A method and system for coordinated control of drainage cells for emergency water accumulation

Abstract

The present application relates to the technical field of emergency water accumulation emergency drainage, in particular to a drainage square bin cooperative control method and system for emergency water accumulation, comprising the following steps: real-time acquisition of medium physical characteristic parameters in the water accumulation area and real-time operation parameters of each drainage square bin; construction of a medium characteristic-parameter drift correlation relationship based on the medium physical characteristic parameters and the real-time operation parameters, and establishment of a parameter drift chain conduction logic. The present application establishes a dynamic correlation model between the water accumulation medium characteristics and the drainage square bin operation parameters, realizes early prediction and hierarchical cooperative correction of the control parameter drift, solves the problems of square bin operation parameter imbalance, increased energy consumption and intensified equipment wear caused by neglecting the dynamic change of medium characteristics in the prior art, and can adapt the operation state of multiple drainage square bins to the real-time water accumulation environment at all times, ensuring the stability and continuity of emergency drainage operation.

Description

Technical Field

[0001] This invention relates to the field of emergency drainage technology for sudden flooding, specifically to a collaborative control method and system for drainage silos used in emergency flooding. Background Technology

[0002] Urban flooding is a common urban disaster during extreme weather events. Drainage compartments, as mobile emergency drainage equipment, can be quickly deployed to flooded areas, using high-powered pumps to pump water into municipal sewer systems or designated discharge points. Drainage compartments typically integrate power, drainage, control, and auxiliary systems, enabling them to independently complete water pumping operations. They are widely used for emergency drainage in urban roads, underground parking garages, and low-lying areas. Currently, most drainage compartments support remote centralized control of multiple units, allowing for adjustments to overall drainage power based on water depth to address varying degrees of flooding.

[0003] When multiple drainage silos operate in concert, all control logic focuses on the flow rate and efficiency of water pumping, completely ignoring the implicit coupling effect between changes in the characteristics of the water medium and the operating parameters of the silos. In emergency waterlogging scenarios, the water is not a single clean water medium; it continuously mixes with different proportions of silt, floating debris, and dissolved pollutants during the pumping process, causing the density, viscosity, and other medium properties of the water to change dynamically. Because of the different water inlet areas, the drainage silos in different locations encounter different water medium characteristics, resulting in varying operating resistance and energy consumption of their drainage pumps. This fluctuation is transmitted to the control module through the power system, causing implicit drift in the control parameters of each silo, gradually disrupting the originally coordinated operating state. More critically, drift in the control parameters of a single silo can be transmitted to surrounding silos via the flow of accumulated water, triggering a chain reaction of parameter drift. This results in a severe mismatch between the operating parameters of multiple silos and the real-time characteristics of the accumulated water medium. This not only significantly increases power consumption but also leads to accelerated wear of the drainage pump impeller, abnormal operating noise, and even sudden drops in local flow rates. Current technologies lack any mechanism for identifying, predicting, and collaboratively correcting the implicit drift and chain imbalances in control parameters caused by dynamic changes in the characteristics of the accumulated water medium, making it impossible to achieve dynamic adaptation of silo operating parameters to the characteristics of the accumulated water medium. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a collaborative control method and system for drainage silos used in emergency flooding, which solves the problem of parameter drift and chain imbalance caused by dynamic changes in the characteristics of the water medium during collaborative operation of existing drainage silos.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a collaborative control method for drainage silos used in emergency flooding, comprising the following steps: Real-time acquisition of physical property parameters of the medium in the water accumulation area and real-time operating parameters of each drainage compartment; Based on the physical properties of the medium and the real-time operating parameters, a correlation between medium properties and parameter drift is constructed, and a parameter drift chain propagation logic is established. Using the time-series prediction results of the physical property parameters of the medium, and combined with the correlation between the medium properties and parameters, the drift trend of the control parameters of each drainage compartment and its transmission impact on surrounding drainage compartments are analyzed. Based on the comparison between the quantified value of the control parameter drift trend and the preset threshold, hierarchical collaborative correction is performed. By adjusting the operating load and filtration level of the drainage silos, the chain transmission of parameter drift between the drainage silo groups is blocked. The matching degree of the corrected operating parameters is verified, and the correlation between the medium characteristics and parameter drift is dynamically corrected based on the verification results.

