Yunyuan Intelligent Water Conservancy Project Standardized Management Platform
Through the Yunyuan Intelligent Management Water Conservancy Project Standardized Management Platform, the data collection, prediction and early warning and water conservancy scheduling modules are used to solve the problem of insufficient adaptability of traditional water conservancy project management in extreme weather, improve the accuracy of water resource prediction and scheduling, and reduce the number of times the accuracy of water resource prediction and scheduling. Disaster losses and more reasonable water allocation was achieved.
Patent Information
- Application Number
- CN202411282317.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-13
AI Technical Summary
Traditional water conservancy engineering management technology has limitations in terms of accuracy and flexibility, making it difficult to quickly adapt to extreme weather or emergencies, resulting in low resource allocation efficiency and accuracy, and the inability to adjust the reservoir water release strategy in time, resulting in damage to flood control capabilities and water resource allocation. unreasonable.
Provide a standardized management platform for Yunyuan Intelligent Management Water Conservancy Engineering. It collects real-time meteorological data through the data collection module, predicts and early warning modules for flood control and early warning analysis, the water conservancy dispatch module calculates the water volume predicted by the reservoir, and monitors the ecological health status of the water area through the environmental assessment module to identify Pollution source, build a water level prediction model for river basin, and generate a flood control scheduling plan.
It improves the accuracy of water resource prediction, judges dangerous areas, generates reasonable water conservancy scheduling plans, early warning of natural disasters, reduces disaster losses, and achieves more reasonable and efficient water resource allocation, ensuring water safety.
Smart Images

Figure CN118822469B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of water conservancy project management, and in particular to a cloud source intelligent water conservancy project standardized management platform. Background Art
[0002] With the rapid development of information technology, more and more water conservancy information infrastructure and application systems are being applied to water conservancy project construction and management, water administrative business handling, and water conservancy project management technology. The field of water conservancy project management technology involves planning, design, implementation, monitoring and maintenance of various engineering projects related to water resources, including but not limited to reservoirs, dams, irrigation systems, water treatment facilities and flood control measures. The core goal is to optimize the utilization and management of water resources, ensure water safety, and enhance disaster management capabilities, while considering environmental protection and socio-economic development needs. With technological progress, this field has gradually integrated information technology and intelligent tools to improve the efficiency and effectiveness of project management. Among them, the water conservancy project management intelligent system is an advanced management tool that integrates data analysis, artificial intelligence and information technology. It aims to improve the planning, execution, monitoring and maintenance efficiency of water conservancy projects, optimize resource allocation through intelligent means, improve decision-making quality, reduce project risks, and enhance the sustainability and environmental compatibility of projects. Through the realization of goals, the system expects to achieve higher engineering efficiency, cost-effectiveness and positive impacts on the environment and society.
[0003] Traditional water conservancy project management technology has limitations in accuracy and flexibility, and it is difficult to quickly adapt to environmental changes or emergencies in extreme weather, which limits the efficiency and accuracy of resource allocation. For example, when encountering extreme weather events, traditional systems cannot adjust reservoir water release strategies in a timely manner, resulting in damage to flood control capabilities and even flood disasters. Traditional water conservancy management methods make it difficult to accurately grasp the real-time status of water resources, resulting in irrational water resource allocation. Sometimes there will be severe water shortages in some areas and waste of water resources in other places. Traditional monitoring methods rely on manual inspections, which is not only time-consuming and labor-intensive, but also prone to omissions or false alarms. When flood disasters occur, traditional water conservancy management systems often cannot respond quickly, resulting in increased losses. The maintenance of water conservancy projects requires a lot of manpower and material resources, and lacks effective maintenance plans and standard processes, resulting in high maintenance costs. Therefore, it is necessary to provide a cloud source intelligent management water conservancy project standardized management platform that can achieve accurate prediction of water resource changes under extreme weather and water conservancy scheduling optimization solutions. Summary of the invention
[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.
[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a cloud source intelligent management water conservancy project standardized management platform to solve the problem that traditional water conservancy project management technology has limitations in accuracy and flexibility and is difficult to quickly adapt to extreme weather environmental changes or emergencies.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0007] In a first aspect, the present invention provides a cloud source intelligent water conservancy project standardization management platform, including:
[0008] The data acquisition module is used to collect real-time meteorological data and historical meteorological data, perform trend analysis and forecast on the meteorological data, and determine whether the meteorological forecast result is extreme weather. If the meteorological forecast result is extreme weather, the forecast and warning module is used to perform flood prevention and warning analysis;
[0009] A prediction and warning module is used to perform the flood prevention and warning analysis on the water resources of each branch basin based on the meteorological prediction results of the data acquisition module, build a basin water level prediction model according to meteorological data, predict the water level changes of each basin, and obtain basin prediction results;
[0010] A water conservancy dispatching module is used to calculate the predicted water volume of the reservoir based on the basin prediction results of the prediction and early warning module, obtain the prediction results of the reservoir water resources change, and generate a water conservancy dispatching plan according to the prediction results;
[0011] The environmental assessment module is used to monitor the ecological health status of the water area based on the water conservancy scheduling plan, and if there is water pollution, the pollution source is identified and reported.
