AI intelligent collaborative monitoring management system for multi-index water volume system

Abstract

The invention discloses an AI intelligent collaborative monitoring management system for a multi-index water volume system, and relates to the technical field of monitoring management, the collaborative monitoring management system comprises a data acquisition module, a water volume system analysis module, a collaborative monitoring module, an emergency early warning module, an early warning scheme module and a data visualization module, all the modules are connected through electric signals. According to the AI intelligent collaborative monitoring management system for the multi-index water volume system, abnormal changes in water quality, water volume and water ecological indexes are identified through anomaly detection, an early warning mechanism is triggered according to the detected anomaly, early warning information is sent to management personnel through various modes such as a visual interface, a short message and an email, and the management personnel can carry out early warning on the water quality, the water volume and the water ecological indexes. According to the invention, the time interval from the occurrence of the abnormity to the discovery of the abnormity is greatly shortened, and valuable response time is provided for managers, so that further deterioration of the abnormity is effectively restrained, and the safety and sustainable utilization of water resources are guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of monitoring and management technology, and specifically to an AI intelligent collaborative monitoring and management system for a multi-indicator water quantity system. Background Art

[0002] Traditional water resource management methods mainly rely on manual monitoring and scheduling, which have problems such as low efficiency and delayed response. They are unable to achieve comprehensive perception and dynamic management of water resources and are unable to meet the needs of modern water resource management.

[0003] In the assessment and grading of the multi-indicator water system, data conflicts are prone to occur due to the mutual interference of multi-indicator data, resulting in unstable water system assessment results, making it difficult to make effective comprehensive decisions. Therefore, how to weaken the interference of multi-indicator data to improve the collaborative monitoring efficiency of the multi-indicator water system is the problem we need to solve. To this end, an AI intelligent collaborative monitoring and management system for a multi-indicator water system is proposed. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: an AI intelligent collaborative monitoring and management system for a multi-indicator water quantity system, the collaborative monitoring and management system comprising a data acquisition module, a water quantity system analysis module, a collaborative monitoring module, an emergency warning module, a warning scheme module and a data visualization module, wherein the modules are connected by electrical signals; The data acquisition module is used to collect multi-index water quantity data from various monitoring points in real time, including water quality, water quantity and water ecological data, to achieve comprehensive monitoring of water resources, ensure the comprehensiveness and real-time nature of the data, provide a basis for subsequent data processing and analysis, and pre-process the collected multi-index water quantity data to improve the accuracy and reliability of the data and reduce the possibility of data conflicts; The water quantity system analysis module analyzes the pre-processed multi-index water quantity data, performs trend analysis on water quality, water quantity and water ecological indicators, and finds the correlation and mutual influence between the indicator data; The collaborative monitoring module is used to integrate the data of each monitoring point, realize the collaborative monitoring of the multi-indicator water volume system, reduce the interference between the multi-indicator data, and improve the accuracy and stability of monitoring; The emergency warning module comprehensively analyzes the abnormal conditions of water quality, water quantity and water ecological indicators according to the results of the water quantity system analysis module, and sets warning thresholds to trigger alarms for abnormal conditions; The early warning scheme module formulates a corresponding early warning scheme for the identified abnormal situation based on the results of the data analysis module and the information of the emergency warning module; The data visualization module is used to display abnormal situations and early warning plans in the form of charts, which is convenient for users to understand and analyze, improves the readability and usability of data, and helps users better grasp the changing trend of the water volume system.

[0005] Preferably, in the data collection module, the process of collecting multi-index water volume data includes: According to the topography, water flow characteristics, and pollution source distribution factors of the monitoring area, the location and number of monitoring points are determined, and corresponding sensors are deployed at each monitoring point to monitor water quality, water quantity, and water ecological data. The location and number of monitoring points must cover the entire monitoring area and represent the water quality, water quantity, and water ecological status of the entire water body. Among them, the sensors include pH sensors, dissolved oxygen sensors, flow meters, water level meters, and algae sensors; Use the deployed sensors to monitor and record water quality, water quantity and water ecological data, and convert the monitored data into electrical signals and transmit them to the data acquisition system, which are then stored in the data warehouse. For water quality index data, use pH sensors to measure the pH of water bodies at monitoring points to reflect the chemical properties of water bodies and measure the impact of water pH on aquatic organisms and human health. Use dissolved oxygen sensors to measure the oxygen content in water to evaluate the self-purification capacity of water bodies and the health of ecosystems. For water quantity index data, use flow meters to collect the flow of water bodies at monitoring points to reflect the flow of water bodies. Use water level meters to measure the water level to reflect the water storage capacity of water bodies. For water ecological indicators, use on-site algae sensors to measure the density of algae in the water to reflect the nutritional status and ecological health of water bodies. Regularly analyze the content of suspended matter and organic matter in water bodies to measure water transparency and evaluate water ecological conditions. Preprocessing of the collected multi-indicator water volume data includes data cleaning and data standardization steps, where data cleaning is used to remove outliers and noise, thresholds are set to exclude data points outside the normal range, data standardization is used to convert data of different dimensions and magnitudes into a unified format for comparison and analysis, data from different sensors are integrated to obtain more comprehensive monitoring results, and data synchronization is performed to make the timestamps of different monitoring points and different types of data consistent for subsequent analysis; Store the preprocessed data in a data warehouse to ensure data security and traceability, and set up a data backup and recovery mechanism to prevent data loss or damage.