[0006] Furthermore, the physical properties of the medium include the density, viscosity, contaminant concentration, and conductivity of the accumulated water; The real-time operating parameters include the pump speed, inlet and outlet pressure, operating current, and impeller vibration frequency. The real-time acquisition process adopts a combination of high-frequency acquisition and intermittent acquisition. When the fluctuation value of the physical characteristic parameter of the medium exceeds the fluctuation threshold, the acquisition is switched from intermittent acquisition to high-frequency acquisition.

[0007] Furthermore, the sensor surface for acquiring the physical property parameters of the medium is covered with a nano-anti-stick coating, and high-pressure spray cleaning is initiated at preset intervals. The sensors are deployed at the inlet, middle and outlet of the water accumulation area, and each drainage compartment has an independent set of sensors deployed at its inlet.

[0008] Furthermore, the medium characteristic-parameter drift correlation is established by analyzing the coupled effects of changes in medium density and viscosity on the operating resistance of the drainage pump; The parameter drift interlocking transmission logic is used to identify the path, amplitude, and rate at which parameter fluctuations of a single drainage silo are transmitted to surrounding drainage silos through the water flow medium.

[0009] Furthermore, when the quantized value of the control parameter drift trend is lower than the correction threshold, a micro-call instruction is sent to the drainage container to reduce the parameter drift rate of the drainage container by initiating an autonomous micro-calibration process and fine-tuning the pump body operating load.

[0010] Furthermore, the hierarchical collaborative correction includes a local correction layer, a regional collaborative layer, and a global control layer; wherein, the local correction layer is used to perform parameter depth correction of the drainage container; The regional coordination layer is used to send pre-correction commands to other container units within a preset range around the drainage container unit to build a drift blocking barrier; The global control layer is used to coordinate and fine-tune the operating parameters of all drainage compartments within the waterlogged area.

[0011] Furthermore, when a sudden change in the physical properties of the medium is detected, the media pretreatment components of the drainage container are controlled to switch the filtration level to filter out pollutants and silt in the accumulated water. Simultaneously, the medium characteristic-parameter drift correlation is updated based on the parameters after the mutation, and a synchronous correction command is issued to all drainage silos in the affected area.

[0012] Furthermore, the time-series prediction result is a prediction curve generated by combining historical medium data and real-time acquired data using a deep learning algorithm. The prediction curve reflects the direction of change of the medium's physical property parameters within a preset time period in the future.

[0013] Furthermore, the matching degree verification adopts a dual verification standard, simultaneously verifying the matching degree between the corrected operating parameters and the medium characteristics, as well as the operating stability and energy consumption value of the drainage container. If the verification fails, the verification result will be fed back and a secondary correction process will be triggered.

