A method for predicting the critical pressure of urban pipe networks based on data modeling

Abstract

The present invention discloses a method for predicting the critical pressure of urban pipe networks based on data modeling, belonging to the technical field of urban management. Specifically, it includes: establishing a mapping model between the water flow state of the pipe network and the time series of pressure conduction to predict the expected time for the pressure fluctuation to be conducted to a specified pipe network node; maintaining the standard data acquisition frequency of the target node before the pressure fluctuation reaches the target node; activating the enhanced acquisition mode of the target node when the predicted remaining conduction time is less than the set threshold; adaptively adjusting the frequency increase multiple of the enhanced acquisition mode according to the weight level of the pipe section where the target node is located and the amplitude level of the predicted pressure fluctuation; after the pressure fluctuation reaches the target node, correcting the conduction rate parameter in the pressure conduction time series mapping model based on the high-density pressure data obtained in the enhanced mode; the present invention realizes the dynamic adjustment of the monitoring of pipe network pressure data.

Description

Technical Field

[0001] The present invention relates to the technical field of urban management, and particularly to a method for predicting the critical pressure of urban pipe networks based on data modeling. Background Art

[0002] As an important part of urban infrastructure, urban pipe networks undertake the crucial task of delivering water resources to urban residents and various enterprises. With the acceleration of the urbanization process, the urban scale is constantly expanding, and the coverage and complexity of urban pipe networks are also increasing day by day. The stable operation of the pipe network system is crucial for ensuring the normal production and living order of the city and promoting the sustainable development of the economic society. Once the pressure in the pipe network is abnormal, a series of problems such as insufficient water supply, pipe rupture, and water quality pollution may be triggered, which will not only bring great inconvenience to the daily life of residents, but also cause huge economic losses and social impacts. Therefore, effective monitoring and prediction of urban pipe network pressure have important practical significance.

[0003] Currently, in the field of urban pipe network pressure prediction, there are already some related technologies and methods. Some technologies establish simple mathematical models to describe the relationship between water flow and pressure in the pipe network, and make a preliminary prediction of future pressure changes based on historical data. There are also some technologies that use sensors to monitor the pressure in the pipe network in real time and issue an alarm in a timely manner when the pressure fluctuates. In addition, some researchers have tried to predict the conduction of pressure fluctuations in the pipe network by analyzing the pipe network topology and water flow state.

[0004] In terms of data acquisition, the current pipe network mathematical models mostly adopt a fixed data acquisition frequency to periodically monitor the pressure in the pipe network. There are also some technologies that use sensors to obtain the pressure information in the pipe network in real time, but lack flexibility in adjusting the data acquisition frequency. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for predicting the critical pressure of urban pipe networks based on data modeling, and solve the following technical problems:

[0006] The current pipe network mathematical models lack flexibility in adjusting data acquisition.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A method for predicting the critical pressure of urban pipe networks based on data modeling includes the following steps:

[0009] Establish a mapping model between the water flow state of the pipe network and the time sequence of pressure conduction, and predict the expected time for pressure fluctuations to be conducted to a specified pipe network node according to the real-time water flow direction, velocity, and valve opening and closing states;

[0010] Before the pressure fluctuation reaches the target node, maintain the standard data acquisition frequency of the target node; when the predicted remaining conduction time is less than the set threshold, activate the enhanced acquisition mode of the target node and increase the acquisition frequency of the pressure sensor to a preset multiple of the standard data acquisition frequency;

[0011] According to the weight level of the pipe section where the target node is located and the amplitude level of the predicted pressure fluctuation, adaptively adjust the frequency increase multiple of the enhanced acquisition mode;

[0012] After the pressure fluctuation reaches the target node, based on the high-density pressure data obtained in the enhanced mode, correct the conduction rate parameter in the pressure conduction timing mapping model.

[0013] As a further solution of the present invention: the establishment of the mapping model includes:

[0014] Mark all valve positions and water flow detection points in the three-dimensional pipe network model, obtain the water flow direction scalar and velocity vector of each pipe section in real time through the water flow sensor array, and convert the water flow direction scalar into a pressure conduction path direction indication signal in the pipe network topology; construct a pressure wave speed calculation network with valves as control nodes and pipe sections as conduction paths, associate the valve opening and closing actions and water flow mutation events as the trigger sources of pressure conduction, and establish a pressure wave speed reference parameter library including pipe material type, pipe diameter size and service life for each pipe section in the pressure wave speed calculation network; according to the dynamic connection relationship of the pipe network topology, update the node-to-node correlation of the pressure conduction path in real time to ensure that when the valve state changes or the water flow direction changes, the pressure wave speed calculation network automatically remaps the logical link of the conduction path.

