An emergency water supply intelligent scheduling method and system for water source sudden pollution

Abstract

The application discloses an emergency water supply intelligent scheduling method and system for sudden pollution of a water source, and belongs to the technical field of automatic control, which comprises the following steps: acquiring multi-dimensional pollution parameters, performing fluid mechanics simulation and geological parameter fusion calculation, and generating a three-dimensional pollution cloud picture; extracting a pollution diffusion boundary and generating pollution blocking boundary parameters; performing pipe network control logic decision according to the pollution blocking boundary parameters, generating a pressure control unit working mode instruction set; calculating pressure pulse characteristic parameters, generating a pressure buffer wave control signal, and dynamically matching the pressure buffer wave control signal with pipe network pressure threshold parameters to generate a hierarchical response execution instruction; and controlling a pipe network valve group switching working mode according to the hierarchical response execution instruction. The application adopts a multi-dimensional boundary calculation model fused with the layered characteristics of underground water medium and a progressive generation method of pipe network fluid simulation line feature constrained pulse control signals, and can realize spatiotemporal precise collaborative intervention in the pollution isolation pressure compensation and water quality harmless switching process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic control, in particular to an emergency water supply intelligent scheduling method and system for sudden pollution of a water source. BACKGROUND

[0002] The water treatment scheduling system based on water quality sensing and pipe network model is an important guarantee technology for water supply safety, which often includes remote valve execution and pipe network pressure dynamic compensation function modules. The existing method discriminates the pollution diffusion trend by monitoring the basic parameters and triggers part of the isolation operation, and the execution subject is concentrated on the physical blockage of a single pollution source and part of the pressure compensation.

[0003] The conventional technology at the present stage mostly adopts the mode of threshold triggered valve control to drive the emergency water supply switching decision, and the pressure adjustment amount is set by a fixed gradient, and the elimination measures of water hammer effect depend on the static model of historical test data. The coupling degree of the water quality monitoring system and the valve action logic is subject to the fixed analysis interval division strategy, and the determination of the isolation boundary needs to rely on artificial review calibration. This mechanical grading execution mode cannot respond to the interference factors of the stratified permeation anomaly of the geological medium, causing the risk of incomplete isolation.

[0004] The defects of the prior art mainly reflect the linearization setting of the pressure parameters of the dynamic isolation operation, which does not consider the complex transient disturbance of the underground flow velocity distribution of the porous medium, resulting in that the stress oscillation of the isolation area deviates from the equipment tolerance limit for a long time; in addition, the artificial water quality checking parameters of the standby water source switching stage lag behind the demand timeliness of the valve opening operation, and the flow control characteristic curve does not match the trajectory of the pollution front migration path during the reverse process flushing, which reduces the system reliability of the emergency blocking measures. SUMMARY

[0005] To solve the above problems, the present application provides an emergency water supply intelligent scheduling method and system for sudden pollution of a water source, which adopts a multi-dimensional boundary calculation model fused with the stratified characteristics of underground water medium and a progressive generation method of pipe network fluid simulation line feature constrained pulse control signal, which can realize the spatiotemporal precise collaborative intervention of pollution isolation pressure compensation and water quality harmless switching process.

[0006] The above object can be achieved by the following scheme:

[0007] An emergency water supply intelligent scheduling method for sudden pollution of a water source, comprising: acquiring pH value, heavy metal concentration and organic matter content collected by a movable water quality detection buoy group to generate multi-dimensional pollution parameters; performing fluid mechanics simulation and geological parameter fusion calculation on the multi-dimensional pollution parameters to generate a three-dimensional pollution cloud map; extracting a pollution diffusion boundary based on the three-dimensional pollution cloud map to generate pollution blocking boundary parameters; performing pipe network control logic decision according to the pollution blocking boundary parameters to generate a pressure control unit working mode instruction set; calculating pressure pulse characteristic parameters based on the pressure control unit working mode instruction set to generate a pressure buffer wave control signal; dynamically matching the pressure buffer wave control signal with pipe network pressure threshold parameters to generate a hierarchical response execution instruction; and controlling pipe network valve group switching working modes according to the hierarchical response execution instruction, wherein the working modes include electromagnetic drive mode, mechanical self-locking mode and gravity self-locking mode.

[0008] Optionally, the generating a three-dimensional pollution cloud map comprises: performing data cleaning and standardization processing on the multi-dimensional pollution parameters to generate standardized pollution parameters; acquiring a permeability coefficient of groundwater hydrogeological parameter data; performing spatial superposition calculation on the standardized pollution parameters and the permeability coefficient to generate a vertical direction pollution migration rate distribution map; calculating a horizontal direction pollution diffusion range through a fluid mechanics equation to generate a horizontal direction pollution range prediction map; and fusing the vertical direction pollution migration rate distribution map and the horizontal direction pollution range prediction map according to a weight ratio of the permeability coefficient and the standardized pollution parameters to generate a three-dimensional pollution cloud map.

[0009] Optionally, the generating a pressure control unit working mode instruction set comprises: identifying a pollution concentration gradient mutation area based on the three-dimensional pollution cloud map to generate pollution blocking boundary parameters; dividing the pollution blocking boundary parameters to determine a pollution core area isolation range and a pollution diffusion buffer area boundary; generating an isolation mode control instruction based on the pollution core area isolation range; generating a reverse flushing mode control instruction based on the pollution diffusion buffer area boundary; generating a normal mode control instruction in a non-polluted area; and combining the isolation mode control instruction, the reverse flushing mode control instruction and the normal mode control instruction to generate a pressure control unit working mode instruction set.

[0010] Optionally, the generating a pressure buffer wave control signal comprises: calculating a pipe network flow mutation amplitude based on the pressure control unit working mode instruction set to generate an expected flow mutation gradient parameter; determining a pressure pulse frequency and amplitude according to the expected flow mutation gradient parameter to generate a pressure pulse characteristic parameter; and performing dynamic superposition calculation on the pressure pulse characteristic parameter and a preset pipe network elastic compensation coefficient to generate a pressure buffer wave control signal.

[0011] Optionally, the generating the hierarchical response execution instruction comprises: extracting fluctuation frequency and amplitude characteristics in the pressure buffer wave control signal, generating an emergency level parameter; matching the emergency level parameter with a preset pollution event level division standard, determining a current event level; calling a pipe network pressure threshold parameter corresponding to the current event level, generating a hierarchical response execution instruction; wherein the pipe network pressure threshold parameter includes an upper pressure limit value, a pressure fluctuation tolerance range, and an emergency pressure relief trigger condition.

[0012] Optionally, the determining the current event level comprises: comparing the emergency level parameter with a threshold range in the pollution event level division standard; according to the comparison result, attributing the emergency level parameter to an event level corresponding to the threshold range; determining the attributed event level as the current event level.

[0013] Optionally, the controlling the pipe network valve group switching mode according to the hierarchical response execution instruction comprises: analyzing the hierarchical response execution instruction to identify event level information contained therein; determining the level of the current pollution event according to the event level information; when the level of the current pollution event is a first level, controlling the valve group to switch to an electromagnetic drive mode; when the level of the current pollution event is a second level, controlling the valve group to switch to a mechanical self-locking mode; when the level of the current pollution event is a third level, controlling the valve group to switch to a gravity self-locking mode and starting a backup water source switching process.

