Intelligent river ecological water supplementing and water quality regulation and control system and method based on Internet of Things

Abstract

The invention relates to the technical field of water conservancy projects and ecological restoration, in particular to an intelligent river ecological water supplementing and water quality regulation and control system and method based on the Internet of Things, and the method comprises the steps: collecting river water quality data and environmental parameters; local real-time preprocessing is carried out, abnormal data are removed, and an emergency response instruction is generated when it is detected that the dissolved oxygen is lower than a set value; uploading the preprocessed data to a cloud decision platform; based on a machine learning model and an ecological water demand model, predicting a water quality change trend and generating a collaborative regulation and control suggestion, and calling a dynamic water replenishing algorithm to calculate the rotating speed of a variable frequency pump station and the opening degree of an intelligent electromagnetic valve; after receiving the instruction, controlling the multi-stage variable frequency pump station to start and adjust the flow, and controlling the intelligent electromagnetic valve to supply water according to the opening degree; the running state of equipment is monitored in real time, pump station abnormity is recognized, and an upstream valve is automatically closed; when the inclination angle of the detection equipment is greater than the set angle, triggering the scram button to cut off the power supply. And the treatment efficiency and stability are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water conservancy and ecological restoration, in particular to an intelligent river ecological water replenishment and water quality regulation system and method based on the Internet of Things. BACKGROUND

[0002] In river ecological management, water quality protection and rational utilization of water resources are core issues. With the rapid development of industrialization and urbanization, river water pollution problems are increasingly prominent, leading to water quality deterioration, ecological system imbalance, and seriously affecting the sustainable use of water resources and the surrounding ecological environment. Traditional river ecological water replenishment and water quality management has the following significant limitations: In terms of water resource utilization, existing river replenishment strategies are often based on fixed schedules or empirical judgments, lacking precise assessment of actual river water demand and water quality conditions. This leads to excessive or insufficient replenishment, failing to effectively meet river ecological needs, and even possibly causing waste of water resources; in terms of water quality maintenance, lacking real-time monitoring and dynamic regulation mechanisms, resulting in frequent water quality deterioration problems such as dissolved oxygen below 5 mg / L and ammonia nitrogen exceeding standards; in terms of ecological protection, single replenishment methods destroy aquatic habitat environments, causing ecological system imbalance and reducing river self-purification capacity by more than 40%.

[0003] In the face of sudden pollution incidents, traditional methods lack rapid and effective emergency response mechanisms. This can lead to pollution spreading, further exacerbating water quality deterioration, and causing irreversible damage to the ecological system. SUMMARY

[0004] To solve the above problems, the present application provides an intelligent river ecological water replenishment and water quality regulation system and method based on the Internet of Things.

[0005] In a first aspect, the present application provides an intelligent river ecological water replenishment and water quality regulation system based on the Internet of Things, comprising an ecological water replenishment module, a water quality monitoring module, an intelligent regulation module, and an ecological restoration module; The ecological water replenishment module includes a multi-stage variable frequency pump station, a distributed pipeline network, and a rainwater recovery unit. The multi-stage variable frequency pump station is connected to the river through the distributed pipeline network, and the rainwater recovery unit is connected to the distributed pipeline network after sedimentation and filtration, used to dynamically adjust the water replenishment amount according to the river segment water demand and realize rainwater resource utilization; The water quality monitoring module includes a fixed monitoring terminal and a mobile monitoring unmanned aerial vehicle. The fixed monitoring terminal is deployed at key sections of the river, and the mobile monitoring unmanned aerial vehicle is used to cover the fixed monitoring blind area. Both the fixed monitoring terminal and the mobile monitoring unmanned aerial vehicle are integrated with pH, dissolved oxygen, turbidity, and ammonia nitrogen sensors, used to collect water quality data in real time and upload to the intelligent regulation module; The intelligent regulation module comprises an edge computing gateway and a cloud decision platform, the edge computing gateway is in communication connection with a water quality monitoring module, an ecological water supplement module and an ecological restoration module, is used for local real-time processing of water quality data and responding to emergency instructions, and the cloud decision platform is in communication connection with the edge computing gateway, is deployed with a machine learning model, is used for predicting water quality change trend and generating a coordinated regulation strategy of water supplement, aeration and purification. The ecological restoration module comprises a stepped constructed wetland unit and a biofilm reactor, the constructed wetland unit is planted with submerged plants, and the biofilm reactor is filled with biological filler and is matched with an aerator and is used for adsorbing heavy metals and degrading organic pollutants. The intelligent regulation module controls the water supplement amount of the ecological water supplement module through a dynamic water supplement algorithm based on real-time data collected by the water quality monitoring module, meteorological forecast data and ecological water demand data calculated based on an ecological water demand model, and adjusts the operation parameters of the aerator of the ecological restoration module through an aeration control algorithm, so that efficient use of water resources, real-time optimization of water quality and ecological coordinated restoration are realized.

[0006] The system can collect river water quality data in real time, dynamically adjust the water supplement amount, accurately predict the water quality change trend and generate a coordinated regulation strategy. The technical scheme significantly improves the efficiency and accuracy of river management and effectively solves the problems of backward monitoring means and extensive regulation strategy in the traditional method.

[0007] As a preferred embodiment of the present application, in the ecological water supplement module, the multi-stage variable frequency pump station is a stainless steel cubic structure, and a variable frequency water pump with a set power range is built-in, the distributed pipeline network adopts a PE pipeline with a preset diameter range, the pipeline surface is coated with an ultraviolet-proof coating, and an intelligent electromagnetic valve control node with an aluminum alloy shell is arranged along the river bank at every set distance; the rainwater recovery unit comprises a conical water collecting tank and a sedimentation and filtration box, and a plurality of layers of quartz sand and activated carbon filter elements are arranged in the sedimentation and filtration box.

