Lake water quality real-time monitoring method and system based on sensor array

Abstract

The invention relates to a lake water quality real-time monitoring method and system based on a sensor array. The method comprises the steps that the sensor array is arranged in a target lake, and data acquisition frequency parameters are set; acquiring working parameters of the sensor array in real time, analyzing the working parameters, determining health states of the sensors, and performing adaptive adjustment on the sensors based on the health states of the sensors; collecting water quality monitoring data in real time based on the adjusted sensor array, performing preprocessing and quality control verification on the water quality monitoring data, and constructing a monitoring data set with qualified quality control; and comparing each water quality index in the monitoring data set with qualified quality control with a preset environmental standard limit value, marking a limit value exceeding event, and performing early warning, thereby completing real-time monitoring of the water quality of the target lake. According to the invention, intelligent real-time monitoring, abnormity identification, data quality control and early warning response of lake water quality are realized, and comprehensive technical support is provided for water environment management.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality monitoring, and in particular to a real-time lake water quality monitoring method and system based on a sensor array. Background Art

[0002] As important freshwater resources and ecosystem carriers, the water quality of lakes is directly related to regional ecological security, drinking water supply, and sustainable economic and social development. With the acceleration of industrialization and the intensification of environmental pollution, the deterioration of lake water quality has become increasingly prominent. The establishment of an efficient and accurate water quality monitoring system has become an urgent need for environmental protection and water resources management. Traditional lake water quality monitoring mainly relies on manual sampling and laboratory analysis, with obvious defects such as low monitoring frequency, insufficient spatial coverage, and poor data timeliness. Although existing automated monitoring equipment can provide continuous data, it generally has problems such as sparse monitoring points, weak data quality control, and low system reliability, making it difficult to meet the actual needs of real-time monitoring of lake water quality over a large area.

[0003] The core challenge facing real-time monitoring of lake water quality stems from the dynamic complexity of monitoring data. Lake water quality parameters are highly variable in their spatiotemporal distribution, and conventional fixed-frequency data acquisition modes cannot effectively capture water quality mutation events, resulting in the omission of key pollution processes. This inadaptability of data acquisition further leads to technical difficulties in data quality control. Sensors are prone to abnormal readings and noise interference in complex water environments, and the lack of effective real-time data screening and quality control mechanisms makes it difficult for the monitoring system to distinguish between real water quality changes and equipment failures or environmental interference. The accumulation of data quality problems directly affects the long-term stable operation of the monitoring system. When equipment anomalies cannot be identified and processed in a timely manner, the continuity and reliability of the monitoring work will be seriously threatened, ultimately leading to the risk of failure of the entire monitoring network. Therefore, the present invention proposes a real-time lake water quality monitoring method and system based on a sensor array. Summary of the Invention

[0004] The purpose of the present invention is to provide a real-time lake water quality monitoring method and system based on a sensor array, which can realize adaptive data acquisition, real-time data quality control, and ensure continuous and stable monitoring operation.

[0005] To achieve the above objectives, the present invention provides a method for real-time monitoring of lake water quality based on a sensor array, comprising:

[0006] Deploy sensor arrays in target lakes and set data collection frequency parameters;

[0007] collecting operating parameters of the sensor array in real time, analyzing the operating parameters to determine the sensor health status, and adaptively adjusting the sensors based on the sensor health status;

[0008] Collecting water quality monitoring data in real time based on the adjusted sensor array, preprocessing and quality control verification of the water quality monitoring data, and constructing a monitoring data set that meets quality control standards;

[0009] Compare each water quality indicator in the monitoring data set that has passed quality control with the preset environmental standard limits, mark the limit-exceeding events and issue early warnings to complete real-time monitoring of the water quality of the target lake.

[0010] Optionally, a sensor array is deployed in the target lake and data acquisition frequency parameters are set, including:

[0011] Deploying the sensor array based on the area, shape, water depth, and water flow conditions of the target lake;

[0012] Establishing a multi-parameter time series model based on the historical water quality monitoring data of the target lake, and analyzing the spatiotemporal variation patterns of water quality indicators based on the parameter time series model;

[0013] Based on the temporal and spatial variation law, an adaptive Kalman filter algorithm is used to calculate the optimal sampling interval and optimal sampling frequency of each monitoring point.

