Automatic monitoring method and system for ecological hydraulic engineering

Abstract

The invention relates to the technical field of hydraulic engineering monitoring control, and discloses an automatic monitoring method and system for ecological hydraulic engineering. The method comprises the steps that water body parameters are collected through a sensor and preprocessed to obtain standard monitoring data; performing noise reduction alignment and correlation analysis on the monitoring data to obtain an optimized data set and a feature library; evaluating the water environment state according to the data set and the feature library to obtain an evaluation index and an early warning signal; analyzing the treatment scheme according to the index and the signal to obtain a regulation and control instruction; adjusting equipment operation parameters according to the instruction to obtain operation state data; and performing cycle analysis and strategy optimization based on the state data to obtain regulation and control parameters. Multi-dimensional correlation analysis of water quality parameters is realized, an accurate water environment regulation and control scheme is formulated on the basis, and the pertinence and efficiency of water quality improvement are improved.

Description

Technical Field

[0001] The present application relates to the technical field of water conservancy project monitoring and control, and in particular to an automated monitoring method and system for ecological water conservancy projects. Background Art

[0002] In the existing ecological water conservancy project monitoring technology, the water environment management is mainly carried out by combining single-point water quality monitoring and manual inspection. The traditional monitoring method is to set up water quality monitoring stations in important sections of the river to collect basic water quality parameters such as dissolved oxygen, turbidity, and pH value, and rely on manual regular sampling for water quality analysis. Water environment regulation mainly relies on experience judgment, and water quality is improved by adjusting the gate opening, turning on aeration equipment, etc. Some projects have begun to use automatic monitoring equipment to realize the real-time collection of water quality data and establish a simple water quality early warning mechanism.

[0003] However, the existing technologies have the following shortcomings: the collection and processing of monitoring data lacks systematicity, resulting in uneven data quality; the correlation analysis between water quality parameters is not in-depth enough, making it difficult to accurately determine the root causes of water quality problems; the formulation of control plans relies too much on experience and lacks scientific quantitative analysis and optimization processes; the improvement process of different water quality indicators lacks synergistic considerations, often neglecting one while focusing on another; the water quality improvement effect evaluation method is single and cannot accurately reflect the overall response characteristics of the ecosystem; the optimization of the operating parameters of the control equipment is not precise enough, resulting in energy waste and low processing efficiency. Summary of the invention

[0004] The present application provides an automated monitoring method and system for ecological water conservancy projects, which is used to realize multi-dimensional correlation analysis of water quality parameters, and on this basis, formulate accurate water environment control plans to improve the pertinence and efficiency of water quality improvement.

[0005] In the first aspect, the present application provides an automated monitoring method for ecological water conservancy projects, which includes: collecting dissolved oxygen, turbidity, water level flow and pump station gate operating status of water bodies through monitoring sensors, and obtaining standardized monitoring data of water conservancy projects through data preprocessing; performing water quality parameter noise reduction and hydrological data spatiotemporal alignment based on the standardized monitoring data of water conservancy projects, analyzing the correlation of ecological water system parameters, and obtaining a water ecological optimization data set and a water quality abnormality feature library; based on the water ecological optimization data set and the water quality abnormality feature library, establishing an ecological water system health assessment system to perform water environment dynamic analysis, and obtain a water conservancy project ecological assessment index and water quality early warning signal; based on the water conservancy project ecological assessment index and water quality early warning signal, constructing a water environment regulation model to analyze water system management plans and obtain river and lake water system zoning regulation instructions; based on the river and lake water system zoning regulation instructions, adjusting the operating parameters and analyzing the working conditions of hydraulic regulating devices and water purification equipment to obtain project operation status data; based on the project operation status data, obtaining water conservancy project regulation parameters through water ecological restoration cycle analysis and water quality improvement strategy optimization.

[0006] In a second aspect, the present application provides an automated monitoring system for an ecological water conservancy project, the automated monitoring system for an ecological water conservancy project comprising: The acquisition module is used to collect dissolved oxygen, turbidity, water level flow and pump station gate operation status of the water body through monitoring sensors, and obtain standardized monitoring data of water conservancy projects through data preprocessing; An alignment module is used to perform water quality parameter noise reduction and hydrological data spatiotemporal alignment based on the standardized monitoring data of the water conservancy project, analyze the correlation of ecological water system parameters, and obtain a water ecological optimization data set and a water quality anomaly feature library; An analysis module is used to establish an ecological water system health assessment system to conduct dynamic analysis of the water environment based on the water ecological optimization data set and the water quality abnormality feature library, and obtain an ecological assessment index for water conservancy projects and a water quality early warning signal; An early warning module is used to construct a water environment control model to analyze water system management plans and obtain river and lake water system zoning control instructions based on the water conservancy project ecological assessment index and water quality early warning signals; An adjustment module is used to adjust the operating parameters and analyze the working conditions of the hydraulic regulating device and water purification equipment according to the river and lake water system zoning control instructions to obtain the project operation status data; The optimization module is used to obtain the water conservancy project control parameters through water ecological restoration cycle analysis and water quality improvement strategy optimization based on the project operation status data.

[0007] In the technical solution provided in this application, the problem of unstable data quality in traditional monitoring methods is effectively solved by adopting layered data collection and multi-dimensional data processing technology, and comprehensive monitoring of dissolved oxygen, turbidity, water level flow and pump station gate operation status of water bodies is realized. The standardized monitoring data of water conservancy projects obtained after data preprocessing provides a reliable data basis for subsequent analysis, and the influence of data noise and spatiotemporal differences is effectively eliminated by denoising water quality parameters and aligning hydrological data in time and space. Combined with the correlation analysis of ecological water system parameters, the intrinsic connection between water quality indicators is deeply excavated. The formed water ecological optimization data set and water quality abnormality feature library provide important basis for the diagnosis of water quality problems. At the same time, based on the water ecological optimization data set and water quality abnormality feature library The ecological water system health assessment system established by the database, the water project ecological assessment index and water quality early warning signal obtained through dynamic analysis of the water environment, achieved early identification and early warning of water quality problems, and then built a water environment regulation model based on the assessment index and early warning signal. The river and lake water system zoning regulation instructions generated through the analysis of the water system management plan achieved the precise implementation of regulation measures. The operating parameter adjustment and operating condition analysis of the hydraulic regulating device and water purification equipment ensured the effective implementation of the regulation measures. The water project regulation parameters obtained through the analysis of the water ecological restoration cycle and the optimization of the water quality improvement strategy established a complete closed-loop management system of water environment monitoring-analysis-regulation-optimization, which significantly improved the intelligent management level and water quality improvement effect of ecological water conservancy projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0009] Figure 1 A schematic diagram of an embodiment of an automated monitoring method for ecological water conservancy projects in an embodiment of the present application; Figure 2 This is a schematic diagram of the turbidity value measurement and principle in the embodiments of this application; Figure 3 This is an introduction diagram of the grouping index in the embodiment of the present application; Figure 4 This is a schematic diagram of an embodiment of an automated monitoring system for ecological water conservancy projects in an embodiment of the present application. DETAILED DESCRIPTION

[0010] The present application embodiment provides a kind of automatic monitoring method and system for ecological water conservancy project. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable in appropriate circumstances, so that the embodiments described here can be implemented in a sequence other than the content illustrated or described here. In addition, the terms "including" or "having" and any variation thereof are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment including a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0011] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In the embodiments of the present application, an embodiment of the automated monitoring method for ecological water conservancy projects includes: Step S101, collecting dissolved oxygen, turbidity, water level flow and pump station gate operation status of water bodies through monitoring sensors, and obtaining standardized monitoring data of water conservancy projects through data preprocessing; Step S102: perform water quality parameter noise reduction and hydrological data spatiotemporal alignment based on standardized monitoring data of water conservancy projects, analyze the correlation of ecological water system parameters, and obtain a water ecological optimization data set and a water quality abnormality feature library; Step S103: Based on the water ecological optimization data set and the water quality abnormality feature library, an ecological water system health assessment system is established to perform a dynamic analysis of the water environment, and obtain a water conservancy project ecological assessment index and a water quality early warning signal; Step S104: construct a water environment control model to analyze water system management plans based on the water conservancy project ecological assessment index and water quality early warning signals, and obtain river and lake water system zoning control instructions; Step S105: According to the river and lake water system zoning control instructions, the hydraulic regulating device and water purification equipment are adjusted in operating parameters and analyzed in working conditions to obtain engineering operation status data; Step S106: According to the project operation status data, water ecological restoration cycle analysis and water quality improvement strategy optimization are performed to obtain water conservancy project control parameters.

[0012] It is understandable that the execution subject of the present application may be an automated monitoring system for ecological water conservancy projects, or a terminal or a server, which is not specifically limited here. The present application embodiment is described by taking a server as the execution subject as an example.