[0008] The multi-stage variable frequency pump station adopts a stainless steel cubic structure and a variable frequency water pump with a set power range is built-in, so that the durability and adjustment flexibility of the pump station are improved; the distributed pipeline network adopts a PE pipeline with a preset diameter range and is coated with an ultraviolet-proof coating, so that the service life of the pipeline is prolonged; the intelligent electromagnetic valve control node is arranged, so that accurate control of water supplement is realized. These design optimizations improve the performance of the water supplement system, reduce the maintenance cost and improve the water resource utilization efficiency.

[0009] As a preferred embodiment of the present application, in the water quality monitoring module, the fixed monitoring terminal is a cylindrical buoy structure made of ABS engineering plastic and integrates a solar panel at the top; the mobile monitoring unmanned aerial vehicle is designed as a six-rotor wing and adopts a carbon fiber body and suspends a miniature sensor cabin with a waterproof level of IP68 at the bottom.

[0010] The fixed monitoring terminal adopts a cylindrical buoy structure and integrates a solar panel to realize self-power supply and long-term stable monitoring; the mobile monitoring unmanned aerial vehicle adopts a six-rotor design and a carbon fiber body to improve the cruising efficiency and data acquisition accuracy. These innovative designs make water quality monitoring more comprehensive and accurate, providing reliable data support for intelligent control and helping to timely discover and handle water quality abnormal events.

[0011] As a preferred technical solution of the present application, the intelligent control module is provided with a wall-mounted aluminum alloy box body, an industrial-grade PLC supporting RS485 / CAN bus and a 5G communication module are built-in; the cloud decision platform is deployed in a server cluster, and the front-end interactive interface supports three-dimensional river model visualization based on GIS map, and the control instructions are issued through a fiber network.

[0012] The edge computing gateway is provided with a wall-mounted aluminum alloy box body, and an industrial-grade PLC and a 5G communication module are built-in, which improves the data processing and transmission capacity; the cloud decision platform is deployed in a server cluster, and supports three-dimensional river model visualization based on GIS map, which enhances the scientificity and intuitiveness of decision-making. These improvements make intelligent control more rapid and accurate, effectively improving the intelligent level of river management.

[0013] As a preferred technical solution of the present application, in the ecological restoration module, the artificial wetland unit adopts an HDPE impermeable membrane base and plants submerged plants according to a set planting density; the biofilm reactor is a cylindrical stainless steel tank body, which is internally filled with polyethylene biological filler and is matched with a centrifugal aerator.

[0014] The artificial wetland unit adopts an HDPE impermeable membrane base and submerged plant planting, which improves the self-purification capacity of the water body; the biofilm reactor adopts a cylindrical stainless steel tank body and polyethylene biological filler, which accelerates the degradation of organic pollutants. The implementation of these ecological restoration measures effectively improves the river water quality and promotes the recovery and stability of the ecological system.

[0015] As a preferred technical solution of the present application, the system further comprises a hybrid power driving system, which is electrically connected with the multi-stage variable frequency pump station of the ecological water supplement module, and comprises a diesel / electric dual-mode driving unit and a solar auxiliary power supply unit; the diesel / electric dual-mode driving unit comprises a single-cylinder water-cooled diesel engine and a brushless DC motor, and automatically switches the power mode based on water flow resistance, battery capacity and water supplement demand through an intelligent switching controller; the solar auxiliary power supply unit comprises a folding photovoltaic panel array and a lithium iron phosphate battery pack.

[0016] The intelligent switching of the power mode is realized, the optimal power source is automatically selected according to water flow resistance, battery capacity and water supplement demand, meanwhile, solar energy is used for auxiliary power supply, the operation cost is reduced, the energy utilization efficiency is improved, and the green and sustainable development concept is met.

[0017] As the preferred technical scheme of the present application, the input of the dynamic water supplement algorithm includes real-time water quality data, meteorological forecast data of rainfall and evaporation, and ecological water demand data calculated based on an ecological water demand model, the output is the rotating speed of the variable frequency pump station and the opening degree of the electromagnetic valve, and the optimization target is to minimize the water supplement energy consumption and maximize the water quality compliance rate. The aeration control algorithm is a PID control based on dissolved oxygen feedback, and the rotating speed of the aerator is adjusted in the set rotating speed range, and the aerator is automatically operated at a reduced frequency at night.

[0018] The dynamic water supplement algorithm takes minimizing the water supplement energy consumption and maximizing the water quality compliance rate as the optimization target, calculates the rotating speed of the variable frequency pump station and the opening degree of the electromagnetic valve through real-time water quality data, meteorological forecast data and ecological water demand data calculated based on an ecological water demand model, and the aeration control algorithm adopts a PID control based on dissolved oxygen feedback to adjust the rotating speed of the aerator in the set range. The application of these algorithms realizes efficient utilization of water resources and real-time optimization of water quality, and improves the scientificity and effectiveness of river ecological management.

[0019] As the preferred technical scheme of the present application, the artificial wetland unit and the biofilm reactor of the ecological restoration module are connected through quick release bolts or hydraulic joints, the pipeline interface adopts double sealing of O-rings and waterproof cement, and the upstream valve is automatically closed when the pipeline pressure drop is detected to exceed the set threshold value; the aerator adopts a float type structure, and the suspension height is adjusted through a counterweight.

[0020] The artificial wetland unit and the biofilm reactor are connected through quick release bolts or hydraulic joints, the pipeline interface adopts double sealing of O-rings and waterproof cement, and the stability and safety of the system are ensured; the aerator adopts a float type structure, and the suspension height is adjusted through a counterweight, thereby improving the aeration efficiency.

