Rain and sewage diversion optimization method based on combination of terrain gravity and pipe network

Abstract

The invention relates to the technical field of rain and sewage diversion, in particular to a rain and sewage diversion optimization method based on combination of terrain gravity and a pipe network, in the rain and sewage diversion optimization method, slope calculation, flow gradient analysis and section resistance matching are combined, a rain and sewage mixed flow trend and a pipeline full flow section are accurately recognized, drainage capacity distribution is optimized, and the rain and sewage diversion efficiency is improved. According to the method, a slope imbalance section and a discharge capacity difference area can be recognized in advance through transmission capacity calculation and flow velocity gradient analysis, data support is provided for load distribution optimization, a Markov switching system is combined with flow direction transfer rate calculation and pressure fluctuation analysis, the system adjusts the flow direction based on dynamic changes of different discharge modes, and the flow direction transfer rate calculation and pressure fluctuation analysis are combined. The influence of burst flow impact is reduced, a dynamic flow direction adjusting strategy is constructed through a hidden Markov model, self-adaptive matching is formed between flow direction change analysis and a diversion transfer strategy, the accuracy of rainwater and sewage diversion is improved, regulation and control error calculation is combined with flow direction equilibrium adjustment, and setting of switching points and overflow adjusting parameters is more flexible.

Description

Technical Field

[0001] The present invention relates to the technical field of rainwater and sewage separation, and in particular to a rainwater and sewage separation optimization method based on the combination of terrain gravity and a pipe network. Background Art

[0002] The field of rainwater and sewage separation technology aims to achieve separate collection, transportation and treatment of rainwater and sewage through independent rainwater and sewage pipe network systems, improve the efficiency of drainage systems, reduce the burden on sewage treatment plants, reduce overflow pollution, and optimize water resource management.

[0003] The purpose of the rainwater and sewage diversion optimization method based on the combination of terrain gravity and pipeline network is to make full use of the natural height difference of the terrain, guide the flow of rainwater and sewage through gravity, reduce energy consumption, and optimize the pipeline network layout to make rainwater and sewage diversion more efficient, reduce the processing burden of sewage treatment plants, reduce the energy consumption of pipeline network transportation, improve the stability and reliability of urban drainage systems, avoid urban waterlogging during heavy rains, and reduce environmental pollution caused by mixed rainwater and sewage discharge.

[0004] Existing technologies are unable to accurately calculate the matching of water flow potential energy and slope, resulting in discharge capacity overload in some areas of the pipeline, while some areas are in a low-load state, resulting in reduced drainage efficiency. It is difficult to quickly respond to instantaneous flow changes in the intersection of rainwater and sewage, causing local pipeline overload and overflow, increasing the burden of sewage treatment, and the discharge path and flow direction adjustment method are relatively fixed. When encountering extreme weather or a sudden increase in upstream drainage, the flow direction cannot be flexibly adjusted, resulting in downstream pipeline overload and even urban flooding. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the existing technology and propose a rainwater and sewage diversion optimization method based on the combination of terrain gravity and pipe network.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a rainwater and sewage diversion optimization method based on the combination of terrain gravity and pipe network, comprising the following steps: Step 1: Use sensors to extract terrain elevation data, drainage zone boundaries, and gravity potential energy distribution, calculate slope direction, extract flow gradients, and track water flow paths. This screens high-potential energy catchment areas and low-potential energy discharge areas to generate a terrain water flow potential matrix. Step 2: Based on the terrain water flow potential matrix, perform slope calculation, flow gradient analysis, and cross-section resistance matching to extract the rainwater and sewage mixed flow trend and the full flow section of the pipeline, and generate a pipe network gravity discharge capacity parameter set; Step 3: Based on the pipeline network gravity discharge capacity parameter set, perform transportation capacity calculation and velocity gradient analysis, screen out uneven slope sections and discharge capacity difference areas, and generate the pipeline network load distribution state; Step 4: Based on the load distribution state of the pipe network, a Markov switching system is used to calculate the flow transfer rate and analyze the pressure fluctuation, extract the flow imbalance points and the rainwater and sewage intersection area, and generate the optimal configuration of rainwater and sewage diversion; Step 5: Based on the optimized configuration of rainwater and sewage diversion, a hidden Markov model is used to perform flow adjustment calculation and flow direction change analysis, extract slope influencing parameters and diversion transfer strategies, and generate a dynamic optimization plan for flow regulation; Step 6: Based on the flow regulation dynamic optimization scheme, perform regulation error calculation and flow direction balance adjustment, select flow direction switching points and dynamic overflow regulation parameters, and generate a flow direction regulation execution parameter set; Step 7: Based on the flow direction control execution parameter set, perform execution error calculation and flow direction offset correction, extract sudden flow adjustment points and overflow control nodes, and generate a pipe network drainage intelligent regulation strategy.

[0007] As a further solution of the present invention, the specific steps of generating the terrain water flow potential energy matrix are: Sensors are used to extract terrain elevation data, drainage zone boundaries, and gravity potential energy distribution. Elevation grid interpolation is performed and the rate of elevation change is calculated. Slope direction analysis is performed and slope mutation points are identified. Water flow direction is calculated and the slope influence range is extracted. Water flow diversion areas are screened to generate slope gradient distribution data. Based on the slope gradient distribution data, the confluence area is classified and the slope flow direction trend is extracted. The slope flow direction is calculated and the slope change point is determined. The flow direction stability is analyzed and the water flow transfer area is screened. The high potential energy confluence area and the low potential energy discharge area are extracted to generate the water flow convergence and dispersion distribution data. Based on the water flow convergence and dispersion distribution data, the slope flow velocity is calculated and the flow velocity change value is extracted, the water flow energy loss is calculated and the potential energy decrease rate is measured, the hydraulic flow direction is matched and the discharge path is adjusted, the stable flow path and the potential energy decrease channel are screened, and the terrain water flow potential energy matrix is ​​generated.

[0008] As a further solution of the present invention, the specific steps of generating the pipe network gravity discharge capacity parameter set are: Based on the terrain water flow potential energy matrix, slope change calculation is performed and slope matching is determined, flow gradient analysis is performed and flow change rate is calculated, slope impact identification is performed and flow imbalance sections are extracted, slope impact pipe sections and flow adjustment points are screened, and slope and flow distribution data are generated; Based on the slope and flow distribution data, the pipeline transport capacity is calculated and the flow velocity change is measured. The water flow resistance is calculated and the resistance impact is analyzed. The stability of the rainwater-sewage mixed flow is analyzed and the flow mutation area is screened. The rainwater-sewage intersection area, the mixed flow mutation area and the water flow buffer area are extracted to generate the pipeline mixed flow trend and transport capacity data. Based on the pipeline mixed flow trend and conveying capacity data, the flow velocity of the full flow section is calculated and the pipeline conveying capacity is measured, the discharge capacity is evaluated and the overload points are extracted, the gravity discharge capacity is analyzed and the water flow guidance path is adjusted, the high-load pipe sections and discharge overload areas are screened, and the pipeline network gravity discharge capacity parameter set is generated.

