Self-adaptive water supply and drainage pipeline flow adjusting method and system

Abstract

The invention relates to the technical field of water supply and drainage flow monitoring, and discloses a self-adaptive water supply and drainage pipeline flow adjusting method and system.The method comprises the steps that equipment positions related to flow monitoring and adjusting are recognized through a three-dimensional stereogram, and a flow monitoring equipment position set and a flow adjusting equipment position set are obtained; converting the collected flow analog signal into a digital signal, and outputting the digital signal; according to the historical flow data set of the water supply and drainage pipeline, the self-adaptive flow adjustment model is trained; inputting the real-time water flow data into a self-adaptive flow adjustment model to obtain the supply demand of the water flow of the main path and the branch path of the water supply and drainage pipeline; and adjusting the flow adjustment equipment according to the supply demand to obtain the operation parameters of the adjusted flow adjustment equipment. The system comprises a signal output module, a supply demand module and a parameter adjustment module. Dynamic adjustment and optimization of the water supply and drainage flow are achieved, and the self-adaptive capacity and controllability of the system are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of water supply and drainage flow monitoring, and in particular to a method and system for adaptively adjusting flow in water supply and drainage pipelines. Background Art

[0002] In the water supply and drainage system, flow regulation is an important means to ensure efficient operation of the system and meet user needs. The flow of water can be controlled by the opening of the valve to meet different water needs. For example, during peak or low water usage periods, the water flow can be controlled by adjusting the valve to ensure stable water pressure and water supply needs.

[0003] Prior art 1, Chinese patent, application number: 202121479212.4 discloses a water supply and drainage pipe with flow monitoring function, including a meter and a soft layer, a main body is arranged on the right side of the meter, and an upper cover body is arranged on the upper outer side of the main body, a connecting rod is fixed on the upper part of the upper cover body, and a sleeve is arranged on the outer side of the connecting rod, a handle is fixed on the lower outer side of the sleeve, a lower cover body is arranged on the lower outer side of the main body, and a card slot is fixed on the surface of the lower cover body, a connecting ring is fixed on the right end of the main body, and a card strip is arranged on the surface of the connecting ring, and a card ring is installed on the right end of the connecting ring, and the soft layer is arranged inside the lower cover body, and screws are penetrated inside the card strip, and a filter is fixed on the inner side of the card strip. Although the water supply and drainage pipe with flow monitoring function is provided with a soft layer and has good softness, it reduces the pressure between the lower cover body and the main body, effectively prevents damage to the surface of the main body, ensures the integrity of the main body, and is easy to use, but the degree of intelligence is low, and the real-time monitoring and early warning capabilities are insufficient.

[0004] Prior art 2, Chinese patent, application number CN202410278739.2 discloses a flow regulating device and flow regulating method, including a main flow path, a bypass flow path, a large flow regulating valve and a high-frequency fast-response valve, the two ends of the bypass flow path are connected to the main flow path, the large flow regulating valve is arranged on the main flow path, and the high-frequency fast-response valve is arranged on the bypass flow path and connected in parallel with the large flow regulating valve. Although the large flow regulating valve can quickly adjust the flow, and the high-frequency fast-response valve can accurately adjust the flow, by connecting the large flow regulating valve and the high-frequency fast-response valve in parallel, the flow regulating device can achieve rapid and accurate adjustment of the flow, but the valve adjustment performance is limited by its own structure, and the cost is high, and the maintenance cost is high.

[0005] Prior art three, Chinese patent, application number CN202211463071.6 discloses a flow regulating valve and a flow regulating system, wherein the flow regulating valve includes a valve body, the interior of which is provided with a water inlet chamber, a regulating chamber and a first water outlet chamber in sequence along the water flow direction; a first water outlet is provided in the first water outlet chamber; a rotating body, which is rotatably installed in the regulating chamber; an adjusting ring, which is arranged in the regulating chamber and connected to the rotating body; a stepped groove is provided on the outer wall of the adjusting ring; when the adjusting ring is driven by the rotating body to rotate to partially block the first water outlet, the water flow can flow out of the first water outlet through the stepped groove; the adjusting ring partially blocks the first water outlet until the adjusting ring continues to rotate to close the first water outlet, and the water flow can flow out of the first water outlet in a step-by-step decreasing manner through the stepped groove. Although the flow regulation is achieved by the step-by-step decreasing of the stepped groove, there is an error in the accuracy of the flow measurement in the drainage system, which affects the accuracy of the flow regulation.

[0006] At present, the existing technologies 1, 2 and 3 have the problems of low intelligence, insufficient real-time monitoring and early warning capabilities, valve adjustment performance limited by its own structure, high cost, and large error in flow measurement accuracy. Therefore, the present invention provides an adaptive water supply and drainage pipeline flow adjustment method and system. Summary of the invention

[0007] The main purpose of the present invention is to provide an adaptive water supply and drainage pipeline flow adjustment method and system to solve the problems in the prior art of low industrial intelligence, insufficient real-time monitoring and early warning capabilities, valve adjustment performance limited by its own structure, high cost, and large errors in flow measurement accuracy.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] An adaptive water supply and drainage pipeline flow adjustment method, the adaptive water supply and drainage pipeline flow adjustment method comprising:

[0010] Obtain a three-dimensional stereogram of the water supply and drainage pipeline, identify the location of equipment related to flow monitoring and adjustment through the three-dimensional stereogram, and obtain a flow monitoring equipment location set and a flow adjustment equipment location set; the flow monitoring equipment is a flow monitoring equipment, which collects the water flow of the water supply and drainage pipeline in real time; convert the collected flow analog signal into a digital signal, and output the digital signal;

[0011] The adaptive flow adjustment model is trained based on the flow data set of the historical water supply and drainage pipelines; the real-time water flow data is input into the adaptive flow adjustment model to obtain the supply and demand of the water flow of the main and branch lines of the water supply and drainage pipelines;

[0012] The flow regulating device is adjusted according to the supply demand to obtain the operating parameters of the adjusted flow regulating device. At the same time, the water pressure of the branch of the water supply and drainage pipeline after the adjusted operating parameters is measured by the water pressure monitoring device. If the pressure threshold is triggered, an early warning is issued.

[0013] As a further improvement of the present invention, the location of equipment related to flow monitoring and adjustment is identified through a three-dimensional stereogram, including:

[0014] Arrange multiple view scanning devices in the target water supply and drainage network area, perform 360-degree rotation scanning, and obtain multiple scanning views; at the same time, use multi-view high-resolution cameras for synchronous shooting to obtain texture information on the equipment and pipeline surfaces;

[0015] Integrate multiple scanned views into a single 3D surface model to preliminarily generate point cloud data; post-process the preliminarily generated point cloud data to remove noise points and outliers that exceed the distance threshold, clean the point cloud data, and obtain pre-processed point cloud data;

[0016] Analyze the preprocessed point cloud data, perform geometric fitting on the curved surface of the pipeline and the surface of equipment such as valves and pumps, and obtain the rough shape of the equipment; convert the point cloud data into a raster image, extract the significant edges from the raster image, select the edge part in the straight line direction, and gradually connect the edge points in the same direction and close to form multiple independent straight line segments;

[0017] Analyze the extracted straight line segments, set similar lengths and angle ranges for combination, aggregate the straight line segments to form a closed shape representing the contours of the pipeline and equipment, and construct a preliminary structural diagram based on the aggregated line segments as a contour feature description of the equipment; compare the newly generated contour features with the equipment model in the database, use shape similarity and direction consistency to evaluate the similarity of the morphology, and determine the position, angle, and installation direction of the equipment based on the matching results.

[0018] As a further improvement of the present invention, multiple scanned views are integrated into a single three-dimensional surface model, including:

[0019] At each scanning position, the view scanning device generates a point cloud data set containing the three-dimensional coordinates and intensity information of objects around the position; a reference point is selected as the origin of the global coordinate system, and the directions of the X, Y, and Z coordinate axes are defined based on the far point;

[0020] Detect the feature points of the edges and corners in each point cloud; select the feature points in the overlapping area in each data set and align the two adjacent point clouds; align the adjacent multiple point cloud data through rigid transformation; calculate the rotation matrix and translation vector of each point cloud relative to the reference coordinate system through an iterative method based on the least squares method, and use the overlapping parts of multiple point clouds for multiple iterations, and compare them with the set tolerance threshold until the error reaches the tolerance threshold;

[0021] The registered point cloud data sets are merged according to the rotation matrix and translation vector, the coordinates of each point cloud data are transformed into the global coordinate system, and a point cloud data set is formed; the merged point cloud data set is triangulated and meshed to convert the point cloud data set into a three-dimensional surface model.

