A time-segmented intelligent pressure regulation management method and system for secondary water supply

Abstract

This invention discloses a time-segmented intelligent pressure regulation management method and system for secondary water supply, belonging to the field of water supply management technology. Specifically, it includes: dividing a day into peak and off-peak water usage periods based on historical water flow data, and determining the start and end times of each period; locking the terminal pressure control point of the water supply system through hydraulic calculations and actual water supply pressure monitoring, and collecting the water supply pressure data of this point in real time; implementing a peak pressure boosting control strategy during peak water usage periods; analyzing historical water supply pressure data of the terminal pressure control point during off-peak water usage periods to set a safe pressure threshold for off-peak periods; sending a pressure command to the control system based on this threshold to control the output pressure of the water supply equipment according to the threshold; monitoring the water supply pressure of the terminal pressure control point in real time, triggering a pre-alarm and continuously recording pressure changes when the pressure is lower than the safe pressure threshold for off-peak periods; if the pre-alarm status continues, switching to the peak-period peak pressure boosting control strategy.

Description

Technical Field

[0001] This invention relates to the field of water supply management technology, specifically to a time-segmented intelligent pressure regulation management method and system for secondary water supply. Background Technology

[0002] In urban building and community water supply systems, secondary water supply systems play a crucial role in pressurizing and delivering municipal water to users. However, traditional secondary water supply systems have significant limitations in pressure control: to ensure stable water supply during peak water usage periods, the system often uses a fixed, higher pressure setting. This "one-size-fits-all" approach leads to water pressure far exceeding actual demand during off-peak hours, resulting in significant waste of pump energy and potentially increased pipeline wear and maintenance costs due to prolonged high-pressure operation. Furthermore, some systems lack real-time monitoring of pressure at the end-point control points, making it difficult to accurately detect changes in end-point water pressure, which can easily lead to unstable or insufficient pressure, affecting user comfort.

[0003] Energy-saving retrofits of traditional secondary water supply systems face numerous challenges: on the one hand, large-scale equipment replacement is not only costly but may also disrupt normal water supply; on the other hand, existing control strategies rely heavily on manual experience, making it difficult to dynamically adjust pressure based on water usage patterns, thus failing to balance water supply security and energy conservation goals. Against this backdrop, achieving precise time-of-use pressure regulation through intelligent means without adding expensive new equipment has become crucial for solving the high energy consumption and low efficiency problems of secondary water supply systems, and also provides a new technological path for energy-saving upgrades of urban water supply systems. Summary of the Invention

[0004] The purpose of this invention is to provide a time-segmented intelligent pressure regulation management method and system for secondary water supply, solving the following technical problems:

[0005] Large-scale equipment replacement is not only costly, but may also affect normal water supply. On the other hand, existing control strategies rely heavily on human experience, making it difficult to dynamically adjust pressure according to water usage patterns, and thus failing to balance water supply security and energy conservation goals.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] Firstly, a time-segmented intelligent pressure regulation management method for secondary water supply includes the following steps:

[0008] S1. Based on historical water flow data, the day is divided into peak water consumption period and low water consumption period, and the start and end time nodes of each period are determined.

[0009] S2. Through hydraulic calculations and actual water supply pressure monitoring, the pressure control point at the end of the water supply system is located, and the water supply pressure data at this point is collected in real time; the process of locating the pressure control point at the end of the water supply system is as follows:

[0010] S21. Construct a digital twin model of the water supply system;

[0011] S22. Based on the digital twin model, input historical typical working conditions covering water flow data in different time periods and seasons, carry out steady-state and transient hydraulic simulations through hydraulic calculation software, output the theoretical pressure values ​​of each node and generate the theoretical pressure field distribution of multiple working conditions, and mark the candidate node set with the lowest theoretical pressure under each working condition.

[0012] S23. Based on the distribution characteristics of candidate nodes in the theoretical pressure field, monitoring points are set up along the pipeline and at the user end.

[0013] S24. During typical water usage periods covering peak and off-peak periods, the digital twin model and dynamic monitoring network are run synchronously to collect theoretical pressure data and actual pressure data under the same time series. Error analysis is performed by calculating the deviation between theoretical and actual values, and the pipeline resistance coefficient and node flow distribution parameters in the model are adjusted until the deviation between the pressure distribution output by the model and the actual monitoring results is within the preset range.

[0014] S25. Based on the calibrated model and combined with the real-time pressure data of the dynamic monitoring network, extract the lowest pressure value, the duration of pressure below the preset basic threshold, and the pressure fluctuation amplitude of each node in the entire working cycle. Use a multi-feature weighted algorithm to comprehensively score all nodes, where the algorithm weight is set according to the priority of water supply safety, and the node with the lowest score is the pressure control point at the end of the water supply system.

[0015] S3. During peak water usage periods, implement peak pressure boosting control strategy;

[0016] S4. During the off-peak water usage period, analyze the historical water supply pressure data of the terminal pressure control point and set a safe pressure threshold for the off-peak period; send a pressure command to the control system according to the threshold and control the output pressure of the water supply equipment according to the threshold.

[0017] S5. Monitor the water supply pressure at the terminal pressure control point in real time. When the pressure is lower than the low-peak pressure safety threshold, trigger an alarm and continuously record pressure changes. If the alarm continues, switch to the peak-peak pressure boosting control strategy through the control system. After the water supply pressure at the terminal pressure control point returns to normal, automatically correct the low-peak pressure safety threshold for that period.

[0018] As a further aspect of the present invention: In step S1, the process of dividing a day into peak water consumption periods and low water consumption periods based on historical water flow data, and determining the start and end times of each period, is as follows:

[0019] S11. Collect raw water flow data for 30 consecutive days, convert it into a continuous time series with 15-minute time units, remove extreme outliers using box plot method, and fill in missing data segments using linear interpolation method;

[0020] S12. Calculate the flow rate value for each time unit, calculate the average flow rate within the window based on the 2-hour sliding window, and take the average of the 30-day data in the same time unit to generate the daily average flow rate distribution curve.