[0021] In the second aspect, the present application also provides an intelligent river ecological water supplement and water quality regulation method based on the Internet of Things, which comprises the following steps: S1, collect river water quality data and environmental parameters through fixed monitoring terminals and mobile monitoring drones, collect pH, dissolved oxygen, turbidity, ammonia nitrogen and other data through the fixed monitoring terminals and upload them to the edge computing gateway; the mobile monitoring drones carry sensor cabins to collect blind area water quality data and return them to the edge computing gateway; at the same time, collect river water level, flow and rainfall and evaporation data in meteorological forecast.

[0022] S2, the edge computing gateway receives the collected data and performs local real-time preprocessing, eliminates abnormal data, generates emergency response instructions when detecting that the dissolved oxygen is lower than the set value or a sudden pollution event occurs; at the same time, the preprocessed data is uploaded to the cloud decision platform; S3, the cloud decision platform predicts the water quality change trend and generates a coordinated control suggestion based on a machine learning model combined with an ecological water demand model, and calls a dynamic water replenishment algorithm to calculate the rotating speed of the variable frequency pump station and the opening of the intelligent electromagnetic valve; S4, after receiving the instructions, the edge computing gateway controls the multi-stage variable frequency pump station to start and adjust the flow, and controls the intelligent electromagnetic valve to supply water according to the opening; simultaneously, the rainwater recovery unit is started to collect and filter the rainfall runoff and supplement the water replenishment system; according to the dissolved oxygen monitoring data, the aeration control algorithm is called to adjust the rotating speed of the centrifugal aerator, and the ecological restoration module is started to purify the water body; S5, the intelligent power controller automatically switches the diesel / electric dual-mode driving mode according to the water replenishment demand and aeration load; solar auxiliary power supply is enabled to preferentially supply power to the sensor network and control system, and the energy storage battery pack stores surplus power, and switches to grid charging during the night valley power price period; S6, real-time monitoring of equipment operating state, identifying pump station abnormalities, automatically closing upstream valves; detecting that the inclination angle of the equipment is greater than the set angle, triggering the emergency stop button to cut off the power supply.

[0023] As a preferred technical solution of the present application, step S3 comprises: The cloud decision platform receives the preprocessed water quality data, river water level, flow and weather forecast data uploaded by the edge computing gateway; Based on the LSTM neural network machine learning model, the ecological water demand model is combined to predict the water quality change trend; According to the prediction result, the ecological water demand, water quality standard requirement and water replenishment energy consumption are comprehensively considered to generate a water replenishment, aeration and purification coordinated control suggestion; The dynamic water replenishment algorithm is called, the minimum water replenishment energy consumption and the maximum water quality standard rate are taken as the optimization objectives, the real-time water quality data, weather forecast data and ecological water demand model parameters are input, and the rotating speed of the variable frequency pump station and the opening of the intelligent electromagnetic valve in the distributed pipeline network are calculated.

[0024] In step S3, based on the LSTM neural network machine learning model, the ecological water demand model is combined to predict the water quality change trend, and the specific steps comprise: The water quality data, river water level, flow and weather forecast data uploaded to the cloud decision platform are normalized, and the data is converted into a format suitable for input of the LSTM model; The input sequence of the LSTM model is constructed, and the water quality data, river water level, flow and meteorological forecast data after normalization processing are combined into an input feature vector in time sequence; The ecological water demand of the river is calculated according to the ecological water demand model, and the ecological water demand is taken as an additional feature and integrated into the input sequence of the LSTM model; The LSTM neural network model is trained using historical data, and after training, the constructed input sequence is input into the trained LSTM model to predict the water quality change trend in the future period; The prediction results output by the LSTM model are subjected to inverse normalization processing to convert into actual water quality parameter values, and the prediction results of the water quality change trend are obtained.

[0025] As a preferred technical solution of the present application, according to the prediction results, the steps of generating the water supplementing, aeration, purification collaborative control suggestions considering the ecological water demand, water quality standard requirement and water supplementing energy consumption include: A multi-objective optimization function is constructed to minimize the water supplementing energy consumption, maximize the water quality standard compliance rate and meet the ecological water demand; The standard compliance constraints of water quality parameters are set, for example, the dissolved oxygen (DO) is not less than 5 mg / L, and the ammonia nitrogen (NH3-N) does not exceed the specified limit value; the ecological water demand constraint condition is set to ensure that the ecological water demand of the river is met; A multi-objective optimization algorithm such as genetic algorithm or particle swarm optimization algorithm is called to optimize the operation parameters such as water supplementing, aeration and purification; According to the optimization results, specific collaborative control suggestions such as water supplementing, aeration, purification and the like are generated, including the speed of the variable frequency pump station, the opening of the intelligent electromagnetic valve, the speed of the aerator and the starting conditions of the ecological restoration module and the like; The generated collaborative control suggestions are verified to ensure that they can effectively reduce the water supplementing energy consumption under the premise of meeting the ecological water demand and water quality standard requirement; if necessary, the suggestions are adjusted to optimize the overall performance.

[0026] As can be seen from the above technical solution, the present application has the following advantages: through the dynamic adjustment of the water supplementing amount by the multi-stage variable frequency pump station and the precipitation and filtration technology of the rainwater recovery unit, the precise allocation of water resources and the utilization of rainwater resources are realized, and the comprehensive water saving efficiency is improved; the fixed monitoring terminal and the mobile unmanned aerial vehicle cooperatively collect data, and the local emergency response of edge computing and the prediction of the cloud machine learning model are combined to realize the rapid identification and dynamic regulation of water quality abnormalities; the combination of the artificial wetland and the biological membrane reactor enhances the adsorption of heavy metals and the degradation of organic pollutants, and cooperates with the ecological water demand model to protect the habitat environment of aquatic organisms, so that the self-purification capacity of the river is significantly improved; the Internet of Things technology integrates the whole process of sensing, decision-making and execution, reduces manual intervention, realizes the closed-loop regulation and control of monitoring, analysis, decision-making and execution, and improves the treatment efficiency and stability. Attached Figure Description

[0027] To more clearly illustrate the technical solution of this application, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 A block diagram of a system provided in an embodiment of the present invention.