[0013] Specifically, data collection is performed by deploying multiple types of monitoring sensors. Dissolved oxygen monitoring in water uses an optical dissolved oxygen sensor to measure dissolved oxygen content through the principle of fluorescence quenching; turbidity monitoring uses a scattered light turbidimeter to measure the turbidity value of the water body according to the intensity of scattered light at 90 degrees; water level and flow monitoring uses an ultrasonic water level meter and an electromagnetic flow meter to obtain cross-section water level height and flow data respectively; pump station gate operation status monitoring uses opening sensors and speed sensors to collect operating parameters. The collected raw data is subjected to standardized preprocessing, including unit unification processing, range normalization processing, and outlier elimination, and converted into a standard data format to form standardized monitoring data for water conservancy projects.

[0014] In the further processing of standardized monitoring data, the wavelet transform method is used to reduce the noise of water quality parameters, and the water quality data such as dissolved oxygen and turbidity are decomposed at multiple scales to remove high-frequency noise components. The spatial and temporal alignment of hydrological data is based on the spatial distribution characteristics of the monitoring points, and a spatial interpolation function is established to achieve the alignment and matching of data at different sampling points and different sampling times. The parameter correlation analysis determines the degree of mutual influence between the monitoring indicators by calculating the Pearson correlation coefficient, and constructs a parameter correlation matrix. Through cluster analysis, data with similar change characteristics are combined to form a water ecological optimization data set; at the same time, abnormal data features are extracted to establish a water quality abnormality feature library. In the ecological water system health assessment stage, an evaluation index system is set based on the water ecological optimization data set, including three levels of water quality indicators, hydrological indicators and ecological indicators, and the hierarchical analysis method is used to determine the weight of each indicator. In the dynamic analysis process, each indicator is calculated in real time to obtain the ecological evaluation index of the water conservancy project; combined with the characteristic patterns in the water quality abnormality feature library, potential water quality abnormalities are identified and water quality warning signals are generated.

[0015] The process of constructing the water environment control model focuses on the integrity and systematicness of the water system, divides the river and lake water system into multiple control units, and analyzes the hydraulic connection and water quality impact between each unit. According to the input of the ecological assessment index and the early warning signal, the control amount required by each control unit is calculated, and the upstream and downstream relationships and water quality target requirements are considered to generate the zoning control instructions for the river and lake water system. In the equipment control execution stage, the zoning control instructions are converted into specific equipment operating parameters. The hydraulic regulating devices mainly include hydraulic structures such as pump stations and gates, and water volume control is achieved by adjusting parameters such as opening and flow; water purification equipment includes aeration equipment, ecological floating beds, etc., and the operating condition parameters are adjusted to improve water quality. At the same time, the equipment operation data is collected, the working condition analysis is carried out, and the project operation status data is obtained.

[0016] The final stage focuses on the effect of water ecological restoration and analyzes the time response characteristics of water quality improvement. By statistically analyzing the water quality recovery cycle under different control measures, the corresponding relationship between control measures and water quality improvement effects is established. Based on actual operation data, the control strategy is optimized and the optimal water conservancy project control parameters are determined.

[0017] For example, when eutrophication occurs in a certain river section, monitoring data shows that the dissolved oxygen content remains below 4 mg / L and the turbidity increases. After data processing and analysis, it is found that this phenomenon is closely related to changes in the water quality of the upstream water and the gate scheduling method. The ecological assessment system determines that a water quality warning has occurred and immediately initiates a control response. According to the zoning control instructions, the downstream flow of the upstream gate is increased, and the aeration equipment is turned on for oxygen supplementation. The dissolved oxygen recovery process is continuously monitored, and the aeration intensity and duration are dynamically adjusted according to the recovery rate in different time periods until the water quality indicators return to normal.

[0018] In the embodiments of the present application, by adopting layered data collection and multi-dimensional data processing technology, the problem of unstable data quality in traditional monitoring methods is effectively solved, and comprehensive monitoring of dissolved oxygen, turbidity, water level flow and pump station gate operation status of water bodies is achieved. The standardized monitoring data of water conservancy projects obtained after data preprocessing provides a reliable data basis for subsequent analysis, and by denoising water quality parameters and aligning hydrological data in time and space, the influence of data noise and time and space differences is effectively eliminated. Combined with the correlation analysis of ecological water system parameters, the intrinsic connection between water quality indicators is deeply excavated, and the formed water ecological optimization data set and water quality anomaly feature library provide important basis for the diagnosis of water quality problems. At the same time, based on the water ecological optimization data set and water quality anomaly feature library, a reliable data basis for subsequent analysis is established. An ecological water system health assessment system has been established. The ecological assessment index and water quality warning signals of water conservancy projects obtained through dynamic analysis of the water environment have achieved early identification and warning of water quality problems. Furthermore, a water environment regulation model has been constructed based on the assessment index and warning signals. The river and lake water system zoning regulation instructions generated through analysis of the water system management plan have achieved precise implementation of regulation measures. The operating parameter adjustments and operating condition analysis of hydraulic regulating devices and water purification equipment have ensured the effective implementation of regulation measures. Through the analysis of the water ecological restoration cycle and the optimization of water quality improvement strategies to obtain the regulation parameters of water conservancy projects, a complete closed-loop management system of water environment monitoring-analysis-regulation-optimization has been established, which has significantly improved the intelligent management level and water quality improvement effect of ecological water conservancy projects.

[0019] In a specific embodiment, the process of executing step S101 may specifically include the following steps: (1) Collect dissolved oxygen data in water through water sensors, group the dissolved oxygen data according to the sampling time, perform signal denoising on each group of data, calculate the average value according to the time window, and then verify the value range, remove data points that exceed the range, and obtain standardized dissolved oxygen data; (2) The turbidity of the water body is collected through an optical sensor, the original turbidity data is linearly calibrated, the data is compensated according to the ambient light intensity, interference fluctuations are removed through signal filtering, and the processed data is rearranged according to the time series to obtain standardized turbidity data; (3) Pair the water level data collected by the water level station with the flow data collected by the flow station according to the sampling time, fill in the missing data points through linear interpolation, perform data verification according to the water level-flow relationship curve, eliminate outliers that do not conform to the relationship curve, and obtain standardized water level and flow data; (4) Collect opening data and speed data from the control system of the pump station gate, convert the opening data into a percentage value, normalize the speed data, verify the validity according to the upper and lower limits of the equipment operating parameters, screen out data that meets the operating specifications, and obtain standardized operating status data; (5) Import the standardized dissolved oxygen data, standardized turbidity data, standardized water level flow data, and standardized operation status data into the time series database, align them according to a unified timestamp, downsample or interpolate the data with different sampling frequencies, normalize the data after unifying the time resolution, and obtain time series correlation data; (6) Perform data integrity check on time series correlation data, calculate the correlation coefficient of each parameter, identify outliers based on the distribution characteristics of historical data, integrate all processed data into a unified data structure, and obtain standardized monitoring data for water conservancy projects.

[0020] Specifically, for the collection of dissolved oxygen data in water bodies, an optical dissolved oxygen sensor is used to measure the dissolved oxygen content based on the principle of fluorescence quenching. The sensor collects data every 10 minutes, and the data within 24 hours is grouped per hour. Each group of data is first denoised by wavelet transform, the original signal is decomposed into wavelet coefficients of different scales, a threshold is set to remove high-frequency noise, and then the signal is reconstructed to obtain smoothed data. The arithmetic mean of the reconstructed data is calculated within each hourly time window as the representative value of the period. The data is then range-checked. The normal range of dissolved oxygen is 0-20 mg / L. Data points outside this range are marked as abnormal and removed to obtain a standardized dissolved oxygen data sequence.

[0021] The water turbidity data is collected using a scattered light turbidimeter, which measures the turbidity value through 90-degree scattered light. Figure 2As shown, it is a schematic diagram of the turbidity value determination and principle in the embodiment of the present application, wherein the light source part (the black rectangle on the left side of the figure): emits a stable beam of light, usually using an LED light source or a tungsten filament lamp, and the wavelength is within the visible light range. This beam of light is shot into the water sample in a straight line. The water sample container (the rectangular frame in the middle): is a transparent container for holding the water sample to be tested. The black dots in the container represent the suspended particles in the water, which may be silt, microorganisms or other insoluble substances. The scattered light path (indicated by the dotted line): the horizontal dotted line: represents the main light path of the incident light, and the upward vertical dotted line: represents the 90-degree scattered light path. When the incident light irradiates the suspended particles in the water, part of the light will be scattered, among which the 90-degree scattered light can best reflect the turbidity of the water body; the detector (the rectangle on the top): is used to receive the 90-degree scattered light and convert it into an electrical signal. The stronger the scattered light intensity, the more suspended matter there is in the water and the higher the turbidity. The ambient light sensor (the circle in the upper right corner): is used to monitor the ambient light intensity to eliminate the interference of external light on the measurement results. The turbidity of water is determined by measuring the 90-degree scattering intensity of the incident light by the water sample. The original turbidity data is first linearly calibrated, and the scattered light intensity is converted into a turbidity value according to the instrument calibration curve. Considering the influence of ambient light on the measurement results, the ambient light intensity is measured by the built-in light intensity sensor, and a compensation function is established to correct the measured value. The corrected data is filtered through a Butterworth low-pass filter to remove high-frequency interference fluctuations, and the cutoff frequency of the filter is set to 1 / 10 of the sampling frequency. The filtered data is sorted according to the time series to form a standardized turbidity data sequence. The water level and flow data are collected from the ultrasonic water level meter at the water level station and the electromagnetic flow meter at the flow station. The data of the two stations are paired according to the timestamp, and the piecewise linear interpolation method is used to supplement the missing data points caused by equipment failure or communication interruption. The interpolation calculation is based on the adjacent valid data points to maintain the continuity and smoothness of the data. After the interpolation is completed, the data is verified using the established water level-flow relationship curve, which is obtained by fitting based on long-term observation data. The measured data points are compared with the relationship curve, and a deviation threshold is set. Data points exceeding the threshold are determined as outliers and eliminated to obtain standardized water level and flow data.

