Intelligent control method, device, system and equipment for water supply station and medium

Abstract

The invention discloses an intelligent control method, device and system for a water supply station and a medium. The method comprises the steps that acoustic environment data of a plurality of sensing nodes are obtained, the sensing nodes are arranged on a water supply network, and the acoustic environment data are used for monitoring the operation state of the water supply network; performing anomaly identification on the acoustic environment data to obtain an identification result; under the condition that the identification result comprises abnormal signals, a first leakage interval is determined according to the abnormal signals of the multiple sensing nodes, and the first leakage interval comprises a distance interval between two adjacent target sensing nodes; performing frequency dispersion characteristic analysis on the target environment data of the target sensing node to obtain a second leakage position; and generating a control strategy of the water supply pipe network where the second leakage position is located. According to the embodiment of the invention, the water supply pipe network and the water supply station can be monitored in real time, the fault position can be accurately positioned under the condition that the water supply pipe network breaks down, and the water supply station is controlled to supply water intelligently.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of water supply control, and particularly relates to a water supply station intelligent control method, device, system and medium. BACKGROUND

[0002] With the continuous advancement of urbanization, the scale and complexity of urban water supply systems are increasing, and how to realize efficient monitoring and intelligent analysis of water supply networks has become a key problem in the construction of smart water affairs.

[0003] At present, urban water supply is usually taken as a water supply source by a water supply station, which plays a crucial role in the urban water supply system. Usually, drinking water is input to a user's home by a water supply station through a water supply network. Conventional water supply network monitoring methods mainly rely on manual inspection, water quality sampling at fixed points, and simple flow and pressure measurement points. Although this method can monitor the water supply station and the water supply pipeline, the monitoring efficiency is low, and there is a lack of global awareness of the overall network system operation state. At the same time, there are problems such as single parameter dimension and simplified calculation model, which makes it difficult to accurately evaluate the operation state in a complex water environment. How to improve the monitoring efficiency and automation level of the water supply network and improve the accuracy of water affairs state evaluation has become a problem to be solved. SUMMARY

[0004] The embodiments of the present application provide a water supply station intelligent control method, device, system and medium, which can monitor the water supply network and the water supply station in real time, accurately locate the fault position in the case of water supply network failure, and control the intelligent water supply of the water supply station.

[0005] In one aspect, the embodiments of the present application provide a water supply station intelligent control method, which comprises:

[0006] Acquire acoustic environment data of a plurality of sensing nodes, the sensing nodes are arranged on the water supply network, and the acoustic environment data is used to monitor the operation state of the water supply network;

[0007] Abnormal identification is performed on the acoustic environment data to obtain an identification result;

[0008] In the case that the identification result includes an abnormal signal, a first leakage interval is determined according to the abnormal signal of the plurality of sensing nodes, and the first leakage interval includes a distance interval between two adjacent target sensing nodes;

[0009] Frequency dispersion characteristic analysis is performed on the target environment data of the target sensing node to obtain a second leakage position;

[0010] A control strategy of the water supply network where the second leakage position is located is generated.

[0011] Optionally, the determining the first leakage interval according to the abnormal signals of the plurality of sensor nodes comprises:

[0012] obtaining a first duration corresponding to the abnormal signals;

[0013] in a case that the first duration is less than a preset time window, determining a leakage event of the water supply network;

[0014] obtaining at least three sensor node positions corresponding to the leakage event and a corresponding first timestamp of the abnormal signals transmitted by each of the sensor node positions;

[0015] calculating a time difference of the abnormal signals based on the first timestamp in pairs;

[0016] determining a first leakage interval by using a preset hyperbolic equation, the time difference and a preset sound wave propagation speed.

[0017] Optionally, the determining the first leakage interval by using the preset hyperbolic equation, the time difference and the preset sound wave propagation speed comprises:

[0018] determining a distance difference based on the time difference and the preset sound wave propagation speed, the distance difference being used to represent a distance between a leakage point and an adjacent sensor, the preset sound wave propagation speed being used to represent a propagation speed of a sound wave under different pipeline parameters;

[0019] determining an intersection according to a plurality of preset hyperbolic equations;

[0020] determining the first leakage interval based on the intersection.

[0021] Optionally, after the determining the first leakage interval by using the preset hyperbolic equation, the time difference and the preset sound wave propagation speed, the method further comprises:

[0022] obtaining a deviation of each of the sensors from a preset standard time, a signal-to-noise ratio, a model fitting residual agreement degree, a sensor consistency parameter and a topology rationality score, wherein the deviation is used to represent a synchronization accuracy of a sensor clock participating in positioning, the signal-to-noise ratio is used to represent a signal-to-noise ratio of a sensor participating in positioning in a leakage characteristic frequency band, the model fitting residual agreement degree is used to represent an agreement degree between a theoretical model and measured data, the sensor consistency parameter is used to represent a consistency of events reported by different sensors in characteristics, and the topology rationality score is used to represent a physical rationality of a leakage point;

[0023] weighting and summing the deviation, the signal-to-noise ratio, the model fitting residual agreement degree, the sensor consistency parameter and the topology rationality score according to a preset weight ratio to obtain a confidence score;

[0024] Based on the confidence score and a preset confidence level, a confidence strategy is generated, which is used to represent an action suggestion.

[0025] Optionally, the dispersion feature analysis on the target environmental data of the target sensing node obtains a second leakage position, including:

[0026] Performing time-frequency transformation on the target acoustic environmental data to obtain a time-frequency spectrum, the target acoustic environmental data being acoustic environmental data transmitted by a target sensor on the target sensing node;

[0027] In the time-frequency spectrum, a pipe propagation theory curve is calculated based on a preset physical propagation model;

[0028] Based on a preset actual dispersion relationship, an actual propagation theory curve is determined;

[0029] According to the pipe propagation theory curve and the actual propagation theory curve, a second leakage position is determined by using a preset matching algorithm.

[0030] Optionally, the actual propagation theory curve is determined based on a preset actual dispersion relationship, including:

[0031] The target acoustic environmental data is filtered in narrow band to obtain a plurality of single frequency components;

[0032] For each single frequency component, a phase angle of each target acoustic sensor is calculated;

[0033] Based on the difference of the phase angles, a phase difference is determined;

[0034] According to a preset actual dispersion relationship and the phase difference, a wave number difference is determined;

[0035] According to the wave number difference, a phase velocity is determined;

[0036] According to the phase velocity, the actual propagation theory curve is drawn.