[0014] Optionally, after obtaining the optimal sampling interval and the optimal sampling frequency, the method further includes adjusting the optimal sampling interval and the optimal sampling frequency in real time according to changes in water quality parameters at the monitoring points, and the real-time adjustment includes:

[0015] If the rate of change of water quality parameters at any monitoring point exceeds a preset threshold, the high-frequency acquisition mode is triggered and the sampling frequency of the monitoring point is adjusted;

[0016] The multi-parameter time series model is updated through the adjusted sampling frequency, the spatiotemporal variation patterns of various water quality indicators are reanalyzed, and the adaptive Kalman filter algorithm is reapplied to optimize the sampling interval and sampling frequency of each monitoring point.

[0017] Optionally, collecting operating parameters of the sensor array in real time, analyzing the operating parameters, determining a sensor health state, and adaptively adjusting the sensor based on the sensor health state includes:

[0018] Monitor the operating parameters of each sensor in the sensor array in real time. If any operating indicator deviates from the preset operating range, generate a fault warning signal and evaluate the health status of the sensor;

[0019] The remaining service life of the sensor and the optimal calibration time point are calculated based on the sensor health status assessment results, and the failure probability is predicted by analyzing the performance degradation trend curve. If the failure probability exceeds the preset probability value, the backup sensor is switched.

[0020] Optionally, preprocessing and quality control verification are performed on the water quality monitoring data to construct a monitoring data set that meets quality control requirements, including:

[0021] Cross-validate multiple monitoring data of the same water quality parameter through multi-sensor data fusion technology and mark abnormal data;

[0022] Wavelet denoising algorithm is used to filter out the abnormal data and obtain the water quality monitoring data after noise filtering;

[0023] By establishing a water quality parameter correlation matrix to analyze the intrinsic correlation between different water quality indicators, and combining the multiple linear regression model to perform quality control verification on the noise-filtered data, a monitoring data set with qualified quality control is obtained.

[0024] Optionally, a wavelet denoising algorithm is used to filter out noise from abnormal data to obtain water quality monitoring data after noise filtering, including:

[0025] Performing multi-scale decomposition on the abnormal data by using a wavelet denoising algorithm to separate low-frequency trend components and high-frequency noise components;

[0026] Calculating the energy proportion of the high-frequency noise component, and if the energy proportion of the high-frequency noise component exceeds a preset proportion, processing the high-frequency noise component using a soft threshold denoising algorithm to obtain a denoised high-frequency noise component;

[0027] The denoised high-frequency noise components and low-frequency trend components are reconstructed through inverse wavelet transform to obtain the denoised water quality monitoring data.

[0028] Optionally, performing quality control verification on the noise-filtered data includes:

[0029] A multivariate linear regression model is used to fit the denoised water quality monitoring data to obtain the sum of squares of the regression residuals. If the sum of squares of the regression residuals exceeds the preset control limit, data re-collection is triggered, new water quality monitoring parameters are obtained, and preprocessing and quality control verification are performed until the sum of squares of the regression residuals meets the preset control limit, and the monitoring data set that passes the quality control is obtained.

[0030] On the other hand, the present invention also provides a real-time lake water quality monitoring system based on a sensor array, comprising:

[0031] The sensor deployment module is used to deploy sensor arrays in the target lake and set data collection frequency parameters;

[0032] a sensor adjustment module, configured to collect operating parameters of the sensor array in real time, analyze the operating parameters, determine the sensor health status, and adaptively adjust the sensor based on the sensor health status;

[0033] A water quality acquisition module is used to collect water quality monitoring data in real time based on the adjusted sensor array, pre-process the water quality monitoring data and perform quality control verification on the water quality monitoring data to construct a monitoring data set that meets quality control standards;

[0034] The water quality monitoring module is used to compare the water quality indicators in the monitoring data set that has passed quality control with the preset environmental standard limits, mark limit-exceeding events and issue early warnings, and complete real-time monitoring of the water quality of the target lake.