[0022] As a further improvement of the present invention, the construction of the adaptive traffic adjustment model includes:

[0023] Obtain historical flow data including historical real-time water flow data from each flow monitoring device, including flow information of the main and branch roads, and timestamps, to form a complete flow time series; at the same time, record water usage events within the corresponding time period, including water consumption peaks, changes in equipment operating status, and weather conditions;

[0024] The historical flow data is sorted in time series to form a structured database; each record should contain information such as time, main road flow, branch road flow, related water use events and user needs; the sample data stored in the database is labeled, and each set of water flow data is associated with the corresponding supply and demand to form flow data, events and supply and demand pairs to obtain a sample data set;

[0025] Extract features including daily, weekly, and monthly trends and fluctuations of water flow from the sample dataset; convert the intensity and type of water use events into numerical features;

[0026] Use the collated sample data set to construct a supply-demand relationship table; associate the change pattern of main and branch flow with various water use events; create a supply-demand function, and form a supply-demand mapping by statistically analyzing the correlation between the main flow characteristics and supply and demand;

[0027] The adaptive traffic adjustment model is trained using the training set divided by the sample data set, and is evaluated using the validation set divided by the sample data set. The accuracy of supply and demand under specific conditions is predicted, and the accuracy is obtained by comparing the output of the adaptive traffic adjustment model with the result of supply and demand mapping. The error of the model parameters is adjusted based on the accuracy.

[0028] As a further improvement of the present invention, a sample data set is obtained, including:

[0029] Obtain historical data sets containing main and branch water flows from flow monitoring equipment, with each record having a timestamp, main flow, and branch flow fields; extract information matching the corresponding timestamp from the stored water usage event data, including water usage peaks, equipment status changes, and weather information;

[0030] Clean the flow data and event data in the historical data set, remove missing values ​​and outliers, and convert all timestamps into a unified time format; connect the flow data with the corresponding water use event data based on the timestamp;

[0031] Generate a structured data frame, whose rows represent water flow records at each time point, and columns include information such as time, main flow, branch flow, and corresponding water use events; for each flow data, create a supply and demand label according to the type and intensity of the water use event, and mark the water flow during the peak water use period as high demand, and mark it as low demand during the low-peak period; organize the processed flow data and the corresponding supply and demand labels into a sample data set in a tabular form, including flow-related input fields and output fields.

[0032] As a further improvement of the present invention, the intensity and type of water use events are converted into numerical features, including:

[0033] For each collected water use event, perform numerical conversion based on its original intensity value and classification information; extract water use in the time period, quantify the frequency and intensity of the event within the time window and number it; for events involving multiple users, convert the proportion of each type of water use into numerical features;

[0034] Construct a set of numerical features. Each record will contain numerical information of multiple dimensions, including timestamp, main road flow, branch road flow, water use event type, water use event intensity, and the proportion of each type of water use event.

[0035] The generated numerical features are integrated into a unified feature matrix to form the final data output for model construction; each row of the matrix represents a complete water use event record at a point in time, including all relevant numerical features.

[0036] As a further improvement of the present invention, a supply demand mapping is formed, including:

[0037] Extract key features related to supply and demand from the collated sample data set, including main road flow, branch road flow, type and intensity of water use events, and time factors of weather data set; each key feature is marked with a field;

[0038] The extracted key features are analyzed, and the correlation coefficient is used to evaluate the strength of the relationship between various flow characteristics and supply and demand, and the main factors affecting supply and demand are identified; based on the correlation analysis, a supply and demand function is constructed, which predicts the output demand through the input features;

[0039] Use the labeled input and output pairs to fit and form a mapping relationship; convert the trained supply and demand function into a mapping matrix, mapping the relationship between the input features of the matrix and the output demand. Each row represents the predicted output under different input conditions, providing supply and demand forecasts for upcoming flow conditions and water use events.

[0040] As a further improvement of the present invention, the adaptive traffic adjustment model is trained, including:

[0041] Configure the input layer and output layer to ensure that the input features of each main flow, branch flow, and water use event intensity are mapped to the output requirements; divide the sample data set into a training set and a validation set. The training set is used for parameter learning of the adaptive flow adjustment model, while the validation set is used to evaluate the predictive ability and accuracy of the adaptive flow adjustment model;

[0042] The adaptive traffic adjustment model is trained using the training set. After each training cycle, the error between the output of the adaptive traffic adjustment model and the actual supply and demand is calculated. Error feedback adjustment is implemented for the loss function of the adaptive traffic adjustment model evaluation. The accuracy of the adaptive traffic adjustment model is evaluated using the validation set. The accuracy and recall indicators are obtained by comparing the estimated results with the actual supply and demand.

[0043] After training is completed, the hyperparameters are automatically adjusted based on the performance indicators of the adaptive traffic adjustment model.

[0044] As a further improvement of the present invention, the operating parameters of the adjusted flow rate adjustment device are obtained, including:

[0045] After receiving the supply demand, a set of control signals is generated and sent to the flow control device, including the current demand parameters, target flow, target pressure, and instructions for operating status monitoring; the flow control device performs real-time status assessment on valves and pumps, and collects current flow, pressure and status information;

[0046] Obtain the target value of the control signal, compare the current operating value of the valve and pump with the target value, and calculate the required adjustment amount; for each flow control valve, the supply demand changes generate the opening value and conversion speed; the operating status of the pump adjusts the speed or power output;

[0047] The newly generated operating parameters of valves and pumps are saved in the device configuration files.

[0048] To achieve the above object, the present invention also provides the following technical solutions:

[0049] An adaptive water supply and drainage pipeline flow adjustment system is applied to the adaptive water supply and drainage pipeline flow adjustment method. The adaptive water supply and drainage pipeline flow adjustment system comprises:

[0050] The signal output module is used to obtain a three-dimensional stereogram of the water supply and drainage pipeline, identify the position of equipment related to flow monitoring and adjustment through the three-dimensional stereogram, and obtain a flow monitoring equipment position set and a flow adjustment equipment position set; the flow monitoring equipment is a flow monitoring equipment, which collects the water flow of the water supply and drainage pipeline in real time; converts the collected flow analog signal into a digital signal, and outputs the digital signal;

[0051] The supply and demand module is used to train the adaptive flow adjustment model based on the flow data set of the historical water supply and drainage pipelines; input the real-time water flow data into the adaptive flow adjustment model to obtain the supply and demand of the water flow of the main and branch lines of the water supply and drainage pipelines;

[0052] The parameter adjustment module is used to adjust the flow adjustment device according to the supply demand and obtain the operating parameters of the adjusted flow adjustment device; at the same time, the water pressure of the branch of the water supply and drainage pipeline after the adjustment of the operating parameters is measured by the water pressure monitoring equipment. If the pressure threshold is triggered, an early warning is issued.

[0053] The present invention obtains a three-dimensional stereogram of a water supply and drainage pipeline. By obtaining the three-dimensional stereogram, the system can fully understand the spatial structure and layout of the pipeline; identify the specific locations of flow monitoring equipment and flow adjustment equipment, and form a set of equipment locations; realize the real-time acquisition capability of the flow monitoring equipment, and ensure the timely availability of flow data; effectively convert analog signals into digital signals, laying the foundation for subsequent data processing. The significance achieved: through detailed three-dimensional spatial information, the management and maintenance of pipeline equipment can be carried out more scientifically; provide real and reliable basic data for data analysis and flow adjustment, and improve the accuracy and real-time performance of flow monitoring. The training of the adaptive flow adjustment model uses historical flow data sets to train the model, and establish the ability to understand and predict water flow under different conditions; input real-time water flow data, and the model can automatically calculate the water flow supply demand of the main road and the branch road, and provide a basis for dynamic adjustment. The significance achieved: the flow adjustment method has adaptive capabilities, and can respond to the real-time changing water flow conditions, thereby improving the intelligence level of the system; it helps to optimize the allocation and use of water resources, reduce waste, and improve the economy and sustainability of the system. The flow adjustment device is adjusted and the water pressure is monitored. The flow adjustment device is adjusted according to the supply demand to obtain the operating parameters so that the water flow meets the actual demand. The water pressure of the adjusted branch is monitored by the water pressure monitoring device. If the water pressure exceeds the preset pressure threshold, the early warning mechanism is triggered. The significance achieved: Ensure that the adjusted water flow meets the actual demand, while maintaining the safety of the pipeline and preventing the risk of damage caused by system out of control; provide real-time system monitoring capabilities, ensure the stable operation of the system through a timely early warning mechanism, and enhance the safety and reliability of the water supply and drainage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram of the steps of an embodiment of the method for adaptively adjusting flow of water supply and drainage pipelines of the present invention;

[0055] Figure 2 A schematic flow chart of the steps of identifying the location of equipment related to flow monitoring and adjustment through a three-dimensional stereogram in one embodiment of the method for adaptively adjusting flow of water supply and drainage pipelines of the present invention;

[0056] Figure 3 A schematic flow chart of the steps of constructing an adaptive flow adjustment model of an embodiment of an adaptive water supply and drainage pipeline flow adjustment method of the present invention;

[0057] Figure 4 A schematic flow chart of steps for obtaining the operating parameters of the adjusted flow regulating device according to an embodiment of the method for adaptively regulating flow of water supply and drainage pipelines of the present invention;