[0015] As a further solution of the present invention: the prediction process of the pressure fluctuation conduction time is as follows:

[0016] Determine the main path of pressure conduction according to the current water flow direction, and sequentially mark the pipe network nodes that may be affected downstream along the main path; based on the pipe material type, pipe diameter size and service life data stored in the pressure wave speed reference model, calculate the theoretical conduction speed of the pressure wave under no interference conditions, and generate the theoretical conduction time baseline value of each pipe section; combine the real-time obtained branch flow split ratio data, calculate the attenuation amount of the main path pressure wave speed caused by branch flow split, and add it to the theoretical conduction time baseline value; at the same time, call the wall state parameters uploaded by the pipe section corrosion degree detection device, and dynamically correct the theoretical conduction time baseline value according to the influence law of the corrosion degree on the pressure wave speed, and finally generate the conduction time prediction result including environmental interference factors.

[0017] As a further solution of the present invention: the activation process of the enhanced acquisition mode includes:

[0018] Set multiple warning stages in the pressure conduction timing prediction model, where each warning stage corresponds to a different remaining conduction time interval and acquisition frequency adjustment strategy; when the predicted remaining conduction time enters the first warning stage, trigger the pressure sensor of the target node to start the medium-frequency acquisition mode, in which the sensor acquisition frequency is increased to the set first multiple of the normal mode, and the pre-analysis function of pressure fluctuation characteristics is enabled; when the remaining conduction time enters the second warning stage, switch to the high-frequency acquisition mode, the sensor acquisition frequency is increased to the set second multiple of the normal mode, and at the same time start the multi-sensor synchronous calibration mechanism to eliminate single-point data errors; after the pressure fluctuation actually reaches the target node, continuously maintain the high-frequency acquisition mode until the pressure data fluctuation amplitude drops below the preset steady-state threshold, and then automatically restore the normal acquisition frequency.

[0019] As a further solution of the present invention: the process of setting the pipe section weight level is as follows:

[0020] Divide the basic weight coefficient according to the level of the pipe section in the pipe network topology. Among them, the main pipeline connects the core water supply facilities and the regional distribution nodes, and is given the highest basic weight; the secondary pipeline connects the regional distribution nodes and the secondary user clusters, and is given the medium basic weight; the branch pipeline connects the end user nodes and is given the lowest basic weight; superimpose the weight correction value generated by the user density data in the service area on the basic weight coefficient. The user density is comprehensively calculated by the number of terminal water metering devices accessing the pipe section and the historical peak water consumption; further load the risk weighting factor in the historical leakage event database of the pipe section, and the risk weighting factor is determined according to the event frequency and severity of the pipe section with leakage or repair records within the set time period.

[0021] As a further solution of the present invention: the process of classifying the pressure fluctuation amplitude is as follows:

[0022] Obtain the pressure-bearing design value parameter library of the target pipe section, and divide the ratio of the current predicted pressure fluctuation peak value to the pressure-bearing design value into multiple pressure level intervals, each interval corresponding to a differentiated enhanced acquisition strategy; for low-level pressure fluctuations, only trigger the linear frequency increase strategy of the target node, that is, the acquisition frequency increases in a fixed proportion and the data storage uses the normal compression algorithm; for medium-level pressure fluctuations, synchronously trigger the exponential frequency increase strategy and the auxiliary monitoring mode of adjacent nodes. While the acquisition frequency of the target node is doubled, wake up the pressure sensors of adjacent nodes for auxiliary data verification; for high-level pressure fluctuations, on the basis of exponentially increasing the acquisition frequency of the target node, forcefully activate the monitoring devices of all associated branch nodes in the pipe network system to form a radial collaborative monitoring network centered on the target node, and cross-verify by integrating the pressure waveforms of multiple nodes in real time through the data bus.