[0037] Optionally, the control strategy of the water supply network in which the second leakage position is located is generated, including:

[0038] A network topology map of the water supply network is obtained;

[0039] According to the network topology map, a digital twin map is constructed;

[0040] In the digital twin map, a connected pipe network and a water supply site corresponding to the second leakage position are found;

[0041] According to the connected pipe network and the water supply site, a leakage amount is estimated;

[0042] generate a valve start-stop strategy of the water supply pipe network based on the leakage amount and the connected pipe network.

[0043] In another aspect, the embodiments of the present application provide a water supply site intelligent control device, which comprises:

[0044] an acquisition module configured to acquire acoustic environment data of a plurality of sensing nodes, the sensing nodes being arranged on a water supply pipe network, and the acoustic environment data being used to monitor an operation state of the water supply pipe network;

[0045] an anomaly identification module configured to perform anomaly identification on the acoustic environment data to obtain an identification result;

[0046] a determination module configured to, in a case where the identification result comprises an anomaly signal, determine a first leakage interval according to the anomaly signal of the plurality of sensing nodes, the first leakage interval comprising a distance interval between two adjacent target sensing nodes;

[0047] an analysis module configured to perform dispersion characteristic analysis on target environment data of the target sensing nodes to obtain a second leakage position;

[0048] a generation module configured to generate a control strategy of the water supply pipe network in which the second leakage position is located.

[0049] In another aspect, the embodiments of the present application provide a water supply site intelligent control system, which comprises:

[0050] a water supply pipe network;

[0051] a sensor arranged on the water supply pipe network;

[0052] a cloud platform arranged on a water supply site, and the sensor is in network connection with the cloud platform, and the cloud platform is configured to execute the water supply site intelligent control method of the first aspect.

[0053] In another aspect, the embodiments of the present application provide a computer storage medium, and the computer readable storage medium stores computer program instructions, and the computer program instructions are executed by a processor to implement the water supply site intelligent control method of any one of the first aspect.

[0054] The water supply station intelligent control method, device, system and storage medium provided by the embodiments of the present application can perform real-time monitoring on the water supply pipe network through acoustic environment data of multiple sensing nodes, and then perform preliminary acoustic environment data anomaly identification on each sensing node. In the case that the identification result includes an abnormal signal, it can be preliminarily determined that the water supply pipe network may be leaking, or there may be a leak at a certain place of the water supply station. At this time, the first leakage interval can be determined through the abnormal signal, and the two target sensing nodes can be roughly positioned. Then, the dispersion characteristic analysis of the water supply station is performed to obtain the second leakage position, and the leakage point is accurately positioned. The water supply pipe network and the water supply station can be monitored in real time, the fault position is accurately positioned in the case that the water supply pipe network fails, and the water supply station is intelligently controlled. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly introduced. Those skilled in the art can obtain other drawings according to these drawings without creating any creative labor.

[0056] Figure 1 is a flowchart of a water supply station intelligent control method provided by an embodiment of the present application;

[0057] Figure 2 is a positioning diagram of a leakage point provided by an embodiment of the present application;

[0058] Figure 3 is a structural diagram of a water supply station intelligent control device provided by another embodiment of the present application;

[0059] Figure 4 is a structural diagram of an electronic device provided by another embodiment of the present application. DETAILED DESCRIPTION

[0060] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application more clear and apparent, the present application will be further described in detail below with reference to the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, but not to limit the present application. The present application can be implemented without some of these specific details by those skilled in the art. The following description of the embodiments is only intended to provide a better understanding of the present application by showing examples of the present application.

[0061] It is to be noted that, in the present document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0062] In the related art, urban water supply pipe network monitoring mainly relies on manual inspection and fixed point sensors, and the traditional method makes local state judgment through single parameters such as pressure and flow. Due to the complex structure and wide coverage of the pipe network, manual inspection has problems such as response lag and insufficient coverage of blind areas, and fixed sensors can only reflect the instantaneous state of limited nodes and cannot capture the dynamic changes inside the pipeline. When pipeline leakage occurs, conventional methods are difficult to quickly determine the abnormal position, often requiring the closure of a large range of pipe networks for segmented investigation, resulting in water supply interruption and resource waste.

[0063] In order to solve the problems in the prior art, the embodiments of the present application provide a water supply site intelligent control method, device, system, equipment and medium. In the embodiments of the present application, the water supply pipe network can be monitored in real time through acoustic environment data of a plurality of sensing nodes. Then, on each sensing node, the acoustic environment data can be used for preliminary anomaly identification. In the case that the identification result includes an abnormal signal, it can be preliminarily determined that there may be a water supply pipe network leakage or a leakage at a certain water supply site. At this time, the first leakage interval can be determined through the abnormal signal, and the two target sensing nodes can be roughly positioned. Then, the dispersion characteristic analysis of the water supply site is performed to obtain the second leakage position, and the leakage point is accurately positioned. The water supply pipe network and the water supply site can be monitored in real time, the fault position is accurately positioned in the case that the water supply pipe network fails, and the water supply site is intelligently controlled.

[0064] Firstly, the water supply site intelligent control method provided by the embodiments of the present application is introduced.

[0065] Figure 1 The flowchart of the water supply site intelligent control method provided by one embodiment of the present application is shown. As shown in Figure 1 The water supply site intelligent control method can include S101-S105:

[0066] S101, acquire acoustic environment data of a plurality of sensing nodes, the sensing nodes being arranged on a water supply pipe network, the acoustic environment data being used to monitor an operation state of the water supply pipe network;

[0067] S102, perform anomaly identification on the acoustic environment data to obtain an identification result;

[0068] S103, in a case where the identification result includes an abnormal signal, determine a first leakage interval according to the abnormal signal of the plurality of sensing nodes;

[0069] S104, perform dispersion feature analysis on target environment data of a target sensing node to obtain a second leakage position;

[0070] S105, generate a control strategy of the water supply pipe network where the second leakage position is located.

[0071] In the embodiment of the present application, in S101, the acoustic environment data can be pipe sound signals collected by a hydrophone or a vibration sensor, and can be implemented by using a wideband sensor with a frequency range of 20 Hz-20 kHz, and the acoustic environment data can include pipe vibration and fluid turbulence.

[0072] In S102, the anomaly identification can detect the sudden transient component in the acoustic signal by using a machine learning model, and can be implemented by using a threshold judgment algorithm based on wavelet transform to distinguish normal water flow noise from leakage shock wave.

[0073] In S103, the first leakage interval can be a possible leakage area calculated by the time difference of the sensor signals uploaded by the plurality of sensing nodes, and a hyperbolic positioning equation can be used to solve the intersection point of the sound wave propagation path to narrow the subsequent analysis range. That is, a lightweight neural network model is deployed on each sensing node to make a preliminary anomaly judgment. For example, when an abnormal signal is identified, it can be preliminarily determined that there is a leakage point.

