0024] This invention provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments for online monitoring of multi-parameter water quality.

[0025] In this embodiment of the invention, the computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), spoofing random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0026] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0027] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to the technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions claimed in this invention.

Claims

1. A multi-parameter online water quality monitoring method, characterized in that, Includes the following steps: S100: Obtain the growth status of aquatic plants and the water flow status at each installation location of the environmental monitoring equipment, and at the same time obtain the operating status of the equipment; S200: Predict the growth of aquatic plants at the corresponding installation location by analyzing the water flow and the growth of aquatic plants at the corresponding location. S300 predicts the damage to monitoring equipment at the installation location caused by water flow impact, equipment protection status, and the buffering effect of aquatic plant growth at the corresponding installation location. Damage refers to the physical risk of structural deformation or functional damage to the equipment caused by water flow impact; this includes the following specific aspects: The system obtains the average water velocity and flow density at corresponding locations for each historical period, as well as data on the surface hardness and elasticity of the corresponding equipment, reflecting the equipment's protective capabilities. It also obtains the aquatic plant growth density at corresponding locations for each historical period. Based on the aquatic plant growth density, water-blocking characteristics of the aquatic plants, and the water velocity at corresponding locations, the system estimates the water velocity at which the water flows through the aquatic plants and impacts the corresponding equipment. The system imports the water velocity at which the water flows through the aquatic plants and impacts the corresponding equipment, the area of ​​the corresponding location, and the flow density into the water flow impact force calculation formula to calculate the water flow impact force at the corresponding location. The system divides the water flow impact force at the corresponding time by the safe impact force to obtain the water flow impact anomaly. Obtain the hardness and elasticity of the corresponding equipment surface. Divide the hardness of the corresponding equipment surface by the safe hardness to obtain the hardness safety factor. Divide the elasticity of the corresponding equipment surface by the safe elasticity to obtain the elasticity safety factor. Weight the hardness safety factor and the elasticity safety factor to obtain the impact resistance coefficient of the corresponding equipment. The damage analysis results of the monitoring equipment at the installation location are obtained by dividing the water flow impact anomaly at each moment of the future monitoring cycle by the impact resistance coefficient and then averaging over the time range. S400. The interference of aquatic plant growth on the detection equipment is analyzed by the growth characteristics of aquatic plants at the corresponding location and the detection characteristics of the equipment. The interference refers to the attenuation of sensor signal caused by the physical obstruction of aquatic plants. S500: The installation location is selected based on the damage analysis results of the monitoring equipment at the installation location caused by water flow impact and the interference analysis results of the detection equipment caused by aquatic plant growth.

2. The multi-parameter online water quality monitoring method according to claim 1, characterized in that, The prediction of aquatic plant growth at the corresponding location includes the following specific steps: The system obtains information on aquatic plant density, growth rate, and species at each location, as well as environmental conditions of the corresponding water body and atmospheric environment. Based on the initial aquatic plant density, initial aquatic plant growth rate, water environment and atmospheric environment of the corresponding location, and the aquatic plant density at each future time, a long short-term memory neural network model is constructed with the initial aquatic plant density, initial aquatic plant growth rate, water environment and atmospheric environment of the corresponding location as inputs and the aquatic plant density at each future time as outputs. The initial aquatic plant density, initial aquatic plant growth rate, corresponding water environment conditions, and future atmospheric environment conditions of the current aquatic plant species are imported into the constructed long short-term memory neural network model to output the aquatic plant growth density at each time point.

3. The multi-parameter online water quality monitoring method according to claim 2, characterized in that, The construction of the Long Short-Term Memory neural network model includes the following specific steps: Historical data is collected, covering the initial aquatic plant density, initial growth rate, corresponding aquatic and atmospheric environmental information, and future aquatic plant density at various times. The data is cleaned, missing and outlier values ​​are removed, and then normalized. Then, each layer is constructed: Input layer: The number of neurons in the input layer is determined by the number of input features, i.e., the total number of initial aquatic plant density, initial growth rate, aquatic environment, and atmospheric environment features; LSTM layer: 1-3 LSTM layers are set, and a fully connected layer is added after the LSTM layers. The fully connected layer performs nonlinear transformation on the features output by the LSTM layers. Output layer: The number of neurons in the output layer is equal to the number of predicted aquatic plant density values ​​at each future time step. The output layer maps the features learned by the previous layers to the final prediction result. Finally, the model is trained using the prepared data, and an appropriate loss function is selected to minimize the error between the predicted value and the true value. After training, the model is evaluated using test data.

4. The multi-parameter online water quality monitoring method according to claim 1, characterized in that, The analysis of the interference of aquatic plant growth on the detection equipment includes the following specific contents: The data on aquatic plant density and the detection sensitivity of the corresponding sensor probes at each moment of the monitoring period are obtained. The influence value of aquatic plant density at each moment of the monitoring period is obtained by dividing the aquatic plant density at each moment by the safe aquatic plant density. The influence anomaly is obtained by multiplying the influence value of aquatic plant density at each moment by the detection sensitivity influence coefficient of the sensor probe. The sensor sensitivity anomaly is obtained by dividing the required sensor probe detection sensitivity by the detection sensitivity data of the corresponding sensor probe. The true sensor sensitivity anomaly at the corresponding moment is obtained by multiplying the sum of 1 and the influence anomaly by the sensor sensitivity anomaly. The interference analysis result of aquatic plant growth on the detection equipment is obtained by calculating the average value of the true sensor sensitivity anomaly over the monitoring period.

5. The multi-parameter online water quality monitoring method according to claim 1, characterized in that, The selection of the installation location specifically includes the following: obtaining the damage analysis results of the monitoring equipment at each location and the interference analysis results of aquatic plant growth on the detection equipment; weighting and summing the damage analysis results of the monitoring equipment at each location and the interference analysis results of aquatic plant growth on the detection equipment to obtain the selection anomaly value of the corresponding location; sorting the selection anomaly values ​​in descending order; obtaining the location with the smallest selection anomaly value as the selection location of the corresponding sensor; and sending the selection location of the corresponding sensor to the client.

6. A multi-parameter online water quality monitoring system, used to implement the multi-parameter online water quality monitoring method according to any one of claims 1-5, characterized in that, Specifically, it includes: The data acquisition module acquires information on the growth of aquatic plants and water flow at each installation location of the environmental monitoring equipment, and also acquires information on the operation of the equipment. The aquatic plant growth prediction module predicts the growth of aquatic plants at the corresponding installation location based on the water flow conditions and the growth of aquatic plants at that location. The damage prediction module predicts the damage to the monitoring equipment at the installation location by considering the water flow impact, equipment protection status, and the buffering effect of aquatic plant growth at the corresponding installation location. The interference analysis module analyzes the interference of aquatic plant growth on the detection equipment by using the growth characteristics of aquatic plants at the corresponding location and the detection characteristics of the equipment. The selection module uses the damage analysis results of water flow impact on the monitoring equipment at the installation location and the interference analysis results of aquatic plant growth on the detection equipment to select the installation location.

7. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the multi-parameter online water quality monitoring method as described in any one of claims 1-5 by calling the computer program stored in the memory.

Images