[0021] S13. Calculate the overall mean and standard deviation based on the daily average flow distribution curve, delineate the peak candidate intervals that are higher than the mean + 1.2 times the standard deviation and the low peak candidate intervals that are lower than the mean - 1.2 times the standard deviation, and adjust the standard deviation multiple iteratively so that the candidate intervals cover more than 90% of the significant fluctuations of the curve.

[0022] S14. Traverse the daily average traffic distribution curve, identify continuous peak and low peak candidate time unit clusters and mark them as preliminary time periods, and merge the same type of preliminary time periods with an interval of no more than 1 time unit.

[0023] S15. Calculate the frequency of occurrence of each preliminary time period that meets the corresponding traffic characteristics in multi-day data, retain stable time periods with a frequency of not less than 75%, and determine the time range of peak and off-peak periods by taking the moment when three consecutive time units meet the characteristics as the start and end nodes.

[0024] As a further aspect of the present invention: in step S23, the density of monitoring points in the candidate node set area is higher than that in other areas, and all monitoring points have real-time data transmission capabilities to collect actual operating pressure data of each node.

[0025] As a further aspect of the present invention: In step S3, the specific method for implementing the peak water usage peak period pressure boosting control strategy is as follows:

[0026] A fixed peak-period water supply pressure threshold is preset, and real-time pressure data of the water supply system is obtained through pressure monitoring. The real-time pressure data is compared with the peak-period water supply pressure threshold. If the real-time pressure is lower than the threshold, the output pressure is increased; if the real-time pressure is higher than the threshold, the output pressure is decreased. According to the comparison results of the real-time pressure data and the peak-period water supply pressure threshold, the corresponding adjustments are made to ensure that the water supply system pressure is always maintained within the peak-period water supply pressure threshold range.

[0027] As a further aspect of the present invention: In step S4, the process of setting a safe pressure threshold for the off-peak water usage period by analyzing historical water supply pressure data from the terminal pressure control point is as follows:

[0028] S41. Collect the off-peak water supply pressure data of the end pressure control points over the past 30 days, classify them by date, and form a historical water supply pressure dataset of the end pressure control points.

[0029] S42. Based on the determined start and end times of the off-peak period and combined with the historical water flow fluctuation characteristics, the off-peak period is further divided into several off-peak sub-periods; the duration of each off-peak sub-period is fixed, and the fluctuation range of water flow in each sub-period is within a preset range.

[0030] S43. For each off-peak period, extract the pressure characteristic parameters of the corresponding period from the historical water supply pressure dataset of the terminal pressure control point, including the average pressure, minimum pressure, standard deviation of pressure, and duration of continuous pressure stability within the sub-period.

[0031] S44. For each off-peak sub-period, the pressure benchmark value is calculated using the weighted average method:

[0032] S45. Analyze the distribution of the difference between the historical minimum pressure value and the pressure benchmark value for each off-peak period, and set a corresponding safety margin coefficient for each off-peak period in combination with the minimum service head requirement of the water supply system.

[0033] S46. For each off-peak sub-period, multiply its pressure benchmark value by the safety margin coefficient to obtain the off-peak pressure safety threshold for that sub-period; summarize the thresholds of all off-peak sub-periods to form a complete off-peak pressure safety threshold system.

[0034] As a further aspect of the present invention: step S44 further includes:

[0035] The average pressure value of a sub-period is calculated by weighting the duration of continuous and stable pressure within that sub-period. The weighting rule is that the average pressure value with a continuous and stable pressure duration longer than the preset duration is given a higher weight.

[0036] As a further aspect of the present invention: in step S5, the process of automatically correcting the low-peak pressure safety threshold for that period is as follows:

[0037] S51. When the water supply pressure at the terminal pressure control point rises above the original low-peak pressure safety threshold and remains stable for a continuous period of time, it is determined that the pressure has returned to normal.

[0038] S52. Extract the complete data sequence of this pre-alarm event, including: the duration of pressure below the threshold, the magnitude of pressure fluctuation, the rate of pressure recovery after switching to the peak period strategy, the average pressure and the duration of pressure stabilization during the first complete low-peak period after returning to normal.

[0039] S53. Using the average pressure of the first complete low-peak period after the return to normal as a benchmark, calculate the difference between it and the original low-peak pressure safety threshold to obtain the actual pressure deviation value; combine the maximum extent to which the pressure is lower than the threshold during this abnormal event to generate a deviation coefficient through a proportional algorithm.

[0040] S54. Based on the deviation coefficient, determine the dynamic correction factor and adjust the safety margin coefficient of the original low-peak period sub-period: if the actual pressure deviation value is positive, lower the safety margin coefficient; if it is negative, raise the safety margin coefficient. The adjustment range is determined by the dynamic correction factor.

[0041] S55. The adjusted safety margin factor and the original pressure reference value are used to recalculate and obtain the corrected pressure safety threshold for the sub-period of the off-peak period. The corrected threshold meets the constraint condition of not being lower than the minimum service head of the water supply system.

[0042] Secondly, a time-segmented intelligent pressure regulation management system for secondary water supply, used to implement the aforementioned time-segmented intelligent pressure regulation management method for secondary water supply, includes:

[0043] The water usage period segmentation module divides a day into peak and off-peak water usage periods based on historical water flow data, and determines the start and end times of each period.

[0044] The terminal pressure control point locking module locks the terminal pressure control point of the water supply system through hydraulic calculation and actual water supply pressure monitoring, and collects the water supply pressure data of that point in real time.

[0045] The peak-period booster control module is used to execute peak-period booster control strategies during peak water usage periods.

[0046] The off-peak pressure threshold setting module is used to analyze historical water supply pressure data from the terminal pressure control point during off-peak water usage periods, set a safe pressure threshold for off-peak periods, and send a pressure command to the control system based on the threshold to control the output pressure of the water supply equipment according to the threshold.

