Pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partition
Through the pipeline network pressure monitoring and early warning system based on water pressure fluctuation similarity partition, the problems of insufficient water pressure fluctuation analysis and insufficient linkage of secondary water supply systems in complex water supply networks are solved, and more efficient monitoring and early warning are achieved , improves the stability and regulation capabilities of the water supply system.
Patent Information
- Application Number
- CN202411244908.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-05
AI Technical Summary
Traditional water supply pipeline monitoring systems are difficult to accurately analyze water pressure fluctuations in complex partitions and large-scale water supply networks, resulting in water supply pressure abnormalities not being processed in time and failure to fully consider the linkage of secondary water supply systems, resulting in limited regulation and control capabilities and inability to meet the needs of The city's growing demand for water supply.
Using a pipeline network pressure monitoring and early warning system based on water pressure fluctuation similarity partition, the pipeline network node collection is divided, water pressure fluctuation data is collected and analyzed, the secondary water supply status indicators are dynamically adjusted, the trend change index and correlation evaluation coefficient are calculated, and the correlation evaluation coefficient is generated. Comprehensive early warning model, optimize monitoring point selection and early warning strategy.
It improves the stability and safety of the water supply system, reduces monitoring costs and data processing complexity, promptly responds to changes in water modes, and improves the regulation capabilities and early warning accuracy of the water supply pipeline network.
Smart Images

Figure CN118959892A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of pipe network pressure monitoring, and in particular to a pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity zoning. Background Art
[0002] With the acceleration of urbanization, urban water supply network systems are becoming increasingly complex. How to effectively monitor and regulate the pressure of water supply networks has become an important issue to ensure the safety and stability of urban water supply. Traditional water supply network monitoring systems usually rely on data collection at fixed monitoring points and simple threshold alarm mechanisms.
[0003] However, this approach is often inadequate when dealing with complex water supply network systems, especially in large-scale, complexly partitioned water supply networks. Due to the lack of real-time and accurate analysis of water pressure fluctuations, it is easy for abnormal water supply pressure in local areas to not be handled in a timely manner, which in turn causes a series of water supply problems. At the same time, the existing monitoring system usually fails to fully consider the linkage with the secondary water supply system of the community, resulting in the overall regulation capacity of the water supply network being limited when the secondary water supply status fluctuates greatly, and unable to meet the growing urban water supply demand.
[0004] In the existing technology, although some studies have attempted to improve the pressure monitoring capability of the pipeline network by increasing the density of monitoring points or introducing more complex data analysis algorithms, these methods still have significant deficiencies in practical applications. First, due to the different distribution and water supply conditions of pipeline network nodes, simply adding monitoring points not only greatly increases the construction and maintenance costs of the system, but also the rapid increase in the amount of monitoring data also increases the complexity of data processing, which easily leads to a lag in system response. Secondly, the existing technology usually fails to fully consider the correlation analysis between water pressure fluctuations and secondary water supply status, resulting in the monitoring system being unable to respond in time when the water use pattern of the secondary water supply system changes, thereby missing the best control opportunity. Furthermore, traditional water pressure monitoring systems often ignore the similarities of water pressure fluctuations between different nodes in the water supply network, and fail to effectively use these similarities for regional zoning and representative node selection, resulting in a lack of pertinence and accuracy in the early warning strategy.
[0005] Therefore, how to introduce a more intelligent monitoring and early warning mechanism into the water supply network to improve the stability and safety of the water supply system has become a hot topic in current research and development.
[0006] The above information disclosed in the above Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to one of ordinary skill in the art. Summary of the invention
[0007] The purpose of the present invention is to provide a pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity zoning to solve the problems raised in the above background technology.
[0008] To achieve the above object, the present invention provides the following technical solutions:
[0009] The pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partitioning includes the following specific steps:
[0010] Pipeline network division module: used to determine the monitoring area of the water supply network and mark each pipeline network node in the monitoring area, wherein the pipeline network nodes connected to the secondary water supply system of the community are divided into the first pipeline network node set; the remaining pipeline network nodes are divided into the second pipeline network node set;
[0011] Data acquisition module: used to regularly collect water pressure fluctuation data of the first pipe network node set and the second pipe network node set, as well as secondary water supply status indicators of the community secondary water supply system, and store the collected data to form a historical database;
[0012] Data extraction module: used to receive the historical database, select the time period T immediately before the current moment as the calculation period, extract the water pressure fluctuation data within the calculation period from the historical database, and sequentially form a first extracted data set and a second extracted data set, wherein the first extracted data set and the second extracted data set correspond to the first pipe network node set and the second pipe network node set respectively;
[0013] Secondary water supply status index adjustment module: used to obtain the water use behavior pattern of the community users in the previous time period T, and dynamically adjust the secondary water supply status index according to the behavior pattern;
[0014] A first trend change index building module: used for receiving and analyzing the first extracted data set, calculating the first trend change index for evaluating the similarity of water pressure fluctuations, partitioning the first pipe network node set according to the first trend change index, and selecting a representative pipe network node from each partition as the first monitoring point;
[0015] A second trend change index building module: used for receiving and analyzing the second extracted data set, calculating the second trend change index for evaluating the similarity of water pressure fluctuations, partitioning the second pipe network node set according to the second trend change index, and selecting a representative pipe network node from each partition as a second monitoring point;
[0016] A first correlation evaluation coefficient construction module is used to obtain the first water pressure fluctuation data of the first monitoring point within the calculation period T and the secondary water supply status index at the corresponding position, and perform a correlation analysis on the two to obtain a first correlation evaluation coefficient, which is used to evaluate the correlation degree between the first water pressure fluctuation data and the secondary water supply status index;
[0017] A second correlation evaluation coefficient construction module is used to obtain the second water pressure fluctuation data of the second monitoring point within the calculation period T and the secondary water supply status index at the corresponding position, and perform a correlation analysis on the two to obtain a second correlation evaluation coefficient, which is used to evaluate the correlation between the second water pressure fluctuation data and the secondary water supply status index;
[0018] Comprehensive early warning model construction module: used to analyze and process the first correlation evaluation coefficient, the second correlation evaluation coefficient, the first trend change index and the second trend change index to generate a comprehensive early warning model, which is used to provide corresponding early warning strategies for the first pipeline node set and the second pipeline node set respectively.