[0029] Figure 2 This is a flowchart illustrating the method provided in an embodiment of the present invention. Detailed Implementation

[0030] To make the purpose, features, and advantages of this application more apparent and understandable, specific embodiments and accompanying drawings will be used to clearly and completely describe the technical solution protected by this application. Obviously, the embodiments described below are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0031] Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this application and in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0032] like Figure 1 As shown, the present invention provides an intelligent river ecological water replenishment and water quality control system based on the Internet of Things, including an ecological water replenishment module, a water quality monitoring module, an intelligent control module, and an ecological restoration module; The ecological water replenishment module includes a multi-stage variable frequency pumping station, a distributed pipeline network, and a rainwater harvesting unit. The multi-stage variable frequency pumping station is connected to the river through the distributed pipeline network. The rainwater harvesting unit is connected to the distributed pipeline network after sedimentation and filtration. It is used to dynamically adjust the water replenishment volume according to the water demand of different sections of the river and realize the resource utilization of rainwater. The water quality monitoring module includes a fixed monitoring terminal and a mobile monitoring drone. The fixed monitoring terminal is deployed at key sections of the river channel, and the mobile monitoring drone is used to patrol and cover the fixed monitoring blind area. Both the fixed monitoring terminal and the mobile monitoring drone are integrated with pH, ​​dissolved oxygen, turbidity and ammonia nitrogen sensors to collect water quality data in real time and upload it to the intelligent control module. The intelligent control module comprises an edge computing gateway and a cloud decision platform. The edge computing gateway is in communication connection with the water quality monitoring module, the ecological water supplement module and the ecological restoration module, is used for local real-time processing of water quality data and responding to emergency instructions, and the cloud decision platform is in communication connection with the edge computing gateway, is deployed with a machine learning model, is used for predicting water quality change trend and generating a coordinated control strategy of water supplement, aeration and purification. The ecological restoration module comprises a stepped constructed wetland unit and a biofilm reactor. The constructed wetland unit is planted with submerged plants, and the biofilm reactor is filled with biological filler and is matched with an aerator, and is used for adsorbing heavy metals and degrading organic pollutants. The intelligent control module controls the water supplement amount of the ecological water supplement module through a dynamic water supplement algorithm based on real-time data collected by the water quality monitoring module, meteorological forecast data and ecological water demand data calculated based on an ecological water demand model, and adjusts the operation parameters of the aerator of the ecological restoration module through an aeration control algorithm, so as to realize efficient utilization of water resources, real-time optimization of water quality and ecological coordinated restoration.

[0033] In some embodiments, the ecological water supplement module, the multi-stage variable frequency pump station is a stainless steel cubic structure, and a variable frequency water pump with a set power range is arranged inside. The distributed pipeline network adopts a PE pipeline with a preset diameter range, the pipeline surface is coated with an ultraviolet-proof coating, and an intelligent electromagnetic valve control node with an aluminum alloy shell is arranged every set distance along the river bank. The rainwater recovery unit comprises a conical water collecting tank and a sedimentation and filtration box, and a plurality of layers of quartz sand and activated carbon filter elements are arranged in the sedimentation and filtration box.

[0034] The pump station body is a stainless steel cubic structure (length 2m x width 1.5m x height 1.8m), a variable frequency water pump (power 5-15kW) is arranged inside, and a PE pipeline (diameter 200-300mm) is connected through a flange. The pipeline surface is coated with an ultraviolet-proof coating, and is laid in sections along the river bank, with an intelligent electromagnetic valve control node (size Φ150mm x 200mm, aluminum alloy shell) arranged every 50 meters. The rainwater recovery unit adopts a conical water collecting tank (diameter 3m, height 1.2m, glass steel material), and a sedimentation and filtration box (1m³ volume, multiple layers of quartz sand + activated carbon filter elements) is connected to the bottom.

[0035] In some embodiments, the water quality monitoring module, the fixed monitoring terminal is a cylindrical buoy structure made of ABS engineering plastic, and a solar panel is integrated on the top. The mobile monitoring unmanned aerial vehicle is designed as a six-rotor wing, and a carbon fiber body is adopted, and a waterproof level IP68 miniature sensor cabin is hung on the bottom.

[0036] The fixed monitoring terminal is a cylindrical buoy structure (diameter 0.8 m, height 1.2 m, ABS engineering plastic), the top of which is integrated with a solar panel (0.5 m x 0.5 m), and the inside of which is loaded with multi-parameter sensors (pH, dissolved oxygen, turbidity, ammonia nitrogen, accuracy ±0.5%). The mobile monitoring unmanned aerial vehicle adopts a six-rotor design (shaft distance 1.2 m, carbon fiber body), and the bottom of which is suspended with a micro sensor cabin (size 200 mm x 150 mm x 100 mm, waterproof level IP68), with a cruising radius of 5 km. The sensor data is transmitted back in real time through a 4G module.

[0037] In some embodiments, the intelligent control module, the edge computing gateway is provided with a wall-mounted aluminum alloy box body, an industrial-grade PLC supporting RS485 / CAN bus and a 5G communication module are built-in; the cloud decision platform is deployed in a server cluster, and the front-end interactive interface supports three-dimensional river model visualization based on GIS map, and the control instructions are issued through the optical fiber network.