[0022] The data collection of the pump station gate operation status includes opening data and speed data. The opening data is collected by the displacement sensor, and the physical displacement is converted into the opening percentage value. The gate fully open corresponds to 100%, and the gate fully closed corresponds to 0%. The speed data is collected by the speed sensor, and the speed range of different models of equipment is unified to the 0-1 interval through dimensional normalization. The converted data is verified for validity according to the equipment operation specifications, and the data points that do not meet the upper and lower limits of the equipment parameters are eliminated to obtain standardized operation status data. When importing the above four types of standardized data into the time series database, it is necessary to solve the problem of inconsistent sampling frequencies of different data. The sampling interval of dissolved oxygen and turbidity data is 10 minutes, the water level flow data is 5 minutes, and the equipment operation status data is 1 minute. Align all data to a unified timestamp, adopt the principle of the greatest common divisor, and select 10 minutes as the base time interval. Downsample the data with a sampling frequency higher than 10 minutes, and reduce the sampling rate through moving average; for data with a sampling frequency lower than 10 minutes, increase the sampling points through linear interpolation. After unifying the time resolution, all types of data are normalized, and data of different dimensions are uniformly mapped to the standard interval to form time series correlation data.

[0023] Finally, the integrity of the time series correlation data is checked, and the Pearson correlation coefficient is calculated to evaluate the correlation between the parameters. The distribution characteristics of each parameter are established based on historical data, including statistical characteristics such as mean and standard deviation, and the 3σ criterion is used to identify outliers. All processed data are integrated according to a unified data structure, including fields such as parameter identification, timestamp, value, quality mark, etc., to form standardized monitoring data for water conservancy projects.

[0024] For example, in the actual monitoring of ecological water conservancy projects, a monitoring system was set up in a certain river section. The raw data of the dissolved oxygen sensor showed large fluctuations in the values, and the unreasonable jumps were smoothed through wavelet denoising processing; the turbidity data deviated during the direct sunlight period, and the measurement error was corrected through light intensity compensation; the water level and flow data were missing during the equipment maintenance period, and the data gaps were filled through the interpolation algorithm; the pump station gate operation data had some over-limit values, and the abnormal working conditions were screened out through parameter validity verification. After the various types of data were standardized, they were aligned in the time series to establish a monitoring data set.

[0025] In a specific embodiment, the process of executing step S102 may specifically include the following steps: (1) The water quality parameters in the standardized monitoring data of water conservancy projects are divided into different zones according to the sampling locations, and the signal features are extracted by wavelet decomposition. The coefficients of each frequency band after decomposition are threshold processed, and then the signal is reconstructed to obtain the water quality data after noise reduction. (2) Sort the denoised water quality data by timestamp, calculate the distance matrix between sampling points based on the distribution characteristics of the spatial sampling points, generate spatiotemporal registration data points through interpolation calculation, and obtain spatiotemporal aligned hydrological data; (3) Group and count the time-space aligned hydrological data, calculate the correlation coefficient matrix between different water quality parameters, establish the influence weight relationship between parameters, and obtain the correlation data of water system parameters; (4) Divide the water system parameter correlation data into levels according to the correlation strength, extract the parameter combination characteristics at each level, construct the numerical distribution characteristics of the parameter combination, and obtain the initial water ecological data; (5) Establish a parameter change trend chart based on the initial water ecological data, analyze the parameter change law, extract key inflection points and mutation characteristics, and obtain a water quality abnormality feature library through data clustering; (6) Classify the water quality anomaly feature library, optimize and reorganize the data based on the initial water ecological data, and organize the parameter groups according to the water quality categories to obtain the water ecological optimization data set and water quality anomaly feature library.

[0026] Specifically, the sampling locations are divided into different water body types such as river sections and lake areas. The water quality data of each partition is processed by wavelet decomposition. The db4 wavelet function is selected to decompose the signal into 4 scales to obtain the approximate coefficient and detail coefficient. The detail coefficient is denoised by the soft threshold method. The threshold size is determined according to the standard deviation of the noise at each scale. The main features of the signal are retained while removing high-frequency noise. The signal is reconstructed by inverse wavelet transform to obtain the denoised water quality data. The denoised water quality data is timestamped and arranged in the order of sampling time. Based on the geographic coordinate information of the monitoring points, the Euclidean distance between each sampling point is calculated to construct a distance matrix. For areas with uneven spatial distribution, the inverse distance weighted interpolation method is used to generate virtual sampling points to fill the monitoring blind spots. The data at different locations and times are aligned by the spatiotemporal interpolation algorithm to establish a unified spatiotemporal reference system to obtain spatiotemporal aligned hydrological data.

[0027] The time-space aligned hydrological data are grouped according to the monitoring indicator type, and each group contains parameters such as dissolved oxygen, turbidity, water level and flow. The correlation coefficient matrix R between the parameters is calculated, and the calculation formula is: in, represents the correlation coefficient between the i-th water quality parameter and the j-th hydrological parameter, represents the observed value of the i-th water quality parameter at the k-th moment, represents the observed value of the jth hydrological parameter at the kth moment, and They represent the mean values ​​of the corresponding parameters, and n represents the number of samples.

[0028] Based on the correlation coefficient matrix, the parameter influence weight relationship is constructed. The weight calculation adopts the entropy method, and the weight size is determined by calculating the information entropy of each parameter. The smaller the information entropy, the more effective information the parameter contains, and the larger the corresponding weight. The obtained water system parameter correlation data contains the quantitative relationship between the parameters. The water system parameter correlation data is divided into levels according to the correlation strength, and three levels of high correlation, moderate correlation and weak correlation are set. The parameter combination characteristics are extracted in each level, including the linear relationship, periodic change characteristics and mutation characteristics between parameters. The numerical distribution characteristics of the parameter combination are established, including statistics such as mean, variance, skewness and kurtosis, to form the initial water ecological data.

[0029] According to the initial water ecological data, the parameter change trend is analyzed, the time series change curve is drawn, and the key inflection points and mutation characteristics are identified. The abnormal patterns are classified by the K-means clustering algorithm, and the number of cluster centers is adaptively determined according to the data characteristics. The clustering results are sorted to form a water quality abnormality feature library. Each type of abnormal feature contains feature descriptions, trigger conditions and typical cases. The features in the water quality abnormality feature library are refined and classified according to water quality categories (such as eutrophication, hypoxia, pollution, etc.). Combined with the parameter combination characteristics in the initial water ecological data, the abnormal features are optimized and reorganized, and the mapping relationship between feature parameters and water quality problems is established. The parameter groups are sorted according to water quality categories to obtain the water ecological optimization data set and water quality abnormality feature library.

[0030] For example, multiple water quality monitoring points were set up in a certain river section, and the original data showed that there were large fluctuations in dissolved oxygen and turbidity data. The noise caused by equipment jitter, electromagnetic interference and other factors was removed through wavelet noise reduction processing. Taking into account the uneven distribution of monitoring points, the spatial interpolation method was used to supplement the data of the monitoring blind area. Through correlation analysis, it was found that the dissolved oxygen content in this river section was significantly negatively correlated with water temperature and turbidity, and positively correlated with flow rate. Based on this, the influence weight relationship between water quality parameters was established. During the continuous monitoring process, when the dissolved oxygen content dropped rapidly and the turbidity increased, the typical water pollution characteristics were identified according to the abnormal feature library, and the corresponding control measures were initiated in time to establish the correlation between water quality parameters.

[0031] In a specific embodiment, the process of executing step S103 may specifically include the following steps: (1) The water ecological optimization data set is stratified according to water quality indicators, the evaluation coefficient of each indicator is determined by weight calculation, and the initial health score is obtained through stratified weighted calculation; (2) Extract key parameter nodes based on the water quality anomaly feature library, analyze the fluctuation range by comparing historical data, and obtain the critical value of parameter changes by time period; (3) Water environment quality is graded based on the initial health score, and warning level intervals are divided based on the critical value of parameter changes, and water quality status assessment data is output; (4) Based on the key indicators in the water quality status assessment data, trend prediction and dynamic compensation are carried out in sequence to generate a water environment quality change curve; (5) According to the trend characteristics of the water environment quality change curve, the abnormal change points are extracted segment by segment, and the warning trigger conditions are output after data verification; (6) The early warning triggering conditions are graded and judged, and a comprehensive analysis is conducted based on the water quality status assessment data to obtain the water conservancy project ecological assessment index and water quality early warning signal.