[0074] In the embodiment of the present application, the first leakage interval includes a distance interval between two adjacent target sensing nodes.

[0075] In S104, in a case where the lightweight neural network model on the sensing node determines that there is an abnormal signal, further identification is needed to perform real-time and accurate monitoring on the water supply pipe network and the water supply site.

[0076] After the first leakage interval of the preliminary determined leakage point, dispersion feature analysis can be performed according to the different acoustic fingerprint features at the leakage point to obtain the accurate second leakage position, thereby providing a maintenance basis for maintaining the water supply pipe network and the water supply site.

[0077] The dispersion characteristic analysis can be used to study the phase velocity difference of different frequency components when the sound wave propagates in the pipeline. Specifically, the short-time Fourier transform can be used to extract the phase difference of the narrowband signal, which can be used to accurately locate the leakage point.

[0078] In S105, after obtaining the second leakage position of the leakage point, different control strategies can be generated for the position of the leakage point in the water supply network and / or the water supply site. This not only ensures real-time intelligent control of the water supply network and / or the water supply site, but also reduces resource waste.

[0079] Specifically, the control strategy can automatically generate a valve adjustment instruction according to the leakage position. For example, the pipe network topology graph traversal algorithm can be used to determine the upstream and downstream valves that need to be closed, which can be used to isolate the leakage area.

[0080] For example, a plurality of sensing nodes are distributed at key positions of the water supply network at a preset interval, and continuously collect pipeline vibration acoustic signals. When a pipeline rupture occurs, a wideband acoustic signal is generated at the leakage point and propagates along the pipeline to both ends. The sensors closer to the leakage point will detect abnormal signals first. By comparing the time difference and intensity difference of the signals received by adjacent sensors, it is preliminarily determined that the leakage occurs between the two adjacent sensors. Further, the acoustic signals collected by the two sensors are subjected to frequency spectrum analysis. By using the characteristics of fast attenuation of high-frequency components and long propagation of low-frequency components, the time difference of arrival of acoustic signals of different frequencies is calculated to accurately calculate the distance ratio of the leakage point to the sensor. Finally, combined with the topology structure of the pipe network, an operation instruction for closing the nearest valve and starting the standby water source is automatically generated.

[0081] In the embodiments of the present application, the water supply network can be monitored in real time through acoustic environmental data of a plurality of sensing nodes. Then, on each sensing node, the acoustic environmental data can be used for preliminary anomaly recognition. If the recognition result includes an abnormal signal, it can be preliminarily determined that there may be a leakage in the water supply network or a leakage at a certain position of the water supply site. At this time, the first leakage interval can be determined through the abnormal signal, and the two target sensing nodes can be coarsely located. Then, the dispersion characteristic analysis is performed through the water supply site to obtain the second leakage position, and the leakage point is accurately located. The water supply network and the water supply site can be monitored in real time. In the case of a fault in the water supply network, the fault position can be accurately located, and the water supply site can be controlled to intelligently supply water.

[0082] In some other optional embodiments, S103 can specifically include:

[0083] The first duration corresponding to the abnormal signal is obtained.

[0084] In the case where the first duration is less than a preset time window, a leakage event of the water supply network is determined.

[0085] acquire at least three sensor node positions corresponding to the leakage event and a corresponding first timestamp of the abnormal signal transmission of each sensor node position;

[0086] calculate the time difference of the abnormal signal based on the first timestamp in pairs;

[0087] determine the first leakage interval by using a preset hyperbolic equation, the time difference and a preset sound wave propagation speed.

[0088] In the embodiment, when the abnormal signal is detected by the sensor node, the time stamp can be marked at the moment when the starting point of the abnormal signal is detected, and then the first duration is calculated in real time according to the time stamp. After the cloud platform of the water supply site receives the abnormal signals uploaded by the plurality of sensors, it is detected whether the time stamps of the abnormal signals are within the preset time window. If they are within the preset time window, it can be determined that the sensors detect the leakage event, and the model fragments on each sensor can be quickly extracted for preliminary difference verification to further confirm whether it is the same source of the leakage event or an independent noise event. At this time, at least three sensor node positions corresponding to the leakage event and a corresponding first timestamp of the abnormal signal transmission of each sensor node position can be acquired, so as to calculate the time difference of the abnormal signal reaching each sensor in pairs, thereby determining the first leakage interval.

[0089] Specifically, determining the first leakage interval by using a preset hyperbolic equation, the time difference and a preset sound wave propagation speed includes:

[0090] determining a distance difference based on the time difference and the preset sound wave propagation speed, the distance difference being used to represent the distance between the leakage point and the adjacent sensor;

[0091] determining an intersection point according to a plurality of preset hyperbolic equations;

[0092] determining the first leakage interval based on the intersection point.

[0093] In the embodiment of the application, the position of the leakage point can be assumed as P, and the positions of the sensors A1, A2 and A3 can be determined on the water supply pipe network. Then, the cloud platform stores the preset sound wave propagation speed of the sound wave in the water supply pipe network. It should be noted that the preset sound wave propagation speed is used to represent the propagation speed of the sound speed under different pipe parameters.

[0094] For example, the sound speed in cast iron pipe is about 1100-1300 m / s.

[0095] It is worth noting that the trajectory of the point with a constant distance difference to two fixed points is a hyperbola, so three hyperbolas can be determined by the positions of the leak point P and the sensors A1, A2, and A3, and then the leak point can be determined by the intersection of any two hyperbolas, but due to measurement errors, there may be no intersection, at which time the first leak interval can be determined in this way, that is, between two target sensor nodes, as shown in FIG. 2. Figure 2

[0096] In the embodiment, the first duration can be the time span from the appearance to the disappearance of the abnormal signal, and can be specifically implemented by using the start and end difference calculation of the timestamp sequence to distinguish transient interference from real leakage events.

[0097] The preset time window can be a dynamic threshold interval set according to the pressure fluctuation characteristics of the pipe network, and can be specifically implemented by using historical leakage event statistical data for adaptive adjustment to filter short-time noise interference.

[0098] The first timestamp can be an absolute time record of the arrival of the abnormal signal at each sensor node, and can be specifically implemented by using a high-precision clock synchronization protocol combined with a signal front edge detection algorithm to construct a time difference matrix.

[0099] The preset hyperbolic equation can be a mathematical positioning model established based on the difference in sound wave propagation paths, and can be specifically implemented by pre-setting different propagation speed correction coefficients according to pipe material and pipe diameter parameters to convert the time difference into a spatial distance difference.

