Water conservancy gate station control system based on AI intelligence

Abstract

The invention relates to the technical field of water conservancy, and discloses an AI intelligence-based water conservancy gate station control system, which comprises an AI intelligent monitoring module, a prediction module, a decision control module and an emergency response module, and is characterized in that the AI intelligent monitoring module is used for monitoring and collecting a meteorological data set, a hydrological data set and an equipment data set; the prediction module calculates a water level prediction coefficient and a health difference value of equipment in combination with a collected data set, then evaluates the water level of a gate station and the operation of the equipment according to the calculation result of the water level prediction coefficient and the health difference value of the equipment, and the decision control module performs emergency processing and synchronously sends a signal to the emergency response module; the emergency response module sends received signals to related personnel to make early warning, water level prediction is accurately achieved, powerful support is provided for intelligent control and efficient operation of the water conservancy gate station, faults existing in equipment can be predicted in advance, and the automatic response efficiency, speed and accuracy are high.

Description

Technical Field

[0001] The present invention relates to the field of water conservancy technology, and particularly to a water conservancy sluice and pumping station control system based on AI intelligence. Background Art

[0002] A water conservancy sluice and pumping station is a complex of a sluice and a pumping station, with multiple functions such as water retaining, water discharging, drainage, and water diversion. It plays an irreplaceable role in water resource allocation, flood control and waterlogging drainage, agricultural irrigation, etc. It is a comprehensive water conservancy facility integrating the functions of a sluice and a pumping station, occupying a very important position in the water conservancy system. A water conservancy sluice and pumping station is a water conservancy project building that realizes the effective control, regulation, and transportation of water flow through the opening and closing of the gates of the sluice and the power water lifting of the pumping station. It organically combines the water retaining and discharging capabilities of the sluice and the water lifting function of the pumping station, and can flexibly regulate the water level and flow according to different water conservancy requirements. In terms of farmland irrigation, when the farmland needs water, the water conservancy sluice and pumping station can open the sluice to introduce water sources such as river water and lake water, use the pumping station to lift the water to the required height, and transport it to the fields through irrigation channels to meet the water demand for crop growth. At the same time, when there is too much waterlogging in the fields after heavy rain, it can drain the water in time to prevent the farmland from being flooded, ensure the safety of urban water supply, pressurize and transport the qualified water source to the urban water supply network through the pumping station to meet the domestic water use of residents and industrial production water use. In urban flood control and waterlogging drainage, when floods hit, the sluice and pumping station closes the gates to block the flood from entering the city; when there is urban waterlogging, the pumping station is opened to strongly drain the accumulated water. On the waterway, by adjusting the water level of the sluice and pumping station, the water depth of the waterway is maintained stable to ensure the safe navigation of ships. For example, in a river with a large water level drop between upstream and downstream, ships can smoothly pass through different water level areas with the help of the water level adjustment of the sluice and pumping station.

[0003] At present, although some water conservancy sluice and pumping stations are equipped with an automated control system, the level of intelligence is low. In actual operation, many key operations still rely on manual completion, which is not only inefficient but also prone to errors due to human negligence or misjudgment. Once sudden changes occur, the manual response speed is slow, and it is difficult to take effective control measures in a timely manner, seriously affecting the ability of water conservancy sluice and pumping stations to cope with complex and changeable water conditions. At the same time, the reaction speed of the existing water conservancy sluice and pumping station control system is slow, and there is a lack of scientific and effective emergency plans. When an emergency occurs, the system cannot quickly make an accurate response, nor is there a mature plan to guide the response measures, making it difficult for water conservancy sluice and pumping stations to play their due role at critical moments, posing a potential threat to the production, life, and ecological environment of the surrounding areas. Summary of the Invention

[0004] (I) Technical Problems to be Solved

[0005] In view of the deficiencies of the prior art, the present invention provides a water conservancy sluice station control system based on AI intelligence, which can accurately predict water levels, provide strong support for the intelligent control and efficient operation of water conservancy sluice stations, can predict equipment failures in advance, has high automation response efficiency, high speed, high accuracy, can timely detect and handle different problems, improves the role of water conservancy sluice stations, and reduces the occurrence of abnormal situations, etc.