[0047] The terminal pressure monitoring and correction module is used to monitor the water supply pressure at the terminal pressure control point in real time. When the pressure is lower than the low-peak pressure safety threshold, a pre-alarm is triggered and pressure changes are continuously recorded. If the pre-alarm status continues, the control system switches to the peak-peak pressure boosting control strategy. After the water supply pressure at the terminal pressure control point returns to normal, the low-peak pressure safety threshold for that period is automatically corrected.

[0048] The beneficial effects of this invention are:

[0049] This invention effectively avoids the high costs and water supply interruption risks associated with large-scale equipment replacement by optimizing existing water supply systems to achieve energy-saving upgrades. Its core lies in dividing peak and off-peak periods based on historical water usage data and developing targeted pressure regulation strategies by combining real-time pressure monitoring at end-point pressure control points. No expensive new equipment is required; the system can achieve precise time-segmented pressure regulation based solely on data analysis and intelligent control logic optimization, building upon existing hardware. This upgrade model not only reduces initial investment but also avoids water supply fluctuations that may occur during equipment replacement, ensuring that energy-saving upgrades and normal water supply do not interfere with each other.

[0050] Meanwhile, this invention eliminates reliance on manual experience, achieving a balance between water supply safety and energy conservation through dynamic and intelligent regulation. On one hand, it automatically implements a pressurization strategy during peak periods to ensure stable water supply during peak water usage times; on the other hand, during off-peak periods, it sets safety thresholds based on historical data from end-point pressure control points, reducing pressure output according to actual demand to minimize energy consumption. More importantly, the real-time monitoring and automatic correction mechanism can quickly switch to a safety mode when pressure is abnormal, and dynamically optimize the thresholds after returning to normal, ensuring the system always adapts to changes in water usage patterns. This avoids the lag and errors of manual regulation while achieving a balance between safety and energy efficiency. Attached Figure Description

[0051] The invention will now be further described with reference to the accompanying drawings.

[0052] Figure 1 This is a flowchart illustrating a time-segmented intelligent pressure regulation management method for secondary water supply according to an embodiment of the present invention.

[0053] Figure 2 This is a schematic diagram of a time-segmented intelligent pressure regulation management system for secondary water supply according to an embodiment of the present invention. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] Example 1

[0056] Please see Figure 1 As shown, this invention is a time-segmented intelligent pressure regulation management method for secondary water supply, comprising:

[0057] S1. Based on historical water flow data, the day is divided into peak water consumption period and low water consumption period, and the start and end time nodes of each period are determined.

[0058] In step S1 of this embodiment, the process of dividing a day into peak water consumption periods and off-peak water consumption periods based on historical water flow data, and determining the start and end times of each period, is as follows:

[0059] Raw water flow data was collected for 30 consecutive days, continuously recording water flow information at every moment within those 30 days. This raw data was then converted into a continuous time series with 15-minute intervals. Specifically, each 24-hour day was evenly divided into 96 15-minute intervals. All flow data within each interval were then integrated to form the corresponding flow value, creating a continuous data sequence arranged chronologically. This was done to standardize the time granularity of the data, facilitating subsequent comparison and analysis of water usage patterns across different dates. Extreme outliers were removed using box plots. Box plots first determine the quartiles of the data. The interval between the upper and lower quartiles contains most of the normal data. Values ​​outside this interval are considered extreme outliers, which may be due to monitoring equipment malfunctions, sudden non-water-use factors, etc., and do not reflect the true water usage situation. Removing these outliers prevents them from interfering with the overall analysis results. Linear interpolation was used to fill in missing data segments.

[0060] The process involves calculating the flow rate for each time unit, statistically processing the raw flow rate data within each 15-minute time unit to obtain a representative flow rate for that time period, reflecting water usage within that 15 minutes. A 2-hour sliding window is used to calculate the average flow rate within that window. A 2-hour window contains eight 15-minute time units. The sliding window starts from the first time unit and moves forward one 15-minute time unit at a time to form a new window. The average flow rate for the eight time units within each window is calculated. This smooths out short-term flow fluctuations and more clearly shows water usage trends over a longer period. The 30-day data is then averaged using the same time units. For example, for each 15-minute time unit at the same location each day (e.g., 00:00-00:15), the average flow rate for that time unit over the 30 days is calculated. This method eliminates the influence of exceptional water usage on a single day, resulting in more general flow rate data. Arranging these averages calculated by time unit in chronological order generates a daily average flow rate distribution curve. This curve visually displays the changes in average water flow rate at different times of the day.

[0061] The overall mean and standard deviation are calculated based on the daily average flow distribution curve. The overall mean is the average of the flow rates over all 15-minute time units on the curve, representing the average water consumption level throughout the day. The standard deviation measures the degree to which these average flow rates deviate from the overall mean, reflecting the magnitude of fluctuations in water consumption throughout the day. Peak candidate intervals (above the mean + 1.2 times the standard deviation) and slack candidate intervals (below the mean - 1.2 times the standard deviation) are defined. When the flow rate is above the overall mean plus 1.2 times the standard deviation, it indicates that the flow rate during that time period is significantly higher than the average level, likely representing a peak period with concentrated water consumption. Conversely, when the flow rate is below the overall mean minus 1.2 times the standard deviation, it indicates that the flow rate during that time period is significantly lower than the average level, likely representing a slack period with lower water consumption. By iteratively adjusting the standard deviation multiple, the candidate interval is made to cover more than 90% of the significant fluctuations in the curve. Since the initial standard deviation of 1.2 times may not be able to cover most of the obvious flow fluctuations in the curve, this multiple needs to be continuously adjusted until the peak and trough candidate intervals can include more than 90% of the fluctuations in the curve that are significantly deviated from the average level. This is done to ensure that the candidate intervals can effectively capture the main water flow change periods of the day and provide a reliable basis for subsequent time period division.