[0009] As a further solution of the present invention, the specific steps of generating the pipe network load distribution state are: Based on the pipeline network gravity discharge capacity parameter set, the pipeline transportation capacity is calculated, the transportation limit is extracted by flow segmentation measurement, the flow gradient analysis is performed, the velocity change is measured by along-line flow velocity sampling, the slope effect is determined, the slope comparison analysis is used to screen the flow velocity abnormality section, the slope effect prominent section and the flow change point are extracted, and the pipeline transportation capacity distribution data is generated; Based on the pipeline transportation capacity distribution data, the slope uneven area is screened, the slope continuity measurement is used to extract the influence range of the slope change, the discharge capacity is calculated, the load difference of each pipe section is measured by unit flow load comparison, and the flow balance analysis is performed. The load distribution deviation analysis is used to screen overload and underload areas, extract the slope uneven section and the discharge capacity difference area, and generate the slope and discharge capacity distribution data; Based on the slope and discharge capacity distribution data, pipeline pressure distribution analysis is carried out, cross-sectional pressure calculation is used to extract flow mutation points, discharge load balance measurement is performed, pressure gradient comparison is used to identify pressure overloaded pipe sections, pipeline network pressure adjustment analysis is performed, flow direction stability judgment is used to screen flow optimization points, abnormal slope sections and pressure change areas are extracted, and the pipeline network load distribution status is generated.

[0010] As a further solution of the present invention, the specific steps of generating the optimized configuration of rainwater and sewage diversion are: Based on the load distribution state of the pipeline network, the flow direction transfer rate is calculated, the flow direction conversion matrix under different discharge modes is established using the Markov switching system, pressure fluctuation analysis is performed, the impact of flow adjustment on pressure is measured using dynamic pressure monitoring, the discharge flow adaptability is calculated, and the flow direction dynamic evaluation is used to screen the flow direction change area, extract the flow change points and pressure fluctuation areas, and generate flow direction change distribution data; Based on the flow direction change distribution data, flow imbalance calculation is performed, flow deviation comparison is used to determine the load difference in the imbalanced area, rainwater and sewage intersection areas are screened, mixed flow comparison calculation is used to identify unstable pipe sections, flow direction matching measurement is performed, flow coordination analysis is used to screen the optimized adjustment area, flow imbalance points and rainwater and sewage intersection areas are extracted, and flow direction adjustment optimization data is generated; Based on the flow direction adjustment optimization data, flow control calculations are performed, zone flow adjustment is used to extract flow adjustment parameters, discharge flow direction matching analysis is performed, pipeline load distribution comparison is used to optimize pipeline flow allocation, pipeline control adjustments are made, adjustment parameters are used to dynamically update and screen key adjustment points, rainwater and sewage diversion optimization key parameters are extracted, and rainwater and sewage diversion optimization configuration is generated.

[0011] As a further solution of the present invention, the Markov switching system performs flow state modeling, uses time series segmentation analysis to extract flow characteristics of different emission modes, performs state discretization processing, converts continuous flow changes into a finite state set, and calculates state transition probabilities. It uses mode switching frequency statistics to determine the transition probability between each mode, analyzes the steady-state distribution, uses long-term flow trend backtracking to extract the stable state probability under different modes, evaluates the sensitivity of flow direction changes, uses key mode switching points to screen and identify variable sections, establishes a flow direction conversion matrix, and optimizes the stability of pipeline network flow pattern adjustment.

[0012] As a further solution of the present invention, the specific steps of generating the flow regulation dynamic optimization solution are: Based on the optimized configuration of rainwater and sewage diversion, flow adjustment calculations are performed, cross-sectional flow velocity measurements are used to obtain flow change rates, flow direction change analysis is performed, a hidden Markov model is used to construct a water flow state transfer matrix, flow direction change patterns are identified, flow direction deviation amplitudes are extracted, pressure measurements are performed, and pressure gradient comparisons are used to screen high and low pressure areas to generate flow distribution adjustment data; Based on the flow distribution adjustment data, a slope impact analysis is performed, the slope change calculation is used to extract the slope rate, flow transfer calculation is performed, the diversion ratio is determined by flow direction cross comparison, overload diversion optimization is performed, the load change pipe section is screened by discharge section calculation, the slope impact parameters and diversion adjustment points are extracted, and flow regulation plan data is generated; Based on the flow regulation scheme data, flow direction matching optimization is performed, flow trend backtracking is used to extract dynamic flow direction distribution, the control area is determined, the regulation boundary is determined by pressure fluctuation calculation, load balancing is measured, the load area is screened by adjustment amplitude comparison, key flow regulation parameters are extracted, and a flow regulation dynamic optimization scheme is generated.

[0013] As a further solution of the present invention, the hidden Markov model is used to model the water flow state, use multi-period flow classification to extract characteristic variables under different flow states, set hidden states, use flow change trend analysis to define a set of potential flow direction patterns, calculate state transition probabilities, use continuous time series comparison to determine the transition probabilities between each hidden state, construct an observation probability matrix, use flow velocity, pressure, and flow direction change data matching to optimize state observation distribution, perform state decoding, use forward-backward probability calculation to extract flow direction change paths, generate a water flow state transfer matrix, and optimize flow direction offset pattern recognition.

[0014] As a further solution of the present invention, the specific steps of generating the flow direction control execution parameter set are: Based on the dynamic optimization scheme for flow regulation, control error calculation is performed, error range is determined by flow deviation monitoring, flow direction balance adjustment is performed, balance parameters are extracted by flow direction stability measurement, overflow monitoring is performed, overflow-sensitive areas are screened by flow fluctuation analysis, and flow direction regulation error data is generated; Based on the flow direction adjustment error data, switching point screening is performed, flow inflection points are extracted using pressure gradient analysis, overflow adjustment measurement is performed, overflow control parameters are determined using flow change calculation, discharge path matching is performed, transfer points are screened using flow direction scheduling calculation, and flow direction switching parameter data is generated; Based on the flow direction switching parameter data, dynamic flow direction matching is performed, flow balance measurement is used to extract flow direction adjustment values, overflow buffer optimization is performed, and at the same time, the discharge stable area is measured, and the control parameters are integrated. The pressure change calculation is used to screen the adjustment value, the key flow direction control parameters are extracted, and the flow direction control execution parameter set is generated.