[0012] As a preferred solution of the Yunyuan Intelligent Water Conservancy Project Standardization Management Platform described in the present invention, the workflow of the data acquisition module includes:
[0013] Collect real-time meteorological data including air temperature, humidity, wind speed, air pressure, cloud cover and precipitation in the water resource area, and pre-process the meteorological data;
[0014] Constructing a meteorological prediction model to predict future regional precipitation, and using the historical meteorological data to train the model, and predicting precipitation in future time periods through the trained meteorological prediction model;
[0015] The weather forecast model is expressed as:
[0016] ;
[0017] in, is the predicted precipitation, Indicates the air temperature, Indicates air humidity, Indicates wind speed, Indicates air pressure, represents the cloud cover, represents the intercept term, Represents the adjustment coefficients respectively, represents the error term;
[0018] Determine whether the current weather is extreme based on weather forecast results.
[0019] As a preferred solution of the Yunyuan Intelligent Water Conservancy Project Standardization Management Platform described in the present invention, the workflow of the prediction and early warning module includes:
[0020] Based on extreme weather forecast results, emergency warnings are issued, control centers are notified, and flood prevention strategies are established;
[0021] Establish water area collections for each river basin in the region and establish flood control priorities for each river basin;
[0022] Setting marking points in the river section of each river basin, generating a marking point set of the river basin, and marking the marking points according to the actual geographical location, wherein the point marking includes adjacent position marking and upstream and downstream marking;
[0023] Based on meteorological data and watershed data, a watershed water level prediction model is constructed to obtain the highest water level prediction of the marked point, and the point marks of the marked point set are analyzed to divide the marked points into dangerous areas.
[0024] As a preferred solution of the Yunyuan Intelligent Water Conservancy Project Standardization Management Platform described in the present invention, the construction of the watershed water level prediction model includes:
[0025] Collect historical data and real-time data of the watershed, wherein the historical data of the watershed includes precipitation, water level, soil moisture, land cover type, terrain slope and temperature, and the real-time data of the watershed includes predicted precipitation and current water level, and perform data preprocessing and feature extraction;
[0026] The basin water level prediction model is constructed by combining the improved convolutional neural network and the long short-term memory network, which is expressed as:
[0027] ;
[0028] in, Description mark point The highest water level predicted at any given moment, represents the spatial eigenvector, represents the time series feature vector, Indicates the hidden state of the previous moment, represents a convolutional neural network, represents long short-term memory unit;
[0029] The watershed historical data is divided into a training set and a verification set to train and verify the watershed water level prediction model;
[0030] The input layer of the watershed water level prediction model receives spatial feature vectors and time series feature vectors. The spatial feature vectors include: terrain slope, land cover type, soil moisture, watershed area, and elevation of the marker point, which are combined into a two-dimensional matrix. The time series feature vectors include precipitation, temperature, wind speed, and humidity, and a sequence is constructed with data for each hour.
[0031] The CNN layer of the watershed water level prediction model processes spatial features, and the output of the CNN layer is flattened and converted into a one-dimensional vector through the Flatten layer;
[0032] The LSTM layer of the watershed water level prediction model processes time series features, merges the outputs of the CNN layer and the LSTM layer through the Concatenate layer, and predicts the highest water level of the marked point at a future moment through the fully connected layer.
[0033] As a preferred solution of the Yunyuan Intelligent Water Conservancy Project Standardization Management Platform of the present invention, the division of the marked points into dangerous areas includes:
[0034] Based on the prediction results of the highest water level of the marked points, combined with the point annotation information of the marked points, the dangerous areas of each basin are divided;
[0035] Set the water level warning threshold interval. If the highest water level of the marked point reaches the maximum value of the warning threshold, then combined with the water level values upstream and downstream of the marked point, if the highest water level of the marked point reaching the warning threshold has no downward trend, the marked point will be divided into a dangerous area; otherwise, if the highest water levels of the upstream and downstream marked points of the marked point are lower than the minimum value of the warning threshold, the marked point will not be divided into a dangerous area;
[0036] The division of hazardous areas is expressed as:
[0037] ;
[0038] in, Indicates the marked point The predicted maximum water level is represents the warning threshold interval, Indicates the set of upstream marked points adjacent to the marked point. Representing a collection The marking points in Indicates the set of downstream marking points adjacent to the marking point. Representing a collection The marking points in .