[0100] For example, when the first duration of the abnormal signal is determined to be within the preset time window, the leakage event confirmation mechanism is triggered. The time difference is calculated by combining the arrival time stamps of the abnormal signal collected by at least three sensor nodes to form multiple independent time difference data pairs. Each time difference data pair is converted into a distance difference constraint condition between the leak point and the corresponding sensor node in combination with the preset sound wave propagation speed. The multiple distance difference constraint conditions are substituted into the preset hyperbolic equation for simultaneous solution to obtain an intersection region that satisfies all the constraint conditions, which is defined as the first leak interval. In this process, the dynamic adjustment mechanism of the preset time window can avoid misjudgment caused by environmental noise, and the redundant calculation of the multi-node time difference data improves the robustness of the positioning result.

[0101] In some other embodiments, after S103, the method can further include:

[0102] obtaining the deviation of each sensor from the preset standard time, the signal-to-noise ratio, the fitting residual error, the sensor consistency parameter, and the topology rationality score;

[0103] ​The confidence score is obtained by weighted summation of the deviation, signal-to-noise ratio, model fitting residual fitting degree, sensor consistency parameter and topology rationality score according to a preset weight ratio.

[0104] A confidence strategy is generated based on the confidence score and a preset confidence level, and the confidence strategy is used to represent an action suggestion.

[0105] In the embodiment, the deviation is used to represent the synchronization accuracy of the clock of the sensor participating in positioning, the signal-to-noise ratio is used to represent the signal-to-noise ratio of the sensor participating in positioning in the leakage characteristic frequency band, the model fitting residual fitting degree is used to represent the fitting degree between the theoretical model and the measured data, the sensor consistency parameter is used to represent the consistency of events reported by different sensors in characteristics, and the topology rationality score is used to represent the rationality of the leakage point in physics.

[0106] Specifically, the deviation of the sensor from the preset standard time refers to the synchronization accuracy of the clock of the sensor participating in positioning, which can be realized by a GPS synchronization module or a network time protocol, and is used to eliminate the calculation error of the signal arrival time caused by the clock asynchronization. The signal-to-noise ratio refers to the signal quality index of the sensor in the leakage characteristic frequency band, which can be realized by frequency domain filtering combined with power spectral density calculation, and is used to filter the effective signal frequency band. The model fitting residual fitting degree refers to the difference between the theoretical model and the measured data, which can be realized by calculating the residual sum of squares by the least square method, and is used to verify the applicability of the propagation model. The sensor consistency parameter refers to the similarity of the characteristics of the events reported by different sensors, which can be realized by correlation coefficient or covariance matrix analysis, and is used to exclude isolated abnormal signal interference. The topology rationality score refers to the logical matching degree of the leakage point and the physical structure of the pipe network, which can be realized by constructing a scoring model based on the topological relationship of the GIS system, and is used to determine whether the position meets the pipe connection rules.

[0107] In the embodiment, in order to determine the credibility of the leakage point, the confidence score can be calculated in multiple dimensions to automatically filter false positives.

[0108] Specifically, the confidence can be calculated in terms of deviation, signal-to-noise ratio, model fitting residual fitting degree, sensor consistency parameter and topology rationality score.

[0109] For example:

[0110] When calculating the deviation, the clock of each sensor needs to be kept consistent, time synchronization is performed, and then the deviation δti of the clock of each sensor from the standard time is obtained, wherein the standard time can be the GPS time, and then the maximum time deviation Max(δti) of all participating sensors is calculated, and the deviation is calculated by the following formula (1):

[0111] SSsync = max(0, 100 - (Max(δti) / τ) * 100) (1)

[0112] Where τ is a threshold, e.g. 10 microseconds, if the maximum deviation exceeds 10 microseconds, the deviation will linearly decrease until 0, the smaller the deviation, the higher the score.

[0113] When calculating the signal-to-noise ratio, calculate the signal-to-noise ratio SNR_i (unit: dB) of each sensor for its signal segment in the leakage characteristic frequency band. Take the lowest SNR_min among all sensors as the evaluation benchmark (because the worst signal determines the reliability of positioning).

[0114] SS_snr = 0, if SNR_min < SNR_threshold_low (e.g. 5dB, the signal is too poor to be trusted).

[0115] SS_snr = 100, if SNR_min > SNR_threshold_high (e.g. 20dB, the signal is very clear).

[0116] Between high and low thresholds, linear interpolation: SS_snr = (SNR_min - SNR_threshold_low) / (SNR_threshold_high - SNR_threshold_low) * 100.

[0117] When calculating the model fitting residual agreement, the calculation method of root mean square difference can be used for calculation, which is not limited here.

[0118] When calculating the sensor consistency parameter, the features of each sensor signal (such as MFCCs, spectral centroid, etc.) need to be extracted, and the cross-correlation coefficient between them is calculated.

[0119] Take the average value Avg_Correlation of the cross-correlation coefficient of all sensors in pairs.

[0120] SS_consistency = max(0, Avg_Correlation * 100)

[0121] The closer the correlation coefficient is to 1, the more consistent all sensors detect the same source event, the higher the consistency.

[0122] When calculating the topology rationality sub-score, the positioning point can be scored according to the preset rules according to whether it is at the pipe intersection or on the pipe.

[0123] Specifically, the scheme evaluates the reliability of the preliminary positioning result through a multi-dimensional parameter fusion mechanism. First, the time synchronization accuracy data of each sensor is collected, for example, a high-precision clock module is used to control the time deviation within milliseconds; then the signal-to-noise ratio data in the leakage characteristic frequency band is extracted, for example, the power ratio of the signal to the background noise is calculated in the 100-500Hz frequency band. The model fitting residual agreement is calculated by comparing the difference between the measured signal arrival time difference and the predicted value of the theoretical hyperbolic model, for example, when the residual sum of squares is less than a threshold, it is determined that the model is effective. The sensor consistency parameter is obtained by analyzing the correlation of the waveform characteristics of multiple nodes, for example, the phase consistency is calculated using the cross-correlation function. The topology rationality score is based on the spatial constraint condition constructed based on the three-dimensional coordinate data of the pipe network, for example, the leakage point must be located between the two adjacent pipe sections of the maintenance well. The above parameters are linearly superimposed according to the preset weight, for example, the time deviation weight is set to 0.2, the signal-to-noise ratio weight is 0.3, the model residual weight is 0.25, the consistency parameter weight is 0.15, and the topology score weight is 0.1. Finally, a confidence score of 0-100 points is generated. According to the scoring results, three confidence levels are divided, which correspond to different action suggestions such as immediately sending maintenance personnel, arranging planned inspection, and continuous monitoring.