[0015] As a further solution of the present invention, the specific steps of generating the intelligent regulation strategy for pipe network drainage are: Based on the flow direction control execution parameter set, execution error calculation is performed, control deviation value is calculated by comparison using historical flow data, flow direction deviation analysis is performed, deviation direction and amplitude are extracted using real-time flow direction monitoring, pipeline pressure fluctuation is measured, abnormal pressure points are screened using pressure change trend analysis, and execution error distribution data is generated; Based on the execution error distribution data, sudden flow adjustment analysis is performed, abnormal flow distribution points are extracted using flow overload area statistics, discharge path correction is performed, flow direction change at confluence nodes is used to determine and calculate the adjustment direction, overflow impact assessment is performed, high-risk overflow pipes are screened using overload flow threshold comparison, and sudden flow adjustment data is generated; Based on the sudden flow adjustment data, flow direction optimization matching is performed, flow balance calculation is used to extract flow direction adjustment values, overflow control nodes are screened, discharge load distribution analysis is used to extract key control points, flow control parameters are integrated, real-time flow direction adjustment comparison is used to screen discharge adjustment values, key flow direction control parameters are extracted, and an intelligent adjustment strategy for pipe network drainage is generated.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: 1. This invention combines slope calculation, flow gradient analysis, and cross-sectional resistance matching to accurately identify mixed rainwater and sewage flow trends and full-flow sections in pipes, optimize drainage capacity allocation, and calculate conveying capacity and analyze flow velocity gradients. This allows for early identification of sections with uneven slopes and areas with varying discharge capacities, providing data support for load distribution optimization. 2. This invention combines a Markov switching system with flow direction transfer rate calculation and pressure fluctuation analysis to adjust flow direction based on the dynamic changes in different discharge patterns. This system constructs an optimal switching strategy under different hydraulic conditions, improves the adaptability of rainwater and sewage diversion, and reduces the impact of sudden flow shocks. 3. This invention utilizes a hidden Markov model to construct a dynamic flow direction adjustment strategy, enabling adaptive matching of flow direction change analysis with diversion and transfer strategies, improving the accuracy of rainwater and sewage diversion. The combination of control error calculation and flow direction balance adjustment allows for more flexible setting of switching points and overflow adjustment parameters, allowing adjustments based on real-time drainage conditions to reduce instantaneous overload. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0018] Figure 1 It is a schematic diagram of the main steps of the present invention; Figure 2 This is a schematic diagram of the refinement of S1 of the present invention; Figure 3 This is a schematic diagram of the refinement of S2 of the present invention; Figure 4 This is a schematic diagram of the refinement of S3 of the present invention; Figure 5 This is a schematic diagram of the refinement of S4 of the present invention; Figure 6 This is a schematic diagram of the refinement of S5 of the present invention; Figure 7 This is a schematic diagram of the refinement of S6 of the present invention; Figure 8 This is a detailed schematic diagram of S7 of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application; the technical solutions in the embodiments of this application will be described in detail below in conjunction with the drawings.

[0020] See also Figure 1 The present invention provides a technical solution: a rainwater and sewage diversion optimization method based on the combination of terrain gravity and pipe network, comprising the following steps: S1: Sensors are used to extract terrain elevation data, drainage zone boundaries, and gravity potential energy distribution. Slope direction calculations, flow gradient extraction, and water path tracking are performed to screen high-potential energy catchment areas and low-potential energy discharge areas, generating a terrain water flow potential matrix. S2: Based on the terrain water flow potential matrix, slope calculation, flow gradient analysis and cross-section resistance matching are performed to extract the rainwater and sewage mixed flow trend and the full flow section of the pipeline, and generate the gravity discharge capacity parameter set of the pipeline network; S3: Based on the network gravity discharge capacity parameter set, the transmission capacity is calculated and the flow velocity gradient is analyzed to screen the uneven slope sections and the areas with different discharge capacity, and generate the network load distribution status; S4: Based on the load distribution of the pipe network, a Markov switching system is used to calculate the flow transfer rate and analyze the pressure fluctuation, extract the flow imbalance points and the rainwater and sewage intersection area, and generate the optimal configuration of rainwater and sewage diversion; S5: Based on the optimal configuration of rainwater and sewage diversion, the hidden Markov model is used to perform flow adjustment calculations and flow direction change analysis, extract slope influencing parameters and diversion transfer strategies, and generate a dynamic optimization plan for flow regulation; S6: Based on the dynamic optimization scheme for flow regulation, the control error is calculated and the flow direction balance is adjusted. The flow direction switching point and dynamic overflow regulation parameters are selected to generate a flow direction regulation execution parameter set. S7: Based on the flow direction control execution parameter set, the execution error calculation and flow direction offset correction are performed, the sudden flow adjustment point and overflow control node are extracted, and the intelligent regulation strategy for pipe network drainage is generated.

[0021] See also Figure 2 , the specific steps to generate the terrain water flow potential energy matrix are: S101: Extract terrain elevation data, drainage zone boundaries, and gravity potential energy distribution through sensors, perform elevation grid interpolation and calculate elevation change rate, perform slope direction analysis and identify slope mutation points, calculate water flow direction and extract the slope influence range, screen water flow diversion areas, and generate slope gradient distribution data; S102: Based on the slope gradient distribution data, the confluence area is classified and the slope flow direction trend is extracted. The slope flow direction is calculated and the slope change point is determined. The flow direction stability is analyzed and the water transfer area is screened. The high potential energy confluence area and low potential energy discharge area are extracted to generate water flow convergence and dispersion distribution data. S103: Based on the water flow convergence and dispersion distribution data, calculate the slope flow velocity and extract the flow velocity change value, calculate the water flow energy loss and measure the potential energy drop rate, match the hydraulic flow direction and adjust the discharge path, select stable flow paths and potential energy drop channels, and generate a terrain water flow potential energy matrix; S101: Based on the terrain elevation data, drainage zone boundaries, and gravitational potential energy distribution collected by sensors, the IDW interpolation algorithm is used to calculate the elevation grid data. The elevation data is interpolated according to the set interpolation weight coefficient, with the number of neighboring sample points set to 12 and the power exponent set to 2. The elevation change rate data is generated. The slope direction is calculated using the Horn algorithm. The unit slope is calculated using a 3×3 window convolution on the elevation grid data. The slope direction data is discrete Fourier transformed with a Hanning window and 512 FFT points set to extract the slope mutation points. The D8 flow direction algorithm is used to calculate the flow direction of the slope mutation point data. The flow direction of the slope mutation point data is calculated using the maximum slope gradient direction. The Tarboton multi-flow direction algorithm is used to calculate the slope influence range. The weight matrix is ​​set to calculate the cumulative flow in the water flow influence area. The cumulative flow data is thresholded and filtered with a threshold of 300 grid cells to filter the water flow diversion area and generate slope gradient distribution data. S102: Based on the slope gradient distribution data, the confluence area is classified, the number of cluster centers is set to 5, the number of iterations is set to 300, the Euclidean distance is calculated for the cluster classification data, and the cluster centers are calculated and dynamically updated based on the least squares error. The slope flow trend is calculated, the water flow direction is extracted from the slope gradient data matrix using the cumulative flow calculation method, the flow direction stability analysis is performed on the flow direction data using the direction consistency filtering algorithm, the window size is set to 5×5 for directional gradient accumulation calculation, the gradient change rate is calculated using the Sobel operator for the flow direction stability data, and the water flow transfer area is screened. The high potential energy confluence area and the low potential energy discharge area are extracted using the flow potential gradient segmentation method, the connected area is marked for the slope change rate data, and the flow potential threshold is set according to the flow potential distribution weight. The threshold is set to 1.5 times the local average value, the confluence area and the discharge area are distinguished, and the water flow convergence and dispersion distribution data are generated; S103: Based on the water flow convergence and dispersion distribution data, the slope flow velocity is calculated, the roughness coefficient n is set to 0.035, the slope unit flow velocity is calculated and the flow velocity change value is extracted, the Bernoulli equation is used to calculate the water flow energy loss for the flow velocity data, the ratio threshold of the kinetic energy term to the potential energy term is set to 0.75 for hydraulic energy balance calculation, the Dijkstra algorithm is used to calculate the hydraulic flow direction matching path, the hydraulic flow direction data is converted into an adjacency matrix and a shortest path search is performed, the flow channel optimization algorithm is used to adjust the discharge path for the path data, the hydraulic gradient values ​​of adjacent discharge paths are compared to screen stable flow paths, the flow path stability threshold is set, and the threshold is set to the local average gradient value ±10%, and screening is performed. A potential energy drop channel is constructed for the screened path data to generate a terrain water flow potential energy matrix.