[0006] Preferably, in the water quantity system analysis module, the process of water quality and water quantity index trend analysis includes: Using time series analysis methods, draw time series graphs of water quality parameters to observe their changing trends over time, and obtain water quality change assessment indexes by calculating the mean and standard deviation statistical indicators of water quality parameters to assess the stability and fluctuation of water quality. Combined with spatial analysis methods, draw water quality distribution maps to clarify the water quality characteristics and differences in different regions; Analyze the time series changes of water volume data such as precipitation, evaporation, and groundwater level, draw time series graphs, and use the periodic decomposition method to decompose the water volume data into three parts: trend, seasonality, and random fluctuations. Analyze them separately, and combine meteorological data and geographic information to calculate the water volume change assessment index to clarify the impact of natural factors such as precipitation and evaporation on water volume.

[0007] Preferably, the calculation expression of the water quality change assessment index is: ; in, is the water quality change assessment index, For in time Water quality parameter values ​​(such as dissolved oxygen, pH value, turbidity, etc.), is the mean value of water quality parameters at all observation time points, reflecting the average level of water quality parameters. is the standard deviation of water quality parameters, reflecting the fluctuation of water quality parameters. is the minimum value of the water quality parameter at all observation time points, α is the mean weight parameter, which is used to adjust the impact of the mean in the evaluation index, and β is the standard deviation weight parameter, which is used to adjust the impact of the standard deviation in the evaluation index. The value range of is between 0 and 1; The calculation expression of the water volume change evaluation index is: ; in, is the water volume change assessment index, is the variance of water volume data changing over time, is the variance of water volume data changing with seasonal periodicity, is the variance of the overall change in water volume data, including all components (trend, seasonality, and random fluctuations), ∈ is a small positive number, approaching zero, to avoid the situation where the denominator is zero, To adjust the weight parameters for trend and seasonal effects, is the evaporation amount, is the precipitation, To adjust the weight parameters of the relative impact of evaporation and precipitation, The value range is between 0 and 1.

[0008] Preferably, in the water quantity system analysis module, the process of water ecological index trend analysis includes: Analyze the time series changes of water ecological indicators such as biodiversity and eutrophication of water bodies, use statistical methods and data mining technology to analyze the correlation between water ecological indicators and water quality and water quantity indicators, and combine field surveys and remote sensing technology to calculate water ecological assessment indexes to assess the health status and change trends of water ecosystems; The statistical analysis method of Pearson correlation coefficient was used to calculate the correlation between water quality, water quantity and water ecological indicators, and a scatter plot was drawn to show the correlation and trend between the indicators.

[0009] Preferably, the calculation expression of the water ecological assessment index is: ; in, is the water ecological assessment index, For in time Biodiversity index (Shannon-Wiener index, Simpson index, etc.), is the mean value of the biodiversity index at all observation time points, It is the water eutrophication index, indicating the current water eutrophication level (Chl-a concentration, TP concentration, TLI index, etc.). and is the minimum and maximum value of the water eutrophication index. is the mean value of water quality parameters at all observation time points, reflecting the average level of water quality parameters. is the standard deviation of water quality parameters, reflecting the fluctuation of water quality parameters. and is a weight parameter used to adjust the impact of biodiversity, water eutrophication, and water quality fluctuations in the assessment index. is a positive number, close to zero, used to avoid the situation where the denominator is zero. The value range is between 0 and 1.