[0023] As a further solution of the present invention, the process of dynamically correcting the conduction rate parameter in the pressure conduction timing prediction model is as follows:

[0024] In the enhanced acquisition mode, extract the waveform characteristics of the pressure rising edge recorded by the pressure sensor, including the wave crest arrival time, slope change trend, and oscillation decay period; perform time-domain alignment comparison between the measured waveform and the preset waveform propagation template in the prediction model, and calculate the deviation indexes in three dimensions: the wave crest arrival time difference, waveform shape similarity, and energy decay rate between the two; when the deviation in any dimension exceeds the corresponding fault tolerance threshold, automatically trigger the conduction rate parameter optimization program, and reverse-correct the conduction efficiency parameter of the corresponding pipe segment in the pressure wave speed reference model according to the deviation direction; after completing the parameter update, recalculate the remaining conduction time of all downstream nodes, and prompt the prediction result change information through the visualization interface. At the same time, synchronize the corrected parameters to the historical database for subsequent event analysis and call.

[0025] As a further solution of the present invention, if the actual pressure fluctuation arrival time of the target node in the enhanced acquisition mode is earlier than the predicted time, start the reverse conduction path tracing program, and reverse-search for possible abnormal conduction paths along the pressure wave arrival direction in the three-dimensional pipe network model; call the pipe segment connection relationship database during the search process to identify all hidden conduction channels that are physically connected but not included in the current main path prediction; for the discovered hidden channels, extract their pipe segment attribute data and load them into the pressure wave speed calculation network, and add corresponding conduction parameter calculation branches; after completing the path update, run the pressure conduction timing prediction model again, and add the path characteristics and parameter correction records of the hidden channels to the abnormal event knowledge base.

[0026] The beneficial effects of the present invention:

[0027] By establishing a mapping model between the water flow state in the pipe network and the pressure conduction time sequence, and combining the real-time water flow direction, velocity, and the start / stop state of valves, the present invention can accurately predict the expected time when the pressure fluctuation is conducted to a specified pipe network node, solving the problem of large prediction deviation in the prior art due to insufficient consideration of dynamic factors. In terms of data collection, the standard collection frequency is maintained before the pressure fluctuation reaches the target node. When the predicted remaining conduction time is less than the set threshold, the enhanced collection mode is activated, and the frequency increase multiple is adaptively adjusted according to the pipe segment weight level and the pressure fluctuation amplitude level, avoiding the problems of data redundancy or insufficient collection caused by a fixed collection frequency, and enabling timely acquisition of detailed pressure data for monitoring the key pipe network conditions. At the same time, after the pressure fluctuation reaches the target node, the conduction rate parameter in the pressure conduction time sequence mapping model is corrected based on the high-density pressure data in the enhanced mode, enabling the use of real-time data to optimize the prediction model, improving the adaptability and accuracy of the model, and effectively coping with the complex and changeable pipe network operation environment. In addition, when the actual pressure fluctuation arrival time is earlier than the predicted time, a reverse conduction path tracing program is started, which can discover hidden conduction channels and update the prediction model, further improving the accuracy and reliability of pressure conduction prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The present invention will be further described below with reference to the accompanying drawings.

[0029] Figure 1 is a schematic flow chart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0031] Please refer to Figure 1 shown. The present invention is a method for predicting the critical pressure of an urban pipe network based on data modeling, including the following steps:

[0032] First, establish a mapping model between the water flow state in the pipe network and the pressure conduction time sequence. In the urban pipe network system, the water flow state is in dynamic change, which is comprehensively affected by various factors such as the real-time water flow direction, velocity, and the opening and closing states of valves. To accurately predict the expected time for pressure fluctuations to reach a specified pipe network node, these factors need to be comprehensively considered. By constructing a mapping model, the water flow state is associated with the pressure conduction time sequence, and their internal relationship is described in the form of a mathematical model. In the process of model establishment, relevant knowledge such as the pipe network topology structure and the principles of water flow dynamics will be used, combined with the data of water flow direction, velocity, and valve states collected in real time, to achieve accurate prediction of the pressure fluctuation conduction time.