[0022] See also Figure 3 The specific steps to generate the network gravity discharge capacity parameter set are: S201: Based on the terrain water flow potential matrix, calculate the slope change and determine the slope matching degree, perform flow gradient analysis and calculate the flow change rate, identify the slope impact and extract the flow imbalance section, select the slope impact pipe section and flow adjustment point, and generate slope and flow distribution data; S202: Based on the slope and flow distribution data, calculate the pipeline transport capacity and measure the flow velocity change, calculate the water flow resistance and analyze the resistance impact, analyze the stability of the rainwater-sewage mixed flow and screen the flow mutation area, extract the rainwater-sewage intersection area, the mixed flow mutation area and the water flow buffer area, and generate the pipeline mixed flow trend and transport capacity data; S203: Based on the pipeline mixed flow trend and conveying capacity data, the flow velocity of the full flow section is calculated and the pipeline conveying capacity is measured. The discharge capacity is evaluated and overload points are extracted. The gravity discharge capacity is analyzed and the water flow guidance path is adjusted. High-loaded pipe sections and discharge overload areas are selected to generate a pipeline network gravity discharge capacity parameter set. S201: Based on the terrain water flow potential matrix, the finite difference method is used to calculate the slope change. A spatial differential grid is constructed for the slope elevation data. The grid step size is set to 5 meters and the time step size is set to 0.1 seconds. The slope gradient of each grid cell is calculated, and the slope matching degree is calculated. The slope matching error is calculated using the stepwise regression analysis method. The error threshold is set to 0.05. Flow gradient analysis is performed to calculate the flow change rate. The width of the water flow section is set to 1.2 meters and the average flow velocity is set to 2.5 meters per second. The instantaneous flow change is calculated and the slope effect is identified. The local extreme value detection algorithm is used to extract the flow imbalance section. The flow fluctuation area is extracted by comparing the slope gradient change rate. The adaptive threshold segmentation method is used for the flow imbalance section data to screen the slope-affected pipe sections and flow adjustment points, and generate slope and flow distribution data. S202: Based on the slope and flow distribution data, calculate the pipeline transport capacity, set the hydraulic radius to 0.5 meters and the roughness coefficient to 110, calculate the flow rate for different pipe diameter sections and measure the flow velocity change, calculate the water flow resistance, set the Reynolds number to 4000 and the water flow density to 1000 kilograms per cubic meter, calculate the resistance loss along the pipeline, and perform a resistance impact analysis. Use the flow resistance partitioning method to identify local resistance surge points on the pipeline resistance distribution data, perform a variance analysis on the flow velocity stability data, set the standard deviation threshold to 0.15, and perform a rainwater-sewage mixed flow stability analysis. Use a bivariate probability distribution model to calculate the probability of mixed flow change, set the sewage flow ratio range to 0.3 to 0.7, extract the rainwater-sewage intersection area, mixed flow mutation area, and water flow buffer area, use the hydraulic radius adjustment method to calculate the water flow mixing degree for the intersection area data, and perform flow direction reconstruction calculation to generate pipeline mixed flow trend and transport capacity data; S203: Based on the pipeline mixing trend and conveying capacity data, the Chezy formula is used to calculate the flow velocity of the full flow section. The Chezy coefficient is set to 55, the pipe diameter is 1.5 meters, and the slope is 0.0025. The flow velocity of the full flow section is calculated and the pipeline conveying capacity is measured. The mass continuity equation is used to calculate the discharge capacity of the conveying capacity data. The pipeline conveying overload rate is calculated by comparing the inlet flow and the discharge flow, and the overload point is extracted. The gravity discharge equation is used to analyze the gravity discharge capacity. The pipeline inclination is set to 3 degrees, the water flow potential energy conversion rate is calculated, and the water flow guidance path is adjusted. The A* search algorithm is used to screen high-load pipe sections. A weighted graph model is constructed for the pipeline flow direction data. The search step is set to 1.5 meters. The discharge path is calculated, and the discharge overload area is screened to generate a pipeline network gravity discharge capacity parameter set.

[0023] See also Figure 4 , the specific steps to generate the load distribution status of the pipeline network are: S301: Calculate pipeline transport capacity based on the network's gravity discharge capacity parameter set. Calculate the transport limit using flow segmentation. Analyze velocity gradients. Measure velocity changes using along-the-route velocity sampling. Determine the impact of slope drop. Filter out sections with abnormal velocity using slope drop comparison analysis. Detect sections with prominent slope drop effects and flow change points. Generate pipeline transport capacity distribution data. S302: Based on the pipeline transport capacity distribution data, the pipeline performs a screening of areas with uneven slopes. The slope continuity calculation is used to extract the impact range of the slope change. The discharge capacity is calculated. The load differences between each pipe section are measured using a unit flow load comparison. A flow balance analysis is performed. The load distribution deviation analysis is used to screen overloaded and underloaded areas. Unbalanced slope sections and areas with different discharge capacity are extracted to generate slope and discharge capacity distribution data. S303: Based on the slope and discharge capacity distribution data, pipeline pressure distribution analysis is performed. Cross-sectional pressure calculation is used to extract flow mutation points, discharge load balance is measured, pressure gradient comparison is used to identify pressure overloaded pipe sections, and pipeline network pressure adjustment analysis is performed. Flow direction stability is used to select flow optimization points, abnormal slope sections and pressure change areas are extracted, and the pipeline network load distribution status is generated. S301: Based on the network's gravity discharge capacity parameter set, the pipeline's transport capacity is calculated. The pipeline diameter is set to 1.2 meters, the hydraulic radius is 0.6 meters, and the roughness coefficient is 110. The flow rate of the pipeline section is measured and measured in sections to extract the transport limit. The flow rate change rate is compared and a velocity gradient analysis is performed. The Lagrange interpolation method is used to interpolate and fit the velocity sampling data along the process. The sampling interval is set to 50 meters, the velocity change rate is calculated, and the slope effect is determined. The slope comparison analysis method is used to screen out sections with abnormal velocity. The slope change trend is calculated using the piecewise linear regression method for the slope data. The velocity change points are compared to screen out sections with prominent slope effects and flow change points, and the pipeline's transport capacity distribution data is generated. S302: Based on the pipeline transport capacity distribution data, the cubic spline interpolation method is used to screen areas with uneven slope. An interpolation function is constructed for the slope data and the slope continuity error is calculated. The error threshold is set to 0.02. The impact range of the slope change is extracted and the discharge capacity is calculated. The unit flow load comparison method is used to determine the load difference of each pipe section. The unit flow load is compared to calculate the flow balance. The load distribution deviation analysis is used to screen overload and underload areas. The load deviation data is mean-normalized. The load deviation threshold is set to ±15%. The uneven slope sections and the discharge capacity difference areas are extracted to generate the slope and discharge capacity distribution data. S303: Based on the slope and discharge capacity distribution data, the Bernoulli equation is used to analyze the pipeline pressure distribution. The cross-sectional pressure data is calculated and the flow mutation points are extracted. The finite element analysis method is used to construct a pressure distribution model. The pipeline pressure field is discretized and calculated with a calculation step size of 10 meters. The pipeline pressure changes are analyzed and the discharge load balance is calculated. The pressure gradient comparison method is used to identify pressure-overloaded pipe sections. The local gradient of the pressure data is calculated with a gradient threshold set to 1.2 times the local average pressure change rate. The pipeline pressure adjustment analysis is performed. The flow direction stability judgment method is used to screen the flow direction optimization points. The flow direction data is analyzed in time series with a sliding window size set to 100 seconds. The abnormal slope sections and pressure change areas are extracted to generate the pipeline network load distribution status.