[0010] Preferably, in the collaborative monitoring module, the process of collaborative monitoring of the multi-indicator water volume system includes: Integrate the pre-processed data of each monitoring point into the collaborative monitoring module through a unified data interface to ensure real-time update and synchronization of data, set the frequency and mechanism of data update, update the data of each monitoring point to the collaborative monitoring module regularly, and perform quality inspection and verification on the integrated data to ensure the accuracy and completeness of the data; Combined with the analysis results of the correlation and mutual influence between the indicators, a multi-indicator correlation model is established to describe the internal relationship and change law between the indicators; Based on the multi-indicator correlation model, a collaborative monitoring algorithm is designed to process and analyze the integrated data to obtain the collaborative monitoring results of the multi-indicator water quantity system. The monitoring results include the real-time monitoring values ​​and change trends of each indicator. The collaborative monitoring results are compared and verified with the actual situation to evaluate the accuracy of the model, and then the collaborative monitoring algorithm is optimized and improved based on the verification results to improve the performance of the model.

[0011] Preferably, in the emergency warning module, the comprehensive analysis process of abnormal situations includes: Receive the results from the water quantity system analysis module and the collaborative monitoring module, obtain comprehensive analysis data on water quality, water quantity and water ecological indicators, clarify the abnormal judgment results of each indicator of water quality, water quantity and water ecology, and parse and process the received data to ensure the accuracy and completeness of the data, and mark the abnormal judgment results of each indicator for subsequent analysis; According to the water quality change assessment index, water quantity change assessment index and water ecology assessment index, calculate the abnormal warning coefficient and comprehensively analyze the overall abnormality of water quality, water quantity and water ecology indicators; According to historical data, analyze the distribution characteristics of each evaluation index and abnormal warning coefficient, set the corresponding warning threshold based on the abnormal warning coefficient, and judge whether the abnormal warning coefficient reaches the condition of triggering the alarm; The calculated abnormal warning coefficient is compared with the set warning threshold. If the abnormal warning coefficient exceeds the warning threshold, , it is judged as an abnormal situation, triggering an alarm and generating alarm information. The alarm information includes abnormal indicators, abnormal degree, abnormal location and time information. The generated alarm information will be notified to relevant departments and personnel via SMS, email or phone.

[0012] Preferably, the calculation process of the abnormal warning coefficient is: Extract the water quality change assessment index, water quantity change assessment index and water ecology assessment index, calculate the normalized value of each assessment index, and calculate the square of each normalized value. According to the calculation results of the normalized values ​​of each assessment index, analyze the normalized value square of each assessment index, add the normalized value square of each assessment index to obtain the normalized value square sum, and perform square root calculation on the obtained normalized value square sum to obtain the abnormal warning coefficient; The calculation expression of the abnormal warning coefficient is: ; Among them, А is the abnormal warning coefficient, which comprehensively reflects the overall abnormality of water quality, water quantity and water ecological indicators. It is a water quality change assessment index, indicating the degree of abnormality of water quality. It is the water volume change assessment index, indicating the abnormal degree of water volume conditions. It is the water ecology assessment index, which indicates the abnormality of water ecology. The larger the value, the more serious the abnormality of water ecology. is a positive number, close to zero, used to avoid the situation where the denominator is zero. The value range of А ​​is between 0 and 1. , it is judged as an abnormal situation.

[0013] Preferably, in the early warning scheme module, the process of formulating the early warning scheme includes: From the information of the water quantity system analysis module and the emergency warning module, the water quantity system analysis module provides detailed analysis results of water quality, water quantity and water ecological indicators, and the emergency warning module provides abnormal warning coefficients and whether to trigger an alarm. The received information is integrated to form a comprehensive understanding of the abnormal situation, including the specific values ​​of the abnormal indicators, the degree of abnormality, the abnormal location, the time information and the cause analysis; Based on the integrated information, conduct a preliminary assessment of the abnormal situation, determine the severity, urgency and impact of the abnormal situation, and then conduct a detailed risk assessment of the abnormal situation; Based on the results of abnormal situation assessment and risk assessment, formulate corresponding early warning plans, clarify the goals, scope, measures and responsible persons of the early warning, and start the implementation procedures after the early warning plan is formulated.

[0014] The present invention provides an AI intelligent collaborative monitoring and management system for a multi-index water volume system. It has the following beneficial effects: 1. This AI intelligent collaborative monitoring and management system for multi-indicator water quantity systems identifies abnormal changes in water quality, water quantity, and water ecological indicators through anomaly detection, and triggers an early warning mechanism based on detected anomalies. It sends early warning information to managers through a visual interface, text messages, and emails, greatly shortening the time interval from the occurrence of anomalies to their discovery, providing managers with valuable response time, thereby effectively curbing the further deterioration of abnormal situations and ensuring the safety and sustainable use of water resources.