[0038] The edge computing gateway is a wall-mounted metal box body (400 mm x 300 mm x 150 mm, aluminum alloy shell). The cloud decision platform is deployed in a server cluster, and the front-end interactive interface supports three-dimensional river model visualization (based on GIS map, scale 1:500). Control instructions are issued to the pump station and aerator through the optical fiber network.

[0039] In some embodiments, the ecological restoration module, the constructed wetland unit adopts an HDPE impermeable membrane base, and submerged plants are planted according to the set planting density; the biofilm reactor is a cylindrical stainless steel tank, which is filled with polyethylene biological filler, and is matched with a centrifugal aerator.

[0040] The constructed wetland unit is arranged in a stepped manner (single-stage size 10 m x 2 m x 0.5 m, HDPE impermeable membrane base), and submerged plants such as Vallisneria and reed are planted (density 20 plants / m²). The biofilm reactor is a cylindrical stainless steel tank (diameter 2 m, height 3 m, wall thickness 5 mm), which is filled with polyethylene biological filler (diameter 50 mm, porosity 90%) and matched with a centrifugal aerator (power 3 kW, aeration capacity 5 m³ / h).

[0041] In some embodiments, the system further comprises a hybrid drive system, which is electrically connected with the multi-stage variable frequency pump station of the ecological water replenishment module, and comprises a diesel / electric dual-mode drive unit and a solar auxiliary power supply unit; the diesel / electric dual-mode drive unit comprises a single-cylinder water-cooled diesel engine and a brushless DC motor, which automatically switches the power mode based on water flow resistance, battery capacity and water replenishment demand through an intelligent switching controller; the solar auxiliary power supply unit comprises a folding photovoltaic panel array and a lithium iron phosphate battery pack.

[0042] Diesel engine: single-cylinder water-cooled (power 15-20 horsepower), used for high-load working conditions (such as high-flow water replenishment, flood period emergency drainage), equipped with electronic fuel injection system, oil consumption reduced by 15%.

[0043] Brushless DC motor (power 10kW): switch to pure electric mode during daily low-load operation, noise <60dB, support regenerative braking energy recovery.

[0044] Intelligent switching controller: automatically switch power mode based on river flow resistance, battery capacity, and water replenishment demand, response time <0.5 seconds.

[0045] Solar power assistance: Foldable photovoltaic panel array (single panel size 1.2m x 2m, conversion efficiency ≥22%), daily average power generation 8-12kWh, priority for sensor network and control system power supply.

[0046] Energy storage battery pack: 48V / 300Ah lithium iron phosphate battery pack, supports fast charging (2 hours full), cycle life ≥5000 times.

[0047] In some embodiments, the input of the dynamic water replenishment algorithm includes real-time water quality data, weather forecast data of rainfall and evaporation, and ecological water demand data calculated based on the ecological water demand model, and the output is the variable frequency pump station speed and electromagnetic valve opening degree, and the optimization goal is to minimize the water replenishment energy consumption and maximize the water quality compliance rate. The aeration control algorithm is a PID control based on dissolved oxygen feedback, adjusting the aeration machine speed in the set speed range, and automatically reducing the frequency at night.

[0048] Dynamic water replenishment algorithm: Input: real-time water quality data, weather forecast (rainfall, evaporation), ecological water demand data (fish oxygen demand ≥5mg / L) calculated based on the ecological water demand model; Output: variable frequency pump station speed (0-100%), electromagnetic valve opening degree (0-100%); Optimization goal: minimize water replenishment energy consumption, maximize water quality compliance rate.

[0049] Aeration control algorithm: PID control based on dissolved oxygen (DO) feedback, adjusting the centrifugal aerator speed (0-3000rpm), response time ≤10 seconds; Automatic frequency reduction at night (reduce noise pollution).

[0050] In some embodiments, the artificial wetland unit of the ecological restoration module is connected with the biofilm reactor through quick release bolts or hydraulic joints, the pipeline interface adopts double sealing of O-ring and waterproof cement, and the upstream valve is automatically closed when detecting that the pipeline pressure drops by more than a set threshold; the aerator adopts a pontoon type structure, and the suspension height is adjusted through a counterweight.

[0051] As Figure 2 shown, the embodiment of the application also provides a smart river ecological water supplement and water quality regulation method based on Internet of Things, comprising the following steps: S1, collecting river water quality data and environmental parameters through fixed monitoring terminals and mobile monitoring drones, collecting pH, dissolved oxygen, turbidity, ammonia nitrogen and other data by the fixed monitoring terminals and uploading to the edge computing gateway; the mobile monitoring drones carry sensor cabins to collect blind area water quality data and return to the edge computing gateway; at the same time, collecting river water level, flow and rainfall, evaporation data in weather forecast.

[0052] In the embodiment of the application, through the fixed monitoring terminals deployed at key sections of the river and the mobile monitoring drones covering the fixed monitoring blind area, river water quality data and environmental parameters are collected in real time; the fixed monitoring terminals collect pH, dissolved oxygen, turbidity, ammonia nitrogen data and upload to the edge computing gateway; the mobile monitoring drones carry micro sensor cabins, and collect blind area water quality data synchronously during cruising, and return to the edge computing gateway; at the same time, collecting river water level, flow and rainfall, evaporation data in weather forecast.

[0053] S2, after the edge computing gateway receives the collected data, local real-time preprocessing is performed, and abnormal data is eliminated, when detecting that the dissolved oxygen is lower than the set value or a sudden pollution event occurs, an emergency response instruction is immediately generated; at the same time, the preprocessed data is uploaded to the cloud decision platform; In this step, abnormal data is eliminated through Kalman filtering, when detecting that the dissolved oxygen is less than or equal to the first set value or a sudden pollution event occurs, an emergency response instruction is immediately generated; at the same time, the preprocessed data is uploaded to the cloud decision platform, the cloud decision platform based on the LSTM neural network machine learning model, fuses the ecological water demand model, predicts the water quality change trend and generates the collaborative regulation suggestion.