[0024] See also Figure 5 , the specific steps to generate the optimal configuration of rainwater and sewage diversion are: S401: Based on the load distribution of the pipeline network, the flow direction transfer rate is calculated. The flow direction conversion matrix under different discharge modes is established using the Markov switching system. Pressure fluctuation analysis is performed. Dynamic pressure monitoring is used to determine the impact of flow adjustment on pressure. The discharge flow adaptability is calculated. Dynamic flow direction evaluation is used to screen flow direction change areas, extract flow change points and pressure fluctuation areas, and generate flow direction change distribution data. S402: Based on the flow direction change distribution data, flow imbalance calculation is performed. Flow deviation comparison is used to determine the load difference in the imbalanced area. Rainwater and sewage intersection areas are screened. Mixed flow comparison calculation is used to identify unstable pipe sections. Flow direction matching calculation is performed. Flow coordination analysis is used to screen the optimization adjustment areas. Flow imbalance points and rainwater and sewage intersection areas are extracted to generate flow direction adjustment optimization data. S403: Based on the flow direction adjustment optimization data, flow control calculations are performed, flow direction adjustment parameters are extracted using zone flow control, discharge flow direction matching analysis is performed, pipeline flow allocation is optimized using pipe network load distribution comparison, pipeline control adjustments are made, key adjustment points are screened using dynamic update of adjustment parameters, key parameters for rainwater and sewage diversion optimization are extracted, and an optimized rainwater and sewage diversion configuration is generated; S401: Based on the load distribution state of the pipeline network, a Markov switching system is used to establish the flow direction conversion matrix under different discharge modes, an initial probability distribution is set for the flow direction state space, a state transition probability matrix is ​​defined, and the number of states is set to 5. The flow direction switching probability under different discharge modes is calculated, and the flow direction transfer rate is calculated. The transfer rate is calculated using the matrix exponential solution method, and the state transition equation is expanded exponentially with a step size of 0.01 seconds. The matrix is ​​accumulated and summed to calculate the flow direction conversion rate. Pressure data is analyzed for pressure fluctuations. The dynamic pressure monitoring method is used to determine the impact of flow adjustment on pressure. The pressure data is decomposed into time series with a sliding window size of 100 seconds. The wavelet transform method is used to extract high-frequency pressure fluctuation components and discharge flow adaptability is calculated. The flow direction dynamic evaluation method is used to screen the flow direction change area. Dynamic trajectory analysis is performed on the flow direction data with an evaluation period of 60 seconds. The flow direction change rate is calculated, the flow change points and pressure fluctuation areas are extracted, and flow direction change distribution data is generated. S402: Based on the flow direction change distribution data, the standard deviation analysis method is used to calculate flow imbalance. The mean and standard deviation of the flow data are calculated, and the standard deviation threshold is set to 0.2. The pipe sections with deviations exceeding the threshold are screened, and the load differences in the imbalanced areas are measured. The flow deviation comparison method is used to calculate the unit flow load of the pipeline. The flow change rates of adjacent pipe sections are compared, and the rainwater and sewage intersection areas are screened. The mixed flow comparison calculation method is used to identify unstable pipe sections. The continuity calculation of the mixed flow hydraulic radius data is performed, and the calculation spacing is set to 0.5 meters. The mixed flow change rate is extracted and flow direction matching is measured. The flow coordination analysis method is used to screen the optimization adjustment area. A weighted flow network model is constructed for the flow direction data, and a weight matrix is ​​set. The flow deviation minimization objective is optimized and calculated. The flow imbalance points and rainwater and sewage intersection areas are extracted to generate flow direction adjustment optimization data. S403: Based on the flow direction adjustment optimization data, the zone flow regulation method is used to extract the flow direction adjustment parameters, and the dynamic adjustment coefficient is set for each flow zone. The Lagrange multiplier method is used to calculate the flow distribution, and the discharge flow direction matching analysis is performed on the discharge flow direction data. The pipeline load distribution comparison method is used to optimize the pipeline flow allocation, and the hydraulic gradient data of each pipe section are compared. The load balance objective function is set, and the flow distribution is nonlinearly optimized. The pipeline regulation and adjustment are carried out, and the key adjustment points are screened by the dynamic update method of the adjustment parameters. The flow adjustment data is updated in real time, and the adjustment step is set to 10 seconds. The Bayesian update method is used to calculate the adjustment parameters, extract the key parameters for rainwater and sewage diversion optimization, and generate the rainwater and sewage diversion optimization configuration.

[0025] Markov switching system is used to model the flow state, and time series segmentation analysis is used to extract the flow characteristics of different emission modes. State discretization is performed to convert continuous flow changes into a finite state set, and state transition probability is calculated. Mode switching frequency statistics are used to determine the transition probability between each mode, and the steady-state distribution is analyzed. Long-term flow trend backtracking is used to extract the stable state probability under different modes, the sensitivity of flow direction changes is evaluated, and key mode switching points are used to screen and identify variable sections. A flow direction conversion matrix is ​​established to optimize the stability of pipeline network flow pattern adjustment.