[0014] Optionally, the starting the backup water source switching process comprises: obtaining real-time pressure state parameters and real-time water quality parameters of a backup water source pipe network segment; based on the real-time pressure state parameters, adjusting a backup water source booster pump to make the backup water source pressure higher than the pollution area pipe network pressure; when the real-time water quality parameters meet a preset safety threshold, opening a switching valve between the backup water source and the target pipe network segment.

[0015] Optionally, the method further comprises: collecting pollution blocking time, water supply recovery time, and pipe network pressure data to generate pipe network operation parameter records; evaluating system response efficiency according to the pipe network operation parameter records to generate system optimization parameters; adjusting pipe network control logic decision-making processes according to the system optimization parameters.

[0016] Based on the same inventive concept, this invention also provides an emergency intelligent water supply scheduling system for sudden pollution of water sources. The system includes: a data acquisition module for acquiring pH values, heavy metal concentrations, and organic matter content collected by a group of mobile water quality monitoring buoys, generating multi-dimensional pollution parameters; a pollution simulation module for performing fluid dynamics simulation and geological parameter fusion calculations on the multi-dimensional pollution parameters, generating a three-dimensional pollution cloud map; a boundary identification module for extracting pollution diffusion boundaries based on the three-dimensional pollution cloud map, generating pollution blocking boundary parameters; a control decision module for making pipeline control logic decisions based on the pollution blocking boundary parameters, generating a pressure control unit operating mode instruction set; a pressure characteristic module for calculating pressure pulse characteristic parameters based on the pressure control unit operating mode instruction set, generating a pressure buffer wave control signal; an instruction matching module for dynamically matching the pressure buffer wave control signal with pipeline pressure threshold parameters, generating graded response execution instructions; and an execution control module for controlling the pipeline valve group to switch operating modes according to the graded response execution instructions, the operating modes including electromagnetic drive mode, mechanical self-locking mode, and gravity self-locking mode.

[0017] Compared with the prior art, the present invention has the following advantages:

[0018] This invention achieves high-speed dynamic calibration of pollution blocking boundary conditions by establishing a multi-dimensional dynamic feature recognition model of pollutants and deeply binding it with a pressure regulation system. Three-dimensional cloud map analysis technology accurately characterizes the spatial hierarchy of pollutant diffusion, improving the computational efficiency and dynamic adaptability of the isolation area, and overcoming the potential for misjudgment of pollution range caused by reliance on traditional static parameters.

[0019] A dual-track control scheme, combining graded pressure regulation commands with backwashing of the contaminated buffer zone and head optimization in the normal area, achieves non-uniform buffering compensation of the pipeline pressure field from the perspective of water flow inertia. Optimization of flow regulation parameters and elastic wave characteristics restricts pollutant migration interference to a localized space, collaboratively ensuring stable water supply pressure over a wide area and rapid blockage in the core area.

[0020] The backup water source switching adopts a full-link verification mechanism to simultaneously meet the dual requirements of operational safety and water quality compliance. By using a differential pressure compensation function and pipeline resistance simulation parameters to correct the pressure field transition conditions in real time, the risk of hydraulic pulses at the confluence of multiple water sources is gradually reduced, eliminating the risk of secondary pollution chain diffusion and the superposition of pipe burst accidents.

[0021] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below are only some embodiments of the present application, and the other drawings can be obtained by those skilled in the art without any creative work on the basis of these drawings.

[0023] Figure 1 is a flowchart of an emergency water supply intelligent scheduling method for sudden pollution of a water source in an embodiment of the present application.

[0024] Figure 2 is a three-dimensional pollution cloud map spatial distribution schematic diagram in an embodiment of the present application.

[0025] Figure 3 is a pressure buffer wave control signal timing curve in an embodiment of the present application.

[0026] Figure 4 is a blocking efficiency and recovery resilience factor timing change curve in an embodiment of the present application.

[0027] Figure 5 is a structural schematic diagram of an emergency water supply intelligent scheduling system for sudden pollution of a water source in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative work belong to the protection scope of the present application.

[0029] With reference to Figure 1 , one embodiment of the present application proposes an emergency water supply intelligent scheduling method for sudden pollution of a water source, which adopts a multi-dimensional boundary calculation model with fusion of layered characteristics of groundwater medium and a progressive generation method of pulse control signals with fluid simulation line characteristics constraints of pipe network, and can realize the spatiotemporal precise collaborative intervention of pollution isolation pressure compensation and water quality harmless switching process.

[0030] The method of the embodiment specifically includes:

[0031] The pH value, heavy metal concentration and organic matter content collected by the movable water quality detection buoy group are acquired to generate multi-dimensional pollution parameters;

[0032] Fluid mechanics simulation and geological parameter fusion calculation are performed on the multi-dimensional pollution parameters to generate a three-dimensional pollution cloud map.

[0033] extracting a pollution diffusion boundary based on the three-dimensional pollution cloud map, and generating pollution blocking boundary parameters;

[0034] making a pipe network control logic decision according to the pollution blocking boundary parameters, and generating a pressure control unit working mode instruction set;

[0035] calculating pressure pulse characteristic parameters based on the pressure control unit working mode instruction set, and generating a pressure buffer wave control signal;

[0036] dynamically matching the pressure buffer wave control signal with pipe network pressure threshold parameters, and generating a hierarchical response execution instruction;

[0037] controlling a pipe network valve group switching working mode according to the hierarchical response execution instruction, the working mode including an electromagnetic drive mode, a mechanical self-locking mode and a gravity self-locking mode.

[0038] Specifically, multi-dimensional pollution parameters are monitored by deploying movable water quality detection buoys to obtain diffusion characteristic data of pollution substances. A three-dimensional pollution cloud map is generated by fluid mechanics modeling and geological parameter integration to accurately depict the three-dimensional migration trend of pollution substances in water and geological media. Based on the diffusion boundary analysis results of the cloud map, the physical range and direction boundary of pollution blocking are determined to trigger a pipe network control decision model to generate a corresponding pressure control unit working mode instruction set. A pressure buffer wave control signal is formed by calculating the pulse characteristic parameters of water flow dynamics, and a hierarchical response execution instruction is generated by dynamically matching the pipe network pressure threshold to guide the pipe network valve group to automatically switch the working mode according to the emergency level, realizing the collaborative control of pollution area blocking and normal water supply scheduling. This method systematically integrates pollution space analysis, equipment multi-state regulation and control, and fluid transient suppression mechanism, providing an adaptive collaborative control scheme for watershed emergency water supply.

[0039] Optionally, the generating a three-dimensional pollution cloud map comprises:

[0040] performing data cleaning and standardization processing on the multi-dimensional pollution parameters to generate standardized pollution parameters;

[0041] obtaining a permeability coefficient of groundwater hydrogeological parameter data;

[0042] performing spatial superposition calculation on the standardized pollution parameters and the permeability coefficient to generate a vertical direction pollution migration rate distribution map;

[0043] calculating a horizontal direction pollution diffusion range by a fluid mechanics equation to generate a horizontal direction pollution range prediction map;

[0044] Based on the weight ratio of the permeability coefficient and the standardized pollution parameters, a three-dimensional pollution cloud map is generated by fusing the vertical pollution migration rate distribution map and the horizontal pollution range prediction map.