[0006] (II) Technical solution

[0007] To achieve the above object, the present invention provides the following technical solution: A water conservancy sluice station control system based on AI intelligence, including an AI intelligent monitoring module, a prediction module, a decision-making control module, and an emergency response module;

[0008] The AI intelligent monitoring module includes a meteorological monitoring unit, a hydrological monitoring unit, and an equipment monitoring unit. The meteorological monitoring unit is used to monitor and collect meteorological data sets, the hydrological monitoring unit is used to monitor and collect hydrological data sets, the equipment monitoring unit is used to monitor and collect equipment data sets, and the AI intelligent monitoring module numbers the collected data sets and sends them to the prediction module;

[0009] The prediction module calculates the water level prediction coefficient SWbh according to the meteorological data set and the hydrological data set, and calculates the health difference JKzs of the equipment according to the equipment data set. The prediction module sends the calculation results of the water level prediction coefficient and the health difference of the equipment to the decision-making control module through the network;

[0010] The decision-making control module evaluates the water level of the sluice station and the operation of the equipment based on the calculation results of the water level prediction coefficient and the health difference of the equipment, and makes emergency handling. When the decision-making control module makes emergency handling, it synchronously sends a signal to the emergency response module;

[0011] The emergency response module sends a warning to relevant personnel through the received signal.

[0012] Preferably, the meteorological data set is obtained by connecting a meteorological sensor, a satellite, and a meteorological station through the meteorological monitoring unit, the hydrological data set is obtained by connecting a hydrological sensor, a radar, and a monitoring station through the hydrological monitoring unit, and the equipment data set is obtained by connecting an equipment sensor through the equipment monitoring unit.

[0013] Preferably, the meteorological data set includes rainfall, temperature, wind speed, wind direction, and humidity, and its representative numbers are: QXsj = Jl, Qw, Fs, Fx, Sd. In the numbers, QXsj represents the meteorological data set, Jl represents rainfall, Qw represents temperature, Fs represents wind speed, Fx represents wind direction, and Sd represents humidity.

[0014] Preferably, the hydrological data set includes water level data, flow rate data, and flow velocity data, and their representative numbers are: SWsj = Sw, Ll, Ls. In the numbers, SWsj represents the hydrological data set, Sw represents the water level data, Ll represents the flow rate data, and Ls represents the flow velocity data. The water level data includes the initial reservoir water level Scw. The flow rate data includes: the inflow rate Lrl and the power generation diversion flow rate Lfl. The flow velocity data includes: the gate water passing area Lgs, the gate flow velocity Lzs, and the gate opening Lks.

[0015] Preferably, the equipment data set includes gate status data, water pump status data, generator set data, and electrical parameter data, and their representative numbers are: SBsj = Zm, Sb, Fj, Dc. In the numbers, Zm represents the gate status data, Sb represents the water pump status data, Fj represents the generator set data, and Dc represents the electrical parameter data. The gate status data includes the gate opening and closing speed Zbm and the gate operation time Zym. The water pump status data includes: the water pump flow rate Slb and the water pump power Sgb. The generator set data includes the generated electricity amount Fdj, the unit rotation speed Fzj, the water turbine efficiency Fsj, and the generator temperature Fwj. The electrical parameter data includes the voltage Dyc, the current Dlc, the electrical frequency Dpc, and the electrical power Dgc.

[0016] Preferably, the calculation formula of the water level prediction coefficient SWbh is:

[0017]

[0018] In the calculation formula, represents the total value of the ratios between the factors in the meteorological data set and the standard values, QXsj i represents the i-th factor in the meteorological data set, represents the standard value of the i-th factor in the meteorological data set, represents that the meteorological data set starts from i = Jl to i = Sd, all the sum of the values;

[0019] A represents the reservoir water surface area controlled by the water conservancy sluice station, T represents the time interval, Lzs * Lgs * Lks represents the flow rate of the gate, Lfl + Lzs * Lgs * Lks represents the total reservoir outflow flow rate, and Lrl - (Lfl + Lzs * Lgs * Lks) represents the net change in the reservoir water volume within time T, represents the water level change caused by the water volume change.

[0020] Preferably, the calculation formula of the health difference JKzs of the equipment is:

[0021]

[0022] In the calculation formula, SBsj i represents the current value of the i-th factor in the device dataset, and represents the standard value of the i-th factor in the device dataset.

[0023] Preferably, when the value of the water level prediction coefficient SWbh is greater than the maximum threshold of the water level coefficient, it indicates that the water level has a large upward trend and is facing the risk of flood. When the value of the water level prediction coefficient SWbh is less than the minimum threshold of the water level coefficient, it indicates that the water level is decreasing and water source replenishment is required.

[0024] Preferably, when the value of the health difference JKzs of the device is greater than the health threshold of the device, it indicates that the current device has a fault.