[0058] Figure 5It is a functional module schematic diagram of an embodiment of the adaptive water supply and drainage pipeline flow adjustment system of the present invention;

[0059] Figure 6 It is a structural schematic diagram of an embodiment of an electronic device of the present invention;

[0060] Figure 7 It is a schematic structural diagram of an embodiment of the storage medium of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] The terms "first", "second" and "third" in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0063] Reference to an "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0064] like Figure 1 As shown, this embodiment provides an embodiment of a method for adaptively adjusting flow rate of water supply and drainage pipelines. In this embodiment, the method for adaptively adjusting flow rate of water supply and drainage pipelines specifically includes the following steps:

[0065] Step S1: obtaining a three-dimensional stereogram of the water supply and drainage pipeline, identifying the position of equipment related to flow monitoring and adjustment through the three-dimensional stereogram, and obtaining a flow monitoring equipment position set and a flow adjustment equipment position set; the flow monitoring equipment is a flow monitoring equipment, which collects the water flow of the water supply and drainage pipeline in real time; converting the collected flow analog signal into a digital signal, and outputting the digital signal;

[0066] Among them, the expression for converting the flow analog signal into a digital signal is:

[0067] The flow simulation signal is set to Q(t), which is represented by a vector that changes at time t and contains signals from multiple flow sensors:

[0068]

[0069] Wherein, 1, ..., m represents the marking serial number of the flow monitoring device, Q0 represents the reference flow, A1 represents the flow fluctuation amplitude of the first flow monitoring device, ω1 represents the angular frequency of the first flow monitoring device, φ1 represents the initial phase of the first flow monitoring device, and N1(t) represents the noise term of the first flow monitoring device;

[0070] A noise matrix N(t) is introduced to indicate the effect of noise on the flow simulation signal:

[0071]

[0072] Where W(t) is a time-dependent noise matrix and S is a Gaussian distribution;

[0073] The time delay matrix D is set to represent the influence of time delay on the measured flow simulation signal:

[0074]

[0075] d1 represents the time delay of the first flow monitoring device;

[0076] The delayed flow analog signal is expressed as:

[0077] Q delay (t) = D·Q(t)

[0078] Quantization and conversion process, at sampling time t(t n =nT) (where (T) is the sampling period), the sample of each flow simulation signal obtained by sampling is expressed as:

[0079] Q[n]=Q delay (t n )=D·Q(t n )+D·N(tn )

[0080] t n Indicates the flow value of the nth sampling point;

[0081] Quantize the sample flow analog signal. Set a quantization matrix: (\mathbf{Q}{\text{quant}}), which is as follows:

[0082]

[0083] The overall expression is:

[0084]

[0085] ΔQ represents the quantization step size;

[0086] The expression for converting the flow analog signal from analog to digital signal D[n] is:

[0087]

[0088] Step S2: training the adaptive flow adjustment model based on the historical flow data set of the water supply and drainage pipeline; inputting the real-time water flow data into the adaptive flow adjustment model to obtain the water flow supply demand for the main and branch lines of the water supply and drainage pipeline;

[0089] Step S3: According to the supply demand, the flow regulating device is adjusted to obtain the operating parameters of the adjusted flow regulating device; at the same time, the water pressure of the branch of the water supply and drainage pipeline after the adjusted operating parameters is measured by the water pressure monitoring device, and if the pressure threshold is triggered, an early warning is issued.

[0090] Preferably, step S1 of this embodiment obtains a three-dimensional stereogram of the water supply and drainage pipeline. By obtaining the three-dimensional stereogram, the system can fully understand the spatial structure and layout of the pipeline; identify the specific locations of the flow monitoring equipment and the flow adjustment equipment, and form a set of equipment locations; realize the real-time acquisition capability of the flow monitoring equipment, and ensure the timely availability of flow data; effectively convert analog signals into digital signals, laying the foundation for subsequent data processing. The significance achieved: through detailed three-dimensional spatial information, the management and maintenance of pipeline equipment can be carried out more scientifically; provide real and reliable basic data for data analysis and flow adjustment, and improve the accuracy and real-time performance of flow monitoring. Step S2 is the training of the adaptive flow adjustment model, using historical flow data sets to train the model, and establish the ability to understand and predict water flow under different conditions; input real-time water flow data, and the model can automatically calculate the water flow supply demand of the main road and the branch road, and provide a basis for dynamic adjustment. The significance achieved: the flow adjustment method has adaptive capabilities, and can respond to the real-time changing water flow conditions, thereby improving the intelligence level of the system; it helps to optimize the allocation and use of water resources, reduce waste, and improve the economy and sustainability of the system. Step S3: Adjustment of flow adjustment equipment and water pressure monitoring. Adjust the flow adjustment equipment according to supply demand to obtain operating parameters so that the water flow meets the actual demand. Monitor the adjusted branch water pressure through the water pressure monitoring equipment. If the water pressure exceeds the preset pressure threshold, the early warning mechanism is triggered. The significance achieved: Ensure that the adjusted water flow meets the actual demand, while maintaining the safety of the pipeline and preventing the risk of damage caused by system out of control; provide real-time system monitoring capabilities, ensure the stable operation of the system through a timely early warning mechanism, and enhance the safety and reliability of the water supply and drainage system.

[0091] In summary, this embodiment realizes dynamic adjustment and optimization of water supply and drainage flow through precise data collection, intelligent model training and real-time monitoring, and enhances the adaptive ability and controllability of the system. Its significance lies in improving the utilization efficiency of water resources, reducing management and maintenance costs, and enhancing the robustness of the system and its ability to respond to emergencies, which makes an important contribution to improving the intelligent level of urban infrastructure.

[0092] Furthermore, if Figure 2 As shown, the process of identifying the location of equipment related to flow monitoring and adjustment through the three-dimensional stereogram in step S1 specifically includes the following steps:

[0093] Step S11: multiple view scanning devices are arranged in the target water supply and drainage network area to perform 360-degree rotation scanning to obtain multiple scanning views; at the same time, multi-view high-resolution cameras are used for synchronous shooting to obtain texture information of the equipment and pipeline surfaces;

[0094] Step S12: Integrate multiple scanned views into a single three-dimensional surface model to preliminarily generate point cloud data; post-process the preliminarily generated point cloud data to remove noise points and outliers that exceed the distance threshold, clean the point cloud data, and obtain pre-processed point cloud data;

[0095] Among them, the expression for removing noise points is:

[0096] Cleaned P oint C loud=(x i ,y i ,z i );|;||(x i ,y i ,z i )-(x mid ,y mid ,z mid )||<∈

[0097] Where: (x i ,y i ,z i ) represents the coordinates of the i-th point in the point cloud; (x mid ,y mid ,z mid ) represents the coordinates of the center point of the point cloud data; ∈ is the distance threshold, and points exceeding this threshold will be regarded as noise points and removed;

[0098] Step S13: Analyze the preprocessed point cloud data, perform geometric fitting on the curved surface of the pipeline and the surface of the valve, pump and other equipment to obtain the rough shape of the equipment; convert the point cloud data into a raster image, extract significant edges from the raster image, select the edge part in the straight line direction, and gradually connect the edge points in the same direction and close to each other to form multiple independent straight line segments;

[0099] Among them, get the rough shape of the device:

[0100]

[0101] Where: S represents the fitted surface function;

[0102] The edge is obtained by the following formula:

[0103]

[0104] Where: E(x,y) represents the edge strength of point (x,y); I(x,y) represents the pixel value of the image at (x,y); G x and G yThe Sobel operator is used to detect horizontal and vertical edges respectively; next, edge points in the same direction and close to each other are gradually connected to form multiple independent straight line segments;

[0105] Step S14: Analyze the extracted straight line segments, set a similar length and angle range for combination, aggregate the straight line segments to form a closed shape representing the outlines of pipes and equipment, construct a preliminary structure diagram based on the aggregated line segments as a description of the equipment's contour features; compare the newly generated contour features with the equipment models in the database, evaluate the similarity of the shapes using shape similarity and direction consistency, and determine the position, angle, and installation direction of the equipment according to the matching results;

[0106] Among them, the following aggregation formula is used:

[0107] Combined L ine S egments=L j ;|;min(θ ij )<θ<max(θ ij );且;|L i |~|L j |

[0108] Among them: L j represents the combined straight line segment; θ ij is the angle between two straight line segments, |L i | and |L j | are the lengths of the straight line segments L i and L j ;