[0035] The beneficial effects of the present invention are:

[0036] This method analyzes the spatiotemporal variations of key water quality indicators and uses an adaptive Kalman filter algorithm to dynamically adjust the sampling frequency. It also employs multi-sensor data fusion technology for cross-validation, combined with a sliding window anomaly detection algorithm to identify anomalous data. Wavelet denoising is applied to the anomalous data and quality control verification is performed. Furthermore, the method monitors sensor operating status in real time, predicts equipment lifespan and calibration time, and ensures stable monitoring operations. This method enables intelligent, real-time monitoring of lake water quality, anomaly identification, data quality control, and early warning response, providing comprehensive technical support for water environment management. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 This is a flow chart of a method for real-time monitoring of lake water quality based on a sensor array according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0040] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0041] On the one hand, this embodiment provides a real-time monitoring method for lake water quality based on a sensor array, such as Figure 1 As shown, including:

[0042] Deploy sensor arrays in target lakes and set data collection frequency parameters;

[0043] collecting operating parameters of the sensor array in real time, analyzing the operating parameters to determine the sensor health status, and adaptively adjusting the sensors based on the sensor health status;

[0044] Collecting water quality monitoring data in real time based on the adjusted sensor array, preprocessing and quality control verification of the water quality monitoring data, and constructing a monitoring data set that meets quality control standards;

[0045] Compare each water quality indicator in the monitoring data set that has passed quality control with the preset environmental standard limits, mark the limit-exceeding events and issue early warnings to complete real-time monitoring of the water quality of the target lake.

[0046] Specifically, this embodiment analyzes the spatiotemporal variations of key water quality indicators and uses an adaptive Kalman filter algorithm to dynamically adjust the sampling frequency. It also employs multi-sensor data fusion technology for cross-validation, combined with a sliding window anomaly detection algorithm to identify abnormal data. Wavelet denoising is applied to abnormal data and quality control verification is performed. Furthermore, this embodiment monitors sensor operating status in real time, predicts equipment lifespan and calibration time, and ensures stable monitoring operations. This embodiment implements intelligent real-time monitoring of lake water quality, anomaly identification, data quality control, and early warning response, providing comprehensive technical support for water environment management.

[0047] Furthermore, a sensor array is deployed in the target lake and data acquisition frequency parameters are set, including:

[0048] Deploying the sensor array based on the area, shape, water depth, and water flow conditions of the target lake;

[0049] Establishing a multi-parameter time series model based on the historical water quality monitoring data of the target lake, and analyzing the spatiotemporal variation patterns of water quality indicators based on the parameter time series model;

[0050] Based on the temporal and spatial variation law, an adaptive Kalman filter algorithm is used to calculate the optimal sampling interval and optimal sampling frequency of each monitoring point.

[0051] After obtaining the optimal sampling interval and the optimal sampling frequency, the optimal sampling interval and the optimal sampling frequency are adjusted in real time according to the changes in the water quality parameters of the monitoring points. The real-time adjustment includes:

[0052] If the rate of change of water quality parameters at any monitoring point exceeds a preset threshold, the high-frequency acquisition mode is triggered and the sampling frequency of the monitoring point is adjusted;

[0053] The multi-parameter time series model is updated through the adjusted sampling frequency, the spatiotemporal variation patterns of various water quality indicators are reanalyzed, and the adaptive Kalman filter algorithm is reapplied to optimize the sampling interval and sampling frequency of each monitoring point.

[0054] Specifically, this embodiment reasonably arranges the sensor array according to the area, shape, water depth and water flow conditions of the lake. The sensor array includes various types of water quality sensors, such as pH sensors, dissolved oxygen sensors, conductivity sensors, turbidity sensors, ammonia nitrogen sensors, total phosphorus sensors, total nitrogen sensors, etc.