[0039] As a preferred solution of the Yunyuan Intelligent Water Conservancy Project Standardization Management Platform described in the present invention, the workflow of the water conservancy scheduling module includes:
[0040] The water resources in the dangerous areas of the basin are diverted to the reservoir according to the flood control priority, and the diversion rate is controlled by calculating the maximum water level and water flow;
[0041] According to the water source data of the dangerous area, the reservoir water volume in the future time period is predicted and the reservoir change trend is analyzed. The calculation formula of the reservoir water volume is expressed as:
[0042] ;
[0043] in, Indicates time The amount of water in the reservoir, Indicates the evaporation rate, is the reservoir inflow, represents the outflow of the reservoir, represents the average precipitation, Indicates a time interval;
[0044] The water quality in the reservoir is analyzed. When the water level of the predicted water volume in the reservoir is greater than the reservoir water level threshold, the water sources in the reservoir are classified and released according to the water quality analysis results to control the flow rate and time.
[0045] As a preferred solution of the Yunyuan Intelligent Water Conservancy Project Standardization Management Platform described in the present invention, the workflow of the environmental assessment module includes:
[0046] Through the analysis results of water quality, the health of the water area is monitored, and the presence of pollutants is analyzed, the composition of pollutants is analyzed, the pollution source is tracked, a pollution analysis report is generated, and reported to the management station;
[0047] Continuously monitor changes in reservoir water volume, water quality, and downstream demand, and adjust dispatch plans based on real-time monitoring results;
[0048] Regularly evaluate the effectiveness of the scheduling plan, including water utilization rate and water quality compliance rate indicators, and optimize the scheduling plan.
[0049] In a second aspect, the present invention provides a cloud source intelligent water conservancy project standardized management method, comprising:
[0050] Collect real-time and historical meteorological data, perform trend analysis and forecast on meteorological data, and determine whether the meteorological forecast result is extreme weather. If the meteorological forecast result is extreme weather, conduct flood prevention warning analysis through the forecast and warning module;
[0051] Based on the meteorological forecast results of the data acquisition module, the flood prevention warning analysis is performed on the water resources of each branch basin, and according to the meteorological data, a basin water level prediction model is constructed to predict the water level changes of each basin and obtain basin prediction results;
[0052] Based on the basin prediction results of the prediction and early warning module, the predicted water volume of the reservoir is calculated, the prediction results of the change of reservoir water resources are obtained, and a water conservancy dispatching plan is generated according to the prediction results;
[0053] Based on the water conservancy scheduling plan, the ecological health status of the water area is monitored. If water pollution exists, the pollution source is identified and reported.
[0054] In a third aspect, the present invention provides an electronic device, comprising:
[0055] Memory and processor;
[0056] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the module workflow of the Yunyuan Intelligent Water Conservancy Project Standardization Management Platform is implemented.
[0057] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the module workflow of the Yunyuan Intelligent Water Conservancy Project Standardization Management Platform.
[0058] Compared with the prior art, the present invention has the following beneficial effects: the present invention can obtain the water level change trend of each river basin through the collection and analysis of meteorological data, the marking and prediction of river basins, improve the accuracy of water resource prediction, identify dangerous areas, generate water conservancy scheduling plans, and continuously monitor the health of water areas, give early warning of natural disasters, and reduce the losses caused by disasters. The Yunyuan Intelligent Management Water Conservancy Project Standardization Management Platform can more accurately understand the distribution and utilization of water resources through real-time monitoring and data analysis, thereby achieving more reasonable and efficient water resource allocation; it can make predictions and intelligent analyses based on data to formulate the optimal water resource allocation plan to ensure that each water-using area receives a reasonable amount of water supply; through automated monitoring equipment, it can timely detect changes in water quality, take corresponding measures to protect water resources, and ensure water safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] 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 only 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 labor.
[0060] Figure 1 This is a schematic diagram of the structure of the Yunyuan Intelligent Water Conservancy Project Standardization Management Platform according to an embodiment of the present invention;
[0061] Figure 2 The figure is a schematic diagram of the overall process of the standardized management method of Yunyuan Intelligent Water Conservancy Project according to an embodiment of the present invention. DETAILED DESCRIPTION
[0062] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0063] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0064] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0065] Example 1, reference Figure 1-Figure 2 , is an embodiment of the present invention, which provides a cloud source intelligent water conservancy project standardization management platform, such as Figure 1 ,include:
[0066] The data acquisition module 101 is used to collect real-time meteorological data and historical meteorological data, perform trend analysis and forecast on the meteorological data, and determine whether the meteorological forecast result is extreme weather. If the meteorological forecast result is extreme weather, the forecast and warning module 102 performs flood prevention and warning analysis;
[0067] The forecasting and warning module 102 is used to perform flood prevention and warning analysis on the water resources of each branch basin based on the meteorological forecast results of the data acquisition module 101, build a basin water level forecasting model according to meteorological data, predict the water level changes of each basin, and obtain basin forecasting results;
[0068] The water conservancy dispatching module 103 is used to calculate the predicted water volume of the reservoir based on the basin prediction results of the prediction and early warning module 102, obtain the prediction results of the reservoir water resources change, and generate a water conservancy dispatching plan according to the prediction results;
[0069] The environmental assessment module 104 is used to monitor the ecological health status of the water area based on water quality analysis and water conservancy scheduling plans. If water pollution exists, the pollution source is identified and reported.