[0015] 2. This AI intelligent collaborative monitoring and management system for multi-indicator water volume system can instantly capture subtle changes in water quality parameters, dynamic fluctuations in water volume, and abnormal trends in ecological indicators through real-time monitoring of key indicators of water quality, water volume, and water ecology. It can also reveal the intrinsic connections and changing patterns among water quality, water volume, and water ecology through in-depth mining and cross-validation of multi-source data, and provide managers with a comprehensive water health status analysis report. Compared with traditional manual judgment, it is more objective, accurate, and efficient, and helps managers make more precise decisions in complex and changeable water volume systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a module diagram of an AI intelligent collaborative monitoring and management system for a multi-indicator water quantity system according to the present invention; Figure 2 The flowchart of the trend analysis of water quality, water quantity and water ecological indicators of the present invention; Figure 3 It is a comprehensive analysis flow chart of abnormal situations of the present invention. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0018] The first embodiment, as Figure 1 , Figure 2 As shown, the present invention provides a technical solution: an AI intelligent collaborative monitoring and management system for a multi-indicator water quantity system, the collaborative monitoring and management system includes a data acquisition module, a water quantity system analysis module, a collaborative monitoring module, an emergency warning module, a warning scheme module and a data visualization module, wherein the modules are connected by electrical signals; The data acquisition module is used to collect multi-index water volume data from various monitoring points in real time, including water quality, water volume and water ecological data, to achieve comprehensive monitoring of water resources, ensure the comprehensiveness and real-time nature of the data, and provide a basis for subsequent data processing and analysis. It also pre-processes the collected multi-index water volume data to improve the accuracy and reliability of the data and reduce the possibility of data conflicts. According to the topography, water flow characteristics and pollution source distribution factors of the monitoring area, the location and number of monitoring points are determined, and corresponding sensors are deployed at each monitoring point to monitor water quality, water volume and water ecological data. The location and quantity need to cover the entire monitoring area and represent the water quality, water quantity and water ecological status of the entire water body. The sensors include pH sensors, dissolved oxygen sensors, flow meters, water level meters, and algae sensors. The deployed sensors are used to monitor and record water quality, water quantity and water ecological data, and the monitored data are converted into electrical signals and transmitted to the data acquisition system, which are then stored in the data warehouse. For water quality index data, pH sensors are used to measure the pH of the water body at the monitoring point to reflect the chemical properties of the water body and measure the impact of the pH of the water body on aquatic organisms and human health. The dissolved oxygen sensor measures the oxygen content in the water to evaluate the self-purification capacity of the water body and the health of the ecosystem. For water quantity index data, a flow meter is used to collect the flow of the water body at the monitoring point to reflect the flow of the water body. A water level meter is used to measure the water level of the water body to reflect the water storage capacity of the water body. For water ecological indicators, an on-site algae sensor is used to measure the density of algae in the water to reflect the nutrient status and ecological health of the water body. The suspended solids and organic matter content in the water body are regularly analyzed to measure the transparency of the water body and evaluate the water ecological status. The collected multi-indicator water quantity data is preprocessed, including data cleaning and data standardization steps, in which outliers and noise are removed by data cleaning, data points outside the normal range are excluded by setting thresholds, and data standardization is used to convert data of different dimensions and magnitudes into a unified format for comparison and analysis. Data from different sensors are integrated to obtain more comprehensive monitoring results, and data synchronization is performed to make the timestamps of different monitoring points and different types of data consistent for subsequent analysis. The preprocessed data is stored in the data warehouse to ensure the security and traceability of the data, and a data backup and recovery mechanism is set to prevent data loss or damage. The water quantity system analysis module analyzes the pre-processed multi-index water quantity data, performs trend analysis on water quality, water quantity and water ecological indicators, and finds the correlation and mutual influence between the indicator data. The process of water quality and water quantity indicator trend analysis includes: Using the time series analysis method, draw the time series graph of water quality parameters, observe its changing trend over time, and obtain the water quality change assessment index by calculating the mean and standard deviation statistical indicators of water quality parameters, evaluate the stability and fluctuation of water quality, and draw the water quality distribution map in combination with the spatial analysis method to clarify the water quality characteristics and differences in different regions, analyze the time series changes of water volume data such as precipitation, evaporation, and groundwater level, draw the time series graph, and use the periodic decomposition method to decompose the water volume data into three parts: trend, seasonality, and random fluctuation, analyze them separately, and calculate the water volume change assessment index in combination with meteorological data and geographic information to clarify the impact of natural factors such as precipitation and evaporation on water volume; Furthermore, the calculation expression of the water quality change assessment index is: ; in, is the water quality change assessment index, For in time Water quality parameter values ​​(such as dissolved oxygen, pH value, turbidity, etc.), is the mean value of water quality parameters at all observation time points, reflecting the average level of water quality parameters. is the standard deviation of water quality parameters, reflecting the fluctuation of water quality parameters. is the minimum value of the water quality parameter at all observation time points, α is the mean weight parameter, which is used to adjust the impact of the mean in the evaluation index, and β is the standard deviation weight parameter, which is used to adjust the impact of the standard deviation in the evaluation index. The value range of is between 