[0055] This embodiment assumes that 5 monitoring points are set up in the target lake, and dissolved oxygen (DO, in mg / L), total phosphorus (TP, in mg / L), total nitrogen (TN, in mg / L), and turbidity (T, in NTU) data are collected once a month at each point. The data span is from January 2023 to May 2025, a total of 29 months. First, the missing values ​​are filled by linear interpolation. For example, if the DO of a certain point in March 2023 is missing, it is interpolated to 8.6 based on the data of February (8.5) and April (8.7). Next, a multi-parameter time series model is constructed, and the ARIMA model is selected. Each parameter is fitted separately. For example, the DO series is a stationary series after the ADF test, and the ARIMA (1,0,1) model is determined. After the parameters are estimated, the trend for the next 3 months is predicted. In the spatiotemporal variation analysis, the monthly rate of change of each parameter was calculated. For example, if the TP at a particular point increased from 0.03 to 0.035, the rate of change would be (0.035-0.03) / 0.03 = 16.67%, exceeding the threshold of 0.1, indicating significant water quality fluctuations. Spatial analysis used kriging interpolation to generate spatial distribution maps of each parameter, revealing that TP concentrations were higher in the southeastern part of the lake (0.04 mg / L). An adaptive Kalman filter algorithm was used to optimize the sampling interval, initializing the state noise covariance Q = 0.01 and the observation noise covariance R = 0.1. The state vector (parameter value and rate of change) was iteratively updated. If the DO change rate at a particular point reached 0.12 (>0.1), the filter estimated the optimal sampling interval to be adjusted from 30 days to 7 days, triggering high-frequency acquisition mode. For other points, the rate of change was below the threshold, and sampling was maintained at 30 days.

[0056] Furthermore, the operating parameters of the sensor array are collected in real time, the operating parameters are analyzed to determine the sensor health status, and the sensors are adaptively adjusted based on the sensor health status, including:

[0057] Monitor the operating parameters of each sensor in the sensor array in real time. If any operating indicator deviates from the preset operating range, generate a fault warning signal and evaluate the health status of the sensor;

[0058] The remaining service life of the sensor and the optimal calibration time point are calculated based on the sensor health status assessment results, and the failure probability is predicted by analyzing the performance degradation trend curve. If the failure probability exceeds the preset probability value, the backup sensor is switched.

[0059] Specifically, this embodiment first acquires sensor output data at a sampling frequency of 100Hz. Next, the response time is calculated, defined as the time it takes for the sensor to output a stable signal from receiving an excitation. The algorithm uses a sliding window method with a window size of 50ms. The time it takes for the signal to go from 0 to 90% of its full scale is measured. For example, a calculated response time of 12ms, compared to a normal range of 10-15ms, indicates a normal response. Signal stability analysis calculates the signal's standard deviation. Assuming the standard deviation of 1000 collected data points is 0.02V, compared to a normal range of 0-0.05V, this indicates a stable signal. Temperature drift is assessed using data from the built-in temperature sensor. Assuming the current temperature is 25°C, historical data is fitted to the temperature-output curve. Every 1°C of drift causes a 0.01V deviation. The current deviation is 0.008V, below the threshold of 0.02V, indicating normal temperature drift. If any of these indicators are abnormal, such as a response time exceeding 15ms, a fault warning signal is triggered. The health status assessment uses a weighted scoring method. The weights of response time, stability, and temperature drift are 0.4, 0.3, and 0.3, respectively. The comprehensive score is calculated. For example, (12 / 15)*0.4+(0.02 / 0.05)*0.3+(0.008 / 0.02)*0.3=0.84. The threshold value is set above 0.8 for a healthy status, and the result is "device normal."