[0070] Preferably, the workflow of the data acquisition module 101 includes:
[0071] Collect meteorological data including air temperature, humidity, wind speed, air pressure, cloud coverage and precipitation in the water resource area, and pre-process the meteorological data. Various meteorological data can be collected through meteorological stations, satellite remote sensing, radar and other equipment. Data pre-processing includes cleaning and tidying up the original data, removing outliers and missing values, and ensuring data quality;
[0072] It should be noted that the temperature will affect the water vapor content in the air, and thus affect the possibility of precipitation. The higher the relative humidity in the air, the more likely it is to form precipitation. The wind can carry a large amount of water vapor, and the wind direction determines the source direction of the water vapor. Changes in the pressure gradient can indicate the movement of the weather system. Cloud coverage can directly affect the probability of precipitation.
[0073] Build a meteorological forecast model to predict future regional precipitation, use historical meteorological data to train the model, and use the trained meteorological forecast model to predict precipitation in future time periods;
[0074] The weather forecast model is expressed as:
[0075] ;
[0076] in, Indicates the predicted precipitation, in mm, Indicates air temperature in °C. Indicates air humidity, Indicates wind speed in m / s. Indicates air pressure in hPa. represents the cloud cover, represents the intercept term, Represents the adjustment coefficients respectively, represents the error term;
[0077] Determine whether the current weather is extreme based on weather forecast results.
[0078] Specifically, whether the current weather is extreme is as follows:
[0079] Setting precipitation thresholds through statistical analysis of historical data;
[0080] Compare the weather forecast results with the precipitation threshold to determine whether the future time period is extreme weather. If the precipitation in the future time period is greater than the precipitation threshold, it is determined that the current weather is extreme weather. The judgment formula is expressed as:
[0081] ;
[0082] in, Indicates extreme weather, Indicates the precipitation threshold. The precipitation threshold can be set according to the actual application scenario. Preferably, the precipitation threshold It is determined based on the climate characteristics and historical data of the region. In this embodiment, it is a statistical value obtained based on historical data analysis, which can be the maximum precipitation at the 95% or 99% quantile in the region over a period of time in the past.
[0083] Specifically, the coefficient The value of is determined by minimizing the prediction error, and these coefficients are estimated by minimizing the difference between the predicted value and the actual observed value, where the loss function is the mean squared error (MSE), which is expressed as:
[0084] ;
[0085] in, Indicates The actual precipitation observed, Expressing the The predicted value of an observation, Represents the total number of observations.
[0086] Specifically, the training process of the weather forecast model is as follows:
[0087] Collect a sufficient amount of historical meteorological data, including temperature, humidity, wind speed, air pressure, cloud cover and precipitation, clean the data, handle missing values and outliers, ensure data quality, construct the features required for the model, including linear terms and interaction terms, train the model using historical data, estimate the model coefficients by minimizing the mean square error (MSE), evaluate the performance of the model using methods such as cross-validation, ensure that the model has good generalization ability, and use the trained model to predict precipitation in future time periods.
[0088] It should be noted that through trend analysis of historical data, future weather conditions can be predicted more accurately. When the forecast results show extreme weather, the early warning mechanism can be activated immediately to buy time for action.
[0089] Preferably, the workflow of the prediction and warning module 102 includes:
[0090] Based on extreme weather forecast results, emergency warnings are issued, control centers are notified, and flood prevention strategies are established;
[0091] Establish water area collections for each river basin in the region and establish flood control priorities for each river basin;
[0092] Specifically, the basic geographic information of all river basins monitored in the region, including river basin boundaries, river network structure, and hydrological station locations, is collected through the Geographic Information System (GIS). Based on the collected data, all river basins are identified and marked. Based on the identified river basin information, a water area set is established. A flood control priority can be assigned to each river basin based on factors such as the population density of the river basin, the distribution of important facilities, and the frequency of historical flood events. Specifically, it is expressed as:
[0093] ;
[0094] in, represents the population density of the watershed. Indicates the number of important facilities, represents the average number of flood events per year in history, , , They are weight coefficients, which can be adjusted according to actual conditions;
[0095] Marking points are set in the river sections of each basin, a set of marking points of the basin is generated, and the marking points are marked according to the actual geographical location. The point marking includes the marking of adjacent positions and the marking of upstream and downstream positions.