[0014] The present invention also provides a drainage container collaborative control system for emergency flooding, comprising: Distributed media characteristic sensing unit, used to collect parameters of water accumulation media; Multiple drainage compartments, each equipped with an operating parameter acquisition module, a pump load adjustment module, a control parameter self-calibration module, and a media pretreatment component with multi-stage filtration. An edge computing control terminal, which integrates a parameter drift prediction module, a collaborative parameter correction unit, a medium characteristic timing prediction module, a drift conduction blocking module, and a parameter correction verification module; The edge computing control terminal connects the distributed media characteristic sensing unit and each of the drainage silos via bidirectional communication.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention establishes a dynamic correlation model between the characteristics of the water-accumulating medium and the operating parameters of the drainage silo. By combining time-series prediction of medium characteristics and the chain transmission logic of parameter drift, it identifies the drift trend of control parameters of a single silo and its transmission impact on surrounding equipment in advance. Then, it adopts a hierarchical collaborative correction mechanism to dynamically adjust the operating load and filtration level of the silo according to the degree of drift, blocking the chain transmission of parameter drift between silo groups. At the same time, it uses a dual verification standard to verify the correction effect and dynamically correct the correlation model, realizing the dynamic adaptation of the silo operating parameters and the real-time characteristics of the water-accumulating medium. This effectively solves the problem of silo operating imbalance caused by ignoring the dynamic changes of medium characteristics in the prior art, reduces power consumption, reduces impeller wear and abnormal operation of drainage pumps, ensures the stability and continuity of collaborative operation of multiple drainage silos, and improves the adaptability of emergency drainage systems to complex water-accumulating environments. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the overall process of collaborative control of the drainage container of the present invention; Figure 2 This is a schematic diagram of the parameter acquisition mode switching process of the present invention; Figure 3 This is a schematic diagram of the hierarchical collaborative correction execution process of the present invention; Figure 4 This is a schematic diagram of the parameter calibration verification and model correction process of the present invention; Figure 5 This is a schematic diagram of the collaborative control system architecture for drainage storage tanks according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figures 1-4 This invention provides a method for coordinated control of drainage silos for emergency flooding, characterized by the following steps: Real-time acquisition of physical property parameters of the medium in the water accumulation area and real-time operating parameters of each drainage compartment; Based on the physical properties of the medium and the real-time operating parameters, a correlation between medium properties and parameter drift is constructed, and a parameter drift chain propagation logic is established. Using the time-series prediction results of the physical property parameters of the medium, and combined with the correlation between the medium properties and parameters, the drift trend of the control parameters of each drainage compartment and its transmission impact on surrounding drainage compartments are analyzed. Based on the comparison between the quantified value of the control parameter drift trend and the preset threshold, hierarchical collaborative correction is performed. By adjusting the operating load and filtration level of the drainage silos, the chain transmission of parameter drift between the drainage silo groups is blocked. The matching degree of the corrected operating parameters is verified, and the correlation between the medium characteristics and parameter drift is dynamically corrected based on the verification results.

[0019] This solution establishes a dynamic correlation model between the characteristics of the water accumulation medium and the operating parameters of the drainage silo, enabling early prediction and hierarchical collaborative correction of control parameter drift. This solves the problems of imbalance in silo operating parameters, increased energy consumption, and accelerated equipment wear caused by ignoring the dynamic changes in medium characteristics in existing technologies. It ensures that the operating status of multiple drainage silos is always adapted to the real-time water accumulation environment, guaranteeing the stability and continuity of emergency drainage operations.

[0020] In one specific embodiment, the physical property parameters of the medium include the density, viscosity, contaminant concentration, and conductivity of the accumulated water; the real-time operating parameters include the speed of the drainage pump, inlet and outlet pressure, operating current, and impeller vibration frequency; the real-time acquisition process adopts a combination of high-frequency acquisition and intermittent acquisition, and when the fluctuation value of the physical property parameters of the medium exceeds the fluctuation threshold, the intermittent acquisition is switched to high-frequency acquisition.

[0021] Specifically, the acquisition of physical property parameters of the medium can comprehensively reflect the hydrodynamic characteristics and pollution level of the accumulated water, providing basic data for subsequent parameter drift analysis. The real-time operating parameters of the drainage silo directly reflect the equipment's working status and load. The acquisition method adopts a dual-mode switching design: intermittent acquisition is used when the medium characteristics are relatively stable, reducing system energy consumption and data processing pressure; when the medium characteristics change significantly, it automatically switches to high-frequency acquisition to ensure timely capture of key changes that may cause parameter drift. The intermittent acquisition frequency is set to 1 time / 10 seconds, and the high-frequency acquisition frequency is set to 1 time / 1 second; the fluctuation thresholds for the physical property parameters of the medium are quantified as follows: density fluctuation threshold 50 kg / m³, viscosity fluctuation threshold 0.0001 Pa. The thresholds for pollutant concentration fluctuations are 100 mg / L and conductivity fluctuations are 50 μS / cm. The acquisition mode switching is triggered when either threshold is reached.