[0032] Specifically, the water ecological optimization data set is layered in the water environment health assessment stage, and is divided into physical indicator layer, chemical indicator layer and biological indicator layer according to the nature of water quality indicators. The physical indicator layer includes parameters such as water temperature, turbidity and conductivity, the chemical indicator layer includes parameters such as dissolved oxygen, pH value and ammonia nitrogen, and the biological indicator layer includes parameters such as chlorophyll a and plankton density. The weight of each indicator is calculated by the hierarchical analysis method, and an evaluation matrix is ​​established. The weight coefficient is determined according to the degree of influence of the indicator on the health of the water environment. The indicators of each layer are normalized, and the indicators of different dimensions are unified to a comparable scale. Then, a layered weighted calculation is performed to obtain the health score of each layer, and then the scores of each layer are combined to obtain the initial health score. The key parameter nodes are extracted from the water quality anomaly feature library, focusing on the change feature points of sensitive indicators such as dissolved oxygen and turbidity. The historical data of each key parameter are classified according to factors such as season and hydrological conditions, and their fluctuation range is counted. The sliding time window method is used to analyze the time series characteristics of the parameters, and the change rate and amplitude of the parameters on different time scales are calculated. The upper and lower thresholds of parameter changes are determined through statistical analysis, and a critical value system for parameter changes is established in combination with water quality standard requirements.

[0033] Based on the initial health score, the water environment quality is graded, and five levels are set: excellent, good, general, poor, and bad. The corresponding relationship between the score and the level is established. Combined with the critical value of parameter change, the warning interval is subdivided for each level, including safe interval, attention interval, warning interval, and dangerous interval. Taking into account the current value, change trend and critical value of water quality indicators, the specific warning interval of the water environment is determined, and the water quality status assessment data containing the status of each indicator is output. Trend prediction and dynamic compensation are performed on the key indicators in the water quality status assessment data. Trend prediction uses time series analysis methods, considers the seasonal, periodic and trend characteristics of the data, and establishes a prediction model. The dynamic compensation mechanism corrects the prediction results through real-time monitoring data, adjusts the prediction parameters, and improves the prediction accuracy. Combine the prediction results with the measured data to generate a trend curve reflecting the dynamic changes in water environment quality.

[0034] In the water environment quality change curve, the piecewise linear fitting method is used to identify abnormal change points, focusing on the nodes where the slope of the curve changes significantly. The identified abnormal points are data checked and their validity is confirmed through multiple verifications. According to the degree and duration of abnormal changes, different levels of warning conditions are set to form a warning trigger rule set. The warning trigger conditions are graded and judged, and level one, level two and level three warnings are set. The level one warning corresponds to a slight excess or short-term abnormality of water quality indicators, the level two warning corresponds to an obvious excess or continuous abnormality of indicators, and the level three warning corresponds to a serious excess or sudden abnormality. Combined with the status of multiple indicators in the water quality status assessment data, a comprehensive analysis is conducted to determine the warning level. The health score and warning level are normalized to obtain a standardized water conservancy project ecological assessment index, and the corresponding water quality warning signal is generated at the same time.

[0035] In actual applications, the water environment of a river section changes due to changes in the water quality of upstream water. The monitoring data is evaluated in layers, and chemical indicators such as dissolved oxygen and pH value have higher weights. The initial health score is obtained through weighted calculation. Analysis of historical data shows that water quality problems often occur when the dissolved oxygen concentration is lower than 4 mg / L, and the critical value of dissolved oxygen is set accordingly. Combining the health score and the critical value, the water quality of this river section is judged as "poor" and enters the warning interval. Through trend prediction, it is found that the dissolved oxygen concentration shows a continuous downward trend, and it is predicted that it will drop to a lower level after 24 hours. The point where the dissolved oxygen drops rapidly is identified in the water quality change curve, triggering the secondary warning condition. Comprehensive analysis shows that moderate water pollution has occurred in this river section, and the corresponding warning signal is generated.

[0036] In a specific embodiment, the process of executing step S104 may specifically include the following steps: (1) Extract the water quality category judgment value from the water conservancy project ecological assessment index, calculate the difference between it and the regional water quality standards, and output the water quality improvement target value; (2) Based on the water quality warning signal, the warning level range is divided, the impact propagation path is determined according to the water system connectivity, and the regional warning response sequence is generated; (3) Conduct upstream and downstream correlation analysis on the water quality improvement target value, determine the water quality control amount according to the flow relationship, and output water volume allocation parameters; (4) Match and verify the regional early warning response sequence with the water allocation parameters, and obtain the water quality control target sequence through block calculation; (5) Divide the control units according to the water quality control target sequence, calculate the control volume allocation ratio based on the water system connectivity, and generate a regional control plan; (6) Decompose the regional control plan according to the control units, determine the operation sequence according to the hydraulic connection, and obtain the regional control instructions for the river and lake water systems.

[0037] Specifically, the water quality category judgment value is extracted from the ecological assessment index of water conservancy projects. Specific judgment standards are set for each water quality category, including benchmark values ​​of indicators such as dissolved oxygen, turbidity, and ammonia nitrogen. The current water quality indicators are compared with the regional water quality standards, the difference of each indicator is calculated, and the target value that needs to be improved is determined. The difference calculation takes into account the requirements of water body functional zoning, and differentiated improvement targets are set for different functional areas. The warning level is graded based on the water quality warning signal, and three levels of level one warning, level two warning, and level three warning are set. The connectivity of the water system is analyzed according to the river network structure, a water flow map is established, and the hydraulic connection between each section is marked. The propagation path of water quality impact is analyzed through graph theory methods, considering the direction of water flow, flow velocity and water mixing characteristics, the migration law of pollutants in the water system is calculated, and an early warning response sequence is generated.

[0038] The upstream and downstream correlation analysis of the water system is carried out for the water quality improvement target value, and the water quality control amount is calculated as follows: in, represents the water quality control amount from section i to section j, represents the weight coefficient of the kth water quality index, represents the hydraulic transmission coefficient between sections, Indicates the target water quality value of the upstream section, Indicates the current water quality value of the downstream section, Indicates the distance between sections, indicates the attenuation rate of water quality indicators, represents the hydraulic loss coefficient, t represents the water flow transmission time, and m represents the number of water quality indicators.

[0039] Match and check the regional early warning response sequence with the water allocation parameters to establish the corresponding relationship between the early warning level and the regulation intensity. Set different control parameter thresholds according to different early warning levels, and determine the control target of each control unit through block calculation. The control target sequence includes parameters such as water volume regulation, regulation time, and expected water quality indicators. Divide the control units according to the water quality control target sequence, and divide the entire water system into several relatively independent control blocks according to hydraulic characteristics and management needs. Analyze the mutual influence between the control units in combination with the connectivity of the water system, and calculate the allocation ratio of the regulation volume of each unit. Formulate regional control plans based on hydraulic conditions and the distribution characteristics of control facilities.

[0040] Decompose the regional control plan into specific operation instructions, including the operating parameters of hydraulic structures such as pump stations and gates. Analyze the hydraulic connection of each control unit, determine the order of control operations, and compile a control schedule. Generate river and lake water system zoning control instructions based on hydraulic response time and control target requirements.

[0041] For example, the water quality management process of a river-lake connection project reflects the specific implementation of this method. When the water quality assessment index of the upstream river section shows that the ammonia nitrogen exceeds the standard, the target value for improving the ammonia nitrogen concentration is determined by calculating the difference with the water quality standard. The early warning signal is displayed as a secondary warning. By analyzing the river network structure, it is found that the pollution impact will spread downstream along the main river channel. Through upstream and downstream correlation analysis, the amount of clean water to be supplemented is calculated, and the regulation cycle is determined based on the hydraulic transmission time. The early warning response sequence is matched with the regulation parameters, and a water quality improvement plan for each region is formulated. According to the division of control units, the downstream flow of the upstream gate and the water diversion volume of the tributary are determined respectively, forming specific regulation instructions including gate opening adjustment and pump station start and stop arrangements.

[0042] In a specific embodiment, the process of executing step S105 may specifically include the following steps: (1) Decompose the control quantity of the river and lake water system zoning control instructions, determine the opening sequence according to the flow range of the hydraulic regulating device, and generate the operating parameters of the regulating device; (2) Convert the operating parameters of the regulating device into the equipment operation control quantity, calculate the regulation timing according to the equipment response characteristics, and output the regulation control data; (3) Based on the regulation and control data, the operating parameters of the water purification equipment are collected, the changes in purification load are analyzed according to the process flow, and the equipment operating data is obtained; (4) Extract key operating indicators from equipment operating data, perform operating stability analysis based on the equipment dynamic response curve, and generate operating condition evaluation data; (5) Group the operating condition evaluation data according to the operating parameter type, calculate the deviation value against the standard operating condition range, and output the parameter correction data; (6) Perform operation status statistics based on parameter correction data and conduct comprehensive analysis based on the equipment operation efficiency curve to obtain the project operation status data.