[0124] In specific embodiments, the execution strategy can be determined according to the confidence score, for example, if the confidence score is greater than or equal to 90 points, it means that the signal is clear, the model fitting is perfect, the sensors are highly consistent, and the leakage point is confirmed. At this time, the confidence strategy can be to immediately exclude the maintenance team without the need for secondary confirmation. If the confidence score is greater than or equal to 70 points and less than 90 points, it means that the signal quality is good and the positioning result is reliable, but there may be minor uncertainties. At this time, the confidence strategy can be to exclude the maintenance team and suggest that personnel carry listening leak detection instruments and other equipment to quickly review near the positioning point. If the confidence score is greater than or equal to 50 points and less than 70 points, it means that the signal is weak or interfered to a certain extent, and the positioning result has a certain ambiguity. At this time, the confidence strategy can be to further investigate and accurately review the pipe section. If the confidence score is less than 50 points, it means that the signal quality is poor or the sensor data is contradictory, and the positioning result is unreliable. The confidence strategy can be to temporarily not send a maintenance team. The system records it as a "suspected event" and prompts the monitoring personnel to continue to observe the trend of the sensor data in the area. It may be only a transient interference.

[0125] In some other embodiments, S104 can specifically include:

[0126] performing time-frequency transformation on the target acoustic environment data to obtain a time-frequency spectrum, the target acoustic environment data being acoustic environment data transmitted by a target sensor on a target sensing node;

[0127] In the time-frequency spectrum, a pipe propagation theoretical curve is calculated based on a preset physical propagation model;

[0128] determine the actual propagation theoretical curve based on a preset actual dispersion relation;

[0129] determine the second leakage position by using a preset matching algorithm based on the pipeline propagation theoretical curve and the actual propagation theoretical curve.

[0130] In the embodiments of the present application, the time-frequency transformation can be converting the time-domain acoustic signal into a time-frequency joint domain representation, which can be implemented by using a short-time Fourier transform or a wavelet transform, and is used to capture the dynamic change characteristics of the leakage signal in the frequency domain.

[0131] The preset physical propagation model can be a mathematical equation of sound wave propagation established according to the material properties and geometric parameters of the pipeline, which can be implemented by using an elastic waveguide theory model, and is used to describe the dispersion characteristics of sound waves in the pipeline under ideal conditions.

[0132] The preset actual dispersion relation can be a set of sound wave propagation parameters obtained by experiment calibration or historical data statistics, which can specifically include a corresponding table of phase velocity-frequency under different pipe materials and pressure conditions, and is used to correct the deviation between the theoretical model and the actual working condition.

[0133] The preset matching algorithm can be a mathematical method for calculating the similarity of the theoretical curve and the actual curve, which can be implemented by using a dynamic time warping or a correlation coefficient method, and is used to quantify the spatial position matching degree of the two curves.

[0134] In the embodiments of the present application, when determining the second leakage position, the original signals of A2 and A3 can be band-pass filtered to retain the frequency band where the leakage signal energy is most concentrated, such as 100Hz-3kHz, and the known low-frequency and high-frequency interference, the low-frequency interference can be water flow noise, and the high-frequency interference can be electronic noise interference.

[0135] Then, the signals of A2 and A3 after alignment are subjected to short-time Fourier transform (STFT) or wavelet transform (Wavelet Transform). A time-frequency spectrum is generated, the horizontal axis is time, the vertical axis is frequency, and the color brightness represents signal energy.

[0136] In the time-frequency spectrum, waves of different frequencies propagate at different speeds. For example, high-frequency components can propagate quickly and arrive at the sensor first; low-frequency components propagate slowly and arrive late. This time-frequency dependence is a direct manifestation of the dispersion effect, so the sound wave generated by the leakage will not be a vertical line, but a tilted "ridge line".

[0137] In the embodiments, when constructing the pipeline propagation theoretical curve, a physical propagation model of the guided wave in the pipeline can be established according to the known parameters of the target pipeline, wherein the known parameters can include materials, geometric dimensions and constraint conditions.

[0138] Further, the relationship curve of the phase velocity (V phase (f) ) or the group velocity (V group (f) ) of the sound wave in the target pipeline varying with the frequency (f), i.e., the pipeline propagation theory curve, can be calculated through the physical propagation model.

[0139] Specifically, the actual propagation theory curve is determined based on the preset actual dispersion relationship, including:

[0140] The target acoustic environment data is narrowband filtered to obtain a plurality of single-frequency components;

[0141] For each single-frequency component, the phase angle of each target acoustic sensor is calculated;

[0142] The phase difference is determined based on the difference between the phase angles;

[0143] The wave number difference is determined according to the preset actual dispersion relationship and the phase difference;

[0144] The phase velocity is determined according to the wave number difference;

[0145] The actual propagation theory curve is plotted according to the phase velocity.

[0146] In this embodiment, the signals of A2 and A3 can be decomposed into a plurality of single-frequency components through a set of bandpass filters, such as 100Hz, 110Hz, 120Hz, and so on, with a step of 10Hz.

[0147] Then, for each single-frequency component f_i, the phase angles of the S2 signal and the S3 signal at this frequency, φ_S2(f_i) and φ_S3(f_i), are calculated respectively, and then the phase difference between the two sensors is calculated: Δφ(f_i) = φ_S2(f_i) -φ_S3(f_i). The wave number difference is calculated from the phase difference: the phase difference is directly related to the wave number (k = 2π / wavelength) and the sensor spacing (D) : Δφ(f_i) = k(f_i) * D. Due to the dispersion, the wave number k(f_i) is a function of the frequency, and k(f_i) =2πf_i / V phase (f_i).

[0148] Therefore, the phase velocity V phase measured (f_i) of the sound wave at this frequency in the actual pipeline can be deduced from the measured Δφ(f_i).

[0149] In this embodiment, the second leakage position is determined according to the pipeline propagation theory curve and the actual propagation theory curve using a preset matching algorithm, which can be specifically:

[0150] Establish the model of reverse propagation: Assume the leak point P is located between S2 and S3, the distance from S2 is x, and the distance from S3 is D - x (D is the distance between S2 and S3).

[0151] Simulate the propagation path: For a wave of frequency f_i generated by the leak point P, the path to S2 is x, and the path to S3 is D - x. The phase shift on the two paths is different.

[0152] Construct the matching algorithm: The system will try different leak point positions x (from 0 to D), and for each assumed x, calculate the theoretical phase difference:

[0153] Δφ_model(f_i, x) = (2πf_i / V_phase_theoretical(f_i)) * ( (D - x) -x )

[0154] Δφ_model(f_i, x) = (2πf_i / V_phase_theoretical(f_i)) * (D - 2x)

[0155] Find the optimal solution: Compare the theoretical phase difference spectrum Δφ_model(f, x) calculated by the above model with the measured phase difference spectrum Δφ_measured(f). Use optimization algorithms such as least squares or maximum likelihood estimation to find an x value that minimizes the difference between the two at all frequency points.