[0025] Preferably, when the value of the water level prediction coefficient SWbh is greater than the maximum threshold of the water level coefficient, the decision control module increases the opening of the gate through the AI intelligent controller, starts the spillway, reduces the water level, and at the same time reduces or stops the power generation diversion flow to use more water resources for flood discharge;

[0026] When the value of the water level prediction coefficient SWbh is less than the minimum threshold of the water level coefficient, the decision control module reduces the opening of the gate through the AI intelligent controller, reduces the discharge flow, increases the water storage capacity of the reservoir, and at the same time the system starts external water source replenishment;

[0027] When the value of the health difference JKzs of the device is greater than the health threshold of the device, reduce the device load, extend the operation time, and automatically switch to the standby device for operation.

[0028] Compared with the prior art, the present invention provides a water conservancy sluice station control system based on AI intelligence, which has the following beneficial effects:

[0029] 1. By monitoring meteorological data and hydrological data, the present invention can significantly improve the accuracy of water level prediction, provide strong support for the intelligent control and efficient operation of water conservancy sluice stations. By monitoring device data, it can predict in advance the faults existing in the devices, so as to make emergency treatments and avoid the risk of the water conservancy sluice station control system getting out of control due to device failures.

[0030] 2. Through automatic emergency control, the present invention makes different emergency responses according to different scenarios. The automatic control efficiency is high, reducing errors caused by human negligence or judgment mistakes. The intelligent control has a fast response speed, can timely discover and handle different problems, improves the role of water conservancy sluice stations, and reduces the occurrence of abnormal situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a schematic diagram of the system of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0032] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0033] Please refer to Figure 1 , a water conservancy sluice station control system based on AI intelligence, including an AI intelligent monitoring module, a prediction module, a decision control module, and an emergency response module;

[0034] The AI intelligent monitoring module includes a meteorological monitoring unit, a hydrological monitoring unit, and a device monitoring unit. The meteorological monitoring unit is used to monitor and collect meteorological data sets. The hydrological monitoring unit is used to monitor and collect hydrological data sets. The device monitoring unit is used to monitor and collect device data sets. The AI intelligent monitoring module numbers the collected data sets and sends them to the prediction module;

[0035] The meteorological data set is obtained by connecting a meteorological sensor, a satellite, and a meteorological station through the meteorological monitoring unit. The hydrological data set is obtained by connecting a hydrological sensor, a radar, and a monitoring station through the hydrological monitoring unit. The device data set is obtained by connecting a device sensor through the device monitoring unit;

[0036] The meteorological data set includes rainfall, temperature, wind speed, wind direction, and humidity. Its representative numbers are: QXsj = Jl, Qw, Fs, Fx, Sd. In the numbers, QXsj represents the meteorological data set, Jl represents rainfall, Qw represents temperature, Fs represents wind speed, Fx represents wind direction, and Sd represents humidity. Each data in the meteorological data set is a factor affecting the water level change. By monitoring these data, the accuracy of water level prediction can be significantly improved, providing strong support for the intelligent control and efficient operation of the water conservancy sluice station;

[0037] The hydrological data set includes water level data, flow data, and flow velocity data. Its representative numbers are: SWsj = Sw, Ll, Ls. In the numbers, SWsj represents the hydrological data set, Sw represents water level data, Ll represents flow data, and Ls represents flow velocity data. The water level data includes the initial reservoir water level Scw. The flow data includes: the inflow Lrl, the power generation diversion flow Lfl. The flow velocity data includes: the gate water passing area Lgs, the gate flow velocity Lzs, and the gate opening Lks. Each data in the hydrological data set is the key to affecting the water level. By monitoring the hydrological data, the accuracy of water level prediction is improved, providing a reliable basis for water conservancy decision-making;

[0038] The equipment dataset includes gate status data, pump status data, generator set data, and power parameter data, and their representative numbers are: SBsj = Zm, Sb, Fj, Dc. In the numbers, Zm represents gate status data, Sb represents pump status data, Fj represents generator set data, and Dc represents power parameter data. The gate status data includes the gate opening and closing speed Zbm and the gate operation time Zym. The pump status data includes: pump flow Slb and pump power Sgb. The generator set data includes generated electricity Fdj, unit speed Fzj, water turbine efficiency Fsj, and generator temperature Fwj. The power parameter data includes voltage Dyc, current Dlc, electrical frequency Dpc, and electric power Dpc. The data in the equipment dataset are the key to supporting the normal operation of the water conservancy sluice station system. By monitoring these data, potential equipment failures can be predicted in advance, enabling emergency handling and avoiding the risk of the water conservancy sluice station control system getting out of control due to equipment failures;