[0033] Secondly, when the pressure fluctuation has not reached the target node, maintain the standard data acquisition frequency of the target node. The standard data acquisition frequency is preset according to the normal operation conditions of the pipe network and the data acquisition requirements, and can meet the basic monitoring requirements for the pipe network pressure data under normal circumstances. When it is predicted through the mapping model that the remaining time for pressure fluctuation conduction is less than the set threshold, it means that the pressure fluctuation is about to reach the target node. At this time, activate the enhanced acquisition mode of the target node and increase the acquisition frequency of the pressure sensor to a preset multiple of the standard data acquisition frequency. The purpose of the enhanced acquisition mode is to obtain denser and more detailed pressure data during the critical period of pressure fluctuation, so as to analyze the pressure change situation more accurately.

[0034] Then, adaptively adjust the frequency increase multiple of the enhanced acquisition mode according to the weight level of the pipe section where the target node is located and the amplitude level of the predicted pressure fluctuation. The weight level of the pipe section is determined by comprehensively considering various factors such as the level of the pipe section in the pipe network topology structure, the user density in the service area, and the historical leakage events of the pipe section, reflecting the importance of the pipe section in the entire pipe network system. The amplitude level of the pressure fluctuation is divided according to the ratio of the bearing design value of the target pipe section to the current predicted peak value of the pressure fluctuation, reflecting the severity of the pressure fluctuation. According to these two levels, dynamically adjust the frequency increase multiple in the enhanced acquisition mode, so that the data acquisition frequency can be flexibly adjusted according to the actual situation, ensuring that sufficient data can be obtained in critical pipe sections and high-amplitude pressure fluctuations, while avoiding unnecessary data acquisition, and improving the efficiency and pertinence of data acquisition.

[0035] Finally, when the pressure fluctuation reaches the target node, based on the high-density pressure data obtained in the enhanced mode, the conduction rate parameter in the pressure conduction timing mapping model is corrected. Due to the complex and variable actual pipe network operation environment and many uncertain factors, there may be deviations between the conduction rate parameter in the mapping model and the actual situation. By analyzing the high-density pressure data obtained in the enhanced acquisition mode, the actual situation of pressure conduction can be understood more accurately. By comparing and analyzing these actual data with the model prediction results, the deviation of the conduction rate parameter is found and corrected. The corrected model can more accurately reflect the actual situation of pressure conduction in the pipe network, thereby improving the accuracy and reliability of subsequent pressure fluctuation prediction.

[0036] In a preferred embodiment of the present invention, regarding the establishment of the mapping model, the specific operations are as follows:

[0037] In the constructed three-dimensional pipe network model, all valve positions and water flow detection points are accurately marked. Using the water flow sensor array, the water flow direction scalar and velocity vector of each pipe section are obtained in real time and accurately. The obtained water flow direction scalar is converted into a pressure conduction path direction indication signal applicable to the pipe network topological structure according to a specific conversion algorithm, and this signal can intuitively and clearly indicate the direction of pressure conduction. Furthermore, a pressure wave speed calculation network with valves as control nodes and pipe sections as conduction paths is constructed. In this network system, the opening and closing actions of valves and water flow mutation events are set as the trigger sources of pressure conduction through logical association. And for each pipe section in the pressure wave speed calculation network, a pressure wave speed reference parameter library is specifically established, which stores in detail key information such as pipe material type, pipe diameter size, and service life. As the dynamic connection relationship of the pipe network topological structure changes during the operation of the pipe network, based on the real-time monitored information, the node-to-node correlation of the pressure conduction path is updated in a timely manner. Ensure that when the valve state changes or the water flow direction changes, the pressure wave speed calculation network can automatically and quickly remap the logical link of the conduction path, so as to ensure that the mapping model is always closely fitted with the actual operation of the pipe network and achieve an accurate simulation of the pressure conduction path.

[0038] In another preferred embodiment of the present invention, the specific steps of the prediction process of the pressure fluctuation conduction time are as follows:

[0039] First, according to the currently real-time monitored water flow direction, through the analysis of the pipe network topology and the principles of water flow dynamics, accurately determine the main path of pressure conduction. Along the determined main path, in accordance with certain rules, sequentially label the pipe network nodes that may be affected by pressure fluctuations in the downstream direction. Then, based on the data such as pipe material type, pipe diameter size, and service life pre-stored in the pressure wave velocity reference model, use the corresponding calculation formulas to calculate the theoretical conduction velocity of the pressure wave under the ideal condition of no interference. According to this theoretical conduction velocity, further generate the theoretical conduction time baseline value for each pipe segment. At the same time, obtain the branch flow split ratio data in the pipe network in real time, and according to the principles of water flow dynamics, calculate the attenuation amount of the pressure wave velocity of the main path caused by branch flow splitting, and add this attenuation amount to the previously generated theoretical conduction time baseline value. In addition, call the pipe wall state parameters uploaded in real time by the pipe segment corrosion degree detection device, and combine the existing research results on the influence law of corrosion degree on the pressure wave velocity to dynamically correct the theoretical conduction time baseline value. Considering the above various factors comprehensively, finally generate a comprehensive and accurate conduction time prediction result including various environmental interference factors, providing reliable data support for subsequent pipe network pressure monitoring and analysis.

[0040] In another preferred embodiment of the present invention, regarding the activation process of the enhanced acquisition mode, it is as follows:

[0041] In the pressure conduction timing prediction model, according to the characteristics of the pressure fluctuation conduction time and the requirements of data acquisition, scientifically and reasonably set multiple warning stages. Each warning stage corresponds to a different remaining conduction time interval, and a special acquisition frequency adjustment strategy is formulated for each interval. When the remaining conduction time calculated by the prediction model enters the first warning stage, the system will automatically trigger the pressure sensor of the target node to start the medium-frequency acquisition mode. In this medium-frequency acquisition mode, the acquisition frequency of the sensor is increased according to the preset first magnification, which is significantly higher than the conventional mode and can obtain more pressure data. At the same time, turn on the pre-analysis function of pressure fluctuation characteristics to conduct a preliminary characteristic analysis of the upcoming pressure fluctuations and provide basic data for subsequent processing.

[0042] When the remaining conduction time further advances and enters the second warning stage, the system will automatically switch the acquisition mode of the pressure sensor to the high-frequency acquisition mode. At this time, the acquisition frequency of the sensor is increased according to the set second magnification, further greatly improving the data acquisition frequency to meet the requirements for data accuracy when the pressure fluctuation is approaching. And, when switching to the high-frequency acquisition mode, start the multi-sensor synchronous calibration mechanism. Through this mechanism, synchronously calibrate the data of multiple sensors, effectively eliminate the possible errors of single-point data, and ensure the accuracy and reliability of the acquired data.

[0043] After the pressure fluctuation actually reaches the target node, in order to comprehensively and accurately monitor the entire process of the pressure fluctuation, the system will continuously maintain a high-frequency acquisition mode. It will continue until the fluctuation amplitude of the pressure data drops below a preset steady-state threshold, indicating that the pressure fluctuation has tended to be stable. At this time, the system will automatically return to the normal acquisition frequency, thereby reasonably controlling the resource consumption of data acquisition while ensuring the data quality.

[0044] In another preferred embodiment of the present invention, regarding the setting process of the pipe segment weight level, the specific steps are as follows:

[0045] First, according to the hierarchical relationship of the pipe segments in the pipe network topology, the basic weight coefficients of the pipe segments are divided. Among them, the main pipeline, as the key part connecting the core water supply facilities and the regional distribution nodes, undertakes the main water conveyance task in the entire pipe network system, and its importance is self-evident. Therefore, it is given the highest basic weight. The secondary pipeline connects the regional distribution nodes and the secondary user clusters, playing a connecting role in the pipe network system, and is given a medium basic weight. The branch pipeline mainly connects the end user nodes, and relatively speaking, its importance in the pipe network is lower, and it is given the lowest basic weight.

[0046] Next, on the basis of the basic weight coefficient, a weight correction value generated from the user density data in the service area is superimposed. The user density is comprehensively calculated based on the number of terminal water metering devices connected to the pipe segment and the historical peak water consumption. The higher the user density, the more users the pipe segment serves and the greater the influence range on users. Therefore, the corresponding weight correction value is also higher.

[0047] Finally, a risk weighting factor in the historical leakage event database of the pipe segment is further loaded. This risk weighting factor is determined according to the frequency and severity of leakage or repair records of the pipe segments within a set time period. For the pipe segments with a higher frequency and greater severity of leakage or repair events within the set time period, a higher risk weighting factor is given to increase their weight level; conversely, a lower risk weighting factor is given. Through the above steps, a pipe segment weight level setting system that comprehensively considers multiple factors such as the pipe network topology, user influence range, and risk history is finally formed.