[0045] Specifically, the multi-dimensional pollution parameters were first cleaned and standardized to generate standardized pollution parameters. Data cleaning employed the Laida criterion and Kalman filtering algorithm for filtering and real-time calibration. Standardization mapped the monitored values ​​of pH, heavy metal concentration, and organic matter content to the [0,1] interval, respectively. Normalization algorithm:

[0046] ,

[0047] in, The original detection value. This is the lowest historical value for the detection indicator. This is the maximum design threshold for this location. This is the standardized detection value. The permeability coefficient, which has clear hydrological attributes, is obtained from the groundwater geological parameter data. This permeability coefficient is derived from the combined data of ground-penetrating radar and pressure level gauge, and verified by experimental values ​​obtained through comparison with particle sieving experiments of each layer of media in the vertical direction. The vertical migration index and permeability coefficient in the standardized contaminant parameters after cleaning are spatially superimposed to calculate a three-dimensional coordinate system for contaminant transport in each sedimentary layer. The calculation formula is: In the formula, Indicates the first Layer vertical nodes The rate of pollution migration at the location, This is the pollution diffusion potential energy conversion function. The mapping parameters of the artificial neural network model trained on a discrete sample set obtained through groundwater dynamic dispersion experiments are used. The model employs a three-layer fully connected feedforward structure. The input layer nodes correspond to the pollution detection intensity index, equivalent permeability coefficient, and porosity adjustment factor, while the output layer nodes correspond to the predicted pollution migration rate. The activation function uses... The training method is supervised learning, which uses a representative sample set obtained from the experiment (containing different combinations of geological and hydrological parameters and corresponding measured pollutant migration rates) for training and validation. This is a standardized pollution intensity index, which includes solute mass concentration and adsorption reaction rate parameters. The k-th geological body was determined through surveying. Equivalent permeability coefficient in the coordinate system is the time-varying heterogeneous adjustment factor of the pore medium. The horizontal pollution diffusion range is modeled according to the improved two-dimensional heterogeneous medium mass transfer equation, the numerical simulation of the pollution front line evolution is carried out by using Darcy's law combined with the solute diffusion equation, and the partial differential equation is solved by using the finite difference method: When the horizontal fluid meets the porous medium, in the formula is the function of the change of the concentration of the pollutant with time , and respectively, the longitudinal and transverse diffusion coefficients of the formation obtained by isotope tracing test. and are the second-order partial derivatives of the pollutant concentration in the , direction, which describe the change of the concentration gradient. Finally, according to the permeability coefficient and the physical weight of the normalized pollution parameter, the multi-field coupling calculation is carried out, the piecewise linear weighting method is used to distribute the permeability attribute and the gravity potential energy index of the pollution trend in each region, and the mass flux continuity constraint equation in space is satisfied: , wherein, is the optimized weight coefficient of the formation permeability effect matched by the expert knowledge base, is the vertical migration rate, is the soil adsorption coefficient, which describes the difficulty of the pollutant penetrating the weakly permeable layer, , are the pollutant concentration entropy value and diffusion driving moment of each point, respectively, represents the curvature radius of the pollution diffusion main streamline, represents the normal angle between the pollution diffusion main streamline and the rock layer section. As shown in Figure 2 , the figure directly reflects the migration distribution of the pollutant in the three-dimensional space. The method can directly display the advancing risk area of the pollution plume front, provide a data fusion type model basis for the boundary division of the intelligent blocking system, and ensure that the emergency disposal decision is established on the basis of comprehensive cognition of the geological-water flow-pollution chemical coupling effect.

[0048] Optionally, the generated pressure control unit working mode instruction set comprises:

[0049] Identify the pollution concentration gradient mutation area based on the three-dimensional pollution cloud picture, and generate a pollution blocking boundary parameter;

[0050] Divide the pollution blocking boundary parameter to determine the isolation range of the pollution core area and the boundary of the pollution diffusion buffer area;

[0051] Generate an isolation mode control instruction based on the isolation range of the pollution core area;

[0052] Generate a reverse flushing mode control instruction based on the boundary of the pollution diffusion buffer area;

[0053] Generate normal mode control commands in uncontaminated areas;

[0054] The isolation mode control command, the backflushing mode control command, and the normal mode control command are combined to generate a pressure control unit operating mode command set.

[0055] Specifically, based on the three-dimensional pollution cloud map, regions with abrupt changes in pollution concentration gradients are first identified. Then, a joint detection method combining three-dimensional spatial interpolation and kernel density estimation is used to calculate the intensity modulus of pollutant concentration change along the water flow direction at each coordinate point. : ,in, , , These represent the concentration differences between this point and adjacent points in the horizontal longitudinal, horizontal transverse, and vertical directions of the groundwater flow field. , , Its spacing. When The value exceeds the preset mutation detection threshold. The pollution front area was considered as the location of the pollution front. Based on the connectivity between the pollution front and topographic contour points, pollution blocking boundary parameters were generated from continuous boundary coordinate data. Subsequently, spatial clustering was used to divide these boundary coordinate points and extract them as the isolation range of the pollution core area. The boundary morphology of this range was determined based on the persistent biotoxic adsorption factor in historical samples from monitoring wells. and monitoring value concentration threshold Two-way constraints, using variation functions and Interpolation optimization, when the pollutant detection value exceeds Or the cumulative time exceeds The rigid isolation condition of the core area is triggered at this time. Simultaneously, the periphery is assessed based on the diffusion coefficient and the equivalent pumping displacement delay rate. Conversely, a gradual, stratified design is established as a contamination diffusion buffer zone. Corresponding control commands are generated for different areas: within the contamination core zone, a linked process for pump station shutdown and neutralizer dosing is set up and compiled into isolation mode control commands. The buffer zone then undergoes reverse backwashing through multi-level pump station scheduling, with pressure regulation triggered periodically according to the flushing gradient equation. In the formula represent Section No. The flushing volume flow rate at any given time This represents the median of historical measured values ​​for the maximum pressure-bearing capacity of the pipe section. This is the backwash correction factor for the section with the lowest friction resistance. For time, For the hydraulic sensor sampling value based on the pressure regulating unit, all variables are coded into the driving signal parameter field after being verified by the hydraulic model online, and assembled into the backwashing mode control instruction. In the non-polluted area, the booster pump station speed is set based on the normal distribution target pressure compensation equation to realize normal mode regulation. Finally, through the central controller, the isolation, backwashing and normal three types of control instructions are integrated according to the pipe network topology and time sequence to generate the pressure control unit working mode instruction set. The method accurately partitions the strategy, dynamically decouples the intervention demand, improves the linkage efficiency of local pollution blocking and overall pressure safety, and realizes the efficiency and safety protection of emergency scheduling.