0 and 1, when the water quality parameter is very stable and close to the mean; is close to 1, and when the water quality parameters fluctuate greatly or deviate far from the mean, will be close to 0, when the mean When the water quality parameter level increases (i.e. the average level increases), if other conditions remain unchanged, will tend to increase because the effect of the mean term is weakened. When it increases (i.e. the fluctuation of water quality parameters increases), will tend to decrease because the influence of the standard deviation term is enhanced, when the minimum When the water quality parameter decreases (i.e. the water quality parameter reaches an extremely low value at a certain point in time), will also tend to decrease because the influence of the minimum term is enhanced; The calculation expression of water volume change assessment index is: ; in, is the water volume change assessment index, is the variance of water volume data changing over time, is the variance of water volume data changing with seasonal periodicity, is the variance of the overall change in water volume data, including all components (trend, seasonality, and random fluctuations), ∈ is a positive number, approaching zero, to avoid the situation where the denominator is zero, To adjust the weight parameters for trend and seasonal effects, is the evaporation amount, is the precipitation, To adjust the weight parameters of the relative impact of evaporation and precipitation, The value range is between 0 and 1. When the trend and seasonal variance increase (i.e. the water volume data changes more significantly over time), will tend to decrease, meaning that the amount of water is more unstable. When evaporation increases relative to precipitation (i.e., evaporation is stronger), will also tend to decrease, since an increase in evaporation will generally result in a decrease in the amount of water; The process of water ecological indicator trend analysis includes: Analyze the time series changes of water ecological indicators such as biodiversity and eutrophication of water bodies. Use statistical methods and data mining technology to analyze the correlation between water ecological indicators and water quality and water quantity indicators. Combine field surveys and remote sensing technology to calculate the water ecological assessment index to assess the health status and change trend of the water ecosystem. Use the statistical analysis method of the Pearson correlation coefficient to calculate the correlation between water quality, water quantity and water ecological indicators, and draw a scatter plot to show the correlation and trend between the indicators. Furthermore, the calculation expression of the water ecological assessment index is: ; in, is the water ecological assessment index, For in time Biodiversity index (Shannon-Wiener index, Simpson index, etc.), is the mean value of the biodiversity index at all observation time points, It is the water eutrophication index, indicating the current water eutrophication level (Chl-a concentration, TP concentration, TLI index, etc.). and is the minimum and maximum value of the water eutrophication index. is the standard deviation of water quality parameters, reflecting the fluctuation of water quality parameters. and is a weight parameter used to adjust the impact of biodiversity, water eutrophication, and water quality fluctuations in the assessment index. is a positive number, close to zero, used to avoid the situation where the denominator is zero. The value range is between 0 and 1. When it decreases (i.e. biodiversity decreases), Will tend to decrease when the eutrophication index When it increases (i.e. the eutrophication of water bodies increases), will also tend to decrease when the standard deviation of the water quality parameter When it increases (i.e. water quality fluctuation increases), The same will tend to decrease; The collaborative monitoring module is used to integrate the data of each monitoring point, realize the collaborative monitoring of the multi-indicator water system, weaken the interference between the multi-indicator data, and improve the accuracy and stability of monitoring. The pre-processed data of each monitoring point is integrated into the collaborative monitoring module through a unified data interface to ensure the real-time update and synchronization of the data, and set the frequency and mechanism of data update. The data of each monitoring point is updated to the collaborative monitoring module regularly, and the integrated data is quality checked and verified to ensure the accuracy and completeness of the data. Combined with the analysis results of the correlation and mutual influence between the indicators, a multi-indicator correlation model is established to describe the internal relationship and change law between the indicators. Based on the multi-indicator correlation model, a collaborative monitoring algorithm is designed to process and analyze the integrated data to obtain the collaborative monitoring results of the multi-indicator water system. The monitoring results include the real-time monitoring values ​​and change trends of each indicator. The collaborative monitoring results are compared and verified with the actual situation to evaluate the accuracy of the model, and then the collaborative monitoring algorithm is optimized and improved according to the verification results to improve the performance of the model. The emergency warning module comprehensively analyzes the abnormal conditions of water quality, water quantity and water ecological indicators based on the results of the water quantity system analysis module, sets warning thresholds, and triggers alarms for abnormal conditions; The early warning plan module formulates corresponding early warning plans for the identified abnormal situations based on the results of the data analysis module and the information of the emergency warning module; The data visualization module is used to display abnormal situations and early warning plans in the form of charts to facilitate user understanding and analysis, improve the readability and ease of use of data, and help users better grasp the changing trends of the water volume system. The data acquisition module is the data source of the system and provides basic data for other modules. The water volume system analysis module conducts in-depth analysis of the collected data to provide a basis for collaborative monitoring and emergency warning. The collaborative monitoring module integrates and analyzes multi-indicator data to improve the accuracy and stability of monitoring. The emergency warning module sets the warning threshold according to the analysis results and triggers the alarm. The early warning plan module formulates response measures based on the warning information to ensure that the problem is resolved in a timely manner. The data visualization module displays the analysis results and early warning plans to users in an intuitive way to facilitate user decision-making. Through the collaborative work of various modules, comprehensive monitoring and management of the multi-indicator water volume system can be achieved, and the utilization efficiency and management level of water resources can be improved.