[0039] The prediction module calculates the water level prediction coefficient SWbh based on the meteorological dataset and the hydrological dataset, and calculates the health difference JKzs of the equipment based on the equipment dataset. The prediction module sends the calculation results of the water level prediction coefficient and the health difference of the equipment to the decision control module through the network;

[0040] The calculation formula for the water level prediction coefficient SWbh is:

[0041]

[0042] In the calculation formula, represents the total value of the ratios between the various factors in the meteorological dataset and the standard values, QXsj i represents the i-th factor in the meteorological dataset, represents the standard value of the i-th factor in the meteorological dataset, represents that the meteorological dataset starts from i = Jl to i = Sd, and all values, that is, the meteorological factor values affecting the water level change;

[0043] represents the change in water level, A represents the water surface area of the reservoir controlled by the water conservancy sluice station, T represents the time interval, Lzs*Lgs*Lks represents the flow rate of the gate, Lfl + Lzs*Lgs*Lks represents the total reservoir outflow flow rate, and Lrl - (Lrl + Lzs*Lgs*Lks) represents the net change in reservoir water volume within time T, represents the change in water level caused by the change in water volume, represents the water level prediction coefficient that fully considers the influence of meteorological conditions and the change process of water volume, improving the prediction accuracy;

[0044] The calculation formula for the health difference JKzs of the device is as follows:

[0045]

[0046] In the calculation formula, SBsj i represents the current value of the i-th factor in the device dataset, represents the standard value of the i-th factor in the device dataset, represents the difference between the current value and the standard value of the i-th factor in the device dataset, which is used to evaluate the operating status of the device;

[0047] The decision control module evaluates the water level of the sluice station and the operation of the device through the water level prediction coefficient and the calculation result of the health difference of the device, and makes emergency treatment. When the decision control module makes emergency treatment, it synchronously sends a signal to the emergency response module;

[0048] When the value of the water level prediction coefficient SWbh is greater than the maximum threshold of the water level coefficient, it means that the water level has a large upward trend and is facing the risk of flood. When the value of the water level prediction coefficient SWbh is less than the minimum threshold of the water level coefficient, it means that the water level is dropping and the water source needs to be replenished;

[0049] When the value of the health difference JKzs of the device is greater than the health threshold of the device, it means that the current device has a fault;

[0050] When the value of the water level prediction coefficient SWbh is greater than the maximum threshold of the water level coefficient, the decision control module increases the opening of the gate through the AI intelligent controller, starts the spillway, reduces the water level, and at the same time reduces or stops the power generation diversion flow, and uses more water resources for flood discharge;

[0051] When the value of the water level prediction coefficient SWbh is less than the minimum threshold of the water level coefficient, the decision control module reduces the opening of the gate through the AI intelligent controller, reduces the discharge flow, increases the reservoir storage capacity, and at the same time the system starts the external water source replenishment;

[0052] When the value of the health difference JKzs of the device is greater than the health threshold of the device, reduce the device load, extend the operation time, and automatically switch to the standby device for operation;

[0053] Through automatic emergency control, different emergency responses are made according to different scenarios, realizing the automatic control of the system, reducing errors caused by human negligence or judgment errors, with fast intelligent control response speed, timely discovery and handling of different problems, enhancing the role of the water conservancy sluice station, and reducing the occurrence of abnormal situations;

[0054] The emergency response module sends a warning to relevant personnel through the received signal.

[0055] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art will appreciate that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A water conservancy sluice station control system based on AI intelligence, characterized by: Including AI intelligent monitoring module, prediction module, decision-making control module and emergency response module; The AI ​​intelligent monitoring module includes a meteorological monitoring unit, a hydrological monitoring unit and an equipment monitoring unit. The meteorological monitoring unit is used to monitor and collect meteorological data sets, the hydrological monitoring unit is used to monitor and collect hydrological data sets, and the equipment monitoring unit is used to monitor and collect equipment data sets. The AI ​​intelligent monitoring module numbers the collected data sets and sends them to the prediction module; The prediction module calculates the water level prediction coefficient SWbh according to the meteorological data set and the hydrological data set, and calculates the health difference value JKzs of the equipment according to the equipment data set. The prediction module sends the calculation results of the water level prediction coefficient and the health difference value of the equipment to the decision control module through the network; The decision control module evaluates the water level of the sluice station and the operation of the equipment through the calculation results of the water level prediction coefficient and the health difference of the equipment, and makes emergency treatment. When making emergency treatment, the decision control module synchronously sends a signal to the emergency response module; The emergency response module sends the received signal to relevant personnel to issue an early warning alert.