[0109] Preferably, in step S11 scanning and image acquisition of this embodiment, by arranging multiple view scanning devices in the target area, 360-degree point cloud data without dead angles is obtained to ensure a comprehensive record of the actual geometric shapes of the pipeline and equipment; the image acquisition of the synchronous multi-view high-resolution camera adds surface texture information to the point cloud data, which is helpful for texture analysis and visual recognition of the equipment. Significance: Through the combination of laser and high-resolution images, it is ensured that the point cloud data contains rich spatial information and surface features, and the quality of the overall data and the accuracy of the analysis are improved; the high-quality data obtained lays a solid foundation for the implementation of subsequent algorithms and improves the accuracy of shape recognition and feature analysis. Step S12 point cloud integration and cleaning, by integrating multiple scanning views into a single three-dimensional surface model, a complete point cloud data set is formed; the point cloud data is processed, and noise points and outliers outside the distance threshold are deleted to obtain high-quality point cloud data after cleaning. Significance: Through denoising processing, the data in the analysis process is guaranteed to be more accurate and the risk of misidentification is reduced; when constructing a three-dimensional surface model, the authenticity and integrity of the data are guaranteed, which is crucial for subsequent geometric fitting and shape recognition. Step S13: Geometric fitting and edge extraction. The curved surface and equipment of the pipeline are geometrically fitted to generate the rough shape of the equipment. Through rasterization, key edge information is extracted to provide a basis for the subsequent straight line segment connection. Significance: Through the generation of rough shapes, the appearance characteristics of the equipment can be quickly identified, and the relationship and layout between the equipment can be preliminarily defined; accurate edge information provides an important basis for subsequent straight line segment extraction and shape matching, ensuring that the shape features are expressed more clearly. Step S14: Straight line segment assembly and equipment positioning. The extracted straight line segments are combined according to the set aggregation conditions to form a closed geometric shape; the newly generated contour features are compared with the equipment model in the database to determine the actual position, angle and installation direction of the equipment. Significance: The closed shape formed by combining straight line segments can make an adaptive description of the geometric characteristics of the equipment, thereby extracting the equipment feature information; by comparing with the model in the database, the equipment can be quickly and accurately located, and a reference basis can be provided for flow monitoring and adjustment, thereby improving the intelligent level of system management.

[0110] In summary, this embodiment realizes the accurate identification and positioning of flow monitoring and regulation related equipment in the water supply and drainage network. From data collection to point cloud integration, to geometric analysis and equipment positioning, all links are closely connected and complement each other, and finally an efficient, accurate and intelligent flow monitoring and adjustment system is constructed. It can effectively improve the efficiency of equipment management, reduce labor costs, and respond to potential flow problems more quickly and accurately.

[0111] Furthermore, the process of integrating the multiple scanned views into a single three-dimensional surface model in step S12 specifically includes the following steps:

[0112] Step S121: At each scanning position, the view scanning device generates a point cloud data set, including the three-dimensional coordinates and intensity information of objects around the position; selects a reference point as the origin of the global coordinate system, and defines the directions of the X, Y, and Z coordinate axes according to the far point;

[0113] Step S122: Detect feature points of edges and corners in each point cloud; select feature points in overlapping areas in each data set to align two adjacent point clouds; register multiple adjacent point cloud data through rigid transformation; calculate the rotation matrix and translation vector of each point cloud relative to the reference coordinate system through an iterative method based on least squares, use the overlapping parts of multiple point clouds for multiple iterations, and compare with the set tolerance threshold until the error reaches the tolerance threshold;

[0114] Step S123: merge the registered point cloud data sets according to the rotation matrix and the translation vector, transform the coordinates of each point cloud data into the global coordinate system, and form a point cloud data set; perform triangulated meshing on the merged point cloud data set, and convert the point cloud data set into a three-dimensional surface model.

[0115] Preferably, in step S121 of this embodiment, point cloud data generation and global coordinate system definition are used to generate a point cloud data set containing three-dimensional coordinates and intensity information of surrounding objects at each scanning position using a view scanning device. The point cloud data provides geometric information in space; by selecting a reference point as the origin of the coordinate system and defining the directions of the X, Y, and Z axes, a unified reference coordinate system is established. Significance: Rich point cloud data provides a basis for the construction of a three-dimensional surface model. The point cloud data captures the geometric shape, surface features, and environmental information in the target area; by setting a global coordinate system, a spatial reference is provided for the integration of data from different views, avoiding errors caused by coordinate differences. Step S122 feature point detection and point cloud registration detects edges and corners in the point cloud, extracts key information, and enhances the effect of subsequent registration; by selecting feature points in overlapping areas, more important geometric features in the data set can be effectively utilized; using an iterative method based on the least squares method, adjacent point clouds are effectively aligned by calculating the rotation matrix and translation vector between different point clouds until the registration error of all point clouds drops below the set tolerance threshold. Significance: Accurate feature point selection and extraction improve the effect of point cloud registration, making the correspondence between multiple views more reliable; by registering adjacent point clouds according to feature points, the coordination of each data view in a unified reference system is guaranteed, and the accuracy and consistency of the integrated three-dimensional surface model are improved. Step S123: Point cloud merging and gridding processing, merging the registered point cloud data set according to the calculated rotation matrix and translation vector to form a single point cloud data set, and the coordinates of all points are converted to the global coordinate system; the merged point cloud data set is gridded to convert the discrete point cloud data into a continuous three-dimensional surface model to form a complete three-dimensional structure that can be visualized. Significance: Through data merging, the integrated point cloud can form a more comprehensive and detailed three-dimensional surface model, delete redundant information and improve the visualization effect of the model; the generated three-dimensional surface model provides a basis for subsequent analysis, visualization, simulation and other applications, ensuring practicality and accuracy in engineering applications, flow monitoring and equipment management.

[0116] In summary, this embodiment realizes the integration process of multi-view scanning views, and successfully constructs an accurate and complete three-dimensional surface model through point cloud generation, feature extraction and registration, and final merging and meshing processing; the three-dimensional surface model lays the foundation for intelligent management, maintenance decision-making and subsequent spatial analysis, and can improve the efficiency and scientificity of engineering project management.

[0117] Furthermore, if Figure 3 As shown, the process of constructing the adaptive traffic adjustment model in step S2 specifically includes the following steps:

[0118] Step S21: Acquire historical flow data including historical real-time water flow data from each flow monitoring device, including flow information of the main road and branch roads, and timestamps, to form a complete flow time series; at the same time, record water usage events within the corresponding time period, including water usage peaks, changes in equipment operating status, and weather conditions, etc.;

[0119] Step S22: Arrange the historical flow data in time series to form a structured database; each record should contain information such as time, main road flow, branch road flow, related water use events and user needs; annotate the sample data stored in the database, associate each set of water flow data with the corresponding supply and demand, form input (flow data and events) and output (supply and demand) pairs, and obtain a sample data set;

[0120] Step S23: extracting features including daily, weekly, and monthly trends and fluctuations of water flow from the sample data set; converting the intensity and type of water use events into numerical features, such as the proportion of water use by households, factories, parks, etc. in a certain period of time;

[0121] Step S24: construct a supply-demand relationship table using the sorted sample data set; associate the change pattern of the main and branch flow with various water use events; create a supply-demand function, and form a supply-demand mapping by statistically analyzing the correlation between the main flow characteristics and supply and demand;

[0122] Step S25: Use the training set divided by the sample data set to train the adaptive traffic adjustment model, and evaluate the adaptive traffic adjustment model through the validation set divided by the sample data set to predict the accuracy of supply and demand under specific conditions. The accuracy is obtained by comparing the output result of the adaptive traffic adjustment model with the result of supply and demand mapping, and the error of the model parameters is adaptively adjusted according to the accuracy.

[0123] Preferably, in step S21 of this embodiment, data collection collects historical water flow data and information such as timestamps and water use events from each flow monitoring device to form complete time series data. These data provide a basis for subsequent analysis and model building. The significance achieved: ensure the comprehensiveness and accuracy of the data so that the model can obtain the actual water use situation, thereby improving the accuracy of the model prediction. Historical data is the basis for analysis and can reflect the changing trend of supply and demand. Step S22 data sorting, sorting and annotating the collected original flow data, and converting it into a structured database format to form input and output pairs to obtain a sample data set, which lays the foundation for data analysis and model training. The significance achieved: structured data facilitates subsequent algorithm processing and enhances the availability of data; by annotating sample data, the relationship between input and output can be clarified, providing necessary information for establishing an accurate model. Step S23 feature extraction, extracting flow characteristics (such as daily, weekly, monthly trends and fluctuations) and numerical characteristics of water use events from the sample data set, and analyzing water flow changes in different time dimensions. Significance achieved: Feature extraction is an important part of machine learning. By capturing key features, the model can better understand and map the relationship between supply and demand, and improve the accuracy and efficiency of prediction; by digitizing water use events, its impact on flow changes can be quantitatively analyzed. Step S24 Supply and demand relationship construction, using the sorted sample data set to establish a supply and demand relationship table, analyze the relationship between the main and branch flow and water use events, and create a supply and demand function. Significance achieved: Constructing a supply and demand mapping relationship can help understand the causes and patterns of flow changes; in addition, the supply and demand mapping relationship can be used to monitor and adjust the flow in real time, and improve the reasonable allocation and use efficiency of water resources. Step S25 Model training and evaluation, using the training set to train the adaptive flow adjustment model, and using the validation set to evaluate the prediction accuracy of the model, by comparing the output results with the supply and demand mapping results, the model parameters are adjusted. Significance achieved: By evaluating the prediction ability of the model, the model can be continuously optimized to have higher accuracy and adaptability in practical applications. Adaptability is conducive to flow adjustment under different conditions and flexible response to complex water demand.