[0054] S3, the cloud decision platform based on the machine learning model fuses the ecological water demand model, predicts the water quality change trend and generates the collaborative regulation suggestion, calls the dynamic water supplement algorithm to calculate the variable frequency pump station rotating speed and the opening degree of the intelligent electromagnetic valve; In the embodiment, the cloud decision platform calls a dynamic water supplement algorithm to minimize water supplement energy consumption and maximize water quality compliance rate as an optimization target, input real-time water quality data, weather forecast data and ecological water demand model parameters, and calculate the frequency pump station speed and the opening of the intelligent electromagnetic valve in the distributed pipeline network; after the edge computing gateway receives the speed and opening instructions, the multi-stage variable frequency pump station is controlled to start and adjust the flow, and the intelligent electromagnetic valve is controlled to supply water according to the opening; the rainwater recovery unit is simultaneously started, rainfall runoff is collected through the conical water collecting tank, and after filtration through the sedimentation filter box, the water is supplemented to the water supplement system.

[0055] S4, after the edge computing gateway receives the instructions, the multi-stage variable frequency pump station is controlled to start and adjust the flow, and the intelligent electromagnetic valve is controlled to supply water according to the opening; the rainwater recovery unit is simultaneously started, rainfall runoff is collected and filtered and then supplemented to the water supplement system; according to the dissolved oxygen monitoring data, the aeration control algorithm is called to adjust the centrifugal aerator speed and start the ecological restoration module to purify the water body; Specifically, the oxygen monitoring data, the edge computing gateway calls the aeration control algorithm, adjusts the centrifugal aerator speed by PID feedback control, and when the dissolved oxygen is less than the first threshold value, the aeration amount is increased to the second set value; at the same time, the ecological restoration module is started, the cattail and reed planted in the ladder type constructed wetland unit adsorb heavy metals, the polyethylene biological filler filled in the biofilm reactor and the matching aerator accelerate the degradation of organic pollutants in the water body; the aerator is automatically operated at a low frequency at night to reduce noise pollution.

[0056] S5, the intelligent power controller automatically switches the diesel / electric dual-mode driving mode according to the water supplement demand and the aeration load; solar auxiliary power supply is started, the sensor network and the control system are preferentially powered, the energy storage battery pack stores surplus power, and the energy storage battery pack is automatically switched to the power grid charging during the night valley electricity price period; In this step, based on the water supplement demand in S3 and the aeration load in S4, the intelligent power controller automatically switches the diesel / electric dual-mode driving mode: the diesel engine is started in high load working conditions, and the brushless DC motor is switched to in low load working conditions; the solar auxiliary power supply is simultaneously started, the sensor network and the control system are preferentially powered through the folding photovoltaic panel array, the energy storage battery pack stores surplus power, and the energy storage battery pack is automatically switched to the power grid charging during the night valley electricity price period; S6, the real-time monitoring device operating state is monitored, pump station abnormalities are identified, and the upstream valve is automatically closed; when the device inclination angle is greater than the set angle, the emergency stop button is triggered to cut off the power supply. Specifically, in this step, the pump station abnormalities are identified by the vibration sensor and the current monitoring module, and the upstream valve is automatically closed when the pipeline pressure drops by a set percentage; when the device inclination angle is greater than the set angle, the mechanical self-locking emergency stop button is triggered to cut off the power supply.

[0057] As a preferred technical solution of the present application, step S3 comprises: The cloud decision platform receives the pre-processed water quality data, river water level, flow, and weather forecast data uploaded by the edge computing gateway; Based on the LSTM neural network machine learning model, the ecological water demand model is fused to predict the water quality change trend; According to the prediction result, the ecological water demand, water quality standard requirement, and water replenishment energy consumption are comprehensively considered to generate a water replenishment, aeration, and purification collaborative control suggestion; The dynamic water replenishment algorithm is called to minimize the water replenishment energy consumption and maximize the water quality standard compliance rate as the optimization target, and the real-time water quality data, weather forecast data, and ecological water demand model parameters are input to calculate the variable frequency pump station speed and the opening of the intelligent electromagnetic valve in the distributed pipeline network.

[0058] In step S3, the specific steps of predicting the water quality change trend based on the LSTM neural network machine learning model and fusing the ecological water demand model include: The water quality data, river water level, flow, and weather forecast data uploaded to the cloud decision platform are normalized to convert the data into a format suitable for LSTM model input; The normalized water quality data, river water level, flow, and weather forecast data are combined into an input feature vector in time sequence to construct the input sequence of the LSTM model; The ecological water demand of the river is calculated according to the ecological water demand model, and the ecological water demand is fused as an additional feature into the input sequence of the LSTM model; The LSTM neural network model is trained using historical data, and after training, the constructed input sequence is input into the trained LSTM model to predict the water quality change trend in the future period; The prediction result output by the LSTM model is de-normalized to convert into actual water quality parameter values to obtain the prediction result of the water quality change trend.