[0019] Furthermore, within the calculation period T, the water pressure value of each node in the first pipe network node set N1 is marked as P i,N1 (t); For the water pressure value of each node in the second pipe network node set N2, marked as P i′,N2 (t); where i and i′ are the node numbers in the corresponding N1 and N2 sets, respectively, and t is the collection time point in the previous time period T;
[0020] Define the secondary water supply status index as S status (t), the calculation formula is as follows:
[0021]
[0022] Among them, W p is the water pressure weight coefficient, which reflects the weight of the influence of the water pressure of the water supply pump on the system state. The value range of Wp is set between [0.5,1];
[0023] α is the exponential factor of water pressure, which is used to adjust the influence of water pressure; β is the adjustment coefficient of water level, which controls the influence of water level on state indicators. The value range of β is set between [0.1,1]; μ1 is a normal number term, which is used to avoid S status (t) is 0, and 0.01≤μ1≤0.12;
[0024] L(t) represents the water level of the water storage tank at the sampling time point t; P s (t) is the output pressure of the water supply pump at the sampling time t; S p (t) is the operating state of the water supply pump, which is defined as a binary function, 1 means running and 0 means stopping; L ref It is the reference water level, representing the ideal water level value of the water storage tank;
[0025] Limited S status The valid value range of (t) is between (0,10):
[0026] When S status When (t) is closer to 10, it means the system is in better condition, the water pressure is normal and the water level is closer to the ideal state;
[0027] When S status When (t) is closer to 0, it means that the system status is worse, and there is an abnormal situation such as the water supply pump shutting down or the water level is too low;
[0028] The collected data is stored in the system's historical database in real time.
[0029] Furthermore, the formation of the first extracted data set and the second extracted data set specifically includes:
[0030] Extract water pressure fluctuation data within calculation period T from the historical database;
[0031] 2.1) Use SQL query statements to extract data from the historical database;
[0032] 2.2) Classifying the extracted data by nodes, and distinguishing the data belonging to the first pipe network node set N1 and the second pipe network node set N2;
[0033] 2.3) The following data set is formed:
[0034] First extract the dataset D 1 = {P i,N1 (t)|i∈N1,t∈[t start ,t now ]};
[0035] The second extracted dataset D 2 = {P i′,N2 (t)|i′∈N2,t∈[t start ,t now ]};
[0036] Among them, t start =t now -T, t start ,t now They represent the start time of the calculation period T and the current time respectively.
[0037] Furthermore, it is used to obtain the water consumption behavior pattern of the users in the community in the previous time period T, and dynamically adjust the secondary water supply status indicator according to the behavior pattern, specifically including:
[0038] For water use behavior patterns;
[0039] Collect the water consumption data U of each user within the calculation period T j (t), where j represents the user number and t represents the s(t) means the same as the collection time point;
[0040] At each time point t, the water consumption of all users is summed up to calculate the total water consumption U at that time point total (t);
[0041] Define the average water consumption U avg It refers to the average value of total water consumption at all time points within the calculation period T;
[0042] When the real-time total water consumption U total (t) greater than the average water consumption U avg When the system is in the peak period, it will be considered as the trough period.
[0043] For W p Dynamic adjustment to get W p (t):
[0044]
[0045] When U total (t)>U avg When W p (t) increases, W p0 is the initial weight coefficient, a1 is the adjustment coefficient, 0.08≤a1≤0.34, indicating that the current water demand increases and the weight of water pressure needs to be increased to ensure system stability; when U total (t)<U avg When W p (t) decrease;
[0046] For dynamic adjustment of α, we get α(t):
[0047]
[0048] a2 is the adjustment coefficient, 0.13≤a2≤0.56;
[0049] When U total (t)>U avg When U total (t)<U avg When , α(t) approaches 1, reducing the impact of fluctuations;
[0050] The adjusted W p Substitute (t) and α(t) into S status (t) In the original calculation formula, the following adjusted S′ is obtained status (t) calculation formula;
[0051]
[0052] The system collects current pressure data P in real time s (t), water supply pump status S p (t), and water level L(t), are substituted into the above formula to calculate S′ status (t);
[0053] When S′ status When (t)>8, the system is in good condition and no adjustment is required;
[0054] 4≤S′ status When (t)≤8, the system enters the alert state, checks the water supply equipment and makes early warning preparations;
[0055] When S′ status When (t) < 4, the system enters the alarm state, activates the emergency plan, starts the backup pump or adjusts the water pressure setting.