[0124] In summary, this embodiment forms a complete chain from data collection to model evaluation. Each step is to achieve more efficient water resource management and optimal configuration. Finally, an adaptive flow adjustment system that can respond to water supply and drainage pipeline needs in real time, accurately and intelligently is obtained, thereby improving the efficiency of water resource use and ensuring water supply safety.

[0125] Furthermore, the process of obtaining the sample data set in step S22 specifically includes the following steps:

[0126] Step S221: Obtain a historical data set containing main and branch water flow from the flow monitoring device, each record having fields such as timestamp, main flow and branch flow; extract information matching the corresponding timestamp from the stored water usage event data, including water usage peak, equipment status change and weather information;

[0127] Step S222: Clean the flow data and event data in the historical data set, remove missing values ​​and outliers, convert all timestamps into a unified time format; connect the flow data with the corresponding water use event data based on the timestamp;

[0128] Step S223: Generate a structured data frame, whose rows represent water flow records at each time point, and columns include information such as time, main flow, branch flow, and corresponding water use events; for each flow data, create a supply and demand label according to the type and intensity of the water use event, and mark the water flow in the peak water use time period as high demand, and mark it as low demand in the off-peak time period; organize the processed flow data and the corresponding supply and demand labels into a sample data set in a tabular form, including flow-related input fields (main flow, branch flow, event type, etc.) and output fields (supply and demand labels).

[0129] Preferably, step S221 of this embodiment collects and matches data, extracts historical water flow data of the main road and the branch road from the flow monitoring equipment, and extracts water use event information matching the timestamp from the inventory. This process ensures that the acquired data covers multiple dimensions of flow (such as time, location) and key factors that cause flow changes (such as water use peaks, equipment changes); by integrating flow monitoring data and water use event data, a rich background is established, which can more comprehensively consider various factors affecting supply and demand. Significance: Ensure the accuracy and completeness of the data used in the analysis process; data of multiple dimensions connects flow and water use behavior, allowing analysts to understand changes in water resource demand in different scenarios. Step S222 data cleaning and integration improves the quality of the data set by removing missing values ​​and outliers. The cleaning process makes the data more consistent and reliable, and reduces interference factors in subsequent analysis; converting all timestamps into a unified format ensures that the time information in the data set can be seamlessly connected, which facilitates the effective connection of flow data with water use events through timestamps. Significance: The cleaned data can more accurately reflect the real situation and reduce erroneous analysis caused by low data quality; through standardized timestamps, accurate matching of flow data and event data becomes possible, laying the foundation for building an effective supply and demand model. Step S223: Sample data set construction. The structured data frame formed clearly lists the water flow records at each time point, providing a clear framework for data processing and analysis; supply and demand labels (such as "high demand" and "low demand") are assigned to flow data according to the type and intensity of water use events, and the labels cover different situational states in the flow; the formed sample data set has clear input and output fields, clear structure, and is easy to store, query and subsequent use. Significance: The input and output structure design in the sample data set makes subsequent machine learning and predictive analysis simple and clear, and supports model training and effect evaluation; by combining flow data with supply and demand labels, analysts can identify and understand the relationship between supply and demand and its changing trends, providing data support for subsequent scientific decision-making.

[0130] In summary, this embodiment establishes a high-quality, well-structured sample data set to facilitate subsequent model training and analysis. The final output sample data set not only has good functionality, but also can generate real value in practical applications. Through this process, technicians can provide a more accurate data foundation for water resources management, supply and demand forecasting, and decision support systems.

[0131] Furthermore, the process of converting the intensity and type of water use events into numerical features in step S23 specifically includes the following steps:

[0132] Step S231: For each collected water use event, perform numerical conversion based on its original intensity value and classification information; extract the water use in the time period, quantify the frequency and intensity of the event in the time window and number it; for events involving multiple users, convert the proportion of each type of water use into numerical features;

[0133] Step S232: construct a set of numerical features, where each record will contain numerical information of multiple dimensions, including timestamp, main road flow, branch road flow, water use event type, water use event intensity, and the proportion of each type of water use event;

[0134] Step S233: Integrate the generated numerical features into a unified feature matrix to form the final data output for model construction; each row of the matrix represents a complete water use event record at a time point, including all relevant numerical features.

[0135] Preferably, step S231 of this embodiment ensures uniform comparability of data by converting the original intensity value of each water use event into a numerical value; it is crucial for data analysis and model training, and helps to eliminate consistency issues between data; extracting usage in a specific time period and quantifying the frequency and intensity of events within the time window can reveal the changing trend of water use behavior; through statistics on event frequency, water use patterns can be better understood; for events involving multiple users, by calculating and converting the proportion of various water use situations, complex multi-user water use information is simplified into manageable numerical features, enhancing the parseability and practicality of the data. Significance: It lays a solid data foundation for feature generation and integration, ensures that the characteristics of water use events can be quantified into meaningful numerical values, and provides an analytical basis for the model; Quantified frequency and proportion provide a deep perspective for water use behavior analysis, support analysis of water use peaks and troughs under different circumstances, and provide decision support for water supply management optimization. Step S232 constructs a complete set of numerical features, including timestamp, main road flow, branch road flow, water use event type, water use event intensity and proportion; the features not only enrich the data structure, but also provide a diversified perspective for subsequent analysis; various water use information is integrated into a single record, so that each record has multi-dimensional information, which simplifies the complexity of subsequent analysis and can quickly obtain comprehensive information at each time point. Significance: By constructing multi-dimensional features, it is ensured that the data can be smoothly input into machine learning or statistical models; at the same time, the rich data features improve the predictive ability of the model and can capture more complex supply and demand relationships; multi-dimensional numerical features help to deeply understand the dynamic changes of water use events and support various analysis needs, such as trend analysis, anomaly detection, etc. Step S233 integrates all generated numerical features into a unified feature matrix. This structured data output form is highly organized and easy to manage, which is helpful for subsequent analysis; it ensures that each row in the feature matrix represents a complete record at a time point, avoiding confusion and inconsistency between data and improving data availability. Significance: The output forms the basic data for training the adaptive traffic adjustment model, ensuring that the model can use these precisely constructed features for learning and prediction; through the organization of the feature matrix, subsequent data analysis, feature engineering, model training and evaluation are more efficient, improving the speed and accuracy of calculations, and ensuring the smoothness of the overall data processing chain.

[0136] In summary, this embodiment achieves the effective transformation from complex raw water use data to structured numerical features, which not only improves the availability of data, but also provides a solid foundation for model construction and analysis, and has important practical value and theoretical significance.

[0137] Furthermore, the process of forming a supply-demand mapping in step S24 specifically includes the following steps:

[0138] Step S241: extract key features related to supply and demand from the sorted sample data set, including main road flow, branch road flow, type and intensity of water use events, time factors of weather data set (such as hour, day, week), etc.; each key feature is marked with a field;

[0139] Step S242: Analyze the extracted key features, use the correlation coefficient to evaluate the relationship strength between various flow characteristics and supply and demand, and identify the main factors affecting supply and demand; based on the correlation analysis, construct a supply and demand function, which predicts the output demand through the input features;

[0140] The supply and demand function expression is:

[0141] D(X)=β0+β1Q p +β2Q s +β3E+β4I+β5W+β6T

[0142] Where D(X) is the output of the supply and demand function, which represents the supply and demand under a given set of eigenvalues ​​X, β0 represents the intercept term, β1, β2, β3, β4, β5, β6 represent weight coefficients, and β1 represents the main road flow Q p The coefficient indicates the degree of change in supply demand D for each unit increase in main road flow, and the branch flow Q s β3 The coefficient of water use event type E represents the impact of each unit increase in branch flow on supply and demand. β4 The coefficient of event intensity I represents the impact of water use event intensity on supply and demand. β5 The coefficient of weather data W reflects the impact of weather conditions on supply and demand. β6 The coefficient of time factor T represents the impact of time variables (such as hours, days, weeks) on supply and demand.