[0062] The process iterates through the daily average flow distribution curve, examining the flow value for each 15-minute time unit in chronological order to determine if it belongs to a previously defined peak or slack candidate interval. Consecutive clusters of peak and slack candidate time units are identified and marked as preliminary time periods. Specifically, when multiple consecutive 15-minute time units belong to a peak candidate interval, these consecutive units are grouped into one cluster and marked as a preliminary peak period. Similarly, clusters of consecutive time units belonging to a slack candidate interval are marked as preliminary slack periods, as consecutive candidate time unit clusters better reflect a coherent peak or slack water usage pattern. Preliminary time periods of the same type with intervals of no more than one time unit are merged. For example, if two preliminary peak periods are only separated by one 15-minute time unit (which does not belong to a peak candidate interval), this interval may be caused by a brief fluctuation in water usage. In reality, these two periods still belong to the same overall peak cycle. Merging them more accurately reflects continuous peak or slack periods, avoiding the fragmentation of a complete time period due to small intervals.

[0063] The frequency of occurrence of traffic flow characteristics for each preliminary time period in multi-day data is statistically analyzed. Specifically, for each initially defined peak or off-peak period, the number of days in the 30-day raw data that actually match the peak or off-peak traffic flow characteristics (i.e., belong to their respective candidate intervals) is examined. The frequency is the ratio of the number of days matching the characteristics to the 30 days. Stable periods with a frequency of at least 75% are retained because such periods exhibit peak or off-peak characteristics on most days, indicating strong stability and regularity. Periods with lower frequencies are likely occasional exceptions and are not representative, therefore they are excluded. The time range of peak and off-peak periods is determined by using the moment when three consecutive time units match the characteristics. Since three consecutive 15-minute time units (45 minutes) match the peak or off-peak characteristics, the start or end of the period is stable and not caused by short-term traffic fluctuations. Using this as the start and end point allows for a more accurate definition of the specific time range of peak and off-peak periods, ensuring the reliability of the segmentation results.

[0064] S2. By performing hydraulic calculations and monitoring actual water supply pressure, the pressure control point at the end of the water supply system is located, and the water supply pressure data at that point is collected in real time.

[0065] In step S2 of this embodiment, the process of locking the pressure control point at the end of the water supply system through hydraulic calculation and actual water supply pressure monitoring is as follows:

[0066] A digital twin model of the water supply system is constructed. Based on the actual physical structure of the water supply system, including the direction, diameter, and length of the pipes, the location and parameters of the water pumps, the distribution of valves, and the location and distribution of users, a virtual model that is highly consistent with the actual system in terms of structure and operating characteristics is created. This model can reflect the movement law of water flow and pressure changes in the actual system, providing an accurate virtual carrier for subsequent simulation analysis.

[0067] Based on a digital twin model, historical typical operating conditions covering water flow data across different time periods and seasons are input. These different time periods include peak, off-peak, and low-peak periods throughout the day, while the different seasons take into account the impact of seasonal variations on water consumption; for example, summer water consumption is typically higher than winter water consumption. These representative historical operating condition data are selected because they reflect the typical operating states of the system under different water consumption conditions. Steady-state and transient hydraulic simulations are conducted using hydraulic calculation software. Steady-state simulations simulate the system's state when flow and pressure remain stable, suitable for analyzing periods of relatively stable water consumption. Transient simulations simulate the dynamic changes in flow and pressure over time, suitable for analyzing water consumption patterns. During rapidly changing periods, the combination of two simulations can comprehensively reflect the hydraulic characteristics of the system under various conditions. The theoretical pressure values ​​of each node are output, and a multi-condition theoretical pressure field distribution is generated. Based on the principles of energy and momentum conservation in fluid mechanics, the hydraulic calculation software calculates the pressure loss of water flowing in the pipe, thus obtaining the theoretical pressure value of each node. Presenting these pressure values ​​according to spatial location forms the pressure field distribution, which can intuitively show the pressure distribution in the system. The set of candidate nodes with the lowest theoretical pressure under each condition is marked. Under specific conditions, the nodes with the lowest pressure are most prone to insufficient water supply pressure. These nodes are potential end-point pressure control points and require close attention.

[0068] Based on the distribution characteristics of candidate nodes in the theoretical pressure field, monitoring points are deployed along the pipeline and at the user end. The distribution of candidate nodes in the theoretical pressure field can indicate which areas or locations are prone to low pressure levels. Deploying monitoring points along the pipeline and at the user end in these areas is to obtain actual pressure data for these potentially low-pressure points, because theoretical simulation results may deviate from actual conditions. Actual monitoring data can verify and calibrate the theoretical model, ensuring that subsequent analyses are based on real pressure conditions. The monitoring point deployment ensures that the density of candidate node clusters is higher in the candidate node cluster areas than in other areas, and all monitoring points have real-time data transmission capabilities to collect actual operating pressure data for each node.

[0069] During typical water usage periods covering peak and off-peak times, a digital twin model and a dynamic monitoring network are run simultaneously. These two periods are chosen because they represent extreme system operating conditions, allowing for a comprehensive verification of the model's accuracy. Simultaneous operation ensures comparability by acquiring pressure data calculated by the theoretical model and actual pressure data measured at monitoring points under the same time points and water usage conditions. After collecting theoretical and actual pressure data over the same time series, error analysis is performed by calculating the deviation between theoretical and actual values. The magnitude of the deviation reflects the degree of agreement between the theoretical model and the actual system. The pipe resistance coefficient and node flow distribution parameters in the model are adjusted. The pipe resistance coefficient affects the pressure loss of water flow in the pipe; a higher resistance coefficient results in greater pressure loss. The node flow distribution parameters affect the flow rate at each node; different flow rates lead to different node pressures. These parameters may differ from the initial settings due to pipe aging, changes in actual user water usage habits, etc. Adjusting them makes the theoretical model's output closer to reality. The process continues until the deviation between the model's output pressure distribution and the actual monitoring results is within a preset range. At this point, the model accurately reflects the actual system's pressure condition and can be used for subsequent analysis.