[0056] Optionally, the generating the pressure buffer wave control signal comprises:

[0057] Calculating the pipe network flow mutation amplitude based on the pressure control unit working mode instruction set, and generating an expected flow mutation gradient parameter;

[0058] Determining the pressure pulse frequency and amplitude according to the expected flow mutation gradient parameter, and generating a pressure pulse characteristic parameter;

[0059] The pressure pulse characteristic parameter and the preset pipe network elastic compensation coefficient are dynamically superimposed and calculated to generate a pressure buffer wave control signal.

[0060] Specifically, based on the pressure control unit working mode instruction set, the fluid mechanical action time sequence of each group of operation instructions is analyzed, and the pipe network topology and the initial parameters of the pipe section are combined to calculate the pipe network flow instantaneous mutation amplitude caused by the working mode switching. The mutation amplitude adopts the cumulative flow step function modeling: , wherein, represents the flow total variation gradient parameter of the pipe network section in the time window , the flow total variation gradient parameter of the pipe network section in the time window , the flow total variation gradient parameter of the pipe network section in the time window is the single flow change increment caused by the sub-action in the instruction queue, is the time response coefficient of the sub-action trigger time and the total time window . The expected flow mutation gradient parameter is obtained by superimposing the Bayesian decision tree. According to the parameter conversion, the characteristic relationship set of the pressure pulse frequency and amplitude is generated. In this step, the boundary element algorithm based on the fluid transient theory is adopted to establish a three-dimensional propagation compensation model of the pressure wave along different flow directions in the pipe network according to the fluid damping wave transmission equation. The specific pressure pulse frequency is calculated as: , wherein is the maximum allowable flow rate setting value of the pipe section, is the hyperbolic tangent function, is the longitudinal coordinate of the current calculation position, a correction coefficient representing the product of the bulk modulus of the corresponding pipe material and the corresponding water hammer wave speed thereof; is a normalized longitudinal coordinate difference of the position where the fluid disturbance source is located, is a fluid-structure coupling calculation parameter generated according to the pipe connection shape coefficient, and a numerical solution thereof is obtained by iteration of the FTA Fourier transform method, represents a pipe section equivalent diameter influence factor, and is calculated by combining weights of pipe section bending angles and flow velocity gradients. Construction of the pressure pulse amplitude A follows a constraint condition of pipe wall stress distribution optimization, and an optimal solution of superposition effects of two-dimensional wave fields is obtained by solving the following equation group: , wherein is a pressure pulse amplitude, is a deviation ratio of the residual pressure bearing degree of the pipe section to the nominal value; is a phase attenuation item set parameter of the ambient temperature and the aging coefficient; represents a correlation regression analysis equation based on fluid cumulative variation and stress fluctuation rate in the pipe, which is determined according to a hydraulic load back calculation verification curve of a historical leakage detection event. As shown in Figure 3 , the frequency and amplitude of the pressure buffer wave control signal present dynamic changes in the emergency switching process. The time series of the pressure pulse frequency and the amplitude are summarized as a pressure pulse characteristic parameter group, and then parameter correction is performed by using a pipe network elastic compensation coefficient. The pipe network elastic compensation coefficient is calculated in combination with displacement absorption amount of a pipe expansion joint in the area where each valve is located and a bend stress release effect coefficient : , wherein is a fitting feedback factor of the least square residual of the intrinsic vibration frequency actually measured by the transient strain sensor and the least square residual of the pipe network inherent frequency matrix. The corrected pressure buffer wave control signal can be expressed as: , is a function of the pressure pulse frequency changing with time, is a maximum pressure pulse amplitude change amount, is a step function, indicating that compensation is applied after time , is the time of elastic compensation, is the current time. By real-time correlating the expected flow impact characteristics of mechanical operation mode changes with the dynamic response compensation characteristics of the pipe network, multi-objective balance of continuous impact load decomposition and reduction caused by pipe network emergency stop and emergency start and low load shock stabilization is realized. Optionally, the generated hierarchical response execution instruction comprises:

[0061] extracting fluctuation frequency and amplitude characteristics in the pressure buffer wave control signal to generate an emergency level parameter;

[0062] matching the emergency level parameter with a preset pollution event level division standard to determine a current event level;

[0063] calling a pipe network pressure threshold parameter corresponding to the current event level to generate a graded response execution instruction;

[0064] The pipe network pressure threshold parameter includes an upper limit value of pressure, a pressure fluctuation tolerance range, and an emergency pressure relief trigger condition.

[0065] Specifically, first, the fluctuation frequency parameter of the periodic fluctuation is extracted from the pressure buffer wave control signal and the amplitude variable between the wave crest and the wave trough . The amplitude-frequency analysis of the signal is carried out by fast Fourier transform, and the mean value of the first harmonic cycle is taken: , where is the absolute value of the amplitude of the kth harmonic obtained by frequency domain decomposition, is the frequency value at the position of the harmonic, and both are obtained from the signal processing of at least 8 cycle samples obtained from the digitized sensor. The amplitude variable uses the extreme value envelope line fitting method to obtain the optimized dynamic amplitude characterization coefficient by taking the half-width value of the distance between adjacent maximum and minimum points in the time domain waveform sequence for sliding mean optimization processing: , where and represent the th maximum and minimum measurement points in the continuous waveform, is the number of captured peak-valley pairs in the analysis period, is the damping coefficient of the signal fluctuation under time-varying load, which is taken from the torque deviation correlation factor in the variable frequency speed regulator working log. The fluctuation frequency and the amplitude are substituted into the quantile weight classification model to generate the emergency level parameter : , where is a type of reference fluctuation frequency constant set according to the annual maximum operating frequency safety threshold of the pipeline system; is a 90% empirical correction reference value of the allowable alternating stress amplitude obtained from the static water pressure fatigue test of the pipe material. and are the frequency influence coefficient and the amplitude sensitivity coefficient, respectively, and both are distributed by statistical regression of the damage pressure feedback in the accident case, The average frequency sample standard deviation of the monitoring values in the calibration stage, is the inverse proportional factor of the inverse logarithmic distribution function of the cumulative number of impact pressure in the failure case. The preset pollution event level division standard adopts the discrete interval constraint principle, including three level determination bands and three emergency response parameters. The pollution event level determination model adopts the membership interval weighting method to establish the correlation judgment relationship between the calculated value and the interval limit value of the division standard. When calculating, if , match the third level response, , match the second level response, , match the first level response, , and is the optimal boundary value extracted from the learning process of the pressure shock and pollution diffusion event set with historical disposal success. The calculation method uses - The mean clustering analysis divides the actual operation state emergency recovery time sequence and the cumulative damage degree data of the non-normal working pressure after the disturbance of the pipe network to obtain the classification reference value. In the process of calling the pipe network pressure threshold parameter corresponding to the event level, the first safety threshold directory group corresponding to the first level response contains the upper limit value of the pressure with high sensitivity characteristics design , which is expressed as: , wherein is the reliability limit parameter of the pipe material standard ultimate pressure coefficient, is the maximum allowable working pressure value allowed by the pipe network engineering specification. The pressure fluctuation tolerance range parameter is saved in the second safety threshold directory group, which is constructed as: , wherein is the reference working pressure, is the normalized value of the flow velocity standard deviation, is the empirical tolerance amplification ratio parameter of the continuous shock cumulative influence of the pressure detection point within the allowable range, is the deviation angle correction coefficient of the main direction of water flow and the axial support structure of the pipeline, which is converted from the amplitude angle reading of the distributed piezoelectric sensor output. The pressure relief condition trigger condition of the third level emergency response is: , wherein takes the average of the differential pressure dynamic evolution rate in the set response time period , and is the current stage safety margin threshold value of the critical safety pressure calibration point when the pipeline rupture risk approaches. The impact buffer gradient calibration coefficients are used for different material aging levels in different regions. All the above threshold parameters are uniformly stored in the parameter relationship feature library in the emergency control module via the main station. By adaptively matching the action sensitivity range of the pressure buffer valve through standardized response rules, the existing water flow transport pressure is guaranteed to maintain a resilience safety margin under sudden pollution situations, ensuring that the valve switching operation simultaneously follows the principles of water quality protection and pipeline operation supply guarantee.