[0143] Step S243: Use the labeled input (flow data and events) and output (supply and demand) pairs to fit and form a mapping relationship; convert the trained supply and demand function into a mapping matrix, mapping the relationship between the input features and the output demand of the matrix, each row represents the predicted output under different input conditions, and provides supply and demand forecasts for upcoming flow conditions and water use events;

[0144] The mapping matrix expression is:

[0145]

[0146] Preferably, step S241 of this embodiment is feature extraction, which extracts relevant key features from the sorted sample data set to ensure the comprehensiveness and consistency of information; key features include main road flow, branch road flow, water use event type, intensity, weather data and time factors, which provide necessary data support for subsequent analysis; each key feature is accompanied by a field identifier, which makes the use of each feature in the data processing and analysis process clearer and reduces the complexity of data management. Significance: Feature extraction ensures that the basic data for subsequent analysis is powerful and rich, so that model training will not miss key influencing factors, and improves the rationality of analysis; identifying key features related to supply and demand helps the prediction accuracy of subsequent models and provides a basis for making scientific decisions. Step S242 is feature analysis and correlation evaluation, which uses indicators such as correlation coefficients to evaluate the strength of the relationship between various flow characteristics and supply and demand, and quantify the actual effects of influencing factors; the analysis results enable the model to extract useful signals from complex data; based on correlation analysis, a supply and demand function is constructed so that it can directly predict output demand through input features, realizing the effective transformation from data to model. Significance: Clarifying the main factors affecting supply and demand lays the foundation for subsequent quantitative analysis and model optimization, which helps to improve supply strategies in a targeted manner; by constructing a function that can predict demand, it supports water supply managers to plan water supply strategies in advance and improve the responsiveness and flexibility of the water supply system. Step S243: Fitting and mapping relationship construction, using labeled input and output pairs for fitting to form a reliable mapping relationship, involving linear or nonlinear regression and other technologies, to ensure that the model can effectively capture the relationship between input features and demand; converting the trained supply and demand function into a mapping matrix, clearly defining the corresponding relationship between input features and output demand, and the matrix realizes dynamic prediction under input conditions. Significance: Through the mapping matrix, the supply and demand forecast at a certain moment or condition in the future can be quickly obtained, which improves the response speed of flow adjustment and optimizes resource allocation; the structured form of the mapping matrix makes the performance evaluation and subsequent improvement of the model more feasible, and is also convenient for comparison with actual supply and demand.

[0147] In summary, the formation process of the supply and demand mapping in this embodiment constitutes a complete supply and demand forecasting chain by gradually extracting key features, analyzing relationship strength, fitting models and building mapping relationships. The technical effects and significance of each step complement each other, jointly promoting the intelligent and adaptive flow adjustment and water supply management, and providing a solid foundation for achieving efficient water resources management.

[0148] Furthermore, the training of the adaptive traffic adjustment model in step S25 specifically includes the following steps:

[0149] Step S251: configure the input layer and the output layer to ensure that each input feature such as the main flow, branch flow and water use event intensity is mapped to the output demand; divide the sample data set into a training set and a validation set, the training set is used for parameter learning of the adaptive flow adjustment model, and the validation set is used to evaluate the predictive ability and accuracy of the adaptive flow adjustment model;

[0150] Step S252: Use the training set to train the adaptive traffic adjustment model. After each training cycle, calculate the error between the output of the adaptive traffic adjustment model and the actual supply demand; implement error feedback adjustment for the loss function of the adaptive traffic adjustment model evaluation; use the validation set to evaluate the accuracy of the adaptive traffic adjustment model, and obtain indicators such as accuracy and recall by comparing the estimated results with the actual supply demand;

[0151] Step S253: After the training is completed, the hyperparameters are automatically adjusted according to the performance indicators of the adaptive traffic adjustment model.

[0152] Preferably, step S251 of this embodiment configures the input layer and the output layer and the data partitioning. By configuring the input layer and the output layer, it is ensured that various input features (such as main road flow, branch road flow and water use event intensity) can be accurately mapped to the corresponding supply and demand. This mapping process is the basis of model learning and prediction; the sample data set is reasonably divided into a training set and a validation set, and both are kept representative in terms of sample size and distribution, providing sufficient data support during the training and evaluation process, and reducing the risk of overfitting. Practical significance: By reasonably dividing the data, it is ensured that the performance of the model on unseen data can be reliably evaluated, and the generalization ability of the model is improved. It is not only applicable to training data, but also can process new data in actual applications; appropriate input and output design can enhance the efficiency of model learning, ensuring that each iteration can effectively improve the model's understanding and prediction capabilities of supply and demand, laying a good foundation for subsequent steps. Step S252: Model training and error feedback. After each training cycle, the error between the model output and the actual demand is calculated, and feedback adjustment is performed based on the loss function, so that the model can be dynamically optimized. The model is evaluated by using the validation set, and the accuracy, recall and other indicators are calculated to measure the effectiveness of the model. The accuracy and recall can comprehensively evaluate the performance of the model in prediction, and the model parameters can be further adjusted. Practical significance: During the entire training process, through continuous monitoring and adjustment, the model can gradually narrow the gap between prediction and reality, improve the final prediction performance, and enhance the robustness of the model in complex environments. Timely performance evaluation and feedback adjustment enable the model to quickly adapt to data changes during training, reduce uncertainty during training, and have positive significance for the accuracy and stability of actual operation. Step S253: Automatic adjustment of hyperparameters. After the training is completed, the model operation status is monitored and evaluated in real time based on model performance indicators (such as loss, accuracy, etc.), and the key hyperparameters that affect the model performance are identified; hyperparameters (such as learning rate, batch size, etc.) are automatically adjusted, and the optimal combination of hyperparameters is achieved through intelligent algorithms (such as grid search, random search or Bayesian optimization) without manual intervention. Practical significance: Through automated hyperparameter adjustment, the flexibility of the model in practical applications is improved, ensuring the model's adaptability in different scenarios and being able to respond to changes in traffic and demand in real time; the model optimization process is simplified. Compared with manual selection of hyperparameters, the automated method is more efficient and can better guarantee optimal performance, ensuring that the adaptive traffic adjustment model can continue to operate effectively in complex scenarios.

[0153] In summary, this embodiment gradually builds an efficient, flexible, and accurate adaptive flow adjustment model through a series of steps including input and output configuration, model training, and hyperparameter adjustment. This not only ensures that the model has a deep understanding of the relationship between flow and supply and demand, and improves the prediction accuracy and response speed; at the same time, in the face of changing water demand and environmental factors, the model can have strong adaptability, and has a wide range of practical application value and potential commercial benefits.

[0154] Furthermore, the process of dividing the sample data set into a training set and a validation set in step S251 specifically includes the following steps:

[0155] Step S2511: Randomly shuffle the sample data set, implement stratified sampling in the data set according to the specific conditions of water consumption peaks and valleys, and generate training sets and validation sets;

[0156] Step S2512: After the division of the training set and the validation set is completed, a confirmation is performed to verify that the number of samples in the training set and the validation set conform to the set division ratio, and that the feature distribution of each subset matches the sample data set; the specific information of the division is recorded, including the number of samples in the training set and the validation set, the feature distribution, and the stratified sampling;

[0157] Step S2513: At different stages of the adaptive traffic adjustment model training, the composition of the generated training set and validation set is dynamically evaluated, including the validity of the samples, the representativeness of the features, and the phased effect of the training progress.

[0158] Preferably, the random shuffling and stratified sampling in step S2511 of this embodiment ensures the randomness of the sample order and eliminates the order effect in the time series data by randomly shuffling the sample data set; it will not be affected by a specific order of samples during learning, thereby improving the independence and diversity of learning; stratified sampling is performed based on key features such as water consumption peaks and troughs to ensure that the proportion of samples of different categories in the training set and the validation set is consistent with the original data set, ensuring that the model can access important change points in the sample data, and enhancing the learning ability and robustness of the model under different states. Practical significance: Through stratified sampling, it is ensured that the training set and the validation set can fully represent the entire data set, so that the model can make more accurate and reliable predictions of actual scenarios after training; it effectively utilizes limited data resources to ensure that key features are fully learned, so that the model has a stronger response strategy when facing practical problems. Step S2512 confirms and records the data set. After the division is completed, the sample size and feature distribution of the training set and the validation set are verified to ensure that they meet the established division ratio and feature distribution requirements, preventing data imbalance caused by errors in the division process; the system records the specific information of the division, including the sample size, feature distribution and details of stratified sampling of the training set and the validation set, which not only provides a basis for model evaluation, but also an important reference for subsequent model tuning. Practical significance: The clear recording process makes the model development process transparent, which is conducive to communication and collaboration, and also provides a reliable basis for subsequent research and model inheritance; during the model training and evaluation process, ensure that the division of the data set is consistent with the characteristics of the original data set, thereby improving the reliability and effectiveness of the model in the verification stage. Step S2513 dynamically evaluates the composition of the data set, dynamically evaluates the training set and validation set generated during the model training process, detects the sample validity, feature representativeness and training effect, and accumulates data for subsequent adjustment and optimization; according to the evaluation feedback during the training progress, it can timely understand the performance of the model at a specific stage, so that the necessary adjustments can be made to the data set to optimize the model performance. Practical significance: Dynamic evaluation ensures that the model can be continuously optimized and adjusted according to actual conditions during the training process, so that the model can quickly adapt to complex and changing water demand scenarios and improve the practicality of the model; through dynamic inspection of the components of the model data set, the adaptability and foresight of the overall model can be improved, thereby achieving higher accuracy and effect in practical applications.