[0022] In one specific embodiment, the sensor surface for acquiring the physical property parameters of the medium is covered with a nano-anti-stick coating, and high-pressure spray cleaning is initiated at preset intervals. The sensors are deployed at the inlet, middle and outlet of the water accumulation area, and each drainage compartment has an independent set of sensors deployed at its inlet.

[0023] Specifically, the nano-anti-stick coating effectively prevents silt, oil, and floating debris in the water from adhering to the sensor surface, ensuring measurement accuracy. A high-pressure spray cleaning system periodically rinses the sensors, further extending their lifespan and reliability. The sensors are deployed in a distributed manner, comprehensively covering different locations within the waterlogged area and accurately reflecting the spatial distribution differences in media characteristics. Each drainage compartment's inlet has an independently deployed sensor, enabling precise acquisition of the actual water media characteristics processed by each compartment, providing data support for accurate control of individual compartments. The preset cleaning interval can be adjusted according to the degree of water contamination; for example, in waterlogged scenarios with high silt content, the cleaning interval can be set to once every 30 minutes.

[0024] In one specific embodiment, the media characteristic-parameter drift correlation is established by analyzing the coupled effects of changes in media density and viscosity on the operating resistance of the drainage pump; The parameter drift interlocking transmission logic is used to identify the path, amplitude, and rate at which parameter fluctuations of a single drainage silo are transmitted to surrounding drainage silos through the water flow medium.

[0025] Specifically, the establishment of the correlation between medium characteristics and parameter drift is based on the fundamental principles of fluid mechanics. The operating resistance of a drainage pump consists of two parts: pressure differential resistance and viscous resistance. Pressure differential resistance is caused by the pressure difference formed before and after the impeller and is proportional to the square of the fluid density and velocity. Viscous resistance is caused by the boundary layer formed on the impeller surface due to the viscosity of the fluid and is proportional to the fluid viscosity and velocity.

[0026] This application improves upon the fluid dynamics resistance formula by incorporating the special structure of the drainage pump impeller, resulting in the following formula for the operating resistance experienced by the drainage pump impeller:

[0027] The derivation of this formula is as follows: 1. The classic formula for differential pressure resistance is: ,in This is the pressure drag coefficient; 2. The classical viscous resistance formula is: ,in It is the viscous drag coefficient; 3. This application will , The above formula for total resistance is obtained by combining these formulas. in, The operating resistance experienced by the impeller of the drainage pump is expressed in Newtons (N). This refers to the density of the water, expressed in kilograms per cubic meter. The velocity of the water at the impeller is expressed in meters per second. This represents the effective flow area of ​​the impeller, in square meters. The viscosity of the accumulated water is expressed in Pascals per second (Pa). The characteristic length of the fluid within the pump chamber, in meters; and The drag coefficient can be obtained through experimental calibration. The value range is typically from 0.5 to 1.0. The value range is usually from 0.01 to 0.05.

[0028] Based on the above formula for operating resistance, the formula for calculating the drift quantization value of the control parameter is further derived:

[0029] in, The drift quantization value is for the control parameter, and the unit is watts; The mechanical efficiency of the drainage pump; This represents the rated input power of the drainage pump in clean water. The logical relationship of this formula is: changes in operating resistance will lead to changes in the input power of the drainage pump, and the difference between the input power and the rated power is the quantified value of the control parameter drift.

[0030] The parameter drift interlocking logic is constructed based on the fluid network topology and distance weights. The transmission path is determined according to the water flow direction, the spatial distribution of the drainage compartments, and fluid connectivity. The distance weight calculation formula is as follows: ,in The conduction attenuation coefficient is 0.02. This represents the straight-line distance between the faulty storage unit and surrounding storage units, in meters. The formula for quantifying the parameter drift propagation amplitude is as follows: The formula for quantifying conduction rate is: ,in This represents the change in transmission distance. This represents the change in conduction time.