[0026] See also Figure 6 ,The specific steps of generating a dynamic optimization plan for traffic regulation are: S501: Based on the optimized configuration of rainwater and sewage diversion, flow adjustment calculations are performed. The flow change rate is obtained by cross-sectional flow velocity measurement, and flow direction change analysis is performed. The water flow state transition matrix is ​​constructed using the hidden Markov model to identify the flow direction change pattern and extract the flow direction deviation amplitude. Pressure is measured and high and low pressure areas are screened using pressure gradient comparison to generate flow distribution adjustment data. S502: Based on the flow distribution adjustment data, perform a slope impact analysis, extract the slope rate using slope change calculation, perform flow transfer calculation, determine the diversion ratio using flow direction cross comparison, perform overload diversion optimization, use discharge section calculation to select load-variable pipe sections, extract slope impact parameters and diversion adjustment points, and generate flow regulation solution data; S503: Based on the flow regulation plan data, flow direction matching optimization is performed. Dynamic flow direction distribution is extracted by back-tracing the flow trend, the regulation area is determined, the regulation boundary is determined by pressure fluctuation calculation, load balancing is calculated, and load areas are screened by adjusting the amplitude comparison. Key flow regulation parameters are extracted to generate a dynamic optimization plan for flow regulation. S501: Based on the optimized configuration of rainwater and sewage diversion, the cross-sectional flow velocity measurement method is used to obtain the flow change rate. The cross-sectional flow velocity data is sampled point by point, with a sampling interval of 2 meters. The flow velocity difference between adjacent sections is calculated and compared with the average flow change trend. The flow direction change analysis is also performed. The hidden Markov model is used to construct the water flow state transition matrix. The state set is set to include four states: stable flow direction, low-speed deviation, high-speed deviation, and backflow. The state transition probability is calculated and Bayesian update is performed. The initial state probability vector is set, and the time step is set to 5 seconds. The flow direction change pattern is identified, the flow direction deviation amplitude is extracted, and pressure is measured. The pressure gradient comparison method is used to screen high and low pressure areas. The pressure data is spatially interpolated and calculated, with an interpolation grid size of 1 meter. The pressure gradient change rates of different pipe sections are compared, high-pressure and low-pressure areas are screened, and flow distribution adjustment data is generated. S502: Based on the flow distribution adjustment data, a numerical differential method is used to analyze the impact of slope. Discrete differences are calculated for the slope data, with a step size of 1.5 meters. The slope change rate is calculated and the slope velocity is extracted. Flow transfer calculations are performed. The flow direction cross-comparison method is used to determine the diversion ratio. Matrix calculations are performed on the flow data at the intersection of the pipe sections. A diversion coefficient matrix is ​​set. The flow direction distributions at different intersection nodes are compared and overload diversion optimization is performed. The discharge section measurement method is used to screen load-changing pipe sections. Area integral calculations are performed on the discharge section data. The cross-section flow velocity range is set to 0.8 to 2.5 meters per second. The load changes per unit section are compared and abnormal pipe sections are extracted. The slope impact parameters and diversion adjustment points are extracted to generate flow regulation solution data. S503: Based on the flow regulation scheme data, the flow trend backtracking method is used to extract the dynamic flow direction distribution, and the moving average calculation is performed on the historical flow direction data. The time window is set to 120 seconds. The flow direction change trend is calculated and the dynamic flow direction data is extracted. The control area is determined, and the pressure fluctuation calculation method is used to determine the regulation boundary. The pressure gradient change rate in different areas is compared. The fluctuation detection threshold is set to 1.3 times the local average pressure change rate, and load balancing measurement is performed. The adjustment amplitude comparison method is used to screen the load area, and the load data is standardized. The load deviation before and after the adjustment is calculated and the load balancing area is screened. The key parameters of flow regulation are extracted, and a dynamic optimization plan for flow regulation is generated.

[0027] Hidden Markov model is used to model water flow states. Multi-period flow classification is used to extract characteristic variables under different flow states, and hidden states are set. Flow direction change trend analysis is used to define a set of potential flow direction patterns. State transition probabilities are calculated. Continuous time series comparison is used to determine the transition probabilities between hidden states. An observation probability matrix is ​​constructed. Flow velocity, pressure, and flow direction change data are matched to optimize state observation distributions. State decoding is performed. Forward-backward probability calculation is used to extract flow direction change paths, generate a water flow state transfer matrix, and optimize flow direction offset pattern recognition.

[0028] See also Figure 7 The specific steps to generate the flow control execution parameter set are: S601: Based on the dynamic optimization scheme for flow regulation, control error calculation is performed, error range is determined using flow deviation monitoring, flow direction balancing adjustment is performed, balancing parameters are extracted using flow direction stability measurement, overflow monitoring is performed, overflow-sensitive areas are screened using flow fluctuation analysis, and flow direction regulation error data is generated; S602: Based on the flow direction adjustment error data, switching points are screened, flow direction inflection points are extracted using pressure gradient analysis, overflow adjustment is measured, overflow control parameters are determined using flow change calculation, discharge path matching is performed, transfer points are screened using flow direction scheduling calculation, and flow direction switching parameter data is generated; S603: Based on the flow direction switching parameter data, dynamic flow direction matching is performed. Flow direction adjustment values ​​are extracted using flow balance measurement and optimization. Overflow buffering is optimized. Simultaneously, the discharge stability zone is determined. Control parameters are integrated. Adjustment values ​​are screened using pressure change calculations. Key flow direction control parameters are extracted to generate a flow direction control execution parameter set. S601: Based on the dynamic optimization scheme for flow regulation, the error range is determined using the flow deviation monitoring method. Time series analysis is performed on flow data, with an observation period set to 300 seconds. A weighted moving average is used to calculate flow change trends. The error range is calculated by comparing historical averages, and flow direction balance adjustments are made. The flow direction stability measurement method is used to extract balance parameters. The standard deviation of the flow direction data is calculated, and the stability threshold is set to 5% of the local flow direction change rate. Flow direction data with deviations exceeding the threshold are adjusted, and overflow monitoring is performed. The flow fluctuation analysis method is used to screen overflow-sensitive areas. Fourier transform is performed on the overflow section data, with a frequency threshold set to 0.2 Hz. High-frequency fluctuation areas are extracted and overflow-sensitive areas are marked to generate flow direction regulation error data. S602: Based on the flow direction regulation error data, a pressure gradient analysis method is used to extract the flow direction inflection point. The gradient of the pipeline network pressure data is calculated with a calculation step size of 2 meters. The pressure change rate is numerically differentiated, gradient mutation points are screened, and flow direction inflection points are extracted. Overflow regulation measurement is performed. The overflow control parameters are determined using the flow change calculation method. Volume integral calculation is performed on the overflow section data. The flow threshold is set to 1.2 times the local average flow velocity. The overflow control parameters are calculated and discharge path matching is performed. The optimal transfer point is selected using the flow scheduling calculation method. A directed flow graph model is constructed for the pipeline network data. A transfer cost function is set. The optimal path is calculated with the minimum flow loss as the goal, and the optimal flow direction transfer point is selected to generate flow direction switching parameter data. S603: Based on the flow direction switching parameter data, the flow direction adjustment value is extracted by using the flow balance measurement method, the flow data is subjected to least squares regression analysis, the regression window is set to 200 seconds, the flow balance adjustment parameters are calculated, and overflow buffer optimization is performed. The discharge stability zone is determined by using the load regulation measurement method, the local extreme point of the load data is calculated, the stability zone threshold is set to 3% of the flow change rate, the stable area is screened, and the control parameters are integrated. The optimal adjustment value is screened by using the pressure change calculation method, the pressure fluctuation data is compared, the fluctuation detection threshold is set to 1.5 times the local average value, the pressure stability adjustment parameters are screened, the key flow control parameters are extracted, and the flow direction control execution parameter set is generated.