[0066] Optionally, determining the current event level includes:

[0067] Compare the urgency parameter with the threshold range in the pollution event classification standard;

[0068] Based on the comparison results, the urgency parameter is assigned to the event level within the corresponding threshold range;

[0069] The event level to which it belongs is determined as the current event level.

[0070] Specifically, the database of pipeline operation in historical pollution control events is analyzed to establish parameters for the urgency of typical pollution events. A chart showing the distribution characteristics of the value range was used to delineate interval boundary values ​​applicable to various emergency responses. Principal component analysis was applied to analyze the damage rate caused by pressure shock. And pipeline restoration efficiency factor The combined data matrix is ​​used to calculate the interval segmentation criteria and construct a threshold space corresponding to three event levels. The processed historical data forms a four-dimensional scatter plot vector Z= , The input represents the actual duration of each event's handling, after normalization and fuzzy processing. The mean clustering algorithm yields... Optimal cut point under various pressure threshold constraints and The objective function during clustering. The following settings must be met: In the formula Representative sample data points right Membership degree of the center point To smooth out the coefficients and prevent overclassification, This is the center vector for each cluster. The algorithm iterates until all parameters converge and reach a stable state, then extracts... The classification interval points corresponding to the axis, and the upper margin of the intervals corresponding to each emergency level sorted by probability density, are used as the boundary threshold for determining the level of pollution events. of and of During real-time system operation, the urgency level parameter is determined based on the currently generated parameters. a numerical value, in turn, with the event level threshold and a value range interval matching comparison is performed, and the three-level determination rule is as follows: when the calculated numerical value is between the intervals , the third-level emergency event is determined; when it belongs to , it is classified as the second level; and when it exceeds , it is forcibly classified into the first-level super-high emergency degree category. The level identifier after the attribution confirmation is mapped to the topological map of the pollution blocking control master station in combination with the event coordinate geographic code, the regional activity attribute of the current pollution event is marked, and then the corresponding pressure safety control mode envelope function is called from the pipe network stress model library to update the operation rules of the current device group. The method uses the parameter optimization and adaptation ability of the machine learning data interval driving determination benchmark to realize scientific grading logic setting, and improves the scene matching and timeliness of the emergency self-control strategy.

[0071] Optionally, the valve group switching mode is controlled according to the hierarchical response execution instruction:

[0072] The hierarchical response execution instruction is analyzed to identify the event level information contained therein;

[0073] According to the event level information, the level of the current pollution event is determined;

[0074] When the level of the current pollution event is the first level, the valve group is controlled to switch to the electromagnetic driving mode;

[0075] When the level of the current pollution event is the second level, the valve group is controlled to switch to the mechanical self-locking mode;

[0076] When the level of the current pollution event is the third level, the valve group is controlled to switch to the gravity self-locking mode, and a backup water source switching process is started.

[0077] Specifically, the central control unit analyzes the hierarchical response execution instruction, extracts the event level identifier , which uses a three-bit binary number to represent the emergency degree of the pollution event, and the highest bit indicates whether there is a cross-regional diffusion characteristic. Through the instruction analysis engine, the event level mapping library is called to match the corresponding emergency disposal plan number. If the event level is determined to be the first level, the controller issues an electromagnetic driving mode activation instruction, and the valve is quickly driven by the ampere force generated by the coil, with a response time , the valve opening adjustment precision is controlled within an error band of ±2%, and the dynamic positioning algorithm uses the following formula: , wherein is the real-time output valve rotation angle instruction value, and are the proportional and integral coefficients, respectively, which are fitted from the flow characteristics curve in the valve model database; is derived from the target pressure value set in the hierarchical response execution instruction; is the measured pressure value collected by the vibration compensation type pressure transmitter on the pipeline, with a sampling period of 10 ms. The coil temperature rise state is continuously monitored during electromagnetic driving, and when it exceeds the tolerance threshold of the insulation material, it is automatically switched to the backup driving source. If the event level is determined to be the second level, the valve group is switched to the mechanical self-locking mode. The valve stem is precisely adjusted through a worm gear and locked through a ratchet. The locking process is verified by the balance equation of the valve stem axial stress and the sealing specific pressure The locking reliability is verified by the balance equation of the valve stem axial stress , where is the minimum cross-sectional area of the valve stem taken from the valve design drawing; and are the effective diameter and contact width of the sealing ring, respectively; is dynamically adjusted according to the compression permanent deformation test data of the sealing material. Every 5 minutes after mechanical locking, the valve position offset is checked through the displacement sensor, and when is detected, the self-locking compensation process is started. When the event level rises to the third level, the control system performs double operation: first, it sends a hydraulic control switching instruction to the valve dedicated to the gravity self-locking mode, and uses the gravity torque generated by the counterweight to overcome the fluid impact force, and the counterweight mass calculation formula is: , where is the maximum fluid impact force at the third level calculated according to the pipeline simulation model; is the design length of the counterweight arm; takes the measured value of the local gravitational acceleration; is the gear box transmission efficiency, which is calibrated online through the torque sensor; is the safety factor, which is taken from the interval value of 1.5-2.0 according to ASME B31.1 specification. At the same time, the standby water source switching process is started, first obtaining the pressure state parameters and water quality parameter group , where at least contains the turbidity NTU value and the residual chlorine concentration CLR value. When continues for 30 seconds and is 10% higher than the contaminated area pipeline pressure, and meets the GB5749 Drinking Water Health Standard, the control switching valve executes the opening operation, and the opening rate follows: , where is the valve diameter, is the pressure difference between the standby water source and the target pipeline section, This represents the measured value of water flow density. This method establishes a strong correlation mechanism between event level and valve actuation mode, achieving a tiered defense system ranging from millisecond-level electromagnetic control to mechanical rigid locking and then to gravity failure protection.

[0078] Optionally, the process for initiating the backup water source switching includes:

[0079] Obtain real-time pressure status parameters and real-time water quality parameters of the backup water source pipeline section;

[0080] Adjust the backup water source booster pump based on the real-time pressure status parameters to make the backup water source pressure higher than the pipeline pressure in the polluted area.

[0081] When the real-time water quality parameters meet the preset safety threshold, the switching valve between the backup water source and the target pipeline segment is opened.