[0019] The second embodiment is based on the first embodiment. Figure 3 As shown in the figure, in the emergency warning module, the comprehensive analysis process of abnormal situations includes: Receive the results from the water quantity system analysis module and the collaborative monitoring module, obtain comprehensive analysis data on water quality, water quantity and water ecological indicators, clarify the abnormal judgment results of each indicator of water quality, water quantity and water ecology, and parse and process the received data to ensure the accuracy and completeness of the data, mark the abnormal judgment results of each indicator for subsequent analysis, calculate the abnormal warning coefficient according to the water quality change assessment index, water quantity change assessment index and water ecology assessment index, comprehensively analyze the overall abnormality of water quality, water quantity and water ecological indicators, analyze the distribution characteristics of each assessment index and abnormal warning coefficient according to historical data, set the corresponding warning threshold based on the abnormal warning coefficient, judge whether the abnormal warning coefficient meets the conditions for triggering an alarm, compare the calculated abnormal warning coefficient with the set warning threshold, and if the abnormal warning coefficient exceeds the warning threshold , it is judged as an abnormal situation, triggering an alarm and generating alarm information, which includes abnormal indicators, abnormal degree, abnormal location and time information. The generated alarm information is notified to relevant departments and personnel via SMS, email or phone; Furthermore, the calculation process of the abnormal warning coefficient is: Extract the water quality change assessment index, water quantity change assessment index and water ecology assessment index, calculate the normalized value of each assessment index, and calculate the square of each normalized value. According to the calculation results of the normalized values ​​of each assessment index, analyze the normalized value square of each assessment index, add the normalized value square of each assessment index to obtain the normalized value square sum, and perform square root calculation on the obtained normalized value square sum to obtain the abnormal warning coefficient; The calculation expression of abnormal warning coefficient is: ; Among them, А is the abnormal warning coefficient, which comprehensively reflects the overall abnormality of water quality, water quantity and water ecological indicators. It is a water quality change assessment index, indicating the degree of abnormality of water quality. The larger the value, the more serious the abnormality of water quality. It is the water volume change assessment index, which indicates the abnormality of water volume. The larger the value, the more serious the abnormality. It is the water ecology assessment index, which indicates the abnormality of water ecology. The larger the value, the more serious the abnormality of water ecology. is a positive number, close to zero, used to avoid the situation where the denominator is zero. The value range of А ​​is between 0 and 1. , or When any value in increases, the contribution of the corresponding part in the formula will also increase, resulting in an increase in the abnormal warning coefficient А. When the error occurs, it is judged as an abnormal situation; In the early warning plan module, the early warning plan formulation process includes: From the information of the water quantity system analysis module and the emergency warning module, the water quantity system analysis module provides detailed analysis results of water quality, water quantity and water ecological indicators, and the emergency warning module provides abnormal warning coefficients and instructions on whether to trigger an alarm. The received information is integrated to form a comprehensive understanding of the abnormal situation, including the specific values ​​of the abnormal indicators, the degree of abnormality, the abnormal location, time information and cause analysis. Based on the integrated information, a preliminary assessment of the abnormal situation is made to determine the severity, urgency and scope of impact of the abnormality, and then a detailed risk assessment of the abnormal situation is made. Through severity judgment, it is analyzed whether the abnormality has caused a significant impact on water quality, water quantity and water ecology, and whether the impact is likely to continue or intensify. Through urgency judgment, it is evaluated whether the abnormality requires immediate action to avoid or reduce potential hazards. Through impact scope judgment, it is determined that the areas, people or systems that the abnormality may affect, and whether such impact may spread or cause other problems. According to the results of abnormal situation assessment and risk assessment, a corresponding early warning plan is formulated to clarify the goals, scope, measures and responsible persons of the early warning, and after the early warning plan is formulated, the implementation procedure is initiated.