[0029] See also Figure 8 ,The specific steps to generate the intelligent regulation strategy for pipe network drainage are: S701: Based on the flow control execution parameter set, the execution error is calculated. The control deviation value is calculated by comparison with historical flow data. The flow deviation is analyzed. The deviation direction and amplitude are extracted using real-time flow monitoring. The pipeline pressure fluctuation is measured. The abnormal pressure points are screened using pressure change trend analysis to generate execution error distribution data. S702: Based on the execution error distribution data, sudden flow adjustment analysis is performed. Abnormal flow distribution points are extracted using flow overload area statistics, and discharge path correction is performed. The adjustment direction is calculated using flow direction change measurement at the confluence node. Overflow impact assessment is performed. High-risk overflow pipes are screened using overload flow threshold comparison to generate sudden flow adjustment data. S703: Based on the burst flow adjustment data, flow direction optimization matching is performed. Flow direction adjustment values ​​are extracted using flow balance calculations. Overflow control nodes are screened. Key control points are extracted using discharge load distribution analysis. Flow control parameters are integrated. Real-time flow direction adjustment comparison is used to screen discharge adjustment values. Key flow direction control parameters are extracted to generate an intelligent drainage adjustment strategy for the pipe network. S701: Based on the flow control execution parameter set, the control deviation value is calculated using the historical flow data comparison method. The current flow data is compared with the historical flow mean. The time window is set to 300 seconds. The mean square error is calculated and the control deviation data is extracted. Flow direction deviation analysis is performed. The real-time flow direction monitoring method is used to extract the deviation direction and amplitude. Vector decomposition calculation is performed on the flow direction data. The time step is set to 5 seconds. The deviation angle and deviation distance are calculated. The pipeline pressure fluctuation is measured. The pressure change trend analysis method is used to screen abnormal pressure points. The pressure data is subjected to moving average filtering with a filter window size of 10 seconds. The pressure change rate is compared and the mutation points are extracted to generate execution error distribution data. S702: Based on the execution error distribution data, the flow overload area statistics method is used to extract abnormal flow distribution points. Statistical histogram analysis is performed on the flow data. The overload threshold is set to 1.5 times the local average flow rate. The distribution range of abnormal flow points is calculated, and the discharge path is corrected. The optimal adjustment direction is calculated using the flow direction change determination method at the confluence node. The direction vector is calculated for the confluence node flow data. The direction change angle threshold is set to 15 degrees. The flow adjustment direction is selected and the overflow impact assessment is performed. The overload flow threshold comparison method is used to select high-risk overflow pipelines. The pipeline cross-section flow data is compared. The overload flow threshold is set to 1.8 times the local average flow rate. High-risk overflow pipelines are extracted and sudden flow adjustment data is generated. S703: Based on the burst flow adjustment data, the flow direction adjustment value is extracted by using the flow balance calculation method, the unit flow load of each pipe section is compared, the balance target value is set to minimize the flow standard deviation, and the overflow control nodes are screened. The key control points are extracted by using the discharge load distribution analysis method, the load distribution of each discharge node is compared, the load balance objective function is set, the key control points are screened, and the flow control parameters are integrated. The discharge adjustment value is screened by using the real-time flow direction adjustment comparison method, and the flow direction data is subjected to time series regression analysis. The regression step is set to 200 seconds, the discharge adjustment value is calculated, the key flow direction control parameters are extracted, and the intelligent adjustment strategy for pipe network drainage is generated.

[0030] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A rainwater and sewage diversion optimization method based on the combination of terrain gravity and pipe network, characterized in that: The following steps are involved: Step 1: Use sensors to extract terrain elevation data, drainage zone boundaries, and gravity potential energy distribution, calculate slope direction, extract flow gradients, and track water flow paths. This screens high-potential energy catchment areas and low-potential energy discharge areas to generate a terrain water flow potential matrix. Step 2: Based on the terrain water flow potential matrix, perform slope calculation, flow gradient analysis, and cross-section resistance matching to extract the rainwater and sewage mixed flow trend and the full flow section of the pipeline, and generate a pipe network gravity discharge capacity parameter set; Step 3: Based on the pipeline network gravity discharge capacity parameter set, perform transportation capacity calculation and velocity gradient analysis, screen out uneven slope sections and discharge capacity difference areas, and generate the pipeline network load distribution state; Step 4: Based on the load distribution state of the pipe network, a Markov switching system is used to calculate the flow transfer rate and analyze the pressure fluctuation, extract the flow imbalance points and the rainwater and sewage intersection area, and generate the optimal configuration of rainwater and sewage diversion; Step 5: Based on the optimized configuration of rainwater and sewage diversion, a hidden Markov model is used to perform flow adjustment calculation and flow direction change analysis, extract slope influencing parameters and diversion transfer strategies, and generate a dynamic optimization plan for flow regulation; Step 6: Based on the flow regulation dynamic optimization scheme, perform regulation error calculation and flow direction balance adjustment, select flow direction switching points and dynamic overflow regulation parameters, and generate a flow direction regulation execution parameter set; Step 7: Based on the flow direction control execution parameter set, perform execution error calculation and flow direction offset correction, extract sudden flow adjustment points and overflow control nodes, and generate a pipe network drainage intelligent regulation strategy.

2. The rainwater and sewage diversion optimization method based on the combination of terrain gravity and pipe network according to claim 1 is characterized in that: The specific steps of generating the terrain water flow potential energy matrix are: Sensors are used to extract terrain elevation data, drainage zone boundaries, and gravity potential energy distribution. Elevation grid interpolation is performed and the rate of elevation change is calculated. Slope direction analysis is performed and slope mutation points are identified. Water flow direction is calculated and the slope influence range is extracted. Water flow diversion areas are screened to generate slope gradient distribution data. Based on the slope gradient distribution data, the confluence area is classified and the slope flow direction trend is extracted. The slope flow direction is calculated and the slope change point is determined. The flow direction stability is analyzed and the water flow transfer area is screened. The high potential energy confluence area and the low potential energy discharge area are extracted to generate the water flow convergence and dispersion distribution data. Based on the water flow convergence and dispersion distribution data, the slope flow velocity is calculated and the flow velocity change value is extracted, the water flow energy loss is calculated and the potential energy decrease rate is measured, the hydraulic flow direction is matched and the discharge path is adjusted, the stable flow path and the potential energy decrease channel are screened, and the terrain water flow potential energy matrix is ​​generated.

3. The rainwater and sewage diversion optimization method based on terrain gravity and pipe network according to claim 1 is characterized in that: The specific steps for generating the pipe network gravity discharge capacity parameter set are: Based on the terrain water flow potential energy matrix, slope change calculation is performed and slope matching is determined, flow gradient analysis is performed and flow change rate is calculated, slope impact identification is performed and flow imbalance sections are extracted, slope impact pipe sections and flow adjustment points are screened, and slope and flow distribution data are generated; Based on the slope and flow distribution data, the pipeline transport capacity is calculated and the flow velocity change is measured. The water flow resistance is calculated and the resistance impact is analyzed. The stability of the rainwater-sewage mixed flow is analyzed and the flow mutation area is screened. The rainwater-sewage intersection area, the mixed flow mutation area and the water flow buffer area are extracted to generate the pipeline mixed flow trend and transport capacity data. Based on the pipeline mixed flow trend and conveying capacity data, the flow velocity of the full flow section is calculated and the pipeline conveying capacity is measured, the discharge capacity is evaluated and the overload points are extracted, the gravity discharge capacity is analyzed and the water flow guidance path is adjusted, the high-load pipe sections and discharge overload areas are screened, and the pipeline network gravity discharge capacity parameter set is generated.

4. The rainwater and sewage diversion optimization method based on terrain gravity and pipe network according to claim 1 is characterized in that: The specific steps of generating the pipe network load distribution state are: Based on the pipeline network gravity discharge capacity parameter set, the pipeline transportation capacity is calculated, the transportation limit is extracted by flow segmentation measurement, the flow gradient analysis is performed, the velocity change is measured by along-line flow velocity sampling, the slope effect is determined, the slope comparison analysis is used to screen the flow velocity abnormality section, the slope effect prominent section and the flow change point are extracted, and the pipeline transportation capacity distribution data is generated; Based on the pipeline transportation capacity distribution data, the slope uneven area is screened, the slope continuity measurement is used to extract the influence range of the slope change, the discharge capacity is calculated, the load difference of each pipe section is measured by unit flow load comparison, and the flow balance analysis is performed. The load distribution deviation analysis is used to screen overload and underload areas, extract the slope uneven section and the discharge capacity difference area, and generate the slope and discharge capacity distribution data; Based on the slope and discharge capacity distribution data, pipeline pressure distribution analysis is carried out, cross-sectional pressure calculation is used to extract flow mutation points, discharge load balance measurement is performed, pressure gradient comparison is used to identify pressure overloaded pipe sections, pipeline network pressure adjustment analysis is performed, flow direction stability judgment is used to screen flow optimization points, abnormal slope sections and pressure change areas are extracted, and the pipeline network load distribution status is generated.