[0043] Specifically, the control instructions for the river and lake water system are decomposed according to the control units. For each control unit, the required flow change is determined according to the control target, and then the specific gate opening sequence is calculated through the hydraulic model. The hydraulic regulating device has a specific flow regulation range. It is necessary to convert the flow demand into the opening change, and at the same time consider the influence of the water level difference on the flow coefficient, and generate the regulating device operating parameters including the opening, flow, water level and other parameters.

[0044] The conversion of the operating parameters of the regulating device to the equipment operation control quantity involves complex hydraulic calculations. The conversion formula is: in, represents the equipment operation control quantity at time t, represents the device response coefficient of the nth control unit, represents the flow change function of the control unit, Indicates the water level difference, Indicates the inertia attenuation coefficient of the device, represents the dynamic adjustment coefficient, and N represents the total number of control units. The adjustment timing of the device is calculated through this formula to form the adjustment control data.

[0045] Based on the regulation and control data, the operating parameters of the water purification equipment are collected in real time, including inlet water quality, processing load, energy consumption indicators, etc. The equipment load changes are analyzed in accordance with the process sequence, and the relationship between the inlet and outlet water quality, processing load, and equipment energy consumption is established. The operating data of the equipment under different load conditions is recorded and the equipment operating data is compiled. Key operating indicators such as processing efficiency, energy consumption intensity, and operating stability are extracted from the equipment operating data. Through the time series analysis method, the dynamic response curve of the equipment is drawn to analyze the response characteristics of the equipment during the load change process. Focus on the operating stability of the equipment start-stop transition stage and the load mutation stage, record the characteristic parameters of each stage, and generate operating condition evaluation data.

[0046] The working condition evaluation data is grouped and sorted according to different types such as equipment type, operating condition, and load condition. Based on the standard working condition range, the deviation value of each operating parameter is calculated, and the degree and trend of the parameter deviation from the standard working condition are analyzed. The deviation analysis results are statistically summarized to form parameter correction data to guide the adjustment of equipment operating parameters. The equipment operating status is statistically analyzed based on the parameter correction data, and the equipment operating quality is evaluated in combination with the equipment operating efficiency curve. By comparing and analyzing the performance of the equipment under different operating conditions, the optimal operating parameter range is determined, and the engineering operating status data reflecting the overall operating status of the equipment is generated.

[0047] For example, the specific application of this method is demonstrated in the water purification equipment control process in a river water quality improvement project. First, the control instructions are converted into specific gate opening adjustment requirements, and the adjustment sequence of the gate opening from 30% to 50% is determined by calculation. According to the equipment response characteristics, a step-by-step adjustment plan is compiled, and the opening adjustment amplitude is controlled within 5% each time to avoid water flow impact. During the execution of the control process, the equipment operating parameters are monitored in real time, and it is found that the dissolved oxygen treatment load increases with the increase of water inflow, and the aeration intensity is adjusted in time. By analyzing the equipment operation data, the problem of fluctuations in dissolved oxygen concentration when the equipment load suddenly changes is identified, and the control parameters are optimized accordingly. After operating parameter correction and efficiency analysis, the equipment operating parameter combination suitable for this working condition is determined to ensure the stability of the water purification effect.

[0048] In a specific embodiment, the process of executing step S106 may specifically include the following steps: (1) The project operation status data is divided into daily, weekly, and monthly scales according to the time span, and the mean, variance, and coefficient of variation of the operation parameters in each time period are calculated respectively. Then, the water ecological response sequence is generated through cross-validation through parameter fluctuation law; (2) Filter the water quality index change data from the water ecological response sequence, and calculate the dissolved oxygen recovery time, turbidity decline time, and water quality standard time. Compare the response rates under different hydrological conditions, and output the water quality recovery cycle data through data fitting calculation; (3) The water quality recovery cycle data were seasonally grouped, and the differences in recovery cycles between the flood season, normal water season, and dry season were calculated. Weighted calculations were performed based on influencing factors such as temperature and water volume, and the data were classified according to the speed of the response rate to obtain the cycle characteristic parameters. (4) Compare the periodic characteristic parameters with the target values ​​of various water quality indicators item by item, calculate the deviation rate between the time to reach the water quality standard and the target time, determine the adjustment ratio coefficient according to the degree of deviation, and generate a water quality improvement plan through multiple rounds of iterative calculations; (5) Extract the improvement amount and improvement time of water quality indicators based on the water quality improvement plan, compare the improvement effects of similar working conditions in the historical control database, sort them from high to low according to the improvement efficiency, and output strategy optimization data through data screening and parameter matching; (6) The control parameters are calibrated based on the strategy optimization data. The flow regulation range of the hydraulic regulating device, the processing load and energy consumption indicators of the water purification equipment are calculated respectively. The feasibility is verified in combination with the equipment operation constraints. After multi-objective balance calculation, the control parameters of the water conservancy project are obtained.

[0049] Specifically, the project operation status data is first divided according to the time scale. For daily scale data, the 24-hour data is counted at hourly intervals; weekly scale data is summarized according to a 7-day cycle; and monthly scale data is calculated according to natural months. In each time scale, the mean, variance, and coefficient of variation of operating parameters such as dissolved oxygen, turbidity, and flow are calculated respectively, and these statistics reflect the central tendency and dispersion of the parameters. The calculated statistical characteristics are cross-validated, the consistency and correlation of the parameter fluctuation law are analyzed, and a response sequence reflecting the dynamic changes of the water ecosystem is generated. From the water ecological response sequence, the changes in water quality indicators such as dissolved oxygen and turbidity are focused on. For each water quality recovery process after regulation, the time required for dissolved oxygen to rise from a low value to a stable value, the time required for turbidity to drop from a peak value to a baseline value, and the time required for all water quality indicators to reach the standard value are recorded. For the response process under different hydrological conditions, including the influence of factors such as flow changes and water level changes, the corresponding relationship between the water quality improvement rate and hydrological conditions is established. Through the data fitting method, the water quality recovery cycle data under different conditions are obtained.

[0050] The water quality recovery cycle data are seasonally grouped, corresponding to three typical hydrological periods: flood season, normal water season and dry season. The flood season is characterized by abundant flow and strong self-purification capacity of the water body; the hydrological conditions in the normal water season are relatively stable; the dry season faces the problem of insufficient water and reduced self-purification capacity. By comparing and analyzing the differences in the recovery cycles of the three periods, combined with the influence of temperature on the water purification rate and the influence of water volume changes on the dilution effect, a weighted calculation model is established. According to the measured response rate, the recovery cycle is divided into three levels: fast recovery, medium recovery and slow recovery, and the cycle characteristic parameters are obtained. The cycle characteristic parameters are compared with the target values ​​of various indicators specified in the water quality standards, and the deviation between the actual compliance time and the required compliance time is calculated. According to the size of the deviation, the adjustment ratio coefficient of water quality regulation is determined. The larger the deviation, the greater the regulation intensity. Through multiple rounds of iterative calculations, the adjustment parameters are continuously optimized until a regulation scheme that can meet the compliance requirements and is operationally feasible is found to form a water quality improvement plan.

[0051] According to the water quality improvement plan, extract the improvement target and expected improvement time of each water quality indicator. Retrieve the operating records of similar hydrological conditions and water quality problems in the historical control database, and compare and analyze the improvement effects under different control strategies. Sort the control strategies according to the improvement efficiency, select the optimal control parameter combination, and form strategy optimization data through data screening and parameter matching. Check the control parameters of the strategy optimization data, focus on analyzing the flow regulation capacity of the hydraulic regulating device, and ensure that the control plan is within the equipment capacity. At the same time, calculate the processing load of the water purification equipment, evaluate the energy consumption indicators, and determine the optimal operating conditions of the equipment. Combined with the operating constraints of various types of equipment, including start-stop conditions, load change rate restrictions, etc., the feasibility of the control plan is verified. Through multi-objective balance calculation, comprehensively consider factors such as water quality improvement effect, energy consumption, and operating cost, and determine the control parameters of the water conservancy project.

[0052] In a river water quality improvement project, when the dissolved oxygen was first found to be lower than the standard value, the operation status data began to be recorded. By analyzing the data within 24 hours, it was found that the dissolved oxygen content showed a periodic change with low in the morning and evening and high at noon. The data for one week was further statistically analyzed to calculate the daily average value and coefficient of variation of dissolved oxygen, reflecting the overall level and fluctuation of dissolved oxygen. During the water quality regulation process, the time process of dissolved oxygen rising from 3mg / L to 6mg / L was recorded, and the downward trend of turbidity was monitored at the same time. Comparing the recovery rate under different flow conditions, it was found that the fastest recovery was found when the flow rate was 2m³ / s. Considering that it was in the dry season and the water temperature was high, a larger adjustment coefficient was determined through weighted calculation. After multiple rounds of optimization of control parameters, a comprehensive control plan including gate control and aeration and oxygenation was formed. During the implementation of the plan, the equipment operation status was continuously monitored to ensure that the equipment load and energy consumption indicators were within a reasonable range, and the stable improvement of water quality was achieved.