[0070] Based on the calibrated model and combined with real-time pressure data from the dynamic monitoring network, the calibrated model has been validated and can reliably reflect the actual system status. The combination with real-time monitoring data ensures the timeliness and accuracy of the information. The model extracts the minimum pressure value, duration of pressure below a preset threshold, and pressure fluctuation amplitude for each node throughout the entire operating cycle. The entire operating cycle covers various water usage conditions the system may encounter. The minimum pressure value reflects the lowest possible pressure level for the node; the lower the value, the more unfavorable the water supply. The longer the duration of pressure below the preset threshold, the longer the node is in a state of insufficient water supply. The greater the pressure fluctuation amplitude, the more unstable the node's water supply pressure. These characteristics, from different perspectives... This reflects the degree of water supply disadvantage at each node. A multi-feature weighted algorithm is used to comprehensively score all nodes, as a single feature cannot fully evaluate the degree of disadvantage. The weighted algorithm can comprehensively consider the influence of various features. The algorithm weights are set according to the priority of water supply safety. For example, the safety priority of residential water supply nodes is higher than that of industrial water supply nodes. Therefore, in the scoring, the relevant features of residential nodes are given higher weights to reflect their importance in water supply safety. The node with the lowest score is the pressure control point at the end of the water supply system, because after comprehensively considering factors such as minimum pressure, insufficient duration, and fluctuation range, this node exhibits the most severe water supply disadvantage and is the node that requires the most attention and protection in the entire system.

[0071] S3. During peak water usage periods, implement peak pressure boosting control strategy.

[0072] In step S3, the specific method for implementing the peak water usage boosting control strategy during peak water usage periods is as follows:

[0073] A fixed peak-period water supply pressure threshold is preset. This threshold is determined based on the most unfavorable pressure requirements of the water supply system during peak periods and the safe operating pressure range of the pipeline network. It aims to ensure sufficient water pressure at all water usage points during peak hours (such as morning washing and evening cooking) while preventing excessive pressure that could lead to pipe leaks or energy waste. Real-time monitoring of the water supply system's current pressure data is collected. These monitoring points directly reflect the pressure status within the pipeline network, ensuring the representativeness of the acquired data. The system continuously compares real-time collected pressure data with preset peak-hour water supply pressure thresholds. This comparison is the core step in determining whether the current system pressure meets demand. If the real-time pressure is below the threshold, it indicates insufficient water pressure in the pipeline network, which may lead to insufficient water flow or inability to supply water to remote water points. In this case, the control system needs to increase the output power of water supply equipment (such as water pumps) or adjust the opening of pressure regulating valves in the pipeline network to increase the water flow pressure and bring the real-time pressure closer to the threshold. If the real-time pressure is above the threshold, it indicates that the current water supply pressure exceeds actual demand. Excessive pressure not only increases the energy consumption of water pumps but may also accelerate pipe wear and aging. In this case, the output power of water supply equipment needs to be reduced or valves closed to reduce pipeline pressure. Through this closed-loop control method of "monitoring-comparison-adjustment," the system can dynamically respond to changes in water load during peak periods, promptly correct pressure deviations, and ensure that the water supply system pressure is always maintained within the preset peak-hour water supply pressure threshold range, guaranteeing the stability and reliability of water use during peak periods.

[0074] S4. During off-peak water usage periods, analyze historical water supply pressure data from the terminal pressure control point to set a safe pressure threshold for off-peak periods; send a pressure command to the control system based on this threshold to control the output pressure of the water supply equipment according to the threshold.

[0075] In step S4 of this embodiment, the process of setting a safe pressure threshold during off-peak water usage periods by analyzing historical water supply pressure data from the terminal pressure control point is as follows:

[0076] Collecting off-peak water pressure data from end-point pressure control points over the past 30 days requires continuously recording real-time off-peak water pressure information using pressure monitoring equipment previously deployed at these points. Categorizing by date involves grouping the daily recorded off-peak pressure data into a separate category to differentiate pressure conditions on different days. Creating a historical water pressure dataset for end-point pressure control points involves integrating this date-categorized pressure data into a complete dataset containing 30 days of off-peak pressure information. This 30-day dataset covers a significant time frame, encompassing various water usage conditions that may occur on different days, providing sufficient samples for subsequent analysis and ensuring more representative and reliable results.

[0077] Based on the determined start and end times of the off-peak period (i.e., the start and end times of the off-peak period specified in the previous steps), and combined with historical water flow fluctuation characteristics (i.e., referring to the changes in water flow during past off-peak periods, such as which time periods had large flow fluctuations and which time periods had relatively stable flow), the off-peak period is further divided into several off-peak sub-periods. The duration of each off-peak sub-period is fixed, for example, set to 1 hour or 30 minutes, which facilitates unified analysis and comparison of different sub-periods. Furthermore, the fluctuation range of water flow within each sub-period is within a preset range. Fluctuations in water flow directly affect changes in water supply pressure. Small flow fluctuations within the same sub-period mean that the pressure changes during that period are also relatively stable. Dividing such a time period into a sub-period makes the pressure characteristics of each sub-period more consistent, thus laying the foundation for setting targeted pressure thresholds in the future.

[0078] For each off-peak sub-period, pressure characteristic parameters for the corresponding period are extracted from the historical water supply pressure dataset of the terminal pressure control point. This involves identifying the pressure records for each sub-period on different dates from the integrated 30-day data set, and then calculating the relevant parameters for that sub-period. These parameters include: the average pressure within the sub-period (the average of all pressure data for that sub-period, reflecting the typical pressure level); the minimum pressure (the lowest pressure value occurring within the sub-period, reflecting the lowest possible pressure condition); the standard deviation of pressure (measuring the degree to which pressure data deviates from the mean within the sub-period, reflecting the magnitude of pressure fluctuation); and the duration of continuous pressure stability (the duration for which pressure remains within a certain stable range without significant fluctuations within the sub-period, reflecting the degree of pressure stability). These parameters are extracted because they describe the pressure characteristics of the sub-period from different dimensions, comprehensively reflecting the pressure conditions during that period and providing a multifaceted basis for subsequent calculations of benchmark values.