[0056] Further, a first trend change index for evaluating the similarity of water pressure fluctuation is calculated, and the first pipe network node set is partitioned according to the first trend change index, and a representative pipe network node is selected from each partition as the first monitoring point, specifically including:
[0057] Receive and preprocess the first extracted data set D 1 = {P i,N1 (t)|i∈N 1 ,t∈[t start ,t now ]} to ensure data quality and consistency; the data set contains the changes in water pressure values of all nodes in the first pipe network node set N1 over time within the calculation period T;
[0058] Based on the preprocessed data, the first-order derivative P′ is calculated in sequence i,N1 (t) and water pressure fluctuation amplitude A i,N1 , and combined with the first-order derivative and water pressure fluctuation amplitude, the first trend change index TCI of each node is calculated i,N1 ;This index is used to measure the degree of change in water pressure fluctuation at each node;
[0059] The first trend change index TCI of each node i,N1 The calculation formula is as follows:
[0060]
[0061] Among them, A avg is the average value of all node fluctuations, used for standardization, P′ i,N1 (t) is the first-order derivative, which indicates the rate of change of water pressure with time, A i,N1 Reflects the range of water pressure variation at each node;
[0062] According to the first trend change index TCI i,N1 Partitioning the first pipe network node set N1;
[0063] Clustering algorithm is used to group nodes; TCI i,N1 To cluster features, the nodes are divided into multiple subsets, each of which represents an area with similar water pressure fluctuations;
[0064] According to the clustering results, the first pipe network node set N1 is divided into several partitions (Z 1 ,Z 2 ,...,Z m ), and Z k1 ∈{Z 1 ,Z 2 ,...,Z m} is a partition (Z 1 ,Z 2 ,...,Z m ) The k1th partition in the set, the nodes in each partition have similar water pressure fluctuation trends;
[0065] Select the most representative node from each partition as the first monitoring point;
[0066] In each partition Z k1 , select the first trend change index TCI i,N1 The node MJ closest to the center of the partition k1 Act as the representative node of the partition;
[0067] Calculate the TCI of node i i,N1 With the partition center μ k1 Distance between:
[0068] d(i,μ k1 )=|TCI i,N1 -μ k1 |
[0069] Select the node with the smallest distance as the representative node:
[0070]
[0071] The selected representative node is used as the first monitoring point set M1; for subsequent pressure monitoring and early warning, the first monitoring point set M1 is expressed as follows;
[0072] M1={MJ 1 ,MJ 2 ,…,MJ k1 ,…,MJ m}
[0073] And according to the first monitoring point set M1, the following first water pressure fluctuation data set is obtained:
[0074]
[0075] Furthermore, for the second trend change index, the second pipe network node set is partitioned, and a representative pipe network node is selected from each partition as the second monitoring point. The calculation and acquisition method is the same as the first trend change index construction module, which is not repeated here, and the following related content is obtained:
[0076] The second trend change index TCI of each node in the second pipe network node set i′,N2 The calculation formula is as follows:
[0077]
[0078] Among them, A′ avg is the average value of all node fluctuations, used for standardization, P′ i′,N2 (t) is the first-order derivative, which indicates the rate of change of water pressure with time, A i′,N2 Reflects the range of water pressure variation at each node;
[0079] According to the clustering results, the second pipe network node set N2 is divided into several partitions (Z 1 ′,Z′ 2 ,...,Z′m ′ ), and Z k2 ∈{Z′ 1 ,Z′ 2 ,...,Z′ m′} is the partition (Z′ 1 ,Z′ 2 ,...,Z′ m′ ) The k2th partition in the set, the nodes in each partition have similar water pressure fluctuation trends;
[0080] Select the most representative node from each partition as the second monitoring point;
[0081] Specifically, the selected representative node is used as the second monitoring point set M2 for subsequent pressure monitoring and early warning. The second monitoring point set M2 is represented as follows:
[0082] M2={MJ′ 1 ,MJ′ 2 ,…,MJ′ k2 ,…,MJ′ m′}
[0083] And the following second water pressure fluctuation data set is obtained according to the second monitoring point set M2:
[0084]
[0085] Furthermore, a first correlation evaluation coefficient is obtained, and the first correlation evaluation coefficient is used to evaluate the correlation degree between the first water pressure fluctuation data and the secondary water supply state index, specifically including:
[0086] Define the first correlation evaluation coefficient The calculation formula is as follows:
[0087]
[0088] in, is the first water pressure fluctuation data after standardization; It is a standardized indicator of secondary water supply status;
[0089] The value range is -1 to 1, indicating the degree of linear correlation between water pressure fluctuation and water supply status:
[0090] When , it indicates a positive correlation, and the water pressure fluctuation and water supply status change in the same direction;
[0091] When , it indicates a negative correlation, and the water pressure fluctuation and water supply status change in opposite directions;
[0092] , indicating no significant correlation;
[0093] A second correlation evaluation coefficient is obtained, and the second correlation evaluation coefficient is used to evaluate the correlation between the second water pressure fluctuation data and the secondary water supply state index, specifically including:
[0094] The calculation method of the second correlation evaluation coefficient is the same as that of the first correlation evaluation coefficient, which is not repeated here, and the following content is obtained:
[0095] Define the second correlation evaluation coefficient The calculation formula is as follows:
[0096]
[0097] in, is the standardized second water pressure fluctuation data; It is a standardized indicator of secondary water supply status;
[0098] The value range is -1 to 1, indicating the degree of linear correlation between water pressure fluctuation and water supply status:
[0099] When , it indicates a positive correlation, and the water pressure fluctuation and water supply status change in the same direction;
[0100] When , it indicates a negative correlation, and the water pressure fluctuation and water supply status change in opposite directions;
[0101] , indicating no significant correlation.
[0102] Furthermore, the comprehensive early warning model is used to provide corresponding early warning strategies for the first pipe network node set and the second pipe network node set, respectively, including:
[0103] The calculation formula for defining the comprehensive early warning model is as follows:
[0104]
[0105] Among them, S warning is the index value of the comprehensive early warning model, μ2 is a positive constant term, 0.12≤μ2≤0.23, which is used to avoid S warning The case of taking 0;
[0106] S warning The value range of S is (0,1), and based on experimental verification and historical data, S warning The strategy judgment threshold is U1, 0.23≤U1≤0.68;
[0107] The early warning strategy is as follows:
[0108] 3.1) If S warning >U1, when and When the water pressure fluctuation is highly consistent with the water supply status;
[0109] Considering the high correlation between water pressure and water supply status, the water supply pressure of the first set of pipe network nodes is increased by 15%, and the water supply pressure of the second set of pipe network nodes is increased by 13% to enhance the system's ability to cope with pressure fluctuations;
[0110] For the secondary water supply system in the residential area, the inspection frequency is increased to 150%, with a focus on checking the tightness of pipes and equipment to ensure that there are no hidden dangers of water leakage or pressure reduction in the water supply system;
[0111] when and When , the water pressure fluctuation changes in the opposite direction to the water supply status;
[0112] Since the water supply status is negatively correlated with the water pressure, the water supply pressure of the first pipe network node set is reduced by 10%, and the water supply pressure of the second pipe network node set is reduced by 11% to avoid excessive water pressure causing system burden;
[0113] For the secondary water supply system in the community, the inspection frequency is increased to 130%, and the operating status of the water supply valves and pumps is checked to prevent failures caused by unbalanced loads;
[0114] 3.2) If S warning = U1; When And At this time, the water pressure fluctuation is consistent with the water supply status; The water supply pressure of the first pipe network node set is increased by 5%, and the water supply pressure of the second pipe network node set is increased by 3% to maintain the stability of the system;
[0115] The inspection frequency of the secondary water supply system in the community is set to 120% to ensure the normal operation of all components of the system, and the readings of the pressure sensors are monitored key points;
[0116] When And At this time, the water pressure fluctuation changes in the opposite direction to the water supply status;
[0117] Due to the negative correlation between the water supply pressure and the water pressure, the water supply pressure of the first pipe network node is reduced by 5%, and the water supply pressure of the second pipe network node is reduced by 7% to reduce the system burden;
[0118] The inspection frequency of the secondary water supply system in the community is increased to 125% to strengthen the inspection of the water pumps and valves to ensure that they can effectively respond to pressure fluctuations;
[0119] 3.3) If S warning < U1; When And At this time, the water pressure fluctuation is consistent with the water supply status; Since the system performance is stable, the water supply pressures of the first pipe network node set and the second pipe network node set remain unchanged;
[0120] The inspection frequency of the secondary water supply system in the community is set to 105% to ensure that the system is within the normal operating range and conduct routine maintenance;
[0121] When And At this time, the water pressure fluctuation changes in the opposite direction to the water supply status;
[0122] Make a 5% fine adjustment to the water supply pressure of the first pipe network node set and an 8% fine adjustment to the water supply pressure of the second pipe network node set;
[0123] The inspection frequency of the secondary water supply system in the community is increased to 110% to conduct key inspections on the key components in the water supply system to ensure their normal operation.