[0096] Specifically, key positions are selected to set up marking points, the position coordinates of each marking point are recorded, a marking point set is established, and for each marking point, information such as the numbers of its adjacent marking points, upstream and downstream relationships, etc. are annotated.
[0097] Based on meteorological data and watershed data, a watershed water level prediction model is constructed to obtain the highest water level prediction of the marked points. The model is analyzed in combination with the point marks of the marked point set, and the marked points are divided into dangerous areas. Once the dangerous areas are identified, an alert is immediately issued to residents.
[0098] It should be noted that once the forecast results show the possibility of extreme weather, the platform will automatically trigger the early warning mechanism and notify the management personnel at the control desk to remind the staff to enter an emergency state.
[0099] Preferably, constructing a watershed water level prediction model includes:
[0100] Collect historical and real-time data of the watershed. The historical data of the watershed includes precipitation, water level, soil moisture, land cover type, terrain slope and temperature. The real-time data includes predicted precipitation and current water level, and perform data preprocessing and feature extraction.
[0101] The basin water level prediction model is constructed by combining the improved convolutional neural network and the long short-term memory network, which is expressed as:
[0102] ;
[0103] in, Description mark point The highest water level predicted at any given moment, represents the spatial eigenvector, represents the time series feature vector, Indicates the hidden state of the previous moment, represents a convolutional neural network, represents long short-term memory unit;
[0104] The basin water level prediction model is trained and verified by dividing the training set and verification set through the basin historical data;
[0105] The input layer of the watershed water level prediction model receives spatial feature vectors and time series feature vectors. The spatial feature vectors include terrain slope, land cover type, soil moisture, watershed area, and elevation of the marker points, which are combined into a two-dimensional matrix. The time series feature vectors include precipitation, temperature, wind speed, and humidity, and a sequence is constructed with hourly data.
[0106] The CNN layer of the watershed water level prediction model processes spatial features, and the output of the CNN layer is flattened and converted into a one-dimensional vector through the Flatten layer;
[0107] The LSTM layer of the basin water level prediction model processes time series features, merges the outputs of the CNN layer and the LSTM layer through the Concatenate layer, and predicts the highest water level at the marked point in the future through the fully connected layer.
[0108] Specifically, the input size of the CNN layer is a 5 × 5 matrix of spatial features for each marker point, where the number of convolutional layers is 2, the size of the first convolution kernel is 3 × 3, the size of the second convolution kernel is 3 × 3, the activation function is ReLU, the pooling layer is MaxPooling, the window size is 2 × 2, and after two convolutional layers and pooling layers, the output size is a 2 × 2 matrix. The input size of the LSTM layer is 5-dimensional for each time step, the number of hidden layers is 1, the number of hidden units is 64, the activation function is tanh, and Dropout is set to 0.2 to prevent overfitting. Other parameters are set, including a learning rate of 0.001, a batch size of 32, and a training round of 100.
[0109] Preferably, dividing the marking points into dangerous areas includes:
[0110] Based on the prediction results of the highest water level of the marked points, combined with the point annotation information of the marked points, the dangerous areas of each basin are divided;
[0111] Set the water level warning threshold interval. If the highest water level of the marked point reaches the maximum value of the warning threshold, and combined with the water level values upstream and downstream of the marked point, the highest water level of the marked point reaching the warning threshold has no downward trend, then the marked point will be divided into a dangerous area; otherwise, if the highest water levels of the upstream and downstream marked points of the marked point are lower than the minimum value of the warning threshold, the marked point will not be divided into a dangerous area;
[0112] If the highest water level of the marked point is less than the maximum value of the warning threshold, the marked point is not a dangerous area;
[0113] The division of hazardous areas is expressed as:
[0114] ;
[0115] in, Indicates the marked point The predicted maximum water level is Indicates the warning threshold range, which can be set according to actual conditions. Indicates the set of upstream marked points adjacent to the marked point. Representing a collection The marking points in Indicates the set of downstream marking points adjacent to the marking point. Representing a collection The marking points in .
[0116] It should be noted that this embodiment takes into account the influence of the upstream and downstream water levels. If the upstream and downstream water levels are low, even if the water level at the current marked point reaches or exceeds the warning value, the water level at the current marked point may drop due to the influence of the upstream and downstream water levels, so it will not necessarily be classified as a dangerous area. On the contrary, if the upstream and downstream water levels do not provide sufficient relief, even if the water level at the current marked point is slightly higher than the warning value, it will be classified as a dangerous area.
[0117] By analyzing the hydrological characteristics of each branch basin, the possibility and scale of floods can be predicted more accurately. By predicting the changes in water levels in each basin, human and material resources can be better arranged and response efficiency can be improved.