5. The rainwater and sewage diversion optimization method based on the combination of terrain gravity and pipe network according to claim 1 is characterized in that: The specific steps for generating the optimized configuration of rainwater and sewage diversion are as follows: Based on the load distribution state of the pipeline network, the flow direction transfer rate is calculated, the flow direction conversion matrix under different discharge modes is established using the Markov switching system, pressure fluctuation analysis is performed, the impact of flow adjustment on pressure is measured using dynamic pressure monitoring, the discharge flow adaptability is calculated, and the flow direction dynamic evaluation is used to screen the flow direction change area, extract the flow change points and pressure fluctuation areas, and generate flow direction change distribution data; Based on the flow direction change distribution data, flow imbalance calculation is performed, flow deviation comparison is used to determine the load difference in the imbalanced area, rainwater and sewage intersection areas are screened, mixed flow comparison calculation is used to identify unstable pipe sections, flow direction matching measurement is performed, flow coordination analysis is used to screen the optimized adjustment area, flow imbalance points and rainwater and sewage intersection areas are extracted, and flow direction adjustment optimization data is generated; Based on the flow direction adjustment optimization data, flow control calculations are performed, zone flow adjustment is used to extract flow adjustment parameters, discharge flow direction matching analysis is performed, pipeline load distribution comparison is used to optimize pipeline flow allocation, pipeline control adjustments are made, adjustment parameters are used to dynamically update and screen key adjustment points, rainwater and sewage diversion optimization key parameters are extracted, and rainwater and sewage diversion optimization configuration is generated.

6. The rainwater and sewage diversion optimization method based on the combination of terrain gravity and pipe network according to claim 5 is characterized in that: The Markov switching system performs flow state modeling, uses time series segmentation analysis to extract flow characteristics of different emission modes, performs state discretization processing, converts continuous flow changes into a finite state set, and calculates state transition probabilities. It uses mode switching frequency statistics to determine the transition probability between each mode, analyzes steady-state distribution, uses long-term flow trend backtracking to extract stable state probabilities under different modes, evaluates flow direction change sensitivity, uses key mode switching points to screen and identify variable sections, establishes a flow direction conversion matrix, and optimizes the stability of pipe network flow pattern adjustment.

7. The rainwater and sewage diversion optimization method based on terrain gravity and pipe network according to claim 1 is characterized in that: The specific steps of generating the dynamic optimization scheme for flow regulation are: Based on the optimized configuration of rainwater and sewage diversion, flow adjustment calculations are performed, cross-sectional flow velocity measurements are used to obtain flow change rates, flow direction change analysis is performed, a hidden Markov model is used to construct a water flow state transfer matrix, flow direction change patterns are identified, flow direction deviation amplitudes are extracted, pressure measurements are performed, and pressure gradient comparisons are used to screen high and low pressure areas to generate flow distribution adjustment data; Based on the flow distribution adjustment data, a slope impact analysis is performed, the slope change calculation is used to extract the slope rate, flow transfer calculation is performed, the diversion ratio is determined by flow direction cross comparison, overload diversion optimization is performed, the load change pipe section is screened by discharge section calculation, the slope impact parameters and diversion adjustment points are extracted, and flow regulation plan data is generated; Based on the flow regulation scheme data, flow direction matching optimization is performed, flow trend backtracking is used to extract dynamic flow direction distribution, the control area is determined, the regulation boundary is determined by pressure fluctuation calculation, load balancing is measured, the load area is screened by adjustment amplitude comparison, key flow regulation parameters are extracted, and a flow regulation dynamic optimization scheme is generated.

8. The rainwater and sewage diversion optimization method based on terrain gravity and pipe network according to claim 7 is characterized in that: The hidden Markov model is used to model water flow states, extract characteristic variables under different flow states using multi-period flow classification, set hidden states, define a set of potential flow direction patterns using flow direction change trend analysis, calculate state transition probabilities, determine transition probabilities between hidden states using continuous time series comparison, construct an observation probability matrix, optimize state observation distribution using flow velocity, pressure, and flow direction change data matching, perform state decoding, extract flow direction change paths using forward-backward probability calculation, generate a water flow state transition matrix, and optimize flow direction offset pattern recognition.

9. The rainwater and sewage diversion optimization method based on the combination of terrain gravity and pipe network according to claim 1 is characterized in that: The specific steps for generating the flow direction control execution parameter set are: Based on the dynamic optimization scheme for flow regulation, control error calculation is performed, error range is determined by flow deviation monitoring, flow direction balance adjustment is performed, balance parameters are extracted by flow direction stability measurement, overflow monitoring is performed, overflow-sensitive areas are screened by flow fluctuation analysis, and flow direction regulation error data is generated; Based on the flow direction adjustment error data, switching point screening is performed, flow inflection points are extracted using pressure gradient analysis, overflow adjustment measurement is performed, overflow control parameters are determined using flow change calculation, discharge path matching is performed, transfer points are screened using flow direction scheduling calculation, and flow direction switching parameter data is generated; Based on the flow direction switching parameter data, dynamic flow direction matching is performed, flow balance measurement is used to extract flow direction adjustment values, overflow buffer optimization is performed, and at the same time, the discharge stable area is measured, and the control parameters are integrated. The pressure change calculation is used to screen the adjustment value, the key flow direction control parameters are extracted, and the flow direction control execution parameter set is generated.

10. The rainwater and sewage diversion optimization method based on the combination of terrain gravity and pipe network according to claim 1 is characterized in that: The specific steps for generating the intelligent regulation strategy for pipe network drainage are as follows: Based on the flow direction control execution parameter set, execution error calculation is performed, control deviation value is calculated by comparison using historical flow data, flow direction deviation analysis is performed, deviation direction and amplitude are extracted using real-time flow direction monitoring, pipeline pressure fluctuation is measured, abnormal pressure points are screened using pressure change trend analysis, and execution error distribution data is generated; Based on the execution error distribution data, sudden flow adjustment analysis is performed, abnormal flow distribution points are extracted using flow overload area statistics, discharge path correction is performed, flow direction change at confluence nodes is used to determine and calculate the adjustment direction, overflow impact assessment is performed, high-risk overflow pipes are screened using overload flow threshold comparison, and sudden flow adjustment data is generated; Based on the sudden flow adjustment data, flow direction optimization matching is performed, flow balance calculation is used to extract flow direction adjustment values, overflow control nodes are screened, discharge load distribution analysis is used to extract key control points, flow control parameters are integrated, real-time flow direction adjustment comparison is used to screen discharge adjustment values, key flow direction control parameters are extracted, and an intelligent adjustment strategy for pipe network drainage is generated.

Images