[0060] This embodiment uses multi-dimensional sensor data (such as temperature 50°C, vibration frequency 10Hz, current fluctuation 0.5A) to build a performance degradation model, and uses the long short-term memory neural network (LSTM) algorithm to analyze time series data to predict the remaining service life of the equipment. The LSTM model inputs nearly 30 days of sensor data, including 1000 sampling points, and outputs a predicted remaining service life of 1500 hours with an error range of ±50 hours. The model is optimized by the mean square error (MSE), and the MSE value is controlled below 0.02. Then, based on the degradation trend curve (fitted as a quadratic function y=0.001x 2+0.05x+1, where x is the number of operating hours), calculates the optimal calibration time point, sets a performance threshold of 80% initial efficiency, and predicts that the device will drop to this threshold after 1200 hours. The calibration task is automatically scheduled to start at the 1150th hour, sending a command to adjust the sensor sensitivity to the standard value of ±0.1%. Simultaneously, the failure probability is monitored in real time, using a Bayesian network combined with historical failure data (100 failure samples, with characteristics including temperature, vibration, and current). When the predicted failure probability exceeds 80% (for example, reaching 85%), the backup sensor switching procedure is triggered, a switching command is issued, and the backup sensor takes over within 5 seconds. After the switchover, performance is reassessed to ensure output stability above 95%.

[0061] Furthermore, the water quality monitoring data is preprocessed and quality control verified to construct a monitoring data set that meets quality control requirements, including:

[0062] Cross-validate multiple monitoring data of the same water quality parameter through multi-sensor data fusion technology and mark abnormal data;

[0063] Wavelet denoising algorithm is used to filter out the abnormal data and obtain the water quality monitoring data after noise filtering;

[0064] By establishing a water quality parameter correlation matrix to analyze the intrinsic correlation between different water quality indicators, and combining the multiple linear regression model to perform quality control verification on the noise-filtered data, a monitoring data set with qualified quality control is obtained.

[0065] Among them, the wavelet denoising algorithm is used to filter out the abnormal data to obtain the water quality monitoring data after noise filtering, including:

[0066] Performing multi-scale decomposition on the abnormal data by using a wavelet denoising algorithm to separate low-frequency trend components and high-frequency noise components;

[0067] Calculating the energy proportion of the high-frequency noise component, and if the energy proportion of the high-frequency noise component exceeds a preset proportion, processing the high-frequency noise component using a soft threshold denoising algorithm to obtain a denoised high-frequency noise component;

[0068] The denoised high-frequency noise components and low-frequency trend components are reconstructed through inverse wavelet transform to obtain the denoised water quality monitoring data.

[0069] The quality control verification of the noise-filtered data includes:

[0070] A multivariate linear regression model is used to fit the denoised water quality monitoring data to obtain the sum of squares of the regression residuals. If the sum of squares of the regression residuals exceeds the preset control limit, data re-collection is triggered, new water quality monitoring parameters are obtained, and preprocessing and quality control verification are performed until the sum of squares of the regression residuals meets the preset control limit, and the monitoring data set that passes the quality control is obtained.

[0071] Specifically, this embodiment uses multi-sensor data fusion technology to cross-validate multiple measurement signals of the same water quality parameter. For example, three turbidity sensors are used to measure the same water sample at the same time, and the readings are 48NTU, 52NTU, and 49NTU respectively. The fusion mean is calculated as 49.7NTU by a weighted average algorithm (the weights are set according to the historical calibration accuracy of the sensor, such as 0.4, 0.3, and 0.3). The fusion process uses Kalman filtering to optimize signal noise and reduce random errors by about 10%. If the deviation of a single sensor reading from the fusion mean exceeds 15%, it is marked as a suspected anomaly. For example, if a sensor reading is 60NTU, the deviation is (60-49.7) / 49.7≈20.7%. If it exceeds 15%, it is marked as an anomaly. An anomaly detection algorithm is used in combination with the mean and standard deviation of historical data (such as a historical mean of 50NTU and a standard deviation of 2NTU) to further confirm the anomaly and generate a monitoring data set with an anomaly mark.

[0072] In this embodiment, the wavelet basis function is selected as Daubechies (db4), and the number of decomposition layers is set to 4. The abnormal signal is decomposed into a low-frequency trend component (A4) and a high-frequency noise component (D1-D4) through discrete wavelet transform (DWT). The energy of each component is calculated. Assuming that the total energy of the high-frequency components D1-D4 is 1200, it accounts for 30% of the total signal energy 4000 (1200 / 4000=0.3). Since the high-frequency component energy accounts for 30%, the soft threshold denoising condition is met. Soft threshold processing is applied to the high-frequency components D1-D4 one by one, leaving the low-frequency component A4 unchanged. After reconstructing the signal, the denoised data sequence is obtained.