[0079] For each off-peak sub-period, a weighted average method is used to calculate the pressure benchmark value: the average pressure value of the sub-period is calculated by weighting the duration of continuous stable pressure within the sub-period. That is, the average pressure value of the sub-period on different dates is weighted according to the duration of continuous stable pressure for each date. The average pressure value of the date with a longer duration of continuous stable pressure has a larger weight in the calculation. The weighting rule is as follows: the average pressure value with a duration of continuous stable pressure longer than the preset duration is given a higher weight. A longer duration of continuous stable pressure indicates that the pressure state of that sub-period on that date is more stable and more representative of the normal pressure level of that sub-period. It is less affected by accidental fluctuations. Giving a higher weight can make the calculated pressure benchmark value closer to the true and stable pressure level of that sub-period, thus improving the reliability of the benchmark value.

[0080] Analyze the distribution of the historical pressure minimum value and pressure benchmark value for each off-peak sub-period. This involves calculating the difference between the pressure minimum value and the pressure benchmark value for each sub-period on different dates, and then observing the distribution of these differences to understand how much the pressure minimum value is typically lower than the benchmark value. Combined with the minimum service head requirement of the water supply system—the minimum pressure standard to ensure normal water use for users—a corresponding safety margin coefficient is set for each off-peak sub-period. This safety margin coefficient adds a certain pressure margin to the benchmark value to prevent the actual pressure from falling below the minimum service head. Since the distribution of the difference varies across different sub-periods (i.e., the gap between the pressure minimum and the benchmark value differs), different safety margin coefficients need to be set for each sub-period to ensure that the pressure in each sub-period meets the minimum service head requirement.

[0081] For each off-peak sub-period, its pressure baseline value is multiplied by a safety margin coefficient to obtain the off-peak pressure safety threshold for that sub-period. This is because the safety margin coefficient is set based on a proportion of the baseline value. The threshold obtained after multiplication considers both the typical pressure level (baseline value) of that sub-period and the necessary safety margin, ensuring that the water supply pressure of that sub-period will not fall below the minimum service head. By summing up the thresholds of all off-peak sub-periods, a complete off-peak pressure safety threshold system is formed. Such a system can cover all sub-periods of the entire off-peak period, enabling the control system to have corresponding pressure control standards in different off-peak sub-periods, achieving more accurate and reasonable off-peak pressure control.

[0082] S5. Monitor the water supply pressure at the terminal pressure control point in real time. When the pressure is lower than the low-peak pressure safety threshold, trigger an alarm and continuously record pressure changes. If the alarm continues, switch to the peak-peak pressure boosting control strategy through the control system. After the water supply pressure at the terminal pressure control point returns to normal, automatically correct the low-peak pressure safety threshold for that period.

[0083] In step S5 of this embodiment, the process of automatically correcting the off-peak pressure safety threshold for that period is as follows:

[0084] When the water supply pressure at the terminal pressure control point rises above the original low-peak pressure safety threshold, it means that after the previous strategy adjustment, the pressure at that point has reached the originally set safety standard. The continuous stable duration reaching the preset pressure stability duration is to confirm that this rise is not a short-term fluctuation, but a true stabilization above the safety level. If it only briefly exceeds the threshold and then drops, it may indicate that there are still unstable factors in the system and it cannot be considered a true return to normal. Only when both of these conditions are met can it be determined that the pressure has returned to normal.

[0085] The complete data sequence of this pre-alarm event was extracted, including: the duration of pressure below the threshold, which reflects how long the insufficient pressure state lasted; the longer the duration, the greater the potential impact range and severity of the problem; the pressure fluctuation amplitude, which reflects the drastic changes in pressure values ​​during the insufficient pressure period; the greater the fluctuation, the more unstable the system; the rate of pressure recovery after switching to the peak-period strategy, which reflects the effectiveness of the peak-period strategy in increasing pressure; a rapid recovery indicates timely and effective strategy adjustment; and the average pressure and the duration of pressure stability during the first complete low-peak sub-period after returning to normal. These two data points reflect the stable state of the system after returning to normal; the average reflects the normal pressure level, and the stability duration indicates the stability after recovery. These data together constitute a comprehensive record of this abnormal event, providing detailed basis for subsequent threshold adjustments.

[0086] Using the average pressure of the first complete low-peak period after the system returns to normal as a benchmark, this average value represents the pressure of the first complete period after the system stabilizes and reflects the actual pressure level of the system under normal conditions. The difference between this average value and the original low-peak pressure safety threshold is calculated, and the resulting actual pressure deviation value accurately reflects the gap between the original threshold and the current actual normal pressure. Combined with the maximum extent to which the pressure is below the threshold during this abnormal event, which reflects the most severe degree of pressure insufficiency, a deviation coefficient is generated through a proportional algorithm. The proportional algorithm combines the two different dimensions of parameters, deviation value and maximum extent, so that the deviation coefficient can reflect both the difference under normal conditions and the degree of pressure insufficiency under extreme conditions, thus more comprehensively reflecting the direction and degree of adjustment required for the original threshold.

[0087] The dynamic correction factor is determined based on the deviation coefficient. This factor is set according to the magnitude of the deviation coefficient and determines the adjustment range of the safety margin coefficient. A larger deviation coefficient indicates a greater gap between the original threshold and the actual situation, resulting in a larger correction factor and a correspondingly larger adjustment range. The safety margin coefficient for the original off-peak sub-period is adjusted as follows: If the actual pressure deviation is positive, it indicates that the restored actual pressure is higher than the original threshold, suggesting that the original safety margin may be too large, leading to an overly high threshold setting and energy waste. Therefore, the safety margin coefficient is lowered. If it is negative, it indicates that the restored actual pressure is lower than the original threshold, suggesting that the original safety margin is insufficient and may not guarantee water supply safety. Therefore, the safety margin coefficient is increased. The adjustment range is determined by the dynamic correction factor, ensuring that the adjusted safety margin coefficient better reflects the current system's actual situation.