[0124] Compared with the prior art, the beneficial effects of the present invention are as follows: through a zoning method based on the similarity of water pressure fluctuations, the high cost and complex data processing problems caused by the increase in the density of monitoring points in the prior art are solved; through dynamic adjustment of secondary water supply status indicators and correlation analysis, the system can respond to changes in water supply modes in a timely manner, avoiding the problem of delayed response of traditional monitoring systems; at the same time, the similarity of water pressure fluctuations is used for regional zoning and representative node selection, which optimizes the monitoring efficiency and the accuracy of the early warning strategy, and improves the regulation ability and system stability of the water supply network. BRIEF DESCRIPTION OF THE DRAWINGS
[0125] Figure 1 It is a flow chart of the overall system modules of the present invention. DETAILED DESCRIPTION
[0126] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0127] Embodiment 1:
[0128] like Figure 1 The pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partitioning shown in the figure includes the following specific steps:
[0129] Pipeline network division module: used to determine the monitoring area of the water supply network and mark each pipeline network node in the monitoring area, wherein the pipeline network nodes connected to the secondary water supply system of the community are divided into the first pipeline network node set; the remaining pipeline network nodes are divided into the second pipeline network node set;
[0130] Data acquisition module: used to regularly collect water pressure fluctuation data of the first pipe network node set and the second pipe network node set, as well as secondary water supply status indicators of the community secondary water supply system, and store the collected data to form a historical database;
[0131] Data extraction module: used to receive the historical database, select the time period T immediately before the current moment as the calculation period, extract the water pressure fluctuation data within the calculation period from the historical database, and sequentially form a first extracted data set and a second extracted data set, wherein the first extracted data set and the second extracted data set correspond to the first pipe network node set and the second pipe network node set respectively;
[0132] Secondary water supply status index adjustment module: used to obtain the water use behavior pattern of the community users in the previous time period T, and dynamically adjust the secondary water supply status index according to the behavior pattern;
[0133] A first trend change index building module: used for receiving and analyzing the first extracted data set, calculating the first trend change index for evaluating the similarity of water pressure fluctuations, partitioning the first pipe network node set according to the first trend change index, and selecting a representative pipe network node from each partition as the first monitoring point;
[0134] A second trend change index building module: used for receiving and analyzing the second extracted data set, calculating the second trend change index for evaluating the similarity of water pressure fluctuations, partitioning the second pipe network node set according to the second trend change index, and selecting a representative pipe network node from each partition as a second monitoring point;
[0135] A first correlation evaluation coefficient construction module is used to obtain the first water pressure fluctuation data of the first monitoring point within the calculation period T and the secondary water supply status index at the corresponding position, and perform a correlation analysis on the two to obtain a first correlation evaluation coefficient, which is used to evaluate the correlation degree between the first water pressure fluctuation data and the secondary water supply status index;
[0136] A second correlation evaluation coefficient construction module is used to obtain the second water pressure fluctuation data of the second monitoring point within the calculation period T and the secondary water supply status index at the corresponding position, and perform a correlation analysis on the two to obtain a second correlation evaluation coefficient, which is used to evaluate the correlation between the second water pressure fluctuation data and the secondary water supply status index;
[0137] Comprehensive early warning model construction module: used to analyze and process the first correlation evaluation coefficient, the second correlation evaluation coefficient, the first trend change index and the second trend change index to generate a comprehensive early warning model, which is used to provide corresponding early warning strategies for the first pipeline node set and the second pipeline node set respectively.
[0138] Further explanation: the pipe network nodes connected to the secondary water supply system of the community are divided into a first pipe network node set; the remaining pipe network nodes are divided into a second pipe network node set, which specifically includes:
[0139] 1.1) Obtain and process pipeline network structure data;
[0140] The system obtains the structural data of the water supply network; the structural data includes the location of all nodes in the network, the connection relationship between nodes, and the node type, and the node type is: whether it is a node connected to the secondary water supply system of the community;
[0141] Specific operations:
[0142] Import complete pipe network structure data from existing GIS system or pipe network management system;
[0143] Perform preliminary processing on the imported data to ensure its integrity and accuracy, with special attention paid to the connection relationship and type identification of the nodes;
[0144] 1.2) Identify the connection nodes of the community secondary water supply system;
[0145] After obtaining the structural data of the pipe network, identify the pipe network nodes connected to the secondary water supply system of the community; divide these nodes into a first pipe network node set N1;
[0146] Specific operations:
[0147] Based on the pipe network structure data, identify all nodes directly connected to the secondary water supply system of the community; these nodes are usually located at the entrance or inside the community and are directly connected to the secondary water supply facilities of the community, which are secondary water supply pump rooms or water storage tanks;
[0148] Mark these nodes and classify them as the first pipe network node set N1;
[0149] 1.3) Divide other pipe network nodes;
[0150] After identifying and dividing the first pipe network node set N1, the remaining nodes in the water supply pipe network are divided into a second pipe network node set N2;
[0151] Specific operations:
[0152] Automatically classify all nodes that are not classified into the first pipe network node set N1 into the second pipe network node set N2;
[0153] Ensure that each node is correctly assigned to one of the sets to avoid duplication or omission;
[0154] 1.4) Store and manage node set data;
[0155] After completing the node division, the division results are stored in the system database for subsequent monitoring and analysis.