[0073] This example uses the Pearson correlation coefficient to calculate the correlation matrix between water quality parameters such as pH, dissolved oxygen (DO), chemical oxygen demand (COD), and total phosphorus (TP). Assume that the dataset contains 1000 records, each of which includes pH (range 6.5-8.5), DO (2-10 mg / L), COD (10-50 mg / L), and TP (0.1-1.0 mg / L). Using the Python pandas library, the corr() function is called to calculate the correlation coefficient, resulting in a 4×4 matrix.

[0074] For example, the correlation coefficient between pH and DO is 0.75, indicating a strong positive correlation; the correlation coefficient between COD and TP is 0.62, indicating a moderate positive correlation. The matrix is ​​visualized as a heatmap using the heatmap function of the seaborn library, where the color depth reflects the strength of the correlation. Subsequently, a multiple linear regression model was constructed with pH as the dependent variable and DO, COD, and TP as independent variables. The model was fitted using the LinearRegression module of scikit-learn. After the training set (80%) and the test set (20%) were divided, the model R 2 The value is 0.88, and the mean square error is 0.15. The regression residual sum of squares (RSS) is calculated. If the RSS exceeds the preset control limit (such as 0.20), data recollection is triggered, and new data are automatically collected (sampling frequency 1 time / hour). The above steps are repeated until the RSS is lower than 0.20, obtaining a monitoring data set that meets quality control requirements.

[0075] Furthermore, this embodiment compares the water quality indicators in the quality control qualified data set with a preset environmental standard database. If the water quality indicators exceed the environmental standard limits, they are marked as limit-exceeding events. According to the severity of the limit-exceeding events, a decision tree algorithm is used to classify the warning levels to obtain multi-level warning signals. Through the preset response process configuration, corresponding response instructions are generated for the multi-level warning signals, and warning and response logs are recorded to update the monitoring status in real time.

[0076] On the other hand, this embodiment also provides a real-time lake water quality monitoring system based on a sensor array, comprising:

[0077] The sensor deployment module is used to deploy sensor arrays in the target lake and set data collection frequency parameters;

[0078] a sensor adjustment module, configured to collect operating parameters of the sensor array in real time, analyze the operating parameters, determine the sensor health status, and adaptively adjust the sensor based on the sensor health status;

[0079] A water quality acquisition module is used to collect water quality monitoring data in real time based on the adjusted sensor array, pre-process the water quality monitoring data and perform quality control verification on the water quality monitoring data to construct a monitoring data set that meets quality control standards;

[0080] The water quality monitoring module is used to compare the water quality indicators in the monitoring data set that has passed quality control with the preset environmental standard limits, mark limit-exceeding events and issue early warnings, and complete real-time monitoring of the water quality of the target lake.

[0081] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. A real-time lake water quality monitoring method based on a sensor array, characterized in that: include: Deploy sensor arrays in target lakes and set data collection frequency parameters; collecting operating parameters of the sensor array in real time, analyzing the operating parameters to determine the sensor health status, and adaptively adjusting the sensors based on the sensor health status; Collecting water quality monitoring data in real time based on the adjusted sensor array, preprocessing and quality control verification of the water quality monitoring data, and constructing a monitoring data set that meets quality control standards; Compare each water quality indicator in the monitoring data set that has passed quality control with the preset environmental standard limits, mark the limit-exceeding events and issue early warnings to complete real-time monitoring of the water quality of the target lake.

2. The method for real-time monitoring of lake water quality based on a sensor array according to claim 1, characterized in that: Deploy a sensor array in the target lake and set data acquisition frequency parameters, including: Deploying the sensor array based on the area, shape, water depth, and water flow conditions of the target lake; Establishing a multi-parameter time series model based on the historical water quality monitoring data of the target lake, and analyzing the spatiotemporal variation patterns of water quality indicators based on the parameter time series model; Based on the temporal and spatial variation law, an adaptive Kalman filter algorithm is used to calculate the optimal sampling interval and optimal sampling frequency of each monitoring point.