[0048] In another preferred embodiment of the present invention, regarding the classification process of the pressure fluctuation amplitude, the specific operation is as follows:

[0049] First, obtain the pressure-bearing design value parameter library of the target pipe segment, which stores key parameters such as the pressure-bearing design value of the target pipe segment. Then, compare the currently predicted peak pressure fluctuation with the pressure-bearing design value and calculate their ratio. According to the magnitude of this ratio, divide it into multiple different pressure level intervals. Each pressure level interval corresponds to a differentiated enhanced acquisition strategy to meet the data acquisition requirements under different degrees of pressure fluctuation.

[0050] For low-level pressure fluctuations, that is, when the ratio is in a lower interval, only trigger the linear frequency increase strategy of the target node. Under this strategy, the acquisition frequency increases at a fixed ratio, and at the same time, conventional compression algorithms are used for data storage, minimizing the pressure of data storage while ensuring that a certain amount of pressure data can be obtained.

[0051] For medium-level pressure fluctuations, when the ratio is in a medium interval, simultaneously trigger the exponential frequency increase strategy and the auxiliary monitoring mode of adjacent nodes. While the acquisition frequency of the target node doubles exponentially, wake up the pressure sensors of adjacent nodes to make them enter the auxiliary monitoring state and assist in verifying the pressure data of the target node, thereby improving the accuracy and reliability of the data.

[0052] For high-level pressure fluctuations, when the ratio is in a higher interval, on the basis of exponentially increasing the acquisition frequency of the target node, forcibly activate the monitoring devices of all associated branch nodes in the pipe network system. These devices jointly form a radial collaborative monitoring network centered on the target node, and in real time, integrate the pressure waveform data of multiple nodes through a data bus and perform cross-verification to comprehensively and accurately monitor the situation of high-level pressure fluctuations and provide strong data support for the safe operation of the pipe network.

[0053] In another preferred embodiment of the present invention, the process of dynamically correcting the conduction rate parameter of the pressure conduction timing prediction model is as follows:

[0054] After the enhanced acquisition mode is turned on, extract the characteristic information of the pressure rising edge waveform from the data recorded by the pressure sensor. These characteristics include the wave peak arrival time, that is, the moment when the pressure rises to the peak; the slope change trend, reflecting the speed of pressure rise; and the oscillation decay period, that is, the time period when the pressure fluctuation gradually weakens. Then, align and compare the actually measured pressure waveform with the waveform propagation template preset in the prediction model in the time domain. During the comparison process, calculate the deviation indexes in three key dimensions: the wave peak arrival time difference, reflecting the difference between the actually measured and predicted wave peak arrival moments; the waveform shape similarity, measuring the similarity in shape between the actually measured waveform and the template waveform; and the energy decay rate deviation, reflecting the difference in the pressure energy decay speed.

[0055] Once the deviation value in any dimension exceeds the corresponding fault tolerance threshold, the system will automatically trigger the conduction rate parameter optimization program. This program will reverse-correct the conduction efficiency parameters of the corresponding pipe segments in the pressure wave speed reference model according to the direction of the deviation. For example, if the measured wave crest arrival time is earlier than the predicted time, it indicates that the conduction rate may be faster than the model estimate. In this case, the conduction efficiency parameter will be appropriately increased; otherwise, it will be decreased.

[0056] After completing the parameter update operation, recalculate the remaining conduction time for all downstream nodes. At the same time, through the visualization interface, prompt the relevant personnel with the change information of the prediction results to facilitate their timely understanding of the situation. Also, synchronize the corrected parameters to the historical database for subsequent analysis and reference in case of similar events.

[0057] In a preferred case of this embodiment, if, in the enhanced acquisition mode, the actual pressure fluctuation arrival time at the target node is earlier than the predicted time, then the reverse conduction path tracing program will be started. This program will perform a reverse search in the 3D pipe network model along the direction of the pressure wave arrival to find possible abnormal conduction paths. During the search, call the pipe segment connection relationship database to identify all hidden conduction channels that are physically connected but not included in the current main path prediction scope.