[0118] Preferably, the workflow of the water resources scheduling module 103 includes:
[0119] The water resources in the dangerous areas of the basin are diverted to the reservoir according to the flood control priority, and the diversion rate is controlled by calculating the maximum water level and water flow;
[0120] According to the water source data of the dangerous area, the reservoir water volume in the future time period is predicted and the reservoir change trend is analyzed. The calculation formula of the reservoir water volume is expressed as:
[0121] ;
[0122] in, Indicates time The amount of water in the reservoir, Indicates the evaporation rate, is the reservoir inflow, represents the outflow of the reservoir, represents the average precipitation, Indicates a time interval;
[0123] The water quality in the reservoir is analyzed. When the water level of the predicted water volume in the reservoir is greater than the reservoir water level threshold, the water sources in the reservoir are classified and released according to the water quality analysis results to control the flow rate and time.
[0124] Specifically, chemical and biological analyses are conducted on the water in the reservoir to define water quality standards for irrigation, drinking and other purposes. Water distribution is evaluated based on the results of water quality analysis and the needs of downstream users (such as farmland irrigation, urban water supply, etc.). Based on water quality, water quantity and downstream needs, a water scheduling plan is generated, and water sources in the reservoir are classified and released for purposes such as farmland irrigation and urban water supply. The flow rate and time are controlled during the release process.
[0125] It should be noted that the water conservancy scheduling module 103 can improve the flexibility of water resource scheduling, dynamically adjust the reservoir's water storage and release strategies according to the prediction results, ensure the effective use of water resources, and reduce property losses and casualties caused by floods through reasonable scheduling. The reservoir can ensure that there is sufficient water supply in the dry season to meet agricultural irrigation and domestic water needs.
[0126] Preferably, the workflow of the environmental assessment module 104 includes:
[0127] Through the analysis results of water quality, the health of the water area is monitored, and the presence of pollutants is analyzed, the composition of pollutants is analyzed, the pollution source is tracked, a pollution analysis report is generated, and reported to the management station;
[0128] Continuously monitor changes in reservoir water volume, water quality, and downstream demand, and adjust dispatch plans based on real-time monitoring results;
[0129] Regularly evaluate the effectiveness of the scheduling plan, including water utilization rate and water quality compliance rate indicators, and optimize the scheduling plan.
[0130] It should be noted that through water quality monitoring, water quality problems can be discovered in a timely manner and measures can be taken to improve water quality and maintain ecological balance. Through continuous monitoring of the ecological health of water bodies, environmental pollution can be prevented and controlled, and the long-term availability of water resources can be guaranteed. Once the source of pollution is discovered, it can be quickly located and measures can be taken to reduce pollution and protect public health.
[0131] The present invention can obtain the changing trend of water levels in each river basin through the collection and analysis of meteorological data, the marking and prediction of river basins, improve the accuracy of water resource prediction, identify dangerous areas, generate water conservancy scheduling plans, and continuously monitor the health of water areas to warn of natural disasters in advance and reduce the losses caused by disasters. The Yunyuan Intelligent Management Water Conservancy Project Standardization Management Platform can more accurately understand the distribution and utilization of water resources through real-time monitoring and data analysis, thereby achieving more reasonable and efficient water resource allocation; it can make predictions and intelligent analyses based on data to formulate the optimal water resource allocation plan to ensure that each water-using area receives a reasonable amount of water supply; through automated monitoring equipment, it can promptly detect changes in water quality, take corresponding measures to protect water resources, and ensure water safety.
[0132] The above is a schematic scheme of a Yunyuan Intelligent Management Water Conservancy Project Standardization Management Platform of this embodiment. It should be noted that the technical scheme of the Yunyuan Intelligent Management Water Conservancy Project Standardization Management Method and the technical scheme of the Yunyuan Intelligent Management Water Conservancy Project Standardization Management Platform above belong to the same concept. For details not described in detail in the technical scheme of the Yunyuan Intelligent Management Water Conservancy Project Standardization Management Method in this embodiment, please refer to the description of the technical scheme of the Yunyuan Intelligent Management Water Conservancy Project Standardization Management Platform above.
[0133] In this embodiment, the standardized management method of Yunyuan Intelligent Water Conservancy Project is as follows: Figure 2 ,include:
[0134] S201, collect real-time meteorological data and historical meteorological data, perform trend analysis and forecast on the meteorological data, and determine whether the meteorological forecast result is extreme weather. If the meteorological forecast result is extreme weather, perform flood prevention warning analysis through the forecast and warning module 102;
[0135] S202, based on the meteorological forecast results of the data acquisition module 101, a flood prevention warning analysis is performed on the water resources of each branch basin, and a basin water level prediction model is constructed according to the meteorological data to predict the water level changes of each basin and obtain basin prediction results;
[0136] S203, based on the basin prediction results of the prediction and early warning module 102, calculate the predicted water volume of the reservoir, obtain the prediction results of the reservoir water resources change, and generate a water conservancy dispatching plan according to the prediction results;
[0137] S204: Based on water quality analysis and water conservancy scheduling plans, monitor the ecological health status of the river. If water pollution exists, identify and report the pollution source.