[0088] The adjusted safety margin coefficient and the original pressure benchmark value are used to recalculate and obtain the corrected pressure safety threshold for this off-peak sub-period. Because the original pressure benchmark value is a typical pressure level calculated based on historical stable data, it has a certain degree of stability and representativeness. Combined with the adjusted safety margin coefficient, a new threshold that both conforms to the current situation and retains historical experience can be obtained. The corrected threshold meets the constraint that it is not lower than the minimum service head of the water supply system. This is to ensure that no matter how it is adjusted, the most basic water supply pressure requirement can be guaranteed, and the water supply pressure will not fall below the minimum standard required for normal water use by users due to the adjustment, thereby ensuring water supply safety.

[0089] Example 2

[0090] See Figure 2 A time-segmented intelligent pressure regulation management system for secondary water supply, used to implement the time-segmented intelligent pressure regulation management method for secondary water supply described in the above embodiments, comprising:

[0091] The water usage period segmentation module divides a day into peak and off-peak water usage periods based on historical water flow data, and determines the start and end times of each period.

[0092] The terminal pressure control point locking module locks the terminal pressure control point of the water supply system through hydraulic calculation and actual water supply pressure monitoring, and collects the water supply pressure data of that point in real time.

[0093] The peak-period booster control module is used to execute peak-period booster control strategies during peak water usage periods.

[0094] The off-peak pressure threshold setting module is used to analyze historical water supply pressure data from the terminal pressure control point during off-peak water usage periods, set a safe pressure threshold for off-peak periods, and send a pressure command to the control system based on the threshold to control the output pressure of the water supply equipment according to the threshold.

[0095] The terminal pressure monitoring and correction module is used to monitor the water supply pressure at the terminal pressure control point in real time. When the pressure is lower than the low-peak pressure safety threshold, a pre-alarm is triggered and pressure changes are continuously recorded. If the pre-alarm status continues, the control system switches to the peak-peak pressure boosting control strategy. After the water supply pressure at the terminal pressure control point returns to normal, the low-peak pressure safety threshold for that period is automatically corrected.

[0096] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A time-segmented intelligent pressure regulation management method for secondary water supply, characterized in that, Includes the following steps: S1. Based on historical water flow data, the day is divided into peak water consumption period and low water consumption period, and the start and end time nodes of each period are determined. S2. Through hydraulic calculations and actual water supply pressure monitoring, the pressure control point at the end of the water supply system is located, and the water supply pressure data at this point is collected in real time; the process of locating the pressure control point at the end of the water supply system is as follows: S21. Construct a digital twin model of the water supply system; S22. Based on the digital twin model, input historical typical working conditions covering water flow data in different time periods and seasons, carry out steady-state and transient hydraulic simulations through hydraulic calculation software, output the theoretical pressure values ​​of each node and generate the theoretical pressure field distribution of multiple working conditions, and mark the candidate node set with the lowest theoretical pressure under each working condition. S23. Based on the distribution characteristics of candidate nodes in the theoretical pressure field, monitoring points are set up along the pipeline and at the user end. S24. During typical water usage periods covering peak and off-peak periods, the digital twin model and dynamic monitoring network are run synchronously to collect theoretical pressure data and actual pressure data under the same time series. Error analysis is performed by calculating the deviation between theoretical and actual values, and the pipeline resistance coefficient and node flow distribution parameters in the model are adjusted until the deviation between the pressure distribution output by the model and the actual monitoring results is within the preset range. S25. Based on the calibrated model and combined with the real-time pressure data of the dynamic monitoring network, extract the lowest pressure value, the duration of pressure below the preset basic threshold, and the pressure fluctuation amplitude of each node in the entire working cycle. Use a multi-feature weighted algorithm to comprehensively score all nodes, where the algorithm weight is set according to the priority of water supply safety, and the node with the lowest score is the pressure control point at the end of the water supply system. S3. During peak water usage periods, implement peak pressure boosting control strategy; S4. During the off-peak water usage period, analyze the historical water supply pressure data of the terminal pressure control point and set a safe pressure threshold for the off-peak period; send a pressure command to the control system according to the threshold and control the output pressure of the water supply equipment according to the threshold. S5. Monitor the water supply pressure at the terminal pressure control point in real time. When the pressure is lower than the low-peak pressure safety threshold, trigger an alarm and continuously record pressure changes. If the alarm continues, switch to the peak-peak pressure boosting control strategy through the control system. After the water supply pressure at the terminal pressure control point returns to normal, automatically correct the low-peak pressure safety threshold for that period.

2. The time-segmented intelligent pressure regulation management method for secondary water supply according to claim 1, characterized in that, In step S1, the process of dividing a day into peak and off-peak water usage periods based on historical water flow data and determining the start and end times of each period is as follows: S11. Collect raw water flow data for 30 consecutive days, convert it into a continuous time series with 15-minute time units, remove extreme outliers using box plot method, and fill in missing data segments using linear interpolation method; S12. Calculate the flow rate value for each time unit, calculate the average flow rate within the window based on the 2-hour sliding window, and take the average of the 30-day data in the same time unit to generate the daily average flow rate distribution curve. S13. Calculate the overall mean and standard deviation based on the daily average flow distribution curve, delineate the peak candidate intervals that are higher than the mean + 1.2 times the standard deviation and the low peak candidate intervals that are lower than the mean - 1.2 times the standard deviation, and adjust the standard deviation multiple iteratively so that the candidate intervals cover more than 90% of the significant fluctuations of the curve. S14. Traverse the daily average traffic distribution curve, identify continuous peak and low peak candidate time unit clusters and mark them as preliminary time periods, and merge the same type of preliminary time periods with an interval of no more than 1 time unit. S15. Calculate the frequency of occurrence of each preliminary time period that meets the corresponding traffic characteristics in multi-day data, retain stable time periods with a frequency of not less than 75%, and determine the time range of peak and off-peak periods by taking the moment when three consecutive time units meet the characteristics as the start and end nodes.