[0156] Specific operations:
[0157] Create a database table for storing detailed information of the first pipe network node set N1 and the second pipe network node set N2, including the ID, location, and connection relationship of each node;
[0158] Record the criteria for dividing nodes within each set for future review and analysis;
[0159] 1.5) Verify and adjust the division results;
[0160] Finally, verify the partitioning results to ensure that all nodes have been correctly classified; if any anomalies are found, make corresponding adjustments;
[0161] Specific operations:
[0162] Verify the rationality of the first and second pipe network node sets through system simulation or historical data playback;
[0163] If it is found that some nodes are misclassified or missed, the division results in the database should be adjusted and updated in time.
[0164] Further description, the method is used to regularly collect water pressure fluctuation data of the first pipe network node set and the second pipe network node set, as well as the secondary water supply status index of the community secondary water supply system, and store the collected data to form a historical database, specifically including:
[0165] Select water pressure sensors and secondary water supply status monitoring sensors, and deploy them at the first pipe network node set, the second pipe network node set, and key locations of the community secondary water supply system;
[0166] Specific operations:
[0167] Sensor selection: Choose a high-precision pressure sensor suitable for long-term water pressure monitoring. The sensor’s range should cover the expected water pressure range in the pipe network, with a resolution of 0.01 MPa and a sampling frequency of no less than 1 Hz.
[0168] Installation location: Install water pressure sensors at representative nodes in the first pipe network node set N1 and the second pipe network node set N2; for the secondary water supply system of the community, install sensors at the entrance, outlet and key locations of the secondary water supply pump room and water storage tank;
[0169] And ensure that all sensors are connected to the data acquisition host via wired or wireless means to facilitate real-time data transmission;
[0170] Setting a time interval for data collection, and regularly collecting water pressure fluctuation data of the first pipe network node set and the second pipe network node set, as well as secondary water supply status indicators of the community secondary water supply system according to the set time interval;
[0171] Specific operations:
[0172] Collection time interval setting: within the calculation period T, data is collected every Δt seconds to ensure that the details of the water pressure fluctuation are fully captured. In this embodiment, Δt is 10 seconds;
[0173] Water pressure fluctuation data collection: In the calculation period T, for the water pressure value of each node in the first pipe network node set N1, marked as P i,N1 (t); For the water pressure value of each node in the second pipe network node set N2, marked as P i′,N2(t); where i and i′ are the node numbers in the corresponding N1 and N2 sets, respectively, and t is the collection time point in the previous time period T;
[0174] Secondary water supply status indicator collection: At the same time, key indicators of the secondary water supply system of the community are collected, including the operating status S of the water supply pump p (t), water level L(t) in the water storage tank;
[0175] For secondary water supply status indicators:
[0176] Define the secondary water supply status index as S status (t), the calculation formula is as follows:
[0177]
[0178] Among them, W p is the water pressure weight coefficient, which reflects the weight of the water supply pump water pressure on the system state. p The value range is set between [0.5,1]; W p The specific value is determined by the expert group based on the actual situation;
[0179] α is an exponential factor of water pressure, which is used to adjust the influence of water pressure; in this embodiment, α is set to 1 or 2;
[0180] β is the water level adjustment coefficient, which controls the influence of water level on the state index. The value range of β is set between [0.1,1]. The specific value of β is determined by the expert group based on the actual situation. μ1 is a normal number term used to avoid S status (t) The value is 0, and 0.01≤μ1≤0.12; the specific value of μ1 is determined by the expert group based on actual conditions;
[0181] L(t) represents the water level of the water tank at the sampling time point t (unit: m); P s (t) is the output pressure of the water supply pump at the sampling time t (unit: MPa); S p (t) is the operating state of the water supply pump, which is defined as a binary function, 1 means running and 0 means stopping; L ref It is the reference water level, representing the ideal water level value of the water storage tank;
[0182] Terms in the denominator It is a standard logical function that reflects the impact of the water level in the water storage tank on the system state. The closer the water level is to the reference water level L ref , the smaller the impact on the system state; when the water level is lower than the reference water level, the denominator increases, thereby reducing the overall state index S status (t);
[0183] By normalization, we limit Sstatus The valid value range of (t) is between (0,10): The normalization method is the existing technology and will not be described in detail;
[0184] When S status When (t) is closer to 10, it means the system is in better condition, the water pressure is normal and the water level is closer to the ideal state;
[0185] When S status The closer (t) is to 0, the worse the system status is, and the water supply pump may stop or the water level may be too low. The specific value of the water level being too low is determined based on experimental data. In this embodiment, the water level being too low is L ref One third of the total; at this time, it is necessary to further determine whether the water pump is shut down;
[0186] The collected data is stored in real time in the system's historical database for subsequent analysis, modeling and early warning.
[0187] Specific operations:
[0188] Data formatting: The collected water pressure data P i (t) and secondary water supply status index S p (t), L(t) are formatted to ensure data uniformity and integrity;
[0189] Real-time storage: the formatted data is stored in a historical database; the database adopts a relational database, and the database in this embodiment is a MySQL or NoSQL database for storage;
[0190] Data backup: Back up database data regularly to prevent data loss.
[0191] Further, the formation of the first extracted data set and the second extracted data set specifically includes:
[0192] The specific time of the calculation cycle T is determined according to the real-time requirements of the system and the availability of historical data; specifically:
[0193] According to the time characteristics of the pipe network operation, T is selected as the previous hour; according to historical experience, selecting one hour of data can better capture the trend and pattern of water pressure fluctuations;
[0194] Timestamp recording: ensure that the system can record the current time now and the starting time of history t start =t now -T;
[0195] The water pressure fluctuation data within this period is extracted from the historical database, specifically:
[0196] 2.1) Use SQL query statements to extract data from the historical database;
[0197] 2.2) Classifying the extracted data by nodes, and distinguishing the data belonging to the first pipe network node set N1 and the second pipe network node set N2;
[0198] 2.3) The following data set is formed:
[0199] First extract the dataset D 1 = {P i,N1 (t)|i∈N1,t∈[t start ,t now ]};
[0200] The second extracted dataset D 2 = {P i′,N2 (t)|i′∈N2,t∈[t start ,t now ]}.