[0138] This embodiment also provides an electronic device, which is applicable to the standardized management of Yunyuan Intelligent Water Conservancy Project, including:
[0139] Memory and processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the standardized management platform of Yunyuan Intelligent Water Conservancy Project as proposed in the above embodiment.
[0140] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements the cloud source intelligent water conservancy project standardization management platform as proposed in the above embodiment.
[0141] The storage medium proposed in this embodiment and the implementation of the cloud source intelligent water conservancy project standardized management platform proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.
[0142] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.
[0143] Example 2, referring to Table 1, is an embodiment of the present invention, which provides a Yunyuan intelligent water conservancy project standardization management platform. In order to verify its beneficial effects, comparison results of two solutions are provided.
[0144] This embodiment selects a medium-sized city located in the Yangtze River Basin. The simulation period is 365 days. Three extreme rainfall events occurred during the simulation. The reservoir capacity is 50 million cubic meters. The initial water level is 30% capacity (15 million cubic meters).
[0145] By implementing the Yunyuan Intelligent Water Conservancy Project Standardized Management Platform of the present invention, a virtual environment was created using simulation software to simulate the hydrological process under different weather conditions. At the same time, a control group using a traditional water conservancy management platform was set up to conduct a simulation comparison experiment. The experimental results are shown in Table 1.
[0146] Table 1: Comparative test data
[0147] Comparison indicators Experimental group (the present invention) Control group (other traditional platforms) Response time (min) 20 50 Extreme weather forecast accuracy (%) 100 66.7 Water level prediction accuracy (%) 98.5 91.4 Dangerous area identification rate (%) 95 80 Water conservancy regulation effect 30 20 Average energy consumption (kw·h / day) 300 500 Abnormal water quality monitoring times 4 2
[0148] It can be seen from Table 1 that the response time of the present invention is faster, and flood prevention measures can be taken earlier. Through the prediction accuracy of extreme weather and water level, the prediction accuracy of the present scheme is significantly improved, which helps to better cope with the changes in water areas caused by extreme weather. Through the identification of dangerous areas and water conservancy scheduling effects, the traditional system can be reduced to an average of 20% capacity, while the present scheme can be reduced to an average of 30% capacity. The present invention can adopt a better and more reasonable scheduling scheme according to the actual situation of the water area, and is also superior to other systems in terms of energy consumption. Higher prediction accuracy ensures more effective early warning and emergency response, and ensures the effective use of water resources. At the same time, higher water quality monitoring and identification helps to deal with water quality problems in a timely manner, greatly reducing energy consumption and protecting the ecosystem.
[0149] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A cloud source intelligent water conservancy project standardization management platform, characterized by: include: The data acquisition module is used to collect real-time meteorological data and historical meteorological data, perform trend analysis and forecast on the meteorological data, and determine whether the meteorological forecast result is extreme weather. If the meteorological forecast result is extreme weather, the forecast and warning module is used to perform flood prevention and warning analysis; A prediction and warning module is used to perform the flood prevention and warning analysis on the water resources of each branch basin based on the meteorological prediction results of the data acquisition module, build a basin water level prediction model according to meteorological data, predict the water level changes of each basin, and obtain basin prediction results; A water conservancy dispatching module is used to calculate the predicted water volume of the reservoir based on the basin prediction results of the prediction and early warning module, obtain the prediction results of the reservoir water resources change, and generate a water conservancy dispatching plan according to the prediction results; An environmental assessment module is used to monitor the ecological health status of the water area based on the water conservancy scheduling plan, and to identify and report the pollution source if there is water pollution; The workflow of the data acquisition module includes: Collect real-time meteorological data including air temperature, humidity, wind speed, air pressure, cloud cover and precipitation in the water resource area, and pre-process the data; Constructing a meteorological prediction model to predict future regional precipitation, and using the historical meteorological data to train the model, and predicting precipitation in future time periods through the trained meteorological prediction model; The weather forecast model is expressed as: ; in, is the predicted precipitation, Indicates the air temperature, Indicates air humidity, Indicates wind speed, Indicates air pressure, represents the cloud cover, represents the intercept term, Represents the adjustment coefficients respectively, represents the error term; Determine whether the current weather is extreme based on weather forecast results; The workflow of the prediction and early warning module includes: Based on extreme weather forecast results, emergency warnings are issued, control centers are notified, and flood prevention strategies are established; Establish water area collections for each river basin in the region and establish flood control priorities for each river basin; Setting marking points in the river section of each river basin, generating a marking point set of the river basin, and marking the marking points according to the actual