3. The time-segmented intelligent pressure regulation management method for secondary water supply according to claim 1, characterized in that, In step S23, the monitoring points are deployed to ensure that the density of the candidate node set area is higher than that of other areas, and all monitoring points have real-time data transmission capabilities to collect the actual operating pressure data of each node.

4. The time-segmented intelligent pressure regulation management method for secondary water supply according to claim 1, characterized in that, In step S3, the specific method for implementing the peak water usage boosting control strategy during the peak water usage period is as follows: A fixed peak-period water supply pressure threshold is preset, and real-time pressure data of the water supply system is obtained through pressure monitoring. The real-time pressure data is compared with the peak-period water supply pressure threshold. If the real-time pressure is lower than the threshold, the output pressure is increased; if the real-time pressure is higher than the threshold, the output pressure is decreased. According to the comparison results of the real-time pressure data and the peak-period water supply pressure threshold, the corresponding adjustments are made to ensure that the water supply system pressure is always maintained within the peak-period water supply pressure threshold range.

5. The time-segmented intelligent pressure regulation management method for secondary water supply according to claim 1, characterized in that, In step S4, the process of setting a safe pressure threshold during the off-peak water usage period by analyzing historical water supply pressure data from the terminal pressure control point is as follows: S41. Collect the off-peak water supply pressure data of the end pressure control points over the past 30 days, classify them by date, and form a historical water supply pressure dataset of the end pressure control points. S42. Based on the determined start and end times of the off-peak period and combined with the historical water flow fluctuation characteristics, the off-peak period is further divided into several off-peak sub-periods; the duration of each off-peak sub-period is fixed, and the fluctuation range of water flow in each sub-period is within a preset range. S43. For each off-peak period, extract the pressure characteristic parameters of the corresponding period from the historical water supply pressure dataset of the terminal pressure control point, including the average pressure, minimum pressure, standard deviation of pressure, and duration of continuous pressure stability within the sub-period. S44. For each off-peak sub-period, the pressure benchmark value is calculated using the weighted average method: S45. Analyze the distribution of the difference between the historical minimum pressure value and the pressure benchmark value for each off-peak period, and set a corresponding safety margin coefficient for each off-peak period in combination with the minimum service head requirement of the water supply system. S46. For each off-peak sub-period, multiply its pressure benchmark value by the safety margin coefficient to obtain the off-peak pressure safety threshold for that sub-period; summarize the thresholds of all off-peak sub-periods to form a complete off-peak pressure safety threshold system.

6. The time-segmented intelligent pressure regulation management method for secondary water supply according to claim 5, characterized in that, Step S44 also includes: The average pressure value of a sub-period is calculated by weighting the duration of continuous and stable pressure within that sub-period. The weighting rule is that the average pressure value with a continuous and stable duration longer than the preset duration is given a higher weight.

7. The time-segmented intelligent pressure regulation management method for secondary water supply according to claim 1, characterized in that, In step S5, the process of automatically correcting the low-peak pressure safety threshold for that period is as follows: S51. When the water supply pressure at the terminal pressure control point rises above the original low-peak pressure safety threshold and remains stable for a continuous period of time, it is determined that the pressure has returned to normal. S52. Extract the complete data sequence of this pre-alarm event, including: the duration of pressure below the threshold, the magnitude of pressure fluctuation, the rate of pressure recovery after switching to the peak period strategy, the average pressure and the duration of pressure stabilization during the first complete low-peak period after returning to normal. S53. Using the average pressure of the first complete low-peak period after the return to normal as a benchmark, calculate the difference between it and the original low-peak pressure safety threshold to obtain the actual pressure deviation value; combine the maximum extent to which the pressure is lower than the threshold during this abnormal event to generate a deviation coefficient through a proportional algorithm. S54. Based on the deviation coefficient, determine the dynamic correction factor and adjust the safety margin coefficient of the original low-peak period sub-period: if the actual pressure deviation value is positive, lower the safety margin coefficient; if it is negative, raise the safety margin coefficient. The adjustment range is determined by the dynamic correction factor. S55. The adjusted safety margin coefficient and the original pressure reference value are used to recalculate and obtain the corrected pressure safety threshold for the off-peak period. The corrected threshold meets the constraint that it is not lower than the minimum service head of the water supply system.

8. A time-segmented intelligent pressure regulation management system for secondary water supply, characterized in that, A time-segmented intelligent pressure regulation management method for secondary water supply as described in any one of claims 1-7 includes: The water usage period segmentation module divides a day into peak and off-peak water usage periods based on historical water flow data, and determines the start and end times of each period. The terminal pressure control point locking module locks the terminal pressure control point of the water supply system through hydraulic calculation and actual water supply pressure monitoring, and collects the water supply pressure data of that point in real time. The peak-period booster control module is used to execute peak-period booster control strategies during peak water usage periods. The off-peak pressure threshold setting module is used to analyze historical water supply pressure data from the terminal pressure control point during off-peak water usage periods, set a safe pressure threshold for off-peak periods, and send a pressure command to the control system based on the threshold to control the output pressure of the water supply equipment according to the threshold. The terminal pressure monitoring and correction module is used to monitor the water supply pressure at the terminal pressure control point in real time. When the pressure is lower than the low-peak pressure safety threshold, a pre-alarm is triggered and pressure changes are continuously recorded. If the pre-alarm status continues, the control system switches to the peak-peak pressure boosting control strategy. After the water supply pressure at the terminal pressure control point returns to normal, the low-peak pressure safety threshold for that period is automatically corrected.

Images