[0020] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. An AI intelligent collaborative monitoring and management system for a multi-index water quantity system, characterized in that: The collaborative monitoring and management system includes a data acquisition module, a water volume system analysis module, a collaborative monitoring module, an emergency warning module, a warning scheme module and a data visualization module, wherein the modules are connected by electrical signals; The data acquisition module is used to collect multi-indicator water volume data from each monitoring point in real time; The water quantity system analysis module analyzes the pre-processed multi-index water quantity data and performs trend analysis on water quality, water quantity and water ecological indicators respectively; The collaborative monitoring module is used to integrate the data of each monitoring point to achieve collaborative monitoring of the multi-indicator water volume system; The emergency warning module comprehensively analyzes the abnormal conditions of water quality, water quantity and water ecological indicators according to the results of the water quantity system analysis module, and sets warning thresholds to trigger alarms for abnormal conditions; The early warning scheme module formulates a corresponding early warning scheme for the identified abnormal situation; The data visualization module is used to display abnormal situations and early warning plans in the form of charts.

2. The AI ​​intelligent collaborative monitoring and management system for a multi-index water quantity system according to claim 1 is characterized in that: In the data collection module, the process of collecting multi-index water volume data includes: Determine the location and number of monitoring points based on the topography, water flow characteristics, and pollution source distribution factors of the monitoring area, and deploy corresponding sensors at each monitoring point to monitor water quality, water quantity, and water ecological data. The sensors include pH sensors, dissolved oxygen sensors, flow meters, water level meters, and algae sensors. Use the deployed sensors to monitor and record water quality, water quantity and water ecology data, and convert the monitored data into electrical signals and transmit them to the data acquisition system, which is then stored in the data warehouse; Preprocess the collected multi-indicator water volume data, including data cleaning and data standardization steps, and synchronize the data to make the timestamps of different monitoring points and different types of data consistent for subsequent analysis; Store the preprocessed data in the data warehouse and set up data backup and recovery mechanisms.

3. The AI ​​intelligent collaborative monitoring and management system for a multi-index water quantity system according to claim 2 is characterized in that: In the water quantity system analysis module, the process of water quality and water quantity index trend analysis includes: Using time series analysis methods, draw time series graphs of water quality parameters to observe their changing trends over time, and obtain water quality change assessment indexes by calculating the mean and standard deviation statistical indicators of water quality parameters to assess the stability and fluctuation of water quality. Combined with spatial analysis methods, draw water quality distribution maps to clarify the water quality characteristics and differences in different regions; Analyze the time series changes of water volume data such as precipitation, evaporation, and groundwater level, draw time series graphs, and use the periodic decomposition method to decompose the water volume data into three parts: trend, seasonality, and random fluctuations. Analyze them separately, and combine meteorological data and geographic information to calculate the water volume change assessment index to clarify the impact of natural factors such as precipitation and evaporation on water volume.

4. The AI ​​intelligent collaborative monitoring and management system for a multi-index water quantity system according to claim 3 is characterized in that: The calculation expression of the water quality change assessment index is: ； in, is the water quality change assessment index, For in time The water quality parameter values, is the mean value of water quality parameters at all observation time points, is the standard deviation of water quality parameters, is the minimum value of the water quality parameter at all observation time points, α is the mean weight parameter, and β is the standard deviation weight parameter, which is used to adjust the impact of the standard deviation in the evaluation index. The value range of is between 0 and 1; The calculation expression of the water volume change evaluation index is: ； in, is the water volume change assessment index, is the variance of water volume data changing over time, is the variance of water volume data changing with seasonal periodicity, is the variance of the overall change of water volume data, including all components, ∈ is a positive number to avoid the situation where the denominator is zero, To adjust the weight parameters for trend and seasonal effects, is the evaporation amount, is the precipitation, To adjust the weight parameters of the relative impact of evaporation and precipitation, The value range is between 0 and 1.

5. The AI ​​intelligent collaborative monitoring and management system for a multi-index water quantity system according to claim 4 is characterized in that: In the water quantity system analysis module, the process of water ecological index trend analysis includes: Analyze the time series changes of water ecological indicators such as biodiversity and eutrophication of water bodies, use statistical methods and data mining technology to analyze the correlation between water ecological indicators and water quality and water quantity indicators, and combine field surveys and remote sensing technology to calculate water ecological assessment indexes to assess the health status and change trends of water ecosystems; The statistical analysis method of Pearson correlation coefficient was used to calculate the correlation between water quality, water quantity and water ecological indicators, and a scatter plot was drawn to show the correlation and trend between the indicators.