geographical location, wherein the point marking includes adjacent position marking and upstream and downstream marking; Based on meteorological data and watershed data, a watershed water level prediction model is constructed to obtain the highest water level prediction of the marked point, and combined with the point marks of the marked point set for analysis, the marked point is divided into a dangerous area; The flood control priority for each basin is expressed as: ; in, represents the population density of the watershed. Indicates the number of important facilities, represents the average number of flood events per year in history, , , are weight coefficients respectively; The construction of the basin water level prediction model comprises: Collect historical data and real-time data of the watershed, wherein the historical data of the watershed includes precipitation, water level, soil moisture, land cover type, terrain slope and temperature, and the real-time data of the watershed includes predicted precipitation and current water level, and perform data preprocessing and feature extraction; The basin water level prediction model is constructed by combining the improved convolutional neural network and the long short-term memory network, which is expressed as: ; in, Description mark point The highest water level predicted at any given moment, represents the spatial eigenvector, represents the time series feature vector, Indicates the hidden state of the previous moment, represents a convolutional neural network, represents long short-term memory unit; The watershed historical data is divided into a training set and a verification set to train and verify the watershed water level prediction model; The input layer of the watershed water level prediction model receives spatial feature vectors and time series feature vectors. The spatial feature vectors include: terrain slope, land cover type, soil moisture, watershed area, and elevation of the marker point, which are combined into a two-dimensional matrix. The time series feature vectors include precipitation, temperature, wind speed, and humidity, and a sequence is constructed with data for each hour. The CNN layer of the watershed water level prediction model processes spatial features, and the output of the CNN layer is flattened and converted into a one-dimensional vector through the Flatten layer; The LSTM layer of the watershed water level prediction model processes time series features, merges the outputs of the CNN layer and the LSTM layer through the Concatenate layer, and predicts the highest water level of the marked point at a future moment through the fully connected layer; Dividing the marking point into a dangerous area includes: Based on the prediction results of the highest water level of the marked points, combined with the point annotation information of the marked points, the dangerous areas of each basin are divided; Set the water level warning threshold interval. If the highest water level of the marked point reaches the maximum value of the warning threshold, then combined with the water level values upstream and downstream of the marked point, if the highest water level of the marked point reaching the warning threshold has no downward trend, the marked point will be divided into a dangerous area; otherwise, if the highest water levels of the upstream and downstream marked points of the marked point are lower than the minimum value of the warning threshold, the marked point will not be divided into a dangerous area; The division of hazardous areas is expressed as: ; in, Indicates the marked point The predicted maximum water level is represents the warning threshold interval, Indicates the set of upstream marked points adjacent to the marked point. Representing a collection The marking points in Indicates the set of downstream marking points adjacent to the marking point. Representing a collection The marking points in .
2. The Yunyuan Intelligent Water Conservancy Project Standardization Management Platform according to claim 1 is characterized in that: The workflow of the water conservancy scheduling module includes: The water resources in the dangerous areas of the basin are diverted to the reservoir according to the flood control priority, and the diversion rate is controlled by calculating the maximum water level and water flow; According to the water source data of the dangerous area, the reservoir water volume in the future time period is predicted and the reservoir change trend is analyzed. The calculation formula of the reservoir water volume is expressed as: ; in, Indicates time The amount of water in the reservoir, Indicates the evaporation rate, is the reservoir inflow, represents the outflow of the reservoir, represents the average precipitation, Indicates a time interval; The water quality in the reservoir is analyzed. When the water level of the predicted water volume in the reservoir is greater than the reservoir water level threshold, the water sources in the reservoir are classified and released according to the water quality analysis results to control the flow rate and time.
3. The Yunyuan Intelligent Water Conservancy Project Standardization Management Platform according to claim 2 is characterized in that: The workflow of the environmental assessment module includes: Through the analysis results of water quality, the health of the water area is monitored, and the presence of pollutants is analyzed, the composition of pollutants is analyzed, the pollution source is tracked, a pollution analysis report is generated, and reported to the management station; Continuously monitor changes in reservoir water volume, water quality, and downstream demand, and adjust dispatch plans based on real-time monitoring results; Regularly evaluate the effectiveness of the scheduling plan, including water utilization rate and water quality compliance rate indicators, and optimize the scheduling plan.
4. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the module workflow of the Yunyuan Intelligent Water Conservancy Project Standardization Management Platform described in any one of claims 1 to 3 is implemented.
5. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, can implement the module workflow of the Yunyuan Intelligent Water Conservancy Project Standardization Management Platform as described in any one of claims 1 to 3.