[0031] The parameter drift cascading logic considers the continuity of water flow. Changes in the drainage flow of a single silo will alter the water level and velocity distribution in the surrounding area, thus affecting the inlet conditions of surrounding silos and causing corresponding changes in their operating parameters. By establishing a cascading logic model, the propagation range and impact of parameter drift can be accurately predicted.

[0032] In one specific embodiment, when the quantized value of the control parameter drift trend is lower than the correction threshold, a micro-call instruction is sent to the drainage container to reduce the parameter drift rate of the drainage container by initiating an autonomous micro-calibration process and fine-tuning the pump body operating load.

[0033] Specifically, the autonomous micro-calibration process is a built-in self-adjusting function of the drainage silo, capable of making minor adjustments to operating parameters without affecting the overall drainage operation. Fine-tuning the pump's operating load is primarily achieved by adjusting the pump's speed. When parameter drift is minimal, appropriately reducing or increasing the pump speed can bring the operating parameters back to a stable range, slowing down the rate of parameter drift. The calibration threshold can be preset according to the drainage silo's model and performance parameters; for example, the calibration threshold for the operating current can be set to 5% of the rated current.

[0034] The following is a quantitative calculation example: The parameters of a certain type of drainage pump are as follows: effective flow area of ​​the impeller. square meters, fluid characteristic length Meter, mechanical efficiency Rated input power under clean water medium Tiles, drag coefficient , .

[0035] When the water density kilograms per cubic meter, viscosity Pascal-second, flow velocity at the impeller meters per second: 1. Calculate the running resistance:

[0036]

[0037] ox; 2. Calculate the actual input power: watt; 3. Calculate the drift quantization value of the control parameters: watt; The result indicates that the current input power of the drainage pump is far below the rated power, and the pump speed needs to be appropriately increased to increase the drainage flow rate.

[0038] In one specific embodiment, the hierarchical collaborative correction includes a local correction layer, a regional collaboration layer, and a global control layer; wherein, the local correction layer is used to perform parameter depth correction of the drainage container; the regional collaboration layer is used to send pre-correction commands to other containers within a preset range around the drainage container to construct a drift blocking barrier; and the global control layer is used to collaboratively fine-tune the operating parameters of all drainage containers in the water accumulation area.

[0039] Specifically, the hierarchical collaborative correction mechanism can adopt different levels of correction measures based on the severity and scope of parameter drift, achieving precise and efficient control. The local correction layer performs in-depth correction for severe parameter drift in a single drainage silo, quickly restoring the unit to normal operation. The regional collaborative layer, which constructs a drift-blocking barrier, essentially combines control decoupling with pre-correction collaboration. Pre-correction commands are issued from the edge computing control terminal, allowing surrounding silos to adjust their operating parameters in advance, achieving drift transmission blocking at the control level without involving physical barriers or communication isolation. The global control layer is responsible for the overall coordination of the entire waterlogged area, ensuring that the operating parameters of all drainage silos match each other, optimizing overall drainage efficiency. The preset range can be set according to the size of the waterlogged area and the distribution density of the silos; for example, silos within a 50-meter radius can be divided into the same regional collaborative group.

[0040] In one specific embodiment, when a sudden change in the physical property parameters of the medium is detected, the media pretreatment component of the drainage silo is controlled to switch the filtration level to filter pollutants and silt in the accumulated water; at the same time, the media property-parameter drift correlation is updated based on the parameters after the change, and a synchronous correction command is issued to all drainage silos in the affected area.

[0041] Specifically, sudden changes in the physical properties of the medium are usually caused by a large influx of silt, debris, or other pollutants into the flooded area. Switching the filtration level in this situation can effectively prevent large particles from entering the drainage pump, avoiding equipment damage. Synchronously updating the correlation between medium properties and parameter drift ensures the accuracy of the model and provides a reliable basis for subsequent control. Issuing synchronous correction commands to all containers within the affected area allows all equipment to adapt to the changed medium environment simultaneously, preventing mismatches in operating parameters. Filtration levels are typically divided into three stages: primary filtration intercepts large floating objects, secondary filtration intercepts medium-sized particles, and tertiary filtration intercepts fine silt. The appropriate combination of filtration levels can be selected based on the type and severity of the medium change.