[0159] In summary, the implementation of this embodiment ensures that the adaptive traffic adjustment model has a good training foundation and evaluation mechanism through precise data management, so that the model can still perform supply and demand forecasts stably, efficiently and accurately when facing the complexity of actual application. Each step complements each other and jointly promotes the improvement of model capabilities and the success of application.

[0160] Furthermore, if Figure 4 As shown, the process of obtaining the adjusted operating parameters of the flow adjustment device in step S3 specifically includes the following steps:

[0161] Step S31: after receiving the supply demand, a set of control signals is generated and sent to the flow control device, including current demand parameters, target flow, target pressure, and instructions for operating status monitoring; the flow control device performs real-time status evaluation on valves and pumps, and collects current flow, pressure and status information;

[0162] Step S32: Obtain the target value of the control signal, compare the current operating value of the valve and the pump with the target value, and calculate the required adjustment amount; for each flow control valve, generate the opening value and conversion speed according to the supply demand change; adjust the speed or power output according to the operating status of the pump;

[0163] Step S33: The newly generated operating parameters of the valve and pump are saved in the configuration file of the device.

[0164] Preferably, after receiving the supply demand, the control signal generated by step S31 of this embodiment can be quickly and accurately transmitted to the flow adjustment device, ensuring the immediacy and accuracy of the relevant instructions, and helping the flow adjustment device to conduct comprehensive real-time monitoring of the system status. Significance: A communication bridge is established between the flow adjustment system and environmental requirements; through real-time monitoring, the equipment can respond to changes in external conditions in a timely manner to ensure the dynamic balance of the water supply and drainage system; the instant feedback mechanism provides the necessary information basis for subsequent flow regulation, reduces the system's response delay to emergencies, and improves the efficiency of the overall system. In the process of comparing the current operating value with the target value, step S32 can accurately calculate the required adjustment amount. As a result, the flow control valve opening value and the speed or power output of the pump can be accurately set, so that the device can quickly respond to changes in supply demand. Significance: It provides clear operating instructions for flow adjustment, ensuring that the equipment can be finely adjusted according to actual needs; by calculating the adjustment amount, the system reduces the risk of resource waste, optimizes energy consumption, and improves the accuracy of flow adjustment; precise control helps to achieve water and energy saving goals while maintaining the stability and sustainability of the system. In step S33, the newly generated operating parameters of the valve and pump are saved in the configuration file of the device, which ensures the persistence and consistency of the parameters, so that the device can continue to work according to the optimal configuration in subsequent operation. Significance: The step of saving operating parameters provides an important basis for long-term performance monitoring and optimization of the equipment; the data not only reflects the effective configuration of the equipment under specific historical conditions, but also lays the foundation for future adjustments and strategy formulation; regular data display and analysis can guide subsequent maintenance decisions and technical upgrades, thereby improving the intelligence level of the entire water supply and drainage system.

[0165] Among them, the calculation process of the flow control valve

[0166] Calculate the current valve opening and target opening, and obtain the current parameters: First, read the actual opening of the current flow control valve. For example, the current opening is recorded as C current (% or other units);

[0167] Get target parameters: Receive the target flow C in the control signal target and the target opening C obtained based on the flow characteristics current ;

[0168] Calculate the adjustment amount, the adjustment amount formula is:

[0169] Calculate the required adjustment ΔC: ΔC = C target -C current

[0170] Determine the adjustment direction and intensity:

[0171] Based on the calculation results, determine whether the valve opening needs to be increased or decreased, and evaluate the intensity of the adjustment;

[0172] Generate opening value and conversion speed, generate opening value:

[0173] Based on the adjustment amount, set the new opening value: C new =C current +ΔC

[0174] Switching speed setting: Determine the switching speed based on the valve design and actual working characteristics. You can assume the maximum switching speed (V max ) is a known constant, the final conversion speed V is estimated by the following formula: Here, Δt can be set according to the specific application scenario and the rate of change of flow demand.

[0175] Calculation process for pumps

[0176] Calculate the current speed and target speed to get the current speed:

[0177] Read the current speed N of the pump current (Unit is RPM).

[0178] Get the target flow and target speed: According to the target flow C in the control signal target And the pump flow-speed relationship, calculate the target speed N target .

[0179] Calculate the adjustment

[0180] Adjustment formula: Calculate the required speed adjustment ΔN: ΔN=N target -N current

[0181] Determine the adjustment direction and amplitude: According to the positive and negative values ​​of the adjustment amount, confirm whether it is an acceleration or deceleration adjustment;

[0182] In summary, this embodiment forms a complete flow adjustment mechanism from information collection to precise calculation and data storage. The mechanism not only enhances the responsiveness and efficiency of the water supply and drainage system, but also plays a positive role in the efficient management of water resources, helping to achieve a more intelligent water management solution.

[0183] like Figure 5 As shown, this embodiment also provides an embodiment of an adaptive water supply and drainage pipeline flow adjustment system. In this embodiment, the adaptive water supply and drainage pipeline flow adjustment system is applied to the adaptive water supply and drainage pipeline flow adjustment method in the above embodiment. The adaptive water supply and drainage pipeline flow adjustment system includes a signal output module 1, a supply demand module 2, and a parameter adjustment module 3 that are electrically connected in sequence;

[0184] Among them, the signal output module 1 is used to obtain a three-dimensional stereogram of the water supply and drainage pipeline, identify the equipment positions related to flow monitoring and adjustment through the three-dimensional stereogram, and obtain a flow monitoring equipment position set and a flow adjustment equipment position set; the flow monitoring equipment is a flow monitoring equipment, which collects the water flow of the water supply and drainage pipeline in real time; converts the collected flow analog signal into a digital signal, and outputs the digital signal; the supply and demand module 2 is used to train the adaptive flow adjustment model according to the historical flow data set of the water supply and drainage pipeline; inputs the real-time water flow data into the adaptive flow adjustment model to obtain the supply and demand of the water flow of the main and branch roads of the water supply and drainage pipeline; the parameter adjustment module 3 is used to adjust the flow adjustment equipment according to the supply demand, and obtain the operating parameters of the adjusted flow adjustment equipment; at the same time, the water pressure of the branch road of the water supply and drainage pipeline after the operating parameters are adjusted is measured by the water pressure monitoring equipment, and if the pressure threshold is triggered, an early warning is issued.

[0185] like Figure 6 As shown, this embodiment provides an embodiment of an electronic device. In this embodiment, the electronic device 4 includes a processor 41 and a memory 42 coupled to the processor 41.

[0186] The memory 42 stores program instructions for implementing the adaptive water supply and drainage pipeline flow adjustment method of any of the above embodiments.

[0187] The processor 41 is used to execute program instructions stored in the memory 42 to perform adaptive flow adjustment of water supply and drainage pipelines.

[0188] The processor 41 may also be referred to as a CPU (Central Processing Unit). The processor 41 may be an integrated circuit chip having signal processing capabilities. The processor 41 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0189] Further, Figure 7 The schematic diagram of the structure of the storage medium of an embodiment of the present application is that the storage medium 5 of the embodiment of the present application stores program instructions 51 that can implement all the above methods, wherein the program instructions 51 can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0190] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0191] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units. The above is only an implementation mode of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present invention.

[0192] The specific implementation methods of the invention are described in detail above, but they are only examples, and the invention is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the invention, therefore, the equalization, modification, improvement, etc. made without departing from the spirit and principle of the invention should be included in the scope of the invention.

Claims

1. A method for adaptively adjusting flow rate of water supply and drainage pipelines, characterized in that: The adaptive water supply and drainage pipeline flow adjustment method comprises: Obtain a three-dimensional stereogram of the water supply and drainage pipeline, identify the location of equipment related to flow monitoring and adjustment through the three-dimensional stereogram, and obtain a flow monitoring equipment location set and a flow adjustment equipment location set; the flow monitoring equipment is a flow monitoring equipment, which collects the water flow of the water supply and drainage pipeline in real time; convert the collected flow analog signal into a digital signal, and output the digital signal; The adaptive flow adjustment model is trained based on the flow data set of the historical water supply and drainage pipelines; the real-time water flow data is input into the adaptive flow adjustment model to obtain the supply and demand of the water flow of the main and branch lines of the water supply and drainage pipelines; The flow regulating device is adjusted according to the supply demand to obtain the operating parameters of the adjusted flow regulating device. At the same time, the water pressure of the branch of the water supply and drainage pipeline after the adjusted operating parameters is measured by the water pressure monitoring device. If the pressure threshold is triggered, an early warning is issued.