[0053] In a specific embodiment, the process of performing the step of comparing the periodic characteristic parameters with the target values ​​of various water quality indicators item by item may specifically include the following steps: (1) Group the periodic characteristic parameters according to the indicator type, establish the water quality indicator change rate matrix, and obtain the standardized parameter set through unified dimension conversion; (2) Match the target value of the standardized parameter set, calculate the difference sequence between the current value and the target value of each water quality indicator, and generate difference comparison data; (3) Divide the difference comparison data into segments according to the time of reaching the standard, calculate the water quality improvement rate in each time period, establish a time-improvement relationship curve, and output the progress data of reaching the standard; (4) Based on the progress data, calculate the deviation rate between the target time and the specified time for each indicator, divide the priority levels according to the deviation size, and generate the adjustment priority sequence; (5) Conduct correlation analysis on the indicators in the adjustment priority sequence, calculate the complementary or restrictive relationship between the indicators, and determine the adjustment ratio coefficient through feedback correction; (6) Substitute the adjustment ratio coefficient into the water quality improvement objective function, perform step-by-step iterative optimization calculations, screen the optimal control combination, and generate a water quality improvement plan.

[0054] Specifically, the periodic characteristic parameters are grouped according to the indicator type, and divided into a physical indicator group (including water temperature, turbidity, and conductivity), a chemical indicator group (including dissolved oxygen, pH value, and ammonia nitrogen), and a biological indicator group (including chlorophyll a and plankton density). Figure 3 As shown, it is an introduction diagram of the grouping indicators in the embodiment of the present application; a change rate matrix is ​​established for each group of indicators to record the rate of change of the indicators in different time periods. Due to the different dimensions of each indicator, a unified dimension conversion is required, and the maximum and minimum value standardization method is used to map all indicators to the [0,1] interval to form a standardized parameter set. The standardized parameter set is subjected to a target value matching analysis, and the current monitoring value of each water quality indicator is compared with the target value specified in the water quality standard. A difference sequence is established by calculating the difference between the current value and the target value. In the difference sequence, a positive value indicates the degree of exceeding the standard, and a negative value indicates the degree of being better than the standard. The difference sequence is arranged in chronological order to form difference comparison data reflecting the water quality status.

[0055] The difference comparison data is segmented according to the time requirements for reaching the standard. The short-term standard requirement is set to be within 24 hours, the medium-term standard requirement is within 7 days, and the long-term standard requirement is more than 30 days. In each time period, the improvement rate of water quality indicators is calculated, that is, the change in the indicator value per unit time. By drawing a time-improvement relationship curve, the dynamic process of water quality improvement is analyzed, and the progress data for reaching the standard at each time node is determined. Based on the progress data for reaching the standard, the deviation rate between the reaching time of each indicator and the specified time is calculated. The larger the deviation rate, the more difficult it is to reach the standard for the indicator, and priority regulation is required. According to the size of the deviation rate, the indicators are divided into three priority levels: emergency regulation, key regulation, and conventional regulation. The indicators in each level are arranged in descending order according to the deviation rate to generate a regulation priority sequence that reflects the urgency of regulation.

[0056] Conduct correlation analysis on the indicators in the regulation priority sequence. By calculating the correlation coefficients between the indicators, identify the complementary and restrictive relationships between the indicators. The complementary relationship is manifested as the improvement of one indicator driving the change of another indicator in the same direction, such as the increase in dissolved oxygen is often accompanied by a decrease in turbidity; the restrictive relationship is manifested as the increase and decrease of indicators, such as the increase in water temperature will reduce the dissolved oxygen content. According to these relationship characteristics, the adjustment ratio coefficient of each indicator is determined by the feedback correction method. Substitute the determined adjustment ratio coefficient into the water quality improvement objective function, which comprehensively considers multiple objectives such as water quality improvement effect, energy consumption, and operating costs. Through step-by-step iterative optimization calculation, continuously adjust the combination of control parameters until the optimal solution that can meet the water quality improvement requirements and ensure economy is found. Generate a water quality improvement plan containing specific control measures.

[0057] In the process of eutrophication treatment of a certain river channel, the periodic characteristic parameters showed that dissolved oxygen, turbidity, and ammonia nitrogen were the main problem indicators. After standardizing the change rate data of these indicators, it was found that the current value of dissolved oxygen was 4 mg / L, and the difference from the target value of 6 mg / L was 2 mg / L; the current value of turbidity was 25 NTU, and the difference from the target value of 10 NTU was 15 NTU. According to the requirements of the time to reach the standard, the improvement rate was analyzed, and it was found that the dissolved oxygen increased by 0.2 mg / L per hour under the regulation of oxygenation, and the turbidity decreased by 2 NTU per hour through sedimentation treatment. After priority division, the improvement of dissolved oxygen was listed as an emergency regulation indicator. Through correlation analysis, it was found that dissolved oxygen and turbidity showed a negative correlation. When oxygenation measures were taken, turbidity would also improve. A regulation scheme with oxygenation as the main and sedimentation as the auxiliary was determined, and the optimal operating parameters and mud discharge cycle of the aeration equipment were determined through multiple iterative optimizations.

[0058] In a specific embodiment, the process of calculating the deviation rate between the target achievement time and the specified time of each indicator based on the target achievement progress data may specifically include the following steps: (1) Conduct time series analysis on the progress data of compliance with water quality indicators, extract the compliance time nodes of each indicator, and establish the compliance time series; (2) Compare the target time series with the specified time nodes, calculate the lead time and lag time respectively, and obtain the deviation data through time difference statistics; (3) Quantify and classify the deviation data, set the threshold interval according to the deviation rate, calculate the deviation score of each indicator, and output the indicator score table; (4) Arrange the data in the indicator scoring table in descending order, set the weight coefficient according to the degree of deviation, and generate the indicator priority matrix; (5) Divide the indicator priority matrix into segments, calculate the regulation urgency of each priority level, and obtain priority level data through threshold classification; (6) Establish a control order relationship based on the priority data, sort and combine the water quality indicators according to their response time, and generate a regulation priority sequence.

[0059] Specifically, the periodic characteristic parameters are grouped according to the indicator type, and divided into physical indicator groups (including water temperature, turbidity, and conductivity), chemical indicator groups (including dissolved oxygen, pH value, and ammonia nitrogen), and biological indicator groups (including chlorophyll a and plankton density). A change rate matrix is ​​established for each group of indicators to record the change rate of the indicators in different time periods. Due to the different dimensions of each indicator, a unified dimension conversion is required. The maximum and minimum value standardization method is used to map all indicators to the [0,1] interval to form a standardized parameter set. The standardized parameter set is subjected to target value matching analysis, and the current monitoring value of each water quality indicator is compared with the target value specified in the water quality standard. By calculating the difference between the current value and the target value, a difference sequence is established. In the difference sequence, positive values ​​indicate the degree of exceeding the standard, and negative values ​​indicate the degree of being better than the standard. The difference sequence is arranged in chronological order to form difference comparison data reflecting the water quality status.

[0060] The difference comparison data is segmented according to the time requirements for reaching the standard. The short-term standard requirement is set to be within 24 hours, the medium-term standard requirement is within 7 days, and the long-term standard requirement is more than 30 days. In each time period, the improvement rate of water quality indicators is calculated, that is, the change in the indicator value per unit time. By drawing a time-improvement relationship curve, the dynamic process of water quality improvement is analyzed, and the progress data for reaching the standard at each time node is determined. Based on the progress data for reaching the standard, the deviation rate between the reaching time of each indicator and the specified time is calculated. The larger the deviation rate, the more difficult it is to reach the standard for the indicator, and priority regulation is required. According to the size of the deviation rate, the indicators are divided into three priority levels: emergency regulation, key regulation, and conventional regulation. The indicators in each level are arranged in descending order according to the deviation rate to generate a regulation priority sequence that reflects the urgency of regulation.

[0061] Conduct correlation analysis on the indicators in the regulation priority sequence. By calculating the correlation coefficients between the indicators, identify the complementary and restrictive relationships between the indicators. The complementary relationship is manifested as the improvement of one indicator driving the change of another indicator in the same direction, such as the increase in dissolved oxygen is often accompanied by a decrease in turbidity; the restrictive relationship is manifested as the increase and decrease of indicators, such as the increase in water temperature will reduce the dissolved oxygen content. According to these relationship characteristics, the adjustment ratio coefficient of each indicator is determined by the feedback correction method. Substitute the determined adjustment ratio coefficient into the water quality improvement objective function, which comprehensively considers multiple objectives such as water quality improvement effect, energy consumption, and operating costs. Through step-by-step iterative optimization calculation, continuously adjust the combination of control parameters until the optimal solution that can meet the water quality improvement requirements and ensure economy is found. Generate a water quality improvement plan containing specific control measures.