[0042] In one specific embodiment, the time-series prediction result is a prediction curve generated by combining historical medium data and real-time acquired data using a deep learning algorithm. The prediction curve reflects the direction of change of medium physical property parameters within a preset time period in the future.

[0043] Specifically, deep learning algorithms employ a Long Short-Term Memory (LSTM) network model, which effectively processes time-series data, capturing both long-term trends and short-term fluctuations in the characteristics of the medium. The algorithm's application process is as follows: 1. Data preprocessing: Normalize historical media data and real-time acquired data, converting them into an input format acceptable to the model; 2. Model Training: Train the LSTM model using historical data from the past 72 hours to optimize the model's weight parameters; 3. Prediction Generation: Input the real-time data of the most recent hour into the trained model to generate prediction curves of medium characteristic parameters for the next 15 minutes to 1 hour; 4. Result Output: The prediction results are transmitted to the parameter drift prediction module for analysis of the control parameter drift trend; Historical media data includes records of media characteristic parameters under different weather conditions and water accumulation scenarios, while real-time data is acquired from distributed media characteristic sensing units. The preset prediction time can be adjusted according to the needs of emergency drainage operations; in rapidly changing water accumulation scenarios, the prediction time can be appropriately shortened to improve prediction accuracy. Simulation results show that the model can achieve a prediction accuracy of over 90% for media density and viscosity, meeting the requirements for parameter drift prediction.

[0044] In one specific embodiment, the matching degree verification adopts a dual verification standard, which simultaneously verifies the matching degree between the corrected operating parameters and the medium characteristics, as well as the operating stability and energy consumption of the drainage silo; if the verification fails to meet the standard, the verification result is fed back and a secondary correction process is triggered.

[0045] Specifically, the matching degree between operating parameters and media characteristics is verified primarily by comparing the deviation between actual operating parameters and the optimal operating parameters calculated based on the current media characteristics. Operational stability verification is assessed by monitoring the vibration frequency, noise level, and temperature changes of the drainage pump. Energy consumption verification evaluates the energy-saving effect of the correction measures. This dual verification standard comprehensively evaluates the correction effect, ensuring that the corrected operating state adapts to the media environment while guaranteeing safe and stable equipment operation and low energy consumption. The secondary correction process adjusts the correction parameters based on the verification results and re-executes the hierarchical collaborative correction until the verification meets the standards.

[0046] Please see Figure 5 The present invention also provides a collaborative control system for drainage silos used in emergency flooding, comprising: a distributed media characteristic sensing unit for collecting parameters of the flooded media; multiple drainage silos, each equipped with an operating parameter acquisition module, a pump load adjustment module, a control parameter self-calibration module, and a media pretreatment component with multi-level filtration; and an edge computing control terminal, which integrates a parameter drift prediction module, a collaborative parameter correction unit, a media characteristic timing prediction module, a drift conduction blocking module, and a parameter correction verification module; the edge computing control terminal connects the distributed media characteristic sensing unit and each drainage silo via bidirectional communication.

[0047] Specifically, the distributed media characteristic sensing unit and the edge computing control terminal are connected via a LoRa wireless communication interface, with a transmission distance of up to 3 kilometers, meeting the communication needs of large-area waterlogged areas. The transmitted data includes real-time collected data on water density, viscosity, contaminant concentration, and conductivity. Within each drainage compartment, the operating parameter acquisition module, pump load adjustment module, control parameter self-calibration module, and media pretreatment component are physically connected via an RS485 bus, enabling data exchange and control command transmission within the compartment. The drainage compartment and the edge computing control terminal communicate bidirectionally via a 5G wireless communication interface, transmitting real-time operating parameters of the drainage compartment, calibration commands issued by the edge computing control terminal, and pre-calibration commands.