[0059] As a preferred technical solution of the present application, according to the prediction result, the ecological water demand, water quality standard requirement, and water replenishment energy consumption are comprehensively considered to generate a water replenishment, aeration, and purification collaborative control suggestion, which comprises: A multi-objective optimization function is constructed to minimize the water replenishment energy consumption, maximize the water quality standard compliance rate, and meet the ecological water demand; The standard compliance conditions of water quality parameters are set, such as the dissolved oxygen (DO) is not less than 5 mg / L, and the ammonia nitrogen (NH3-N) does not exceed the specified limit value; the ecological water demand constraint condition is set to ensure that the ecological water demand of the river is met; A multi-objective optimization algorithm such as genetic algorithm or particle swarm optimization algorithm is called to optimize the operation parameters such as water replenishment, aeration, and purification. According to the optimization result, specific water supplement, aeration, purification and the like collaborative control suggestions are generated, including the rotating speed of the variable frequency pump station, the opening of the intelligent electromagnetic valve, the rotating speed of the aerator and the starting condition of the ecological restoration module and the like; The generated collaborative control suggestions are verified to ensure that they can effectively reduce the water supplement energy consumption under the premise of meeting the ecological water demand and water quality standard requirements; if necessary, the suggestions are adjusted to optimize the overall performance.

[0060] In the embodiment of the application, the specific steps of generating the collaborative control suggestions include: According to the prediction result of the water quality change trend, it is evaluated whether the current water quality parameter meets the standard requirement, such as whether the dissolved oxygen (DO) is ≥5 mg / L and whether the ammonia nitrogen (NH3-N) is lower than the specified limit value; the ecological water demand of the river channel in the current and future period of time is evaluated in combination with the ecological water demand model to ensure that the water supplement operation can meet the survival demand of aquatic organisms; the energy consumption of the current water supplement and aeration system is analyzed to evaluate the energy consumption difference under different water supplement strategies and aeration intensities; the collaborative control suggestions of water supplement, aeration, purification and the like are generated by comprehensively considering the water quality standard, the ecological water demand and the energy consumption evaluation result, including the rotating speed of the variable frequency pump station, the opening of the intelligent electromagnetic valve, the rotating speed of the aerator and the starting condition of the ecological restoration module and the like.

[0061] The specific steps of the dynamic water supplement algorithm call include: The dynamic water supplement algorithm is initialized, and the basic parameters of the algorithm are set, such as the optimization target weight, the iteration number and the like; the real-time water quality data, the weather forecast data and the ecological water demand model parameters are input into the dynamic water supplement algorithm; the rotating speed of the variable frequency pump station and the opening of the intelligent electromagnetic valve in the distributed pipe network are calculated by the algorithm with the minimum water supplement energy consumption and the maximum water quality standard rate as the optimization target; the rotating speed of the variable frequency pump station and the opening of the intelligent electromagnetic valve instruction are output to control the operation of the water supplement system.

[0062] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined in this application can be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the application will not be limited to these embodiments shown in this application, but will conform to the widest scope consistent with the principles and novel features disclosed in this application.

Claims

1. An Internet of Things-based intelligent river ecological water replenishment and water quality regulation system, characterized in that, The ecological water supplement module, the water quality monitoring module, the intelligent control module and the ecological restoration module are comprised. The ecological water supplement module comprises a multi-stage variable frequency pump station, a distributed pipeline network and a rainwater recovery unit, the multi-stage variable frequency pump station is communicated with the river channel through the distributed pipeline network, the rainwater recovery unit is communicated with the distributed pipeline network after being filtered by precipitation, and is used for dynamically adjusting the water supplement amount according to the water demand of the river channel and realizing rainwater resource utilization. The water quality monitoring module comprises a fixed monitoring terminal and a mobile monitoring unmanned aerial vehicle, the fixed monitoring terminal is arranged at a key section of the river channel, and the mobile monitoring unmanned aerial vehicle is used for cruising and covering the blind area of the fixed monitoring terminal, the fixed monitoring terminal and the mobile monitoring unmanned aerial vehicle are both integrated with pH, dissolved oxygen, turbidity and ammonia nitrogen sensors, and are used for collecting water quality data in real time and uploading the water quality data to the intelligent control module. The intelligent control module comprises an edge computing gateway and a cloud decision platform, the edge computing gateway is communicated with the water quality monitoring module, the ecological water supplement module and the ecological restoration module, is used for locally processing water quality data in real time and responding to emergency instructions, the cloud decision platform is communicated with the edge computing gateway, is arranged with a machine learning model, is used for predicting water quality change trend and generating a collaborative control strategy of water supplement, aeration and purification. The ecological restoration module comprises a stepped artificial wetland unit and a biological membrane reactor, the artificial wetland unit is planted with submerged plants, and the biological membrane reactor is filled with biological filler and is matched with an aerator, and is used for adsorbing heavy metals and degrading organic pollutants. The intelligent control module controls the water supplement amount of the ecological water supplement module through a dynamic water supplement algorithm based on real-time data collected by the water quality monitoring module, meteorological forecast data and ecological water demand data calculated based on an ecological water demand model, and adjusts the operation parameters of the aerator of the ecological restoration module through an aeration control algorithm, so that water resource is efficiently utilized, water quality is optimized in real time, and ecological restoration is collaboratively achieved.

2. The Internet of Things-based intelligent river ecological water replenishment and water quality regulation system according to claim 1, characterized in that, In the ecological water supplement module, the multi-stage variable frequency pump station is a stainless steel cubic structure, and a variable frequency water pump with a set power range is arranged in the multi-stage variable frequency pump station, the distributed pipeline network adopts PE pipes with a preset diameter range, the surface of the pipes is coated with an ultraviolet-proof coating, and an intelligent electromagnetic valve control node with an aluminum alloy shell is arranged along the river bank at every interval of a set distance, the rainwater recovery unit comprises a conical water collecting tank and a precipitation and filtration box, and a plurality of layers of quartz sand and activated carbon filter elements are arranged in the precipitation and filtration box. 3.The Internet of Things based intelligent river ecological water supplementing and water quality regulating system according to claim 2, characterized in that, In the water quality monitoring module, the fixed monitoring terminal is a cylindrical buoy structure and is made of ABS engineering plastic, and a solar panel is integrated on the top of the fixed monitoring terminal, and the mobile monitoring unmanned aerial vehicle is designed as a six-rotor type and has a carbon fiber body, and a miniature sensor cabin with a waterproof level of IP68 is hung on the bottom of the mobile monitoring unmanned aerial vehicle.