[0201] Further explanation: the method for obtaining the water use behavior pattern of the users in the community in the previous time period T and dynamically adjusting the secondary water supply status indicator according to the behavior pattern specifically includes:
[0202] For water use behavior patterns;
[0203] Collect the water consumption data U of each user within the calculation period T j (t), where j represents the user number and t represents the s (t) means the same as the collection time point;
[0204] At each time point t, the water consumption of all users is summed up to calculate the total water consumption U at that time point total (t); the calculation formula is as follows:
[0205]
[0206] Where N′ is the total number of users in the cell, U j (t) is the water consumption of the jth user at time t;
[0207] Through U total (t) Perform trend analysis on the changes in the calculation period T to determine the peak water consumption time t peak and the trough time t low ;
[0208] Define the average water consumption U avg It refers to the average value of the total water consumption at all time points within the calculation period T; it is used as a benchmark value to dynamically adjust the secondary water supply status indicator S status (t) The weight coefficient W in the formula p and exponential factor α;
[0209] Calculate the total water consumption U at all time points in period T sum ;
[0210]
[0211] Among them, t start and t now are the start and end time of period T, U total (t) is the total water consumption at time t;
[0212] The total water consumption U sum Divide by the number of time points n', and you get the average water consumption U avg ;
[0213]
[0214] Where n′ is the number of time points in the calculation period T, and Δt is the time interval between adjacent acquisition time points; it is related to the data acquisition frequency;
[0215] When the real-time total water consumption U total (t) greater than the average water consumption U avg When the system is in the peak period, it will be considered as the trough period.
Claims
1. A pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partitioning, characterized in that: The specific steps include: Pipeline network division module: used to determine the monitoring area of the water supply network and mark each pipeline network node in the monitoring area, wherein the pipeline network nodes connected to the secondary water supply system of the community are divided into the first pipeline network node set; the remaining pipeline network nodes are divided into the second pipeline network node set; Data acquisition module: used to regularly collect water pressure fluctuation data of the first pipe network node set and the second pipe network node set, as well as secondary water supply status indicators of the community secondary water supply system, and store the collected data to form a historical database; Data extraction module: used to receive the historical database, select the time period T immediately before the current moment as the calculation period, extract the water pressure fluctuation data within the calculation period from the historical database, and sequentially form a first extracted data set and a second extracted data set, wherein the first extracted data set and the second extracted data set correspond to the first pipe network node set and the second pipe network node set respectively; Secondary water supply status index adjustment module: used to obtain the water use behavior pattern of the community users in the previous time period T, and dynamically adjust the secondary water supply status index according to the behavior pattern; A first trend change index building module: used for receiving and analyzing the first extracted data set, calculating the first trend change index for evaluating the similarity of water pressure fluctuations, partitioning the first pipe network node set according to the first trend change index, and selecting a representative pipe network node from each partition as the first monitoring point; A second trend change index building module: used for receiving and analyzing the second extracted data set, calculating the second trend change index for evaluating the similarity of water pressure fluctuations, partitioning the second pipe network node set according to the second trend change index, and selecting a representative pipe network node from each partition as a second monitoring point; A first correlation evaluation coefficient construction module is used to obtain the first water pressure fluctuation data of the first monitoring point within the calculation period T and the secondary water supply status index at the corresponding position, and perform a correlation analysis on the two to obtain a first correlation evaluation coefficient, which is used to evaluate the correlation degree between the first water pressure fluctuation data and the secondary water supply status index; A second correlation evaluation coefficient construction module is used to obtain the second water pressure fluctuation data of the second monitoring point within the calculation period T and the secondary water supply status index at the corresponding position, and perform a correlation analysis on the two to obtain a second correlation evaluation coefficient, which is used to evaluate the correlation between the second water pressure fluctuation data and the secondary water supply status index; Comprehensive early warning model construction module: used to analyze and process the first correlation evaluation coefficient, the second correlation evaluation coefficient, the first trend change index and the second trend change index to generate a comprehensive early warning model, which is used to provide corresponding early warning strategies for the first pipeline node set and the second pipeline node set respectively.
2. The pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partitioning according to claim 1 is characterized in that: Divide the pipe network nodes connected to the secondary water supply system of the community into a first pipe network node set; The remaining pipe network nodes are divided into a second pipe network node set, which specifically includes: 1.1) Obtain and process pipeline network structure data; The system obtains the structural data of the water supply network; the structural data includes the location of all nodes in the network, the connection relationship between nodes, and the node type; 1.2) Identify the connection nodes of the community secondary water supply system; After obtaining the structural data of the pipe network, identify the pipe network nodes connected to the secondary water supply system of the community; divide these nodes into a first pipe network node set N1; 1.3) Divide other pipe network nodes; After identifying and dividing the first pipe network node set N1, the remaining nodes in the water supply pipe network are divided into a second pipe network node set N2; 1.4) Store and manage node set data; After completing the node division, the division results are stored in the system database for subsequent monitoring and analysis.
3. The pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partitioning according to claim 2 is characterized in that: It is used to regularly collect water pressure fluctuation data of the first pipe network node set and the second pipe network node set, as well as the secondary water supply status indicators of the community secondary water supply system, and store the collected data to form a historical database, specifically including: Select water pressure sensors and secondary water supply status monitoring sensors, and deploy them at the first pipe network node set, the second pipe network node set, and key locations of the community secondary water supply system; Setting a time interval for data collection, and regularly collecting water pressure fluctuation data of the first pipe network node set and the second pipe network node set, as well as secondary water supply status indicators of the community secondary water supply system according to the set time interval; In the calculation cycle T, the water pressure value of each node in the first pipe network node set N1 is marked as P i,N1 (t); For the water pressure value of each node in the second pipe network node set N2, marked as P i′,N2 (t); where i and i′ are the node numbers in the corresponding N1 and N2 sets, respectively, and t is the collection time point in the previous time period T; Define the secondary water supply status index as S status (t), the calculation formula is as follows: Among them, W p is the water pressure weight coefficient, which reflects the weight of the influence of the water pressure of the water supply pump on the system state, W p The value range is set between [0.5,1]; α is the exponential factor of water pressure, which is used to adjust the influence of water pressure; β is the adjustment coefficient of water level, which controls the influence of water level on state indicators. The value range of β is set between [0.1,1]; μ1 is a normal number term, which is used to avoid S status (t) is 0, and 0.01≤μ1≤0.12; L(t) represents the water level of the water storage tank at the sampling time point t; P s (t) is the output pressure of the water supply pump at the sampling time t; S p (t) is the operating state of the water supply pump, which is defined as a binary function, 1 means running and 0 means stopping; L ref It is the reference water level, representing the ideal water level value of the water storage tank; Limited S status The valid value range of (t) is between (0,10): When S status When (t) is closer to 10, it means the system is in better condition, the water pressure is normal and the water level is closer to the ideal state; When S status When (t) is closer to 0, it means that the system status is worse, and there is an abnormal situation such as the water supply pump shutting down or the water level is too low; The collected data is stored in the system's historical database in real time.