[0156] Objective function: Error(x) = Σ [ Δφ_measured(f_i) - Δφ_model(f_i, x) ]^2

[0157] Solution: Find the x that minimizes Error(x).

[0158] Specifically, the acoustic environment data is first converted into a time-frequency spectrogram, breaking through the limitations of single-time domain analysis and representing the transient characteristics of the leak signal in the time-frequency two-dimensional space. The pipeline propagation theory curve is established, and its mathematical expression contains parameters such as pipe wall thickness and elastic modulus, forming a benchmark reference for sound wave propagation. The actual propagation theory curve is generated by analyzing the historical operation data of the target pipe section, reflecting the sound wave attenuation law under real working conditions, and the matching algorithm compares the two curves point by point. When the shape difference between the theoretical curve and the actual curve reaches the minimum value, the corresponding spatial coordinates are determined as the leak point position. This process uses a double verification mechanism of model prediction and measured data to effectively suppress the interference of environmental noise on the positioning result.

[0159] In the embodiments of the present application, by introducing time-frequency analysis and frequency dispersion feature matching, the leakage signal identification is extended from one-dimensional time domain to time-frequency joint domain, which can effectively distinguish mechanical vibration noise from real leakage signals. The method based on a single propagation model in the prior art cannot adapt to the influence of different pipe materials and aging degree on sound velocity. The present scheme realizes self-adaptive positioning under complex working conditions through collaborative calculation of theoretical model and actual dispersion relationship.

[0160] Through the above technical solution, the present application can accurately extract the leakage characteristic frequency component in a strong background noise environment, solving the positioning deviation problem caused by ignoring the dispersion characteristics in traditional methods. Through cross verification of the theoretical propagation model and the actual dispersion data, the positioning stability under different pipe materials and pressure conditions is significantly improved. The application of the matching algorithm makes the determination of the leakage point coordinates have a clear mathematical basis, avoiding the subjective error of artificial experience judgment. This method is particularly suitable for urban underground pipe network leakage detection scenes with multiple reflected waves and environmental vibration interference.

[0161] In some other embodiments, a control strategy of a water supply network where the second leakage position is located is generated, including:

[0162] Obtaining a network topology map of the water supply network;

[0163] According to the network topology map, a digital twin map is constructed;

[0164] In the digital twin map, the connected pipe network and water supply sites corresponding to the second leakage position are found;

[0165] According to the connected pipe network and water supply sites, the leakage amount is estimated;

[0166] Based on the leakage amount and the connected pipe network, a valve start-stop strategy of the water supply network is generated.

[0167] In the present embodiment, a digital twin map can be constructed on the cloud platform of the water supply site, and then the connected pipe network and water supply sites corresponding to the second leakage position are found according to the determined second leakage position. At this time, the state and alarm information of each sensor can be displayed in real time on the digital twin map, and the leakage point can be accurately marked. In the digital twin map, the pipeline data and flow rate can be pre-stored to estimate the leakage amount and generate a valve start-stop strategy of the water supply network to ensure the water safety of users.

[0168] The water supply site intelligent control method provided by the embodiments correspondingly provides a specific implementation mode of a water supply site intelligent control device. Please refer to the following embodiments.

[0169] Firstly, referring to Figure 3 The water supply site intelligent control device 300 provided by the embodiments of the present application includes:

[0170] The acquisition module 301 is configured to acquire acoustic environment data of a plurality of sensing nodes, the sensing nodes being arranged on a water supply pipe network, and the acoustic environment data being used to monitor an operation state of the water supply pipe network.

[0171] The anomaly identification module 302 is configured to perform anomaly identification on the acoustic environment data to obtain an identification result.

[0172] The determination module 303 is configured to, in a case where the identification result includes an abnormal signal, determine a first leakage interval according to the abnormal signals of the plurality of sensing nodes, the first leakage interval including a distance interval between two adjacent target sensing nodes.

[0173] The analysis module 304 is configured to perform dispersion characteristic analysis on target environment data of a target sensing node to obtain a second leakage position.

[0174] The generation module 305 is configured to generate a control strategy of the water supply pipe network in which the second leakage position is located.

[0175] As an optional implementation, the determination module 303 can be specifically configured to:

[0176] acquire a first duration corresponding to the abnormal signal;

[0177] in a case where the first duration is less than a preset time window, determine a leakage event of the water supply pipe network;

[0178] acquire at least three sensing node positions corresponding to the leakage event and a corresponding first timestamp of the abnormal signal transmitted at each sensing node position;

[0179] calculate a time difference of the abnormal signal based on the first timestamp in pairs;

[0180] determine the first leakage interval by using a preset hyperbolic equation, the time difference, and a preset sound wave propagation speed.

[0181] As an optional implementation, the determination module 303 can be specifically configured to:

[0182] determine a distance difference based on the time difference and a preset sound wave propagation speed, the distance difference being used to represent a distance between a leakage point and an adjacent sensor, and the preset sound wave propagation speed being used to represent a propagation speed of a sound speed under different pipe parameters;

[0183] determine an intersection point according to a plurality of preset hyperbolic equations;

[0184] determine the first leakage interval based on the intersection point.

[0185] As an optional implementation, the determination module 303 can be specifically configured to:

[0186] obtain a deviation of each sensor from a preset standard time, a signal-to-noise ratio, a fitting residual degree of a model, a sensor consistency parameter, and a topology rationality score, wherein the deviation is used to represent synchronization accuracy of a clock of a sensor participating in positioning, the signal-to-noise ratio is used to represent a signal-to-noise ratio of the sensor participating in positioning in a leakage feature band, the fitting residual degree of the model is used to represent a fitting degree between a theoretical model and measured data, the sensor consistency parameter is used to represent consistency of events reported by different sensors in a feature, and the topology rationality score is used to represent a rational degree of a leakage point in a physical aspect;

[0187] perform weighted summation on the deviation, the signal-to-noise ratio, the fitting residual degree of the model, the sensor consistency parameter, and the topology rationality score according to a preset weight ratio to obtain a confidence score;

[0188] generate a confidence strategy based on the confidence score and a preset confidence level, wherein the confidence strategy is used to represent an action suggestion.

[0189] As an optional implementation manner, the analysis module 304 can be specifically used for:

[0190] perform time-frequency transformation on target acoustic environment data to obtain a time-frequency spectrum, wherein the target acoustic environment data is acoustic environment data transmitted by a target sensor on a target sensor node;

[0191] in the time-frequency spectrum, calculate a pipe propagation theoretical curve based on a preset physical propagation model;

[0192] determine an actual propagation theoretical curve based on a preset actual dispersion relationship;

[0193] determine a second leakage position by using a preset matching algorithm according to the pipe propagation theoretical curve and the actual propagation theoretical curve.