[0048] The system also includes a power management module and a data storage module as necessary auxiliary modules. The power management module connects to the distributed media characteristic sensing unit, the drainage silo, and the edge computing control terminal, providing a stable power supply for the entire system and supporting both mains power and diesel generator power supply. The data storage module is integrated inside the edge computing control terminal and connects to the main control chip via a SATA 3.0 interface. It is used to store historical media data, real-time operating data, and correction records, with a data storage capacity of no less than 1TB, capable of meeting at least three months of continuous data storage requirements.

[0049] The system adopts a modular design, with each functional module operating independently, facilitating routine maintenance and fault replacement. When a module fails, only the corresponding module needs to be replaced, without disassembling the entire system. Furthermore, the modular design allows for easy functional expansion, enabling the addition of new sensing or control modules to meet specific needs, thereby enhancing the system's applicability and performance.

[0050] In practical applications, when flooding occurs in an area, the first step is to deploy distributed media characteristic sensing units and multiple drainage silos, and then activate the edge computing control terminal. The distributed media characteristic sensing units begin collecting parameters of the flooded media and transmit the data to the edge computing control terminal. Simultaneously, the operating parameter acquisition modules of each drainage silo collect real-time operating parameters and transmit them to the edge computing control terminal via a 5G network. The media characteristic time-series prediction module in the edge computing control terminal uses the LSTM algorithm to generate prediction curves for the media characteristic parameters, while the parameter drift prediction module analyzes the drift trend and transmission impact of the control parameters of each drainage silo based on the media characteristic-parameter drift correlation. The collaborative parameter correction unit performs hierarchical collaborative correction based on the comparison between the quantified value of the drift trend and a preset threshold. This involves adjusting the operating load of the drainage silos through the pump load adjustment module and switching the filtration level through the media pretreatment component. The drift transmission blocking module sends pre-correction commands to surrounding silos to construct a drift blocking barrier. The parameter correction verification module verifies the matching degree of the corrected operating parameters; if the verification fails, a secondary correction process is triggered. Meanwhile, the system will dynamically correct the correlation between medium characteristics and parameter drift based on the verification results, continuously improving control accuracy.

[0051] In summary, this invention establishes a dynamic correlation model between the characteristics of the water-accumulating medium and the operating parameters of the drainage silo. By combining time-series prediction of medium characteristics with the chain transmission logic of parameter drift, it identifies the drift trend of control parameters of a single silo and its transmission impact on surrounding equipment in advance. Then, it adopts a hierarchical collaborative correction mechanism to dynamically adjust the operating load and filtration level of the silo according to the degree of drift, blocking the chain transmission of parameter drift between silo groups. At the same time, it uses a dual verification standard to verify the correction effect and dynamically correct the correlation model, realizing the dynamic adaptation of the silo operating parameters and the real-time characteristics of the water-accumulating medium. This effectively solves the problem of silo operating imbalance caused by ignoring the dynamic changes of medium characteristics in the prior art, reduces power consumption, reduces impeller wear and abnormal operation of drainage pumps, ensures the stability and continuity of collaborative operation of multiple drainage silos, and improves the adaptability of the emergency drainage system to complex water-accumulating environments.

[0052] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0053] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for coordinated control of drainage silos for emergency flooding, characterized in that, Includes the following steps: Real-time acquisition of physical property parameters of the medium in the water accumulation area and real-time operating parameters of each drainage compartment; Based on the physical properties of the medium and the real-time operating parameters, a correlation between medium properties and parameter drift is constructed, and a parameter drift chain propagation logic is established. Using the time-series prediction results of the physical property parameters of the medium, and combined with the correlation between the medium properties and parameters, the drift trend of the control parameters of each drainage compartment and its transmission impact on surrounding drainage compartments are analyzed. Based on the comparison between the quantified value of the control parameter drift trend and the preset threshold, hierarchical collaborative correction is performed. By adjusting the operating load and filtration level of the drainage silos, the chain transmission of parameter drift between the drainage silo groups is blocked. The matching degree of the corrected operating parameters is verified, and the correlation between the medium characteristics and parameter drift is dynamically corrected based on the verification results.