[0058] For the hidden channels discovered during the search, extract the attribute data of their pipe segments, such as pipe material type, pipe diameter size, service life, etc., and load this data into the pressure wave speed calculation network. At the same time, add a conduction parameter calculation branch corresponding to this hidden channel in the network to accurately calculate the conduction situation of the pressure wave in this channel.

[0059] After completing the path update, run the pressure conduction timing prediction model again so that the model can take into account the newly discovered hidden channels, thereby obtaining a more accurate pressure conduction prediction result. Finally, add the path characteristics of the hidden channels and the relevant records of parameter correction to the abnormal event knowledge base to provide experience and data support for subsequent handling of similar abnormal situations.

[0060] The above has described a detailed implementation example of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the present invention application should still fall within the patent coverage scope of the present invention.

Claims

1. A method for predicting the critical pressure of urban pipe networks based on data modeling, characterized in that, The steps include: Establish a mapping model between the water flow state of the pipe network and the pressure conduction time sequence, and label it as the pressure conduction time sequence mapping model. Predict the expected time for the pressure fluctuation to be conducted to the specified pipe network node according to the real-time water flow direction, velocity, and the opening and closing states of valves. Before the pressure fluctuation reaches the target node, maintain the standard data acquisition frequency of the target node. When the mapping model predicts that the remaining time for the pressure fluctuation conduction is less than the set threshold, activate the enhanced acquisition mode of the target node, and increase the acquisition frequency of the pressure sensor to a preset multiple of the standard data acquisition frequency. According to the weight level of the pipe section where the target node is located and the amplitude level of the predicted pressure fluctuation, adaptively adjust the frequency increase multiple of the enhanced acquisition mode. After the pressure fluctuation reaches the target node, based on the high-density pressure data obtained in the enhanced acquisition mode, correct the conduction rate parameter in the pressure conduction time sequence mapping model. The establishment of the mapping model includes: Mark all valve positions and water flow detection points in the three-dimensional model of the pipe network. Real-time obtain the water flow direction scalar and velocity vector of each pipe section through the water flow sensor array, and convert the water flow direction scalar into the pressure conduction path direction indication signal in the pipe network topology structure. Construct a pressure wave speed calculation network with valves as control nodes and pipe sections as conduction paths, associate the valve opening and closing actions and water flow mutation events as the trigger sources of pressure conduction, and establish a pressure wave speed reference parameter library including pipe material type, pipe diameter size, and service life for each pipe section in the pressure wave speed calculation network. According to the dynamic connection relationship of the pipe network topology structure, real-time update the node-to-node correlation of the pressure conduction path to ensure that when the valve state changes or the water flow direction changes, the pressure wave speed calculation network automatically remaps the logical link of the conduction path.

2. The urban pipe network critical pressure prediction method based on data modeling according to claim 1, wherein The prediction process of the pressure fluctuation conduction time is: Determine the main path of pressure conduction according to the current water flow direction, and sequentially label the pipe network nodes that may be affected downstream along the main path. Based on the pipe material type, pipe diameter size, and service life data stored in the pressure wave speed calculation network, calculate the theoretical conduction speed of the pressure wave under no interference conditions, and generate the theoretical conduction time baseline value for each pipe section. Combine the real-time obtained branch flow split ratio data, calculate the attenuation amount of the main path pressure wave speed caused by branch flow split, and add it to the theoretical conduction time baseline value. At the same time, call the wall state parameters uploaded by the pipe section corrosion degree detection device, and dynamically correct the theoretical conduction time baseline value according to the influence law of the corrosion degree on the pressure wave speed, and finally generate the conduction time prediction result including environmental interference factors.

3. A method for predicting the critical pressure of urban pipe networks based on data modeling according to claim 1, characterized in that, The activation process of the enhanced acquisition mode includes: Multiple warning stages are set in the pressure conduction timing mapping model, and each warning stage corresponds to a different remaining time interval and acquisition frequency adjustment strategy; when the remaining time of pressure fluctuation conduction enters the first warning stage, the pressure sensor of the target node is triggered to start the medium-frequency acquisition mode. In this mode, the sensor acquisition frequency is increased to the set first multiple of the normal mode, and the pressure fluctuation feature pre-analysis function is turned on; when the remaining time of pressure fluctuation conduction enters the second warning stage, it is switched to the high-frequency acquisition mode, and the sensor acquisition frequency is increased to the set second multiple of the normal mode, and the multi-sensor synchronous calibration mechanism is started at the same time to eliminate single-point data errors; after the pressure fluctuation actually reaches the target node, the high-frequency acquisition mode is maintained until the pressure data fluctuation amplitude drops below the preset steady-state threshold, and then the normal acquisition frequency is automatically restored.