[0062] For example, the periodic characteristic parameters show that dissolved oxygen, turbidity, and ammonia nitrogen are the main problem indicators. After standardizing the change rate data of these indicators, it was found that the current value of dissolved oxygen was 4 mg / L, and the difference from the target value of 6 mg / L was 2 mg / L; the current value of turbidity was 25 NTU, and the difference from the target value of 10 NTU was 15 NTU. According to the time requirement for reaching the standard, the improvement rate was analyzed, and it was found that the dissolved oxygen increased by 0.2 mg / L per hour under oxygenation control, and the turbidity decreased by 2 NTU per hour through sedimentation treatment. After priority division, dissolved oxygen improvement was listed as an emergency control indicator. Through correlation analysis, it was found that dissolved oxygen and turbidity showed a negative correlation. When oxygenation measures were taken, turbidity would also improve. A control scheme with oxygenation as the main and sedimentation as the auxiliary was determined, and the optimal operating parameters and sludge discharge cycle of the aeration equipment were determined through multiple iterative optimizations.

[0063] The above describes the automated monitoring method for ecological water conservancy projects in the embodiment of the present application. The following describes the automated monitoring system for ecological water conservancy projects in the embodiment of the present application. Figure 4 In the embodiment of the present application, an automatic monitoring system for ecological water conservancy projects includes: The acquisition module 201 is used to collect dissolved oxygen, turbidity, water level flow and pump station gate operation status of the water body through monitoring sensors, and obtain standardized monitoring data of water conservancy projects through data preprocessing; The alignment module 202 is used to perform water quality parameter noise reduction and hydrological data spatiotemporal alignment based on the standardized monitoring data of the water conservancy project, analyze the correlation of ecological water system parameters, and obtain a water ecological optimization data set and a water quality abnormality feature library; The analysis module 203 is used to establish an ecological water system health assessment system to perform dynamic analysis of the water environment based on the water ecological optimization data set and the water quality abnormality feature library, and obtain the water conservancy project ecological assessment index and water quality early warning signal; The early warning module 204 is used to construct a water environment control model to analyze the water system management plan and obtain the river and lake water system zoning control instructions according to the water conservancy project ecological assessment index and water quality early warning signal; The adjustment module 205 is used to adjust the operating parameters and analyze the working conditions of the hydraulic regulating device and the water purification equipment according to the river and lake water system zoning control instructions to obtain the project operation status data; The optimization module 206 is used to obtain the water conservancy project control parameters through water ecological restoration cycle analysis and water quality improvement strategy optimization based on the project operation status data.

[0064] Through the coordinated cooperation of the above-mentioned components and the use of layered data collection and multi-dimensional data processing technology, the problem of unstable data quality in traditional monitoring methods has been effectively solved, and comprehensive monitoring of dissolved oxygen, turbidity, water level flow and pump station gate operation status in water bodies has been achieved. The standardized monitoring data of water conservancy projects obtained after data preprocessing provides a reliable data basis for subsequent analysis. By reducing the noise of water quality parameters and aligning hydrological data in time and space, the influence of data noise and time and space differences has been effectively eliminated. Combined with the correlation analysis of ecological water system parameters, the intrinsic connection between water quality indicators has been deeply explored. The water ecological optimization data set and water quality anomaly feature library formed provide an important basis for the diagnosis of water quality problems. At the same time, based on the water ecological optimization data set and water quality anomaly feature library, The ecological water system health assessment system established by the feature database and the water conservancy project ecological assessment index and water quality warning signal obtained through dynamic analysis of the water environment have realized the early identification and warning of water quality problems, and then constructed a water environment regulation model based on the assessment index and warning signal. The river and lake water system zoning regulation instructions generated through the analysis of the water system management plan have realized the precise implementation of regulation measures. The operating parameter adjustment and operating condition analysis of the hydraulic regulating device and water purification equipment have ensured the effective implementation of the regulation measures. The water conservancy project regulation parameters obtained through the analysis of the water ecological restoration cycle and the optimization of the water quality improvement strategy have established a complete closed-loop management system of water environment monitoring-analysis-regulation-optimization, which has significantly improved the intelligent management level and water quality improvement effect of ecological water conservancy projects.

[0065] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An automated monitoring method for ecological water conservancy projects, characterized in that: The automated monitoring method for ecological water conservancy projects comprises: The dissolved oxygen, turbidity, water level flow and pump station gate operation status of the water body are collected through monitoring sensors, and standardized monitoring data of water conservancy projects are obtained through data preprocessing; According to the standardized monitoring data of the water conservancy project, water quality parameter noise reduction and hydrological data spatiotemporal alignment are performed, and the correlation analysis of ecological water system parameters is performed to obtain a water ecological optimization data set and a water quality abnormality feature library; Based on the water ecological optimization data set and water quality abnormality feature library, an ecological water system health assessment system is established to conduct dynamic analysis of the water environment, and obtain the water conservancy project ecological assessment index and water quality early warning signal; According to the ecological assessment index of the water conservancy project and the water quality early warning signal, a water environment control model is constructed to analyze the water system management plan and obtain the river and lake water system zoning control instructions; According to the river and lake water system zoning control instructions, the hydraulic regulating device and water purification equipment are adjusted in operation parameters and analyzed in operation conditions to obtain the project operation status data; According to the project operation status data, the water conservancy project control parameters are obtained through water ecological restoration cycle analysis and water quality improvement strategy optimization.

2. The automated monitoring method for ecological water conservancy projects according to claim 1, characterized in that: The monitoring sensors are used to collect the dissolved oxygen, turbidity, water level flow and pump station gate operation status of the water body, and the standardized monitoring data of the water conservancy project is obtained through data preprocessing, including: The dissolved oxygen data of the water body is collected through the water body sensor, and the dissolved oxygen data are grouped according to the sampling time. The signal of each group of data is denoised, and the average value is calculated according to the time window. Then the value range is verified, and the data points beyond the range are eliminated to obtain the standardized dissolved oxygen data; The water turbidity is collected by optical sensors, the original turbidity data is linearly calibrated, the data is compensated according to the ambient light intensity, interference fluctuations are removed by signal filtering, and the processed data is rearranged according to the time series to obtain standardized turbidity data; The water level data collected by the water level station and the flow data collected by the flow station are paired according to the sampling time, the missing data points are supplemented by linear interpolation, the data are verified according to the water level-flow relationship curve, and the outliers that do not conform to the relationship curve are eliminated to obtain the standardized water level and flow data; The opening data and speed data are collected from the control system of the pump station gate, the opening data is converted into a percentage value, the speed data is dimensionally normalized, and the validity is verified according to the upper and lower limits of the equipment operation parameters, and the data that meets the operation specifications is screened out to obtain standardized operation status data; Importing the standardized dissolved oxygen data, standardized turbidity data, standardized water level flow data, and standardized operating status data into a time series database, aligning them according to a unified timestamp, downsampling or interpolating data with different sampling frequencies, normalizing the data after unifying the time resolution, and obtaining time series correlation data; The data integrity check is performed on the time series correlation data, the correlation coefficients of various parameters are calculated, abnormal values ​​are identified according to the distribution characteristics of historical data, and all processed data are integrated into a unified data structure to obtain standardized monitoring data of water conservancy projects.

3. The automated monitoring method for ecological water conservancy projects according to claim 1, characterized in that: The water quality parameter noise reduction and hydrological data spatiotemporal alignment are performed based on the standardized monitoring data of the water conservancy project, and the correlation analysis of ecological water system parameters is performed to obtain a water ecological optimization data set and a water quality abnormality feature library, including: The water quality parameters in the standardized monitoring data of the water conservancy project are divided into zones according to the sampling positions, the signal features are extracted by wavelet decomposition, the coefficients of each frequency band after decomposition are threshold processed, and the signal is reconstructed to obtain the water quality data after noise reduction; The de-noised water quality data are sorted according to timestamps, a distance matrix between sampling points is calculated according to the distribution characteristics of the spatial sampling points, and spatiotemporal registration data points are generated by interpolation calculation to obtain spatiotemporal aligned hydrological data; Perform grouping statistics on the time-space aligned hydrological data, calculate the correlation coefficient matrix between different water quality parameters, establish the influence weight relationship between the parameters, and obtain the water system parameter correlation data; The water system parameter correlation data is divided into levels according to the correlation strength, the parameter combination characteristics at each level are extracted, the numerical distribution characteristics of the parameter combination are constructed, and the initial water ecological data are obtained; Establish a parameter change trend diagram based on the initial water ecological data, analyze the parameter change law, extract key inflection points and mutation characteristics, and obtain a water quality abnormality feature library through data clustering; The water quality anomaly feature library is characterized and classified, and data optimization and reorganization are performed in combination with the initial water ecological data. Parameter groups are sorted according to water quality categories to obtain a water ecological optimization data set and a water quality anomaly feature library.