[0082] Specifically, the first step is to obtain the pressure parameters of the booster pump's inlet pipe. Combination of water quality parameters The latter includes turbidity. and residual chlorine concentration The real-time pressure status parameters of the backup water source pipeline section are verified using a three-point method to improve data confidence. The formula is as follows: In the formula This refers to the real-time pressure status parameters of the backup water source pipeline section. , , Instantaneous sampling averages were taken from three distributed pressure transmitters at the water source inlet main pipe, the branch pipe cross node, and the end user access point to eliminate pulsation distortion caused by local turbulence. Then, the output frequency of the frequency converter controller of the backup water source booster pump was adjusted to... Satisfy pressure connection constraints: ,in, The upper limit of the steady-state pressure fluctuation envelope of the polluted pipeline section, calculated in real time by the front-end monitoring module. This is a pre-set pressure difference compensation margin to overcome the flow resistance difference at the pipe connection. Subsequently, a dual-source water quality status mutual verification algorithm is executed every 5 seconds, and the verification is completed after 3 consecutive verifications. And twice Upon locking the qualified state, the steady-state flow buffering process is initiated. Its duration is... The calculation formula is: ,in The topology adjustment factor is the nominal value of the standard diameter of the main pipeline of the switching pipeline node divided by the equivalent diameter. This indicates the minimum allowable operating pressure calculated synchronously at the key pressure control points of the pipeline network where the original contaminated area is located. Minimum duration; adjust all sensors to meet the requirements of the backup water source. in the national standard qualified interval and When the remaining last three differential pressure stabilization time periods, the switching valve starts the incremental opening program, and the valve opening rate Based on the linear interpolation function gradually increases to the maximum safety opening degree limit point, the formula is: , wherein is the damping control constant, is the pressure difference between the standby water source and the supplied pipe network, , wherein is the average gauge pressure reading of the standby water source within the first 5 seconds before starting, is the maximum impact pressure peak value allowed by the supplied pipe network. The entire process maintains the reverse pressure gradient of the pollution area pipe section blowdown valve group to the last 0.5 seconds before opening is completed Synchronous removal of the lock joint debugging confirmation signal, realize the peak blocking of the whole process of pollutant flow direction. This method ensures that the pipe network pressure regulation process does not destroy the existing hydraulic balance, and at the same time ensures the reliability of the water source switching action and the irreversible compliance characteristics of the water source safety standard.

[0083] Optionally, the method further comprises:

[0084] Collecting pollution blocking time, water supply recovery time and pipe network pressure data to generate pipe network operation parameter record;

[0085] According to the pipe network operation parameter record, the system response efficiency is evaluated, and the system optimization parameter is generated;

[0086] According to the system optimization parameter, the pipe network control logic decision process is adjusted.

[0087] Specifically, the pollution blocking effective time parameter (time required for the core area turbidity to recover to 95%), the water supply recovery stable time parameter (time period from opening of the standby water source valve to pressure stabilization ±5%) and the pipe network pressure fluctuation variance matrix during pollution blocking , Discrete variance formula is used for processing: , wherein is the pressure fluctuation variance, is the instantaneous pressure value of the i-th pressure sampling point, is the target pressure, is the total number of pressure samples, which is collected once every 10ms by default, and the sampling duration of each group of data is equal to the corresponding or period. The system response efficiency takes the overall blocking efficiency and the recovery resilience factor as the index. The flow efficiency attenuation model is used for calculation: ,in The reference value for the nominal blocking time is obtained from the maximum propagation delay characteristics of the pipeline network in a static laboratory test. It is a time-domain compensation coefficient calculated in real time based on the pollution concentration and penetration depth. The value is affected by the fracture rate parameter of the three-dimensional geological block model. The impact is calculated as follows: , The linear adjustment constant is , For the test pressure baseline, This is the actual pressure difference during mining. The geometric effect weighting factor is obtained by converting fluid transport characteristics; This is a condition-corrected parameter for the creep delay characteristics of pipeline materials. (Recovery toughness factor) Based on a comprehensive evaluation of pressure fluctuation distribution characteristics and steady-state recovery rate, the following results were obtained: ,in, The actual damping ratio in the water pipe network is obtained by separating the frequency response relationship of the damping resonance peak from the discrete vibration acceleration signal of the pressure sensor. It is the magnitude of the cumulative phase offset of the top three amplitude values ​​of the time-varying pressure trajectory; The integral result is taken from the time-space integral value of the water supply recovery phase in the regulated area; The fatigue strengthening inhibition factor for pipe sections is determined by calibrating the pressure loss curve of cyclic load test according to the half-life reversal coefficient. This is the temperature correlation correction coefficient for the hysteresis characteristics of the pipeline material, obtained by weighting the mean of the temperature field in the underground passage during the data collection process. For example... Figure 4 As shown, the trend curves of blocking efficiency and recovery resilience factor with event number reflect the system's operational efficiency and resilience after multiple contamination blocking and water source switching operations. Based on efficiency indicators... and Parameter calculation feedback system optimization suggestion parameters Specifically, a genetic algorithm is used to solve the problem: weight and The initial settings were assigned using the Delphi expert interview method, and iterative optimization was performed as more running cases were added. The network management network coordination control response parameter increment to be optimized is mapped to the output valve response period and the acceleration ratio parameter of the backwashing gradient of the isolation mode control instruction. After the optimization results are prioritized, the control logic parameter library is automatically updated, which is used for adjusting the conditions in subsequent emergency process execution. The system parameter adjustment amount generated by the method drives the intelligent algorithm update iteration of the key decision step, forms a self-upgrading mechanism for optimizing the strategy set according to the actual operation and maintenance effect, overcomes the global adjustment failure phenomenon caused by the postposition of the rule update of a single parameter library, and finally constructs a self-adaptive strengthening mechanism for the execution efficiency of the emergency system in multiple events.

[0088] Based on the same inventive concept, as shown in Figure 5 The application also provides an emergency water supply intelligent scheduling system for sudden pollution of a water source, which comprises:

[0089] A data acquisition module is configured to acquire pH value, heavy metal concentration and organic matter content collected by the movable water quality detection buoy group, and generate multi-dimensional pollution parameters.

[0090] A pollution simulation module is configured to perform fluid mechanics simulation and geological parameter fusion calculation on the multi-dimensional pollution parameters, and generate a three-dimensional pollution cloud picture.

[0091] A boundary identification module is configured to extract a pollution diffusion boundary based on the three-dimensional pollution cloud picture, and generate pollution blocking boundary parameters.

[0092] A control decision module is configured to make pipe network control logic decisions according to the pollution blocking boundary parameters, and generate a pressure control unit working mode instruction set.

[0093] A pressure feature module is configured to calculate pressure pulse feature parameters based on the pressure control unit working mode instruction set, and generate a pressure buffer wave control signal.

[0094] An instruction matching module is configured to dynamically match the pressure buffer wave control signal with pipe network pressure threshold parameters, and generate a hierarchical response execution instruction.

[0095] An execution control module is configured to control the pipe network valve group to switch working modes according to the hierarchical response execution instruction, wherein the working modes include an electromagnetic drive mode, a mechanical self-locking mode and a gravity self-locking mode.