2. The method for coordinated control of drainage silos for emergency flooding according to claim 1, characterized in that, The physical properties of the medium include the density, viscosity, contaminant concentration, and conductivity of the accumulated water. The real-time operating parameters include the pump speed, inlet and outlet pressure, operating current, and impeller vibration frequency. The real-time acquisition process adopts a combination of high-frequency acquisition and intermittent acquisition. When the fluctuation value of the physical characteristic parameter of the medium exceeds the fluctuation threshold, the acquisition is switched from intermittent acquisition to high-frequency acquisition.

3. The method for coordinated control of drainage silos for emergency flooding according to claim 1, characterized in that, The sensor surface for acquiring the physical property parameters of the medium is covered with a nano-anti-stick coating, and high-pressure spray cleaning is activated at preset intervals. The sensors are deployed at the inlet, middle and outlet of the water accumulation area, and each drainage compartment has an independent set of sensors deployed at its inlet.

4. The method for coordinated control of drainage silos for emergency flooding according to claim 1, characterized in that, The correlation between media properties and parameter drift was established by analyzing the coupled effects of changes in media density and viscosity on the operating resistance of the drainage pump. The parameter drift interlocking transmission logic is used to identify the path, amplitude, and rate at which parameter fluctuations of a single drainage silo are transmitted to surrounding drainage silos through the water flow medium.

5. The method for coordinated control of drainage silos for emergency flooding according to claim 1, characterized in that, When the quantized value of the control parameter drift trend is lower than the correction threshold, a micro-call command is sent to the drainage container to reduce the parameter drift rate of the drainage container by initiating an autonomous micro-calibration process and fine-tuning the pump body operating load.

6. The method for coordinated control of drainage silos for emergency flooding according to claim 1, characterized in that, The hierarchical collaborative correction includes a local correction layer, a regional collaborative layer, and a global control layer; wherein, the local correction layer is used to perform parameter depth correction of the drainage container; The regional coordination layer is used to send pre-correction commands to other container units within a preset range around the drainage container unit to build a drift blocking barrier; The global control layer is used to coordinate and fine-tune the operating parameters of all drainage compartments within the waterlogged area.

7. The method for coordinated control of drainage silos for emergency flooding according to claim 1, characterized in that, When a sudden change in the physical properties of the medium is detected, the media pretreatment components of the drainage container are controlled to switch the filtration level to filter out pollutants and silt in the accumulated water. Simultaneously, the medium characteristic-parameter drift correlation is updated based on the parameters after the mutation, and a synchronous correction command is issued to all drainage silos in the affected area.

8. The method for coordinated control of drainage silos for emergency flooding according to claim 1, characterized in that, The time-series prediction result is a prediction curve generated by combining historical medium data and real-time acquired data using a deep learning algorithm. The prediction curve reflects the direction of change of medium physical property parameters within a preset time period in the future.

9. A method for coordinated control of drainage silos for emergency flooding according to claim 1, characterized in that, The matching degree verification adopts a dual verification standard, which simultaneously verifies the matching degree between the corrected operating parameters and the medium characteristics, as well as the operating stability and energy consumption of the drainage silo. If the verification fails, the verification result will be fed back and a secondary correction process will be triggered.

10. A coordinated control system for drainage silos in case of emergency flooding, used to execute the coordinated control method for drainage silos in case of emergency flooding as described in any one of claims 1-9, characterized in that, include: Distributed media characteristic sensing unit, used to collect parameters of water accumulation media; Multiple drainage compartments, each equipped with an operating parameter acquisition module, a pump load adjustment module, a control parameter self-calibration module, and a media pretreatment component with multi-stage filtration. An edge computing control terminal, which integrates a parameter drift prediction module, a collaborative parameter correction unit, a medium characteristic timing prediction module, a drift conduction blocking module, and a parameter correction verification module; The edge computing control terminal connects the distributed media characteristic sensing unit and each of the drainage silos via bidirectional communication.

Images