4. The automated monitoring method for ecological water conservancy projects according to claim 1, characterized in that: According to the water ecological optimization data set and water quality abnormality feature library, an ecological water system health assessment system is established to conduct dynamic analysis of the water environment, and obtain the water conservancy project ecological assessment index and water quality early warning signal, including: The water ecological optimization data set is stratified according to water quality indicators, the evaluation coefficient of each indicator is determined by weight calculation, and the initial health score is obtained through stratified weighted calculation; Extract key parameter nodes based on the water quality anomaly feature library, analyze the fluctuation range by comparing historical data, and obtain the critical value of parameter change by time period statistics; The water environment quality is graded based on the initial health score, and the warning level interval is divided according to the critical value of parameter change, and the water quality status assessment data is output; Based on the key indicators in the water quality status assessment data, trend prediction and dynamic compensation are performed in sequence to generate a water environment quality change curve; According to the trend characteristics of the water environment quality change curve, abnormal change points are extracted in sections, and warning trigger conditions are output after data verification; The warning triggering conditions are graded and judged, and a comprehensive analysis is conducted in combination with the water quality status assessment data to obtain the water conservancy project ecological assessment index and water quality warning signal.

5. The automated monitoring method for ecological water conservancy projects according to claim 1, characterized in that: According to the water conservancy project ecological assessment index and water quality early warning signal, a water environment control model is constructed to analyze the water system management plan and obtain the river and lake water system zoning control instructions, including: Extracting the water quality category determination value from the water conservancy project ecological assessment index, performing difference calculation based on the regional water quality standards, and outputting the water quality improvement target value; Divide the warning level range based on the water quality warning signal, determine the impact propagation path according to the water system connectivity, and generate a regional warning response sequence; Conduct upstream and downstream correlation analysis on the water quality improvement target value, determine the water quality control amount according to the flow relationship, and output water volume allocation parameters; The sub-regional early warning response sequence is matched and verified with the water allocation parameters, and the water quality control target sequence is obtained by block calculation; The control units are divided according to the water quality control target sequence, and the control amount allocation ratio is calculated in combination with the water system connectivity relationship to generate a regional control plan; The regional control plan is decomposed according to the control units, and the operation sequence is determined according to the hydraulic connection to obtain the river and lake water system zoning control instructions.

6. The automated monitoring method for ecological water conservancy projects according to claim 1, characterized in that: According to the river and lake water system zoning control instructions, the hydraulic regulating device and water purification equipment are adjusted in operation parameters and analyzed in operation conditions to obtain engineering operation status data, including: Decomposing the control quantity of the river and lake water system zoning control instructions, determining the opening sequence according to the flow range of the hydraulic regulating device, and generating the operating parameters of the regulating device; Convert the operating parameters of the regulating device into equipment operation control quantities, calculate the regulating timing according to the equipment response characteristics, and output the regulating control data; Based on the adjustment control data, the operating parameters of the water purification equipment are collected, and the purification load changes are analyzed according to the process flow to obtain the equipment operating data; Extract key operating indicators from the equipment operating condition data, perform operating stability analysis based on the equipment dynamic response curve, and generate operating condition evaluation data; The operating condition evaluation data are grouped according to the operating parameter type, deviation values ​​are calculated by comparing with the standard operating condition range, and parameter correction data are output; The operation status statistics are performed according to the parameter correction data, and a comprehensive analysis is performed in combination with the equipment operation efficiency curve to obtain the project operation status data.

7. The automated monitoring method for ecological water conservancy projects according to claim 1, characterized in that: According to the project operation status data, water ecological restoration cycle analysis and water quality improvement strategy optimization are performed to obtain water conservancy project control parameters, including: The project operation status data is divided into daily, weekly and monthly scales according to the time span, and the mean, variance and coefficient of variation of the operation parameters in each time period are calculated respectively, and then the water ecological response sequence is generated through cross-validation through parameter fluctuation law; The water quality index change data are selected from the water ecological response sequence, and the dissolved oxygen recovery time, turbidity decrease time and water quality reaching standard time are respectively counted, and the response rates under different hydrological conditions are compared, and the water quality recovery cycle data are output through data fitting calculation; The water quality recovery cycle data is seasonally grouped, the recovery cycle differences between the flood season, the normal water season and the dry season are calculated, weighted calculation is performed based on influencing factors such as temperature and water volume, and the response rates are classified to obtain the cycle characteristic parameters; Compare the periodic characteristic parameters with the target values ​​of various water quality indicators item by item, calculate the deviation rate between the time to reach the water quality standard and the target time, determine the adjustment ratio coefficient according to the degree of deviation, and generate a water quality improvement plan through multiple rounds of iterative calculations; Extract the improvement amount and improvement time of water quality indicators based on the water quality improvement plan, compare the improvement effects of similar working conditions in the historical control database, sort them from high to low according to the improvement efficiency, and output strategy optimization data through data screening and parameter matching; The control parameters are checked according to the strategy optimization data, and the flow regulation range of the hydraulic regulating device, the processing load and energy consumption indicators of the water purification equipment are calculated respectively. The feasibility is verified in combination with the equipment operation constraints, and the control parameters of the water conservancy project are obtained through multi-objective balance calculation.

8. The automated monitoring method for ecological water conservancy projects according to claim 7, characterized in that: The periodic characteristic parameters are compared with the target values ​​of various water quality indicators one by one, the deviation rate between the time of reaching the water quality standard and the target time is calculated, the adjustment ratio coefficient is determined according to the degree of deviation, and a water quality improvement plan is generated through multiple rounds of iterative calculations, including: The periodic characteristic parameters are grouped according to the indicator type, a water quality indicator change rate matrix is ​​established, and a standardized parameter set is obtained through unified dimension conversion; Matching the standardized parameter set to a target value, calculating a difference sequence between the current value and the target value of each water quality indicator, and generating difference comparison data; Divide the difference comparison data into sections according to the time of reaching the standard, count the water quality improvement rate in each time period, establish a time-improvement relationship curve, and output the progress data of reaching the standard; Based on the target achievement progress data, the deviation rate between the target achievement time and the specified time of each indicator is calculated, and the priority levels are divided according to the size of the deviation to generate an adjustment priority sequence; Conducting correlation analysis on the indicators in the adjustment priority sequence, calculating the complementary or restrictive relationship between the indicators, and determining the adjustment ratio coefficient through feedback correction; Substitute the adjustment ratio coefficient into the water quality improvement objective function, perform step-by-step iterative optimization calculations, screen the optimal control combination, and generate a water quality improvement plan.

9. The automated monitoring method for ecological water conservancy projects according to claim 8, characterized in that: The method of calculating the deviation rate between the target achievement time and the specified time of each indicator based on the target achievement progress data, dividing the priority levels according to the deviation size, and generating the adjustment priority sequence includes: Performing time series analysis on the progress data of the compliance according to the water quality indicators, extracting the compliance time node of each indicator, and establishing a compliance time series; Compare the target-reaching time series with the specified time nodes, calculate the lead time and the lag time respectively, and obtain the deviation data through time difference statistics; Quantitatively classify the deviation data, set the threshold interval according to the deviation rate, calculate the deviation score of each indicator, and output the indicator score table; Arrange the data in the indicator scoring table in descending order, set weight coefficients according to the degree of deviation, and generate an indicator priority matrix; Divide the indicator priority matrix into sections, calculate the control urgency of each priority level, and obtain priority level data through threshold classification; A control order relationship is established based on the priority data, and the water quality indicators are sorted and combined according to the response time to generate a regulation priority sequence.

10. An automated monitoring system for ecological water conservancy projects, used to implement the automated monitoring method for ecological water conservancy projects as described in any one of claims 1 to 7, characterized in that: The automatic monitoring system for ecological water conservancy projects includes: The acquisition module is used to collect dissolved oxygen, turbidity, water level flow and pump station gate operation status of the water body through monitoring sensors, and obtain standardized monitoring data of water conservancy projects through data preprocessing; An alignment module is used to perform water quality parameter noise reduction and hydrological data spatiotemporal alignment based on the standardized monitoring data of the water conservancy project, analyze the correlation of ecological water system parameters, and obtain a water ecological optimization data set and a water quality anomaly feature library; An analysis module is used to establish an ecological water system health assessment system to conduct dynamic analysis of the water environment based on the water ecological optimization data set and the water quality abnormality feature library, and obtain an ecological assessment index for water conservancy projects and a water quality early warning signal; An early warning module is used to construct a water environment control model to analyze water system management plans and obtain river and lake water system zoning control instructions based on the water conservancy project ecological assessment index and water quality early warning signals; An adjustment module is used to adjust the operating parameters and analyze the working conditions of the hydraulic regulating device and water purification equipment according to the river and lake water system zoning control instructions to obtain the project operation status data; The optimization module is used to obtain the water conservancy project control parameters through water ecological restoration cycle analysis and water quality improvement strategy optimization based on the project operation status data.

Images