[0096] In order to verify the feasibility of the application in implementation, the application is applied to the urban water supply emergency scheduling system of a certain city. The water source of the city is an upstream river, and there is a risk of sudden pollution caused by industrial accidents. The application aims to quickly and accurately perform emergency scheduling when the water source is suddenly polluted, block the spread of pollution, and ensure the safety of the pipe network and the stability of water supply for downstream users.

[0097] To verify the effectiveness of the present application, a simulated sudden heavy metal pollution event upstream of a city water source was taken as an example to test the whole process of the emergency water supply intelligent scheduling method and system of the present application. The data of pollution detection, diffusion simulation, decision response and valve control were recorded during the monitoring process.

[0098] In the embodiment, the system of the present application detected the pollution event at 10:00 on September 5, 2024. First, the movable water quality detection buoy group deployed at the river section collected abnormal pH value, heavy metal concentration and organic matter content, and the data acquisition module of the system immediately generated multi-dimensional pollution parameters. The pollution simulation module immediately performed fluid mechanics simulation and geological parameter fusion calculation on these parameters, and generated a three-dimensional pollution cloud map at 10:03. The cloud map accurately showed the migration trend of the pollutants in the vertical direction to the aquifer and the diffusion range in the horizontal direction, and predicted that the front edge of the pollution plume would reach the first water intake in 45 minutes.

[0099] Based on the three-dimensional pollution cloud map, the boundary identification module extracted the pollution diffusion boundary at 10:04 and identified the pollution concentration gradient mutation area, and generated the pollution blocking boundary parameters including the isolation range of the pollution core area and the pollution diffusion buffer area. The control decision module made pipe network control logic decision according to the boundary parameters, and generated the pressure control unit working mode instruction set at 10:05, which clearly specified that the core area was executed in isolation mode, the buffer area was executed in reverse flushing mode, and the non-polluted area was maintained in normal mode.

[0100] To prevent the destructive water hammer effect caused by the rapid switching of the valves in the pipe network, the pressure characteristic module calculated that the pipe network flow would have a large mutation based on the instruction set, and combined with the elastic compensation coefficient of the pipe network, generated the pressure buffer wave control signal at 10:06 to smooth the pressure impact. Subsequently, the instruction matching module matched the fluctuation frequency and amplitude characteristics in the signal with the preset pollution event level division standard, determined that the current event level was the second level, and called the corresponding pipe network pressure threshold parameter to generate the hierarchical response execution instruction at 10:07.

[0101] Finally, at 10:08, the execution control module controlled the pipe network valve group to switch to the mechanical self-locking mode according to the instruction, forcibly closed the pipe section of the pollution core area, and started the reverse flushing process, effectively completing the isolation before the pollution group reached the water intake. The whole automatic emergency response process took only 8 minutes from detection to execution, which was much faster than the traditional manual intervention mode which took 2-3 hours, and the efficiency was greatly improved.

[0102] In a more serious simulated pollution event, the emergency level parameter generated by the system exceeded the threshold , the event level is determined as the first level. The system immediately controls the valve group to switch to the electromagnetic drive mode with the fastest response speed (response time less than 150 ms), and synchronously starts the standby water source switching process. After the system monitors that the standby water source pipe network pressure is higher than that of the contaminated area by 10% and the water quality parameters (turbidity , residual chlorine mg / L) continuously meet the standards, the switching valve is smoothly opened, ensuring uninterrupted water supply to the downstream key users, and successfully avoiding pollution transfer.

[0103] By collecting pollution blocking time, water supply recovery time and pipe network pressure data, the system evaluates the response efficiency and generates system optimization parameters. For example, after a response, the system analyzes that the start-up pressure of the backwashing mode can be appropriately increased, and accordingly adjusts the pipe network control logic through the feedback mechanism, so that the recovery resilience factor of the next similar event is increased by about 12%.

[0104] Table 1 Comparison table of response efficiency of sudden pollution event

[0105]

[0106] Table 2 Data table of pipe network valve group graded response mode

[0107]

[0108] Table 3 Key parameter table of standby water source switching process

[0109]

[0110] From the data recorded in the above Tables 1 to 3, it can be seen that the present application exhibits significant technical advantages in emergency water supply scheduling.

[0111] The data in Table 1 clearly shows that the present application significantly shortens the total emergency response time from the traditional 180 minutes to 8 minutes, with a response speed increase of more than 20 times. At the same time, through pressure buffer wave control, the maximum pipe network pressure fluctuation is controlled at 0.08 MPa, which is much lower than the 0.45 MPa that may cause pipe damage in the traditional way, greatly ensuring the safety of pipe network operation.

[0112] Table 2 shows the effectiveness of the system's graded response mechanism. The system can automatically match the optimal valve operation mode according to the calculated emergency level parameter value, achieving a balance between response speed and system energy consumption and mechanical loss, and ensuring that the most appropriate measures are taken under different criticality levels.

[0113] The data in Table 3 verifies the safety and reliability of the backup water source switching process. The system strictly follows the principle of "testing pressure first, then water quality, and then switching." Only after confirming that the backup water source pressure and water quality both meet the standards is the switching operation performed smoothly. This fundamentally eliminates the risk of secondary pollution and the impact on the pipeline network caused by sudden pressure changes, achieving safe and seamless water supply assurance.

[0114] It should be noted that the electrical connections between the various units described above do not necessarily represent direct or indirect connections. Any indirect connection method can be applied to the embodiments of the present invention as long as it achieves the purpose of the present invention. The above descriptions are merely exemplary embodiments of the present invention and should not be construed as limiting the scope of the present invention.

[0115] All equivalent changes and modifications made in accordance with the teachings of this invention are still within the scope of this invention. Those skilled in the art will readily conceive of other embodiments of this invention upon considering the specification and the disclosure of practical truth. This application is intended to cover any variations, uses, or adaptations of this invention that follow the general principles of this invention and include common knowledge or conventional techniques in the art not described herein.

Claims

1. An intelligent emergency water supply scheduling method for sudden pollution of a water source, characterized in that, The method includes: The system acquires pH values, heavy metal concentrations, and organic matter content from a group of mobile water quality monitoring buoys, generating multi-dimensional pollution parameters. Fluid dynamics simulation and geological parameter fusion calculation are performed on the multi-dimensional pollution parameters to generate a three-dimensional pollution cloud map; Based on the three-dimensional pollution cloud map, pollution diffusion boundaries are extracted, and pollution blocking boundary parameters are generated. This includes: firstly, identifying regions of abrupt changes in pollution concentration gradients based on the three-dimensional pollution cloud map; and then, using a joint detection method of three-dimensional spatial interpolation and kernel density estimation, calculating the intensity modulus of pollutant concentration change along the water flow direction at each coordinate point. : ,in, , , These represent the concentration differences between this point and adjacent points in the horizontal longitudinal, horizontal transverse, and vertical directions of the groundwater flow field. , , For its spacing; when The value exceeds the preset mutation detection threshold. The pollution front is considered to be the area where the pollution front is located. Based on the connection between the pollution front and the topographic and water flow potential contour points, pollution blocking boundary parameters with continuous boundary coordinate data are generated. Based on the pollution blocking boundary parameters, pipeline control logic decisions are made to generate a pressure control unit operating mode instruction set. Based on the pressure control unit's operating mode instruction set, pressure pulse characteristic parameters are calculated, and a pressure buffer wave control signal is generated. The pressure buffer wave control signal is dynamically matched with the pipeline pressure threshold parameter to generate a graded response execution command. This includes: extracting the fluctuation frequency and amplitude characteristics from the pressure buffer wave control signal to generate an urgency parameter; matching the urgency parameter with a preset pollution event level classification standard to determine the current event level; and calling the pipeline pressure threshold parameter corresponding to the current event level to generate a graded response execution command. The pipeline pressure threshold parameter includes a pressure upper limit, a pressure fluctuation tolerance range, and an emergency pressure relief trigger condition. According to the graded response execution command, the pipeline valve group is controlled to switch the working mode, which includes electromagnetic drive mode, mechanical self-locking mode and gravity self-locking mode.