2. The method for adaptively adjusting flow rate of water supply and drainage pipelines according to claim 1, characterized in that: Identify the location of equipment related to flow monitoring and regulation through 3D images, including: Arrange multiple view scanning devices in the target water supply and drainage network area, perform 360-degree rotation scanning, and obtain multiple scanning views; at the same time, use multi-view high-resolution cameras for synchronous shooting to obtain texture information on the equipment and pipeline surfaces; Integrate multiple scanned views into a single 3D surface model to preliminarily generate point cloud data; post-process the preliminarily generated point cloud data to remove noise points and outliers that exceed the distance threshold, clean the point cloud data, and obtain pre-processed point cloud data; Analyze the preprocessed point cloud data, perform geometric fitting on the curved surface of the pipeline and the surface of the valve and pump, and obtain the rough shape of the equipment; convert the point cloud data into a raster image, extract the significant edges from the raster image, select the edge part in the straight line direction, and gradually connect the edge points in the same direction and close to form multiple independent straight line segments; Analyze the extracted straight line segments, set similar lengths and angle ranges for combination, aggregate the straight line segments to form a closed shape representing the contours of the pipeline and equipment, and construct a preliminary structural diagram based on the aggregated line segments as a contour feature description of the equipment; compare the newly generated contour features with the equipment model in the database, use shape similarity and direction consistency to evaluate the similarity of the morphology, and determine the position, angle, and installation direction of the equipment based on the matching results.

3. The adaptive water supply and drainage pipeline flow adjustment method according to claim 2, characterized in that: Combine multiple scan views into a single 3D surface model, including: At each scanning position, the view scanning device generates a point cloud data set containing the three-dimensional coordinates and intensity information of objects around the position; a reference point is selected as the origin of the global coordinate system, and the directions of the X, Y, and Z coordinate axes are defined based on the far point; Detect the feature points of the edges and corners in each point cloud; select the feature points in the overlapping area in each data set and align the two adjacent point clouds; align the adjacent multiple point cloud data through rigid transformation; calculate the rotation matrix and translation vector of each point cloud relative to the reference coordinate system through an iterative method based on the least squares method, and use the overlapping parts of multiple point clouds for multiple iterations, and compare them with the set tolerance threshold until the error reaches the tolerance threshold; The registered point cloud data sets are merged according to the rotation matrix and translation vector, the coordinates of each point cloud data are transformed into the global coordinate system, and a point cloud data set is formed; the merged point cloud data set is triangulated and meshed to convert the point cloud data set into a three-dimensional surface model.

4. The method for adaptively adjusting flow rate of water supply and drainage pipelines according to claim 1, characterized in that: The construction of the adaptive traffic adjustment model includes: Obtain historical flow data including historical real-time water flow data from each flow monitoring device, including flow information of the main and branch roads, and timestamps, to form a complete flow time series; at the same time, record water usage events within the corresponding time period, including water consumption peaks, changes in equipment operating status, and weather conditions; The historical flow data is sorted in time series to form a structured database; each record should contain time, main road flow, branch road flow, related water use events and user demand information; the sample data stored in the database is labeled, and each set of water flow data is associated with the corresponding supply and demand to form flow data, events and supply and demand pairs to obtain a sample data set; Extract features including daily, weekly, and monthly trends and fluctuations of water flow from the sample dataset; convert the intensity and type of water use events into numerical features; Use the collated sample data set to construct a supply-demand relationship table; associate the change pattern of main and branch flow with various water use events; create a supply-demand function, and form a supply-demand mapping by statistically analyzing the correlation between the main flow characteristics and supply and demand; The adaptive traffic adjustment model is trained using the training set divided by the sample data set, and is evaluated using the validation set divided by the sample data set. The accuracy of supply and demand under specific conditions is predicted, and the accuracy is obtained by comparing the output of the adaptive traffic adjustment model with the result of supply and demand mapping. The error of the model parameters is adjusted based on the accuracy.

5. The adaptive water supply and drainage pipeline flow adjustment method according to claim 4 is characterized in that: Get a sample data set, including: Obtain historical data sets containing main and branch water flows from flow monitoring equipment, with each record having a timestamp, main flow, and branch flow fields; extract information matching the corresponding timestamp from the stored water usage event data, including water usage peaks, equipment status changes, and weather information; Clean the flow data and event data in the historical data set, remove missing values ​​and outliers, and convert all timestamps into a unified time format; connect the flow data with the corresponding water use event data based on the timestamp; Generate a structured data frame, whose rows represent water flow records at each time point, and columns include time, main flow, branch flow and corresponding water use event information; for each flow data, create a supply and demand label according to the type and intensity of the water use event, mark the water flow during the peak water use period as high demand, and mark it as low demand during the low peak period; organize the processed flow data and the corresponding supply and demand labels into a sample data set in a tabular form, including flow-related input fields and output fields.

6. The adaptive water supply and drainage pipeline flow adjustment method according to claim 4, characterized in that: Convert the intensity and type of water use events into numerical features, including: For each collected water use event, perform numerical conversion based on its original intensity value and classification information; extract water use in the time period, quantify the frequency and intensity of the event within the time window and number it; for events involving multiple users, convert the proportion of each type of water use into numerical features; Construct a set of numerical features. Each record will contain numerical information of multiple dimensions, including timestamp, main road flow, branch road flow, water use event type, water use event intensity, and the proportion of each type of water use event. The generated numerical features are integrated into a unified feature matrix to form the final data output for model construction; each row of the matrix represents a complete water use event record at a point in time, including all relevant numerical features.

7. The method for adaptively adjusting flow rate of water supply and drainage pipelines according to claim 4, characterized in that: Form a supply-demand mapping, including: Extract key features related to supply and demand from the collated sample data set, including main road flow, branch road flow, type and intensity of water use events, and time factors of weather data set; each key feature is marked with a field; The extracted key features are analyzed, and the correlation coefficient is used to evaluate the strength of the relationship between various flow characteristics and supply and demand, and the main factors affecting supply and demand are identified; based on the correlation analysis, a supply and demand function is constructed, which predicts the output demand through the input features; Use the labeled input and output pairs to fit and form a mapping relationship; convert the trained supply and demand function into a mapping matrix, mapping the relationship between the input features of the matrix and the output demand. Each row represents the predicted output under different input conditions, providing supply and demand forecasts for upcoming flow conditions and water use events.

8. The adaptive water supply and drainage pipeline flow adjustment method according to claim 4, characterized in that: Training the adaptive traffic shaping model includes: Configure the input layer and output layer to ensure that the input features of each main flow, branch flow, and water use event intensity are mapped to the output requirements; divide the sample data set into a training set and a validation set. The training set is used for parameter learning of the adaptive flow adjustment model, while the validation set is used to evaluate the predictive ability and accuracy of the adaptive flow adjustment model; The adaptive traffic adjustment model is trained using the training set. After each training cycle, the error between the output of the adaptive traffic adjustment model and the actual supply and demand is calculated. Error feedback adjustment is implemented for the loss function of the adaptive traffic adjustment model evaluation. The accuracy of the adaptive traffic adjustment model is evaluated using the validation set. The accuracy and recall indicators are obtained by comparing the estimated results with the actual supply and demand. After training is completed, the hyperparameters are automatically adjusted based on the performance indicators of the adaptive traffic adjustment model.

9. The adaptive water supply and drainage pipeline flow adjustment method according to claim 1, characterized in that: The adjusted operating parameters of the flow regulating device are obtained, including: After receiving the supply demand, a set of control signals is generated and sent to the flow control device, including the current demand parameters, target flow, target pressure, and instructions for operating status monitoring; the flow control device performs real-time status assessment on valves and pumps, and collects current flow, pressure and status information; Obtain the target value of the control signal, compare the current operating value of the valve and pump with the target value, and calculate the required adjustment amount; for each flow control valve, the supply demand changes generate the opening value and conversion speed; the operating status of the pump adjusts the speed or power output; The newly generated operating parameters of valves and pumps are saved in the device configuration files.

10. An adaptive water supply and drainage pipeline flow adjustment system, which is applied to the adaptive water supply and drainage pipeline flow adjustment method according to any one of claims 1 to 9, characterized in that: The adaptive water supply and drainage pipeline flow adjustment system comprises: The signal output module is used to obtain a three-dimensional stereogram of the water supply and drainage pipeline, identify the position of equipment related to flow monitoring and adjustment through the three-dimensional stereogram, and obtain a flow monitoring equipment position set and a flow adjustment equipment position set; the flow monitoring equipment is a flow monitoring equipment, which collects the water flow of the water supply and drainage pipeline in real time; converts the collected flow analog signal into a digital signal, and outputs the digital signal; The supply and demand module is used to train the adaptive flow adjustment model based on the flow data set of the historical water supply and drainage pipelines; input the real-time water flow data into the adaptive flow adjustment model to obtain the supply and demand of the water flow of the main and branch lines of the water supply and drainage pipelines; The parameter adjustment module is used to adjust the flow adjustment device according to the supply demand and obtain the operating parameters of the adjusted flow adjustment device; at the same time, the water pressure of the branch of the water supply and drainage pipeline after the adjustment of the operating parameters is measured by the water pressure monitoring equipment. If the pressure threshold is triggered, an early warning is issued.

Images