[0194] As an optional implementation manner, the analysis module 304 can be specifically used for:

[0195] perform narrowband filtering on target acoustic environment data to obtain a plurality of single-frequency components;

[0196] for each single-frequency component, calculate a phase angle of each target acoustic sensor;

[0197] determine a phase difference based on a difference between the phase angles;

[0198] determine a wave number difference according to a preset actual dispersion relationship and the phase difference;

[0199] determine a phase velocity according to the wave number difference;

[0200] draw an actual propagation theoretical curve according to the phase velocity.

[0201] As an optional implementation, the generating module 305 can be further specifically configured to:

[0202] obtain a network topology of the water supply network;

[0203] construct a digital twin map according to the network topology;

[0204] find, in the digital twin map, a connected network and a water supply station corresponding to the second leakage position;

[0205] estimate the leakage amount according to the connected network and the water supply station;

[0206] generate a valve start-stop strategy of the water supply network based on the leakage amount and the connected network.

[0207] The embodiments of the present application further provide a water supply station intelligent control system, comprising:

[0208] a water supply network;

[0209] a sensor arranged on the water supply network;

[0210] a cloud platform arranged on the water supply station, and the sensor is in network connection with the cloud platform, and the cloud platform is configured to execute the water supply station intelligent control method.

[0211] In the embodiments of the present application, the water supply network can be monitored in real time through the acoustic environment data of the plurality of sensor nodes. Then, the acoustic environment data can be used for preliminary anomaly recognition on each sensor node. In the case that the recognition result includes an abnormal signal, it can be preliminarily determined that there may be a leakage in the water supply network or there may be a leakage at a certain place of the water supply station. At this time, the first leakage interval can be determined through the abnormal signal, and the two target sensor nodes can be roughly positioned. Then, the dispersion characteristic analysis of the water supply station is performed to obtain the second leakage position, and the leakage point is accurately positioned. The water supply network and the water supply station can be monitored in real time. In the case that the water supply network fails, the fault position can be accurately positioned, and the water supply station can be intelligently controlled.

[0212] Figure 4 A hardware structure schematic diagram of an electronic device provided by the embodiments of the present application is shown.

[0213] The electronic device can include a processor 401 and a memory 402 having computer program instructions stored therein.

[0214] In particular, the processor 401 can include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to perform one or more of the embodiments of the present application.

[0215] The memory 402 can include mass storage for data or instructions. By way of example, and not limitation, the memory 402 can include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc, a magneto-optical disc, magnetic tape, or a Universal Serial Bus (USB) drive or a combination of two or more of these. In one example, the memory 402 can include removable or non-removable (or fixed) media, where the memory 502 is a nonvolatile solid-state memory. The memory 402 can be internal or external to the integrated gateway disaster recovery device.

[0216] In one example, the memory 402 can be a read-only memory (ROM). In one example, the ROM can be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0217] The memory 402 can include read-only memory (ROM), random access memory (RAM), magnetic disc storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software that, when executed (by one or more processors), is operable to perform operations described with reference to the method for intelligent control of a water supply site according to the first aspect of the present disclosure.

[0218] The processor 401 implements the method for intelligent control of a water supply site of one of the embodiments shown by reading and executing computer program instructions stored in the memory 502. Figure 1 The processor 401 implements the method for intelligent control of a water supply site of one of the embodiments shown by reading and executing computer program instructions stored in the memory 502.

[0219] In one example, the electronic device can further include a communication interface 403 and a bus 404. Wherein, as shown, the processor 401, the memory 402, the communication interface 403 are connected through the bus 404 and complete the communication between each other. Figure 4 As shown, the processor 401, the memory 402, the communication interface 403 are connected through the bus 404 and complete the communication between each other.

[0220] The communication interface 403 is mainly configured to realize the communication between the modules, devices, units and / or equipment in the embodiments of the present application.

[0221] The bus 404 includes hardware, software or both that couples components of the electronic device to each other. By way of example, and not limitation, the bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association local (VLB) bus, or another suitable bus or a combination of two or more of these. Where appropriate, the bus 404 can include one or more buses. Although the present embodiments describe and show a particular bus, the present application contemplates any suitable bus or interconnect.

[0222] The electronic device can execute the water supply site intelligent control method in the embodiments of the present application, thereby realizing the water supply site intelligent control method and device described in combination Figures 1-3 with the above-mentioned embodiments.

[0223] In addition, in combination with the water supply site intelligent control method in the above-mentioned embodiments, the embodiments of the present application can provide a computer storage medium to realize. The computer storage medium has computer program instructions stored thereon; the computer program instructions are executed by the processor to realize any one of the water supply site intelligent control methods in the above-mentioned embodiments.

[0224] In an optional embodiment, in combination with the water supply site intelligent control method in the above-mentioned embodiments, the embodiments of the present application can provide a computer program product to realize, and the instructions in the computer program product are executed by the processor of the electronic device, so that the electronic device can realize any one of the water supply site intelligent control methods in the above-mentioned embodiments.

[0225] It is to be understood that the application is not limited to particular configurations and processes described herein and shown in the drawings. For simplicity, detailed descriptions of known methods and apparatuses are omitted so as not to obscure the disclosure. In the above-described embodiments, several specific steps are described and illustrated as examples. However, the methods process of the present application is not limited to the steps described and illustrated, as one of skill in the art will understand that various changes, modifications and additions can be made thereto without departing from the spirit of the present application, or varying the order of the steps.

[0226] The functional blocks shown in the above block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, and the like. When implemented in software, the elements of the present application are program or code segments that are used to perform the required tasks. The program or code segments can be stored in a machine-readable medium, or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. A "machine-readable medium" includes any medium that can store or transport information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. The code segments can be downloaded via computer networks such as the Internet, intranets, and the like.

[0227] It is also to be understood that the example embodiments mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the steps described above, that is, the steps can be performed in the order mentioned in the embodiments, or in an order different from the embodiments, or several steps can be performed simultaneously.

[0228] It is to be understood that the application is not limited to particular configurations and processes described herein and shown in the drawings. For simplicity, detailed descriptions of known methods and apparatuses are omitted so as not to obscure the disclosure. In the above-described embodiments, several specific steps are described and illustrated as examples. However, the methods process of the present application is not limited to the steps described and illustrated, as one of skill in the art will understand that various changes, modifications and additions can be made thereto without departing from the spirit of the present application, or varying the order of the steps.