2. The emergency water supply intelligent scheduling method for sudden pollution of a water source as described in claim 1, characterized in that, The generation of the three-dimensional pollution cloud map includes: The multi-dimensional pollution parameters are cleaned and standardized to generate standardized pollution parameters; Permeability coefficient for obtaining groundwater hydrogeological parameters; The standardized pollution parameters and the permeability coefficient are spatially superimposed to generate a vertical pollution migration rate distribution map. The horizontal pollution diffusion range is calculated using fluid dynamics equations, and a horizontal pollution range prediction map is generated. Based on the weight ratio of the permeability coefficient and the standardized pollution parameters, the vertical pollution migration rate distribution map and the horizontal pollution range prediction map are fused to generate a three-dimensional pollution cloud map.

3. The emergency water supply intelligent scheduling method for sudden pollution of a water source as described in claim 2, characterized in that, The instruction set for the operating mode of the pressure control unit includes: Based on the three-dimensional pollution cloud map, regions with abrupt changes in pollution concentration gradient are identified, and pollution blocking boundary parameters are generated. The pollution blocking boundary parameters are divided to determine the isolation range of the pollution core area and the boundary of the pollution diffusion buffer zone; Based on the isolation range of the core pollution area, generate isolation mode control instructions; Based on the boundary of the contamination diffusion buffer zone, a reverse flushing mode control command is generated; Generate normal mode control commands in uncontaminated areas; The isolation mode control command, the backflushing mode control command, and the normal mode control command are combined to generate a pressure control unit operating mode command set.

4. The emergency water supply intelligent scheduling method for sudden pollution of a water source as described in claim 3, characterized in that, The control signal for generating the pressure buffer wave includes: The pipeline flow rate fluctuation amplitude is calculated based on the pressure control unit's operating mode instruction set, and expected flow rate fluctuation gradient parameters are generated. The pressure pulse frequency and amplitude are determined based on the expected flow rate mutation gradient parameters, and pressure pulse characteristic parameters are generated. The pressure pulse characteristic parameters are dynamically superimposed with the preset pipeline elastic compensation coefficient to generate a pressure buffer wave control signal.

5. The emergency water supply intelligent scheduling method for sudden pollution of a water source as described in claim 1, characterized in that, Determining the current event level includes: Compare the urgency parameter with the threshold range in the pollution event classification standard; Based on the comparison results, the urgency parameter is assigned to the event level within the corresponding threshold range; The event level to which it belongs is determined as the current event level.

6. The emergency water supply intelligent scheduling method for sudden pollution of a water source as described in claim 1, characterized in that, The control network valve group switches its operating mode according to the graded response execution command: Parse the hierarchical response execution instructions to identify the event level information contained therein; Based on the event level information, determine the level of the current pollution event; When the level of the current pollution event is Level 1, control the valve group to switch to electromagnetic drive mode; When the level of the current pollution event is Level 2, control the valve group to switch to mechanical self-locking mode; When the current pollution event is classified as Level 3, the valve assembly is switched to gravity self-locking mode, and the backup water source switching process is initiated.

7. The emergency water supply intelligent scheduling method for sudden pollution of a water source as described in claim 6, characterized in that, The process for switching to the backup water source includes: Obtain real-time pressure status parameters and real-time water quality parameters of the backup water source pipeline section; Adjust the backup water source booster pump based on the real-time pressure status parameters to make the backup water source pressure higher than the pipeline pressure in the polluted area. When the real-time water quality parameters meet the preset safety threshold, the switching valve between the backup water source and the target pipeline segment is opened.

8. The emergency water supply intelligent scheduling method for sudden pollution of a water source as described in claim 1, characterized in that, The method further includes: Collect data on pollution interruption time, water supply restoration time, and pipeline pressure, and generate pipeline operation parameter records; The system response efficiency is evaluated based on the recorded pipeline operation parameters, and system optimization parameters are generated. The pipeline control logic decision-making process is adjusted based on the system optimization parameters.

9. An intelligent emergency water supply scheduling system for sudden pollution of a water source, applied to the intelligent emergency water supply scheduling method for sudden pollution of a water source as described in any one of claims 1-8, characterized in that, The system includes: The data acquisition module is used to acquire pH values, heavy metal concentrations, and organic matter content collected by the mobile water quality monitoring buoy group, and generate multi-dimensional pollution parameters; The pollution simulation module is used to perform fluid dynamics simulation and geological parameter fusion calculation on the multi-dimensional pollution parameters to generate a three-dimensional pollution cloud map. The boundary recognition module is used to extract pollution diffusion boundaries based on the three-dimensional pollution cloud map and generate pollution blocking boundary parameters. This includes: firstly, identifying regions of abrupt changes in pollution concentration gradients based on the three-dimensional pollution cloud map; and then, using a joint detection method of three-dimensional spatial interpolation and kernel density estimation, calculating the magnitude of pollutant concentration change intensity along the water flow direction at each coordinate point. : ,in, , , These represent the concentration differences between this point and adjacent points in the horizontal longitudinal, horizontal transverse, and vertical directions of the groundwater flow field. , , For its spacing; when The value exceeds the preset mutation detection threshold. The pollution front is considered to be the area where the pollution front is located. Based on the connection between the pollution front and the topographic and water flow potential contour points, pollution blocking boundary parameters with continuous boundary coordinate data are generated. The control decision module is used to make pipeline control logic decisions based on the pollution blocking boundary parameters and generate a pressure control unit operating mode instruction set. The pressure characteristic module is used to calculate pressure pulse characteristic parameters based on the working mode instruction set of the pressure control unit and generate a pressure buffer wave control signal. The instruction matching module is used to dynamically match the pressure buffer wave control signal with the pipeline pressure threshold parameter to generate a graded response execution instruction. This includes: extracting the fluctuation frequency and amplitude characteristics from the pressure buffer wave control signal to generate an urgency parameter; matching the urgency parameter with a preset pollution event level classification standard to determine the current event level; and calling the pipeline pressure threshold parameter corresponding to the current event level to generate a graded response execution instruction. The pipeline pressure threshold parameter includes a pressure upper limit, a pressure fluctuation tolerance range, and an emergency pressure relief trigger condition. The execution control module is used to control the pipeline valve group to switch working modes according to the graded response execution command. The working modes include electromagnetic drive mode, mechanical self-locking mode and gravity self-locking mode.

Images