2. According to claim 1, a water conservancy sluice station control system based on AI intelligence is characterized in that: The meteorological data set is obtained by connecting the meteorological monitoring unit to meteorological sensors, satellites and meteorological stations, the hydrological data set is obtained by connecting the hydrological monitoring unit to hydrological sensors, radars and monitoring stations, and the equipment data set is obtained by connecting the equipment monitoring unit to equipment sensors.

3. The AI-based water conservancy sluice station control system according to claim 2 is characterized in that: The meteorological data set includes rainfall, temperature, wind speed, wind direction, and humidity, and its representative number is: QXsj=Jl, Qw, Fs, Fx, Sd, where QXsj represents the meteorological data set, Jl represents rainfall, Qw represents temperature, Fs represents wind speed, Fx represents wind direction, and Sd represents humidity.

4. The AI-based water conservancy sluice station control system according to claim 3 is characterized by: The hydrological data set includes water level data, flow data, and flow velocity data, and its representative number is: SWsj=Sw, Ll, Ls, where SWsj represents the hydrological data set, Sw represents water level data, Ll represents flow data, and Ls represents flow velocity data. The water level data includes the initial reservoir water level Scw, the flow data includes: the inflow flow Lrl, the power generation reference flow Lfl, and the flow velocity data includes: the gate water flow area Lgs, the gate flow velocity Lzs, and the gate opening Lks.

5. The AI-based water conservancy sluice station control system according to claim 4 is characterized in that: The equipment data set includes gate status data, water pump status data, generator set data, and power parameter data, and its representative number is: SBsj=Zm, Sb, Fj, Dc, where Zm represents gate status data, Sb represents water pump status data, Fj represents generator set data, and Dc represents power parameter data. The gate status data includes gate opening and closing speed Zbm and gate operation time Zym. The water pump status data includes: water pump flow Slb and water pump power Sgb. The generator set data includes power generation Fdj, unit speed Fzj, turbine efficiency Fsj, and generator temperature Fwj. The power parameter data includes voltage Dyc, current Dlc, electrical frequency Dpc, and electrical power Dgc.

6. The AI-based water conservancy sluice station control system according to claim 5 is characterized by: The calculation formula of the water level prediction coefficient SWbh is: In the calculation formula, Represents the total value of the ratio between each factor and the standard value in the meteorological data set, QXsj i represents the i-th factor in the meteorological data set, represents the standard value of the i-th factor in the meteorological data set, Represents the meteorological data set starting from i=Jl and ending at i=Sd. The sum of the values; A represents the water surface area of ​​the reservoir controlled by the water conservancy sluice station, T represents the time interval, Lzs*Lgs*Lks represents the flow of the gate, Lfl+Lzs*Lgs*Lks represents the total outflow of the reservoir, and Lrl-(Lfl+Lzs*Lgs*Lks) represents the net change of the reservoir water volume within the time T. Represents the change in water level due to changes in water volume.

7. The AI-based water conservancy sluice station control system according to claim 6 is characterized by: The health difference JKzs calculation formula of the equipment is: In the calculation formula, SBsj i Represents the current value of the i-th factor in the device data set, Represents the standard value of the i-th factor in the equipment dataset.

8. The AI-based water conservancy sluice station control system according to claim 7 is characterized by: When the value of the water level prediction coefficient SWbh is greater than the maximum threshold of the water level coefficient, it means that the water level has a large upward trend and faces a flood risk. When the value of the water level prediction coefficient SWbh is less than the minimum threshold of the water level coefficient, it means that the water level has dropped and the water source needs to be replenished.

9. The AI-based water conservancy sluice station control system according to claim 8 is characterized by: When the value of the health difference JKzs of the device is greater than the health threshold of the device, it means that the current device has a fault.

10. The AI-based water conservancy sluice station control system according to claim 9 is characterized in that: When the value of the water level prediction coefficient SWbh is greater than the maximum threshold of the water level coefficient, the decision control module increases the gate opening through the AI ​​intelligent controller, starts the spillway, lowers the water level, and reduces or stops the power generation flow, so that more water resources are used for flood discharge; When the value of the water level prediction coefficient SWbh is less than the minimum threshold of the water level coefficient, the decision control module reduces the gate opening through the AI ​​intelligent controller, reduces the discharge flow, increases the reservoir water storage capacity, and the system starts external water supply; When the health difference JKzs of the device is greater than the health threshold of the device, the device load is reduced, the operation time is extended, and the device is automatically switched to the standby device for operation.

Images