4. The pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partitioning according to claim 3 is characterized by: The forming of the first extracted data set and the second extracted data set specifically includes: Extract water pressure fluctuation data within calculation period T from the historical database; 2.1) Use SQL query statements to extract data from the historical database; 2.2) Classifying the extracted data by nodes to distinguish data belonging to the first pipe network node set N1 and the second pipe network node set N2; 2.3) The following data set is formed: The first extracted data set D1 = {P i,N1 (t)|i∈N1,t∈[t start ,t now ]}; The second extracted data set D2 = {P i′,N2 (t)|i′∈N2,t∈[t start ,t now ]}; Among them, t start =t now -T, t start ,t now They represent the start time of the calculation period T and the current time respectively.
5. The pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partitioning according to claim 4 is characterized in that: It is used to obtain the water consumption behavior pattern of the users in the community in the previous time period T, and dynamically adjust the secondary water supply status indicator according to the behavior pattern, specifically including: For water use behavior patterns; Collect the water consumption data U of each user within the calculation period T j (t), where j represents the user number and t represents the s (t) means the same as the collection time point; At each time point t, the water consumption of all users is summed up to calculate the total water consumption U at that time point total (t); Define the average water consumption U avg It refers to the average value of total water consumption at all time points within the calculation period T; When the real-time total water consumption U total (t) greater than the average water consumption U avg When the system is in the peak period, it will be considered as the trough period. For W p Dynamic adjustment to get W p (t): When U total (t)>U avg When W p (t) increases, W p0 is the initial weight coefficient, a1 is the adjustment coefficient, 0.08≤a1≤0.34, indicating that the current water demand increases and the weight of water pressure needs to be increased to ensure system stability; when U total (t)<U avg When W p (t) decrease; For dynamic adjustment of α, we get α(t): a2 is the adjustment coefficient, 0.13≤a2≤0.56; When U total (t)>U avg When U total (t)<U avg When , α(t) approaches 1, reducing the impact of fluctuations; The adjusted W p Substitute (t) and α(t) into S status (t) In the original calculation formula, the following adjusted S′ is obtained status (t) calculation formula; The system collects current pressure data P in real time s (t), water supply pump status S p (t), and water level L(t), are substituted into the above formula to calculate S′ status (t); When S′ status When (t)>8, the system is in good condition and no adjustment is required; 4≤S′ status When (t)≤8, the system enters the alert state, checks the water supply equipment and makes early warning preparations; When S′ status When (t) < 4, the system enters the alarm state, activates the emergency plan, starts the backup pump or adjusts the water pressure setting.
6. The pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partitioning according to claim 5 is characterized in that: Calculating a first trend change index for evaluating the similarity of water pressure fluctuations, partitioning the first pipe network node set according to the first trend change index, and selecting a representative pipe network node from each partition as a first monitoring point, specifically including: Receive and preprocess the first extracted data set D1 = {P i,N1 (t)|i∈N1,t∈[t start ,t now ]} to ensure data quality and consistency; the data set contains the changes in water pressure values of all nodes in the first pipe network node set N1 over time within the calculation period T; Based on the preprocessed data, the first-order derivative P′ is calculated in sequence i,N1 (t) and water pressure fluctuation amplitude A i,N1 , and combined with the first-order derivative and water pressure fluctuation amplitude, the first trend change index TCI of each node is calculated i,N1 ;This index is used to measure the degree of change in water pressure fluctuation at each node; The first trend change index TCI of each node i,N1 The calculation formula is as follows: Among them, A avg is the average value of all node fluctuations, used for standardization, P′ i,N1 (t) is the first-order derivative, which indicates the rate of change of water pressure with time, A i,N1 Reflects the range of water pressure variation at each node; According to the first trend change index TCI i,N1 Partitioning the first pipe network node set N1; Clustering algorithm is used to group nodes; TCI i,N1 To cluster features, the nodes are divided into multiple subsets, each of which represents an area with similar water pressure fluctuations; Based on the clustering results, the first pipe network node set N1 is divided into several partitions (Z1, Z2, ..., Z m ), and Z k1 ∈{Z1,Z2,...,Z m } is a partition (Z1, Z2, ..., Z m ) The k1th partition in the set, the nodes in each partition have similar water pressure fluctuation trends; Select the most representative node from each partition as the first monitoring point; In each partition Z k1 , select the first trend change index TCI i,N1 The node MJ closest to the center of the partition k1 Act as the representative node of the partition; Calculate the TCI of node i i,N1 With the partition center μ k1 Distance between: d(i,μ k1 )=|TCI i,N1 -μ k1 | Select the node with the smallest distance as the representative node: The selected representative node is used as the first monitoring point set M1; for subsequent pressure monitoring and early warning, the first monitoring point set M1 is expressed as follows; M1={MJ1,MJ2,…,MJ k1 ,…,MJ m } And according to the first monitoring point set M1, the following first water pressure fluctuation data set is obtained:
7. The pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partitioning according to claim 6 is characterized by: For the second trend change index, the second pipe network node set is partitioned, and a representative pipe network node is selected from each partition as the second monitoring point. The calculation and acquisition method is the same as the first trend change index construction module mentioned above, and will not be repeated, and the following related content is obtained: The second trend change index TCI of each node in the second pipe network node set i′,N2 The calculation formula is as follows: Among them, A′ avg is the average value of all node fluctuations, used for standardization, P′ i′,N2 (t) is the first-order derivative, which indicates the rate of change of water pressure with time, A i′ , N2 Reflects the range of water pressure variation at each node; Based on the clustering results, the second pipe network node set N2 is divided into several partitions (Z1′, Z′2, ..., Z′m ′ ), and Z k2 ∈{Z′1,Z′2,...,Z′ m′ } is a partition (Z′1, Z′2, ..., Z′ m′ ) The k2th partition in the set, the nodes in each partition have similar water pressure fluctuation trends; Select the most representative node from each partition as the second monitoring point; Specifically, the selected representative node is used as the second monitoring point set M2 for subsequent pressure monitoring and early warning. The second monitoring point set M2 is represented as follows: M2={MJ1′,MJ′2,…,MJ′k2,…,MJ′m′} And the following second water pressure fluctuation data set is obtained according to the second monitoring point set M2:
8. The pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partitioning according to claim 7 is characterized in that: A first correlation evaluation coefficient is obtained, and the first correlation evaluation coefficient is used to evaluate the correlation between the first water pressure fluctuation data and the secondary water supply state index, specifically including: Define the first correlation evaluation coefficient The calculation formula is as follows: in, is the first water pressure fluctuation data after standardization; It is a standardized secondary water supply status indicator; The value range is -1 to 1, indicating the degree of linear correlation between water pressure fluctuation and water supply status: When , it indicates a positive correlation, and the water pressure fluctuation and water supply status change in the same direction; When , it indicates a negative correlation, and the water pressure fluctuation and water supply status change in opposite directions; , indicating no significant correlation; A second correlation evaluation coefficient is obtained, and the second correlation evaluation coefficient is used to evaluate the correlation between the second water pressure fluctuation data and the secondary water supply state index, specifically including: The calculation method of the second correlation evaluation coefficient is the same as that of the first correlation evaluation coefficient, which is not repeated here, and the following content is obtained: Define the second correlation evaluation coefficient The calculation formula is as follows: in, is the standardized second water pressure fluctuation data; It is a standardized secondary water supply status indicator; The value range is -1 to 1, indicating the degree of linear correlation between water pressure fluctuation and water supply status: When , it indicates a positive correlation, and the water pressure fluctuation and water supply status change in the same direction; When , it indicates a negative correlation, and the water pressure fluctuation and water supply status change in opposite directions; , indicating no significant correlation.
9. The pipe network pressure monitoring and early warning system based on water pressure fluctuation similarity partitioning according to claim 8 is characterized in that: The comprehensive early warning model is used to provide corresponding early warning strategies for the first pipe network node set and the second pipe network node set, respectively, including: The calculation formula for defining the comprehensive early warning model is as follows: Among them, S warning is the index value of the comprehensive early warning model, μ2 is a positive constant term, 0.12≤μ2≤0.23, which is used to avoid S warning The case of taking 0; S warning The value range of S is (0,1), and based on experimental verification and historical data, S warning The strategy judgment threshold is U1, 0.23≤U1≤0.68; The early warning strategy is as follows: 3.1) If S warning >U1, when and When the water pressure fluctuation is highly consistent with the water supply status; Considering the high correlation between water pressure and water supply status, the water supply pressure of the first set of pipe network nodes is increased by 15%, and the water supply pressure of the second set of pipe network nodes is increased by 13% to enhance the system's ability to cope with pressure fluctuations; For the secondary water supply system in the residential area, the inspection frequency is increased to 150%, with a focus on checking the tightness of pipes and equipment to ensure that there are no hidden dangers of water leakage or pressure reduction in the water supply system; when and When , the water pressure fluctuation changes in the opposite direction to the water supply status; Since the water supply status is negatively correlated with the water pressure, the water supply pressure of the first pipe network node set is reduced by 10%, and the water supply pressure of the second pipe network node set is reduced by 11% to avoid excessive water pressure causing system burden; For the secondary water supply system in the community, the inspection frequency is increased to 130%, and the operating status of the water supply valves and pumps is checked to prevent failures caused by load imbalance; 3.2) If S warning =U1; when and When the water pressure fluctuation is consistent with the water supply status, the water supply pressure of the first pipe network node set is increased by 5%, and the water supply pressure of the second pipe network node set is increased by 3% to maintain the stability of the system; The inspection frequency of the community's secondary water supply system is set to 120% to ensure the normal operation of each component of the system, and focus on monitoring the readings of the pressure sensor; when and When , the water pressure fluctuation changes in the opposite direction to the water supply status; Due to the negative correlation between water supply pressure and water pressure, the water supply pressure of the first pipe network node is reduced by 5%, and the water supply pressure of the second pipe network node is reduced by 7% to reduce the system burden; The inspection frequency of the community's secondary water supply system has been increased to 125%, and inspections of pumps and valves have been strengthened to ensure that they can effectively cope with pressure fluctuations; 3.3) If S warning <U1; when and , the water pressure fluctuation is consistent with the water supply state; since the system performs stably, the water supply pressures of the first pipe network node set and the second pipe network node set are kept unchanged; The inspection frequency of the community's secondary water supply system is set to 105% to ensure that the system is within normal operating range. Perform routine maintenance; when and When , the water pressure fluctuation changes in the opposite direction to the water supply status; The water supply pressure of the first pipe network node set is fine-tuned by 5%, and the water supply pressure of the second pipe network node set is fine-tuned by 8%; The inspection frequency of the community’s secondary water supply system has been increased to 110%, with key components in the water supply system being inspected to ensure their normal operation.
Citation Information
Patent Citations
Real-time hydraulic information based dynamic division and control method of city water supply zone
CN102385313A
Alarm method and system for secondary water supply based on Internet of Things
CN117392815A
Graph neural network water supply network sensor optimization arrangement method and system
CN117436218A
Method for selecting section of water leakage suspicion by water network analysis and water supply integrated management operating system with function thereof
KR101105192B1
Method and apparatus for enhancing operation of a fluid transport pipeline
US20080082215A1
Cited By
Control method of secondary pressurization domestic water supply system
CN119378941A
City pipe network critical pressure prediction method based on data modeling
CN120030956A
Dynamic water affair monitoring method and system and storage medium
CN120890043A