6. The AI ​​intelligent collaborative monitoring and management system for a multi-index water quantity system according to claim 5 is characterized in that: The calculation expression of the water ecological assessment index is: ； in, is the water ecological assessment index, For in time The biodiversity index, is the mean value of the biodiversity index at all observation time points, is the water eutrophication index, indicating the current eutrophication level of the water body. and is the minimum and maximum value of the water eutrophication index. is the mean value of water quality parameters at all observation time points, is the standard deviation of water quality parameters, and is a weight parameter used to adjust the impact of biodiversity, water eutrophication, and water quality fluctuations in the assessment index. is a positive number to avoid the denominator being zero. The value range is between 0 and 1.

7. The AI ​​intelligent collaborative monitoring and management system for a multi-index water quantity system according to claim 6 is characterized in that: In the collaborative monitoring module, the process of collaborative monitoring of the multi-indicator water volume system includes: Integrate the pre-processed data of each monitoring point into the collaborative monitoring module through a unified data interface, set the frequency and mechanism of data update, update the data of each monitoring point to the collaborative monitoring module regularly, and perform quality inspection and verification on the integrated data; Combined with the analysis results of the correlation and mutual influence between the indicators, a multi-indicator correlation model is established to describe the internal relationship and change law between the indicators; Based on the multi-indicator correlation model, a collaborative monitoring algorithm is designed to process and analyze the integrated data to obtain the collaborative monitoring results of the multi-indicator water quantity system. The monitoring results include the real-time monitoring values ​​and change trends of each indicator. The collaborative monitoring results are compared and verified with the actual situation, the accuracy of the model is evaluated, and the collaborative monitoring algorithm is optimized and improved based on the verification results.

8. The AI ​​intelligent collaborative monitoring and management system for a multi-index water quantity system according to claim 7 is characterized in that: In the emergency warning module, the comprehensive analysis process of abnormal situations includes: Receive the results from the water quantity system analysis module and the collaborative monitoring module, obtain comprehensive analysis data on water quality, water quantity and water ecological indicators, clarify the abnormal judgment results of each indicator of water quality, water quantity and water ecology, and parse and process the received data, marking the abnormal judgment results of each indicator; According to the water quality change assessment index, water quantity change assessment index and water ecology assessment index, calculate the abnormal warning coefficient and comprehensively analyze the overall abnormality of water quality, water quantity and water ecology indicators; According to historical data, analyze the distribution characteristics of each evaluation index and abnormal warning coefficient, set the corresponding warning threshold based on the abnormal warning coefficient, and judge whether the abnormal warning coefficient reaches the condition of triggering the alarm; The calculated abnormal warning coefficient is compared with the set warning threshold. If the abnormal warning coefficient exceeds the warning threshold, , it is judged as an abnormal situation, triggering an alarm and generating alarm information.

9. The AI ​​intelligent collaborative monitoring and management system for a multi-index water quantity system according to claim 8, characterized in that: The calculation process of the abnormal warning coefficient is: Extract the water quality change assessment index, water quantity change assessment index and water ecology assessment index, calculate the normalized value of each assessment index, and calculate the square of each normalized value. According to the calculation results of the normalized values ​​of each assessment index, analyze the normalized value square of each assessment index, add the normalized value square of each assessment index to obtain the normalized value square sum, and perform square root calculation on the obtained normalized value square sum to obtain the abnormal warning coefficient; The calculation expression of the abnormal warning coefficient is: ； Among them, А is the abnormal warning coefficient, is the water quality change assessment index, is the water volume change assessment index, is the water ecological assessment index, is a positive number used to avoid the denominator being zero. The value range of А ​​is between 0 and 1. , it is judged as an abnormal situation.

10. The AI ​​intelligent collaborative monitoring and management system for a multi-index water volume system according to claim 9, characterized in that: In the early warning plan module, the process of formulating the early warning plan includes: From the information of the water quantity system analysis module and the emergency warning module, the water quantity system analysis module provides the analysis results of water quality, water quantity and water ecological indicators, and the emergency warning module provides the abnormal warning coefficient and whether to trigger the alarm. The received information is integrated to form a comprehensive understanding of the abnormal situation; Based on the integrated information, conduct a preliminary assessment of the abnormal situation, determine the severity, urgency and impact of the abnormal situation, and then conduct a detailed risk assessment of the abnormal situation; Based on the results of abnormal situation assessment and risk assessment, formulate corresponding early warning plans, clarify the goals, scope, measures and responsible persons of the early warning, and start the implementation procedures after the early warning plan is formulated.

Images