3. The method for real-time monitoring of lake water quality based on a sensor array according to claim 2, characterized in that: After obtaining the optimal sampling interval and the optimal sampling frequency, the optimal sampling interval and the optimal sampling frequency are adjusted in real time according to the changes in the water quality parameters of the monitoring points. The real-time adjustment includes: If the rate of change of water quality parameters at any monitoring point exceeds a preset threshold, the high-frequency acquisition mode is triggered and the sampling frequency of the monitoring point is adjusted; The multi-parameter time series model is updated through the adjusted sampling frequency, the spatiotemporal variation patterns of various water quality indicators are reanalyzed, and the adaptive Kalman filter algorithm is reapplied to optimize the sampling interval and sampling frequency of each monitoring point.

4. The method for real-time monitoring of lake water quality based on a sensor array according to claim 1, characterized in that: Collecting operating parameters of the sensor array in real time, analyzing the operating parameters, determining a sensor health state, and adaptively adjusting the sensor based on the sensor health state, including: Monitor the operating parameters of each sensor in the sensor array in real time. If any operating indicator deviates from the preset operating range, generate a fault warning signal and evaluate the health status of the sensor; The remaining service life of the sensor and the optimal calibration time point are calculated based on the sensor health status assessment results, and the failure probability is predicted by analyzing the performance degradation trend curve. If the failure probability exceeds the preset probability value, the backup sensor is switched.

5. The method for real-time monitoring of lake water quality based on a sensor array according to claim 1, characterized in that: Preprocessing and quality control verification of the water quality monitoring data to construct a quality control qualified monitoring data set, including: Cross-validate multiple monitoring data of the same water quality parameter through multi-sensor data fusion technology and mark abnormal data; Wavelet denoising algorithm is used to filter out the abnormal data and obtain the water quality monitoring data after noise filtering; By establishing a water quality parameter correlation matrix to analyze the intrinsic correlation between different water quality indicators, and combining the multiple linear regression model to perform quality control verification on the noise-filtered data, a monitoring data set with qualified quality control is obtained.

6. The method for real-time monitoring of lake water quality based on a sensor array according to claim 5, characterized in that: Wavelet denoising algorithm is used to filter out abnormal data and obtain water quality monitoring data after noise filtering, including: Performing multi-scale decomposition on the abnormal data by using a wavelet denoising algorithm to separate low-frequency trend components and high-frequency noise components; Calculating the energy proportion of the high-frequency noise component, and if the energy proportion of the high-frequency noise component exceeds a preset proportion, processing the high-frequency noise component using a soft threshold denoising algorithm to obtain a denoised high-frequency noise component; The denoised high-frequency noise components and low-frequency trend components are reconstructed through inverse wavelet transform to obtain the denoised water quality monitoring data.

7. The method for real-time monitoring of lake water quality based on a sensor array according to claim 5, characterized in that: Perform quality control verification on the noise-filtered data, including: A multivariate linear regression model is used to fit the denoised water quality monitoring data to obtain the sum of squares of the regression residuals. If the sum of squares of the regression residuals exceeds the preset control limit, data re-collection is triggered, new water quality monitoring parameters are obtained, and preprocessing and quality control verification are performed until the sum of squares of the regression residuals meets the preset control limit, and the monitoring data set that passes the quality control is obtained.

8. A real-time lake water quality monitoring system based on a sensor array, characterized in that: include: The sensor deployment module is used to deploy sensor arrays in the target lake and set data collection frequency parameters; a sensor adjustment module, configured to collect operating parameters of the sensor array in real time, analyze the operating parameters, determine the sensor health status, and adaptively adjust the sensor based on the sensor health status; A water quality acquisition module is used to collect water quality monitoring data in real time based on the adjusted sensor array, pre-process the water quality monitoring data and perform quality control verification on the water quality monitoring data to construct a monitoring data set that meets quality control standards; The water quality monitoring module is used to compare the water quality indicators in the monitoring data set that has passed quality control with the preset environmental standard limits, mark limit-exceeding events and issue early warnings, and complete real-time monitoring of the water quality of the target lake.

Images