4. The Internet of Things-based intelligent river ecological water replenishment and water quality regulation system according to claim 3, characterized in that, In the intelligent control module, the edge computing gateway is provided with a wall-mounted aluminum alloy box body, an industrial-grade PLC supporting RS485 and CAN bus and a 5G communication module are arranged in the edge computing gateway, the cloud decision platform is arranged in a server cluster, a front-end interactive interface supports three-dimensional river channel model visualization based on a GIS map, and control instructions are issued through a fiber network. 5.The Internet of Things based intelligent river ecological water supplementing and water quality regulating system according to claim 4, characterized in that, The ecological restoration module, the constructed wetland unit adopts HDPE anti-seepage film base, and submerged plants are planted according to a set planting density; the bio-membrane reactor is a cylindrical stainless steel tank body, which is internally filled with polyethylene biological filler, and is matched with a centrifugal aerator. 6.The Internet of Things based intelligent river ecological water supplementing and water quality regulating system according to claim 5, characterized in that, The system also comprises a hybrid power driving system, which is electrically connected with the multi-stage variable frequency pump station of the ecological water replenishment module, and comprises a diesel / electric dual-mode driving unit and a solar auxiliary power supply unit; the diesel / electric dual-mode driving unit comprises a single-cylinder water-cooled diesel engine and a brushless DC motor, and automatically switches the power mode based on the water flow resistance, the battery power and the water replenishment demand through an intelligent switching controller; the solar auxiliary power supply unit comprises a folding photovoltaic panel array and a lithium iron phosphate battery pack.

7. The Internet of Things-based smart river ecological water replenishment and water quality regulation system according to claim 6, characterized in that, The input of the dynamic water replenishment algorithm comprises real-time water quality data, meteorological forecast data of rainfall and evaporation, and ecological water demand data calculated based on an ecological water demand model, the output is the rotating speed of the variable frequency pump station and the opening degree of the intelligent electromagnetic valve, and the optimization target is to minimize the water replenishment energy consumption and maximize the water quality compliance rate; The aeration control algorithm is a PID control based on dissolved oxygen feedback, which adjusts the rotating speed of the aerator in the set rotating speed range, and automatically reduces the rotating speed at night. 8.The Internet of Things based smart river ecological water replenishment and water quality regulation system according to claim 7, characterized in that, The constructed wetland unit and the bio-membrane reactor of the ecological restoration module are connected through quick-release bolts or hydraulic joints, the pipeline interface adopts double sealing of O-rings and waterproof cement, and when the pipeline pressure drops suddenly by more than a set threshold, the upstream valve is automatically closed; the aerator adopts a float type structure, and the suspension height is adjusted through a counterweight.

9. An Internet of Things-based intelligent river ecological water replenishment and water quality regulation method, characterized in that, The method comprises the following steps: S1, collecting river water quality data and environmental parameters through fixed monitoring terminals and mobile monitoring drones, collecting pH, dissolved oxygen, turbidity and ammonia nitrogen data through the fixed monitoring terminals and uploading to an edge computing gateway; The mobile monitoring drones carry sensor cabins to collect blind area water quality data and return to the edge computing gateway; at the same time, collecting river water level, flow and rainfall and evaporation data in weather forecast; S2, after receiving the collected data, the edge computing gateway performs local real-time preprocessing, and eliminates abnormal data; when it is detected that the dissolved oxygen is lower than a set value or a sudden pollution event occurs, an emergency response instruction is immediately generated; at the same time, the preprocessed data is uploaded to a cloud decision platform; S3, the cloud decision platform fuses an ecological water demand model based on a machine learning model, predicts the water quality change trend and generates a coordinated control suggestion, and calls a dynamic water replenishment algorithm to calculate the rotating speed of the variable frequency pump station and the opening degree of the intelligent electromagnetic valve; S4, after receiving the instruction, the edge computing gateway controls the multi-stage variable frequency pump station to start and adjust the flow, and controls the intelligent electromagnetic valve to supply water according to the opening degree; S5, the intelligent power controller automatically switches the diesel / electric dual-mode driving mode according to the water replenishment demand and the aeration load; the solar auxiliary power supply is enabled, and the sensor network and the control system are preferentially powered, and the energy storage battery pack stores surplus electric energy, and switches to grid charging at night during the low valley electricity price period. ​ S6, real-time monitoring equipment running state, identify pump station abnormal, automatic closing upstream valve; detection equipment tilt angle greater than the set angle, trigger emergency stop button cut off power supply. 10.The Internet of Things based smart river ecological water replenishment and water quality regulation method according to claim 9, characterized in that, Step S3 includes: The cloud decision platform receives the pre-processed water quality data, river water level, flow, and weather forecast data uploaded by the edge computing gateway; Based on the LSTM neural network machine learning model, the ecological water demand model is fused to predict the water quality change trend; According to the prediction result, the ecological water demand, water quality standard requirement and water replenishment energy consumption are comprehensively considered to generate water replenishment, aeration and purification collaborative control suggestions; The dynamic water replenishment algorithm is called to minimize the water replenishment energy consumption and maximize the water quality standard rate as the optimization target, the real-time water quality data, weather forecast data and ecological water demand model parameters are input, and the speed of the variable frequency pump station and the opening of the intelligent electromagnetic valve in the distributed pipeline network are calculated.

Images