4. A method for predicting the critical pressure of urban pipe networks based on data modeling according to claim 1, characterized in that, The process of setting the pipe segment weight level is as follows: The basic weight coefficient is divided according to the level of the pipe section in the pipe network topology structure, where the main pipeline connects the core water supply facilities and the regional allocation node, and is assigned the highest basic weight; the secondary pipeline connects the regional allocation node and the secondary user cluster, and is assigned a medium basic weight; the branch pipeline connects the terminal user node, and is assigned the lowest basic weight; the weight correction value generated by the user density data in the service area is superimposed on the basic weight coefficient, and the user density is comprehensively calculated by the number of terminal water metering devices connected to the pipe section and the historical peak water consumption; the risk weighting factor in the historical leakage event database of the pipe section is further loaded, and the risk weighting factor is determined according to the frequency and severity of the event based on the pipe section with leakage or maintenance records within a set period of time.

5. A method for predicting the critical pressure of urban pipe networks based on data modeling according to claim 1, characterized in that The classification process of pressure fluctuation amplitude is: Obtain the pressure design value parameter library of the target pipe section, divide the ratio of the current predicted pressure fluctuation peak to the pressure design value into multiple pressure level intervals, and each interval corresponds to a differentiated enhanced acquisition strategy; for low-level pressure fluctuations, only the linear frequency increase strategy of the target node is triggered, that is, the acquisition frequency increases at a fixed ratio and the data storage adopts a conventional compression algorithm; For medium-level pressure fluctuations, the exponential frequency increase strategy and the auxiliary monitoring mode of adjacent nodes are triggered synchronously. While the acquisition frequency of the target node is doubled, the pressure sensors of the adjacent nodes are awakened for auxiliary data verification. For high-level pressure fluctuations, on the basis of exponentially increasing the acquisition frequency of the target node, the monitoring equipment of all related branch nodes in the pipeline system is forcibly activated to form a radial collaborative monitoring network centered on the target node, and the multi-node pressure waveforms are integrated in real time through the data bus for cross-verification.

6. The critical pressure prediction method for urban pipe networks based on data modeling according to claim 1, characterized in that The process of dynamically correcting the conduction velocity parameters in the pressure conduction timing mapping model is as follows: In the enhanced acquisition mode, the pressure rising edge waveform characteristics recorded by the pressure sensor are extracted, including the peak arrival time, slope change trend and oscillation attenuation period; Align the measured waveform with the preset waveform propagation template in the prediction model in the time domain, and calculate the deviation indexes of the two in three dimensions: the time difference of the peak arrival time, the waveform shape similarity, and the energy attenuation rate; when the deviation in any dimension exceeds the corresponding fault tolerance threshold, automatically trigger the conduction rate parameter optimization program, and reverse-correct the conduction efficiency parameters of the corresponding pipe segments in the pressure wave velocity calculation network according to the deviation direction; after completing the parameter update, recalculate the remaining time of the pressure fluctuation conduction at all downstream nodes, and prompt the prediction result change information through the visualization interface. At the same time, synchronize the corrected parameters to the historical database for subsequent event analysis and call.

7. A method for predicting the critical pressure of urban pipe networks based on data modeling according to claim 6, characterized in that, If the actual pressure fluctuation arrival time of the target node in the enhanced acquisition mode is earlier than the predicted time, start the reverse conduction path tracing program, and reverse-search for possible abnormal conduction paths along the pressure wave arrival direction in the 3D pipe network model; call the pipe segment connection relationship database during the search process to identify all hidden conduction channels that are physically connected but not included in the current main path prediction; for the discovered hidden conduction channels, extract their pipe segment attribute data and load them into the pressure wave velocity calculation network, and add corresponding conduction parameter calculation branches. After completing the path update, run the pressure conduction timing mapping model again, and add the path characteristics and parameter correction records of the hidden conduction channels to the abnormal event knowledge base.

Images