[0229] The functions noted in the description of the structural block diagrams above can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, and the like. When implemented in software, the elements of the present application are program or code segments that are used to perform the required tasks. The program or code segments can be stored in a machine-readable medium, or transmitted through a data signal carried in a carrier wave over a transmission medium or communication link. A "machine-readable medium" includes any medium that can store or transport information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. The code segments can be downloaded via computer networks such as the Internet, intranets, and the like.

[0230] It is also important to note that the examples mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the steps mentioned above, that is, the steps can be performed in the order mentioned in the examples, or in an order different from the examples, or several steps can be performed simultaneously.

[0231] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer program instructions can also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other processing device to operate in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks. The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer program instructions can also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other processing device to operate in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function / act specified in the flowchart and / or block diagram block or blocks.

[0232] The above merely describes a specific implementation of the present application. Those skilled in the art can clearly understand the specific working processes of the system, modules and units described above for the convenience and brevity of description, and can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein again. It should be understood that the protection scope of the present application is not limited to this, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be covered within the protection scope of the present application.

Claims

1. A method for intelligent control of a water supply site, characterized by, The method comprises the following steps: acquiring acoustic environment data of a plurality of sensing nodes, the sensing nodes being arranged on a water supply pipe network, the acoustic environment data being used to monitor the operating state of the water supply pipe network; performing anomaly identification on the acoustic environment data to obtain an identification result; in a case where the identification result includes an abnormal signal, determining a first leakage interval according to the abnormal signal of the plurality of sensing nodes, the first leakage interval including a distance interval between two adjacent target sensing nodes; performing dispersion characteristic analysis on target environment data of the target sensing nodes to obtain a second leakage position; generating a control strategy of the water supply pipe network where the second leakage position is located.

2. The method of claim 1, wherein, The method of determining the first leakage interval according to the abnormal signal of the plurality of sensing nodes comprises the following steps: acquiring a first duration corresponding to the abnormal signal; in a case where the first duration is less than a preset time window, determining a leakage event of the water supply pipe network; acquiring at least three sensor positions corresponding to the leakage event and a corresponding first timestamp of the abnormal signal transmitted at each of the sensor positions; calculating a time difference of the abnormal signal based on the first timestamp; determining the first leakage interval by using a preset hyperbolic equation, the time difference and a preset sound wave propagation speed.

3. The method of claim 2, wherein, The method of determining the first leakage interval by using the preset hyperbolic equation, the time difference and the preset sound wave propagation speed comprises the following steps: determining a distance difference based on the time difference and the preset sound wave propagation speed, the distance difference being used to represent the distance between a leakage point and an adjacent sensor, the preset sound wave propagation speed being used to represent the propagation speed of sound speed under different pipe parameters; determining an intersection point according to a plurality of preset hyperbolic equations; determining the first leakage interval based on the intersection point.

4. The method according to any one of claims 1 to 3, characterized in that, After the first leakage interval is determined by using the preset hyperbolic equation, the time difference and the preset sound wave propagation speed, the method further comprises the following steps: acquiring a deviation of each of the sensors from a preset standard time, a signal-to-noise ratio, a model fitting residual agreement degree, a sensor consistency parameter and a topology rationality score, wherein the deviation is used to represent the synchronization accuracy of the clock of the sensor participating in positioning, the signal-to-noise ratio is used to represent the signal-to-noise ratio of the sensor participating in positioning in the leakage characteristic frequency band, the model fitting residual agreement degree is used to represent the agreement degree between the theoretical model and the measured data, the sensor consistency parameter is used to represent the consistency of the events reported by different sensors in the characteristics, and the topology rationality score is used to represent the physical rationality of the leakage point; weighting and summing the deviation, the signal-to-noise ratio, the model fitting residual agreement degree, the sensor consistency parameter and the topology rationality score according to a preset weight ratio to obtain a confidence score; generating a confidence strategy based on the confidence score and a preset confidence level, the confidence strategy being used to represent an action suggestion.

5. The method of claim 4, wherein, The method of performing dispersion characteristic analysis on the target environment data of the target sensing nodes to obtain the second leakage position comprises the following steps: performing time-frequency transformation on target acoustic environment data to obtain a time-frequency spectrum, the target acoustic environment data being acoustic environment data transmitted by a target sensor on the target sensing node; In the time-frequency spectrogram, a pipe propagation theory curve is calculated based on a preset physical propagation model; An actual propagation theory curve is determined based on a preset actual dispersion relation; A second leakage position is determined based on the pipe propagation theory curve and the actual propagation theory curve by using a preset matching algorithm.

6. The method of claim 5, wherein, The determination of the actual propagation theory curve based on the preset actual dispersion relation comprises: The target acoustic environment data is filtered in narrow bands to obtain a plurality of single-frequency components; For each single-frequency component, a phase angle of each target acoustic sensor is calculated; A phase difference is determined based on a difference between the phase angles; A wave number difference is determined based on the preset actual dispersion relation and the phase difference; A phase velocity is determined based on the wave number difference; The actual propagation theory curve is plotted based on the phase velocity.

7. The method of claim 1, wherein, The generation of a control strategy of a water supply network in which the second leakage position is located comprises: A network topology map of the water supply network is obtained; A digital twin map is constructed based on the network topology map; In the digital twin map, a connected pipe network and a water supply site corresponding to the second leakage position are searched; A leakage amount is estimated based on the connected pipe network and the water supply site; A valve start-stop strategy of the water supply network is generated based on the leakage amount and the connected pipe network.

8. A water supply site intelligent control device, characterized by, The device comprises: An acquisition module configured to acquire acoustic environment data of a plurality of sensor nodes, the sensor nodes being arranged on a water supply network, the acoustic environment data being used to monitor an operating state of the water supply network; An anomaly identification module configured to perform anomaly identification on the acoustic environment data to obtain an identification result; A determination module configured to, in a case where the identification result includes an abnormal signal, determine a first leakage interval based on the abnormal signal of the plurality of sensor nodes, the first leakage interval including a distance interval between two adjacent target sensor nodes; An analysis module configured to perform dispersion characteristic analysis on target environment data of the target sensor nodes to obtain a second leakage position; A generation module configured to generate a control strategy of a water supply network in which the second leakage position is located.

9. A water supply site intelligent control system, characterized by, Comprise: A water supply network; A sensor arranged on the water supply network; A cloud platform arranged on a water supply site, and the sensor is in network connection with the cloud platform, and the cloud platform is used to execute the water supply site intelligent control method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium has computer program instructions stored thereon, and the computer program instructions are executed by a processor to implement the water supply site intelligent control method of any one of claims 1-7.

Images