Digital intelligent water affair pipe network comprehensive scheduling system

Abstract

The invention relates to the technical field of data processing, and discloses a comprehensive dispatching system for a digital intelligent water service pipe network. Comprising a processing module, a layering module, an identification module, a scheduling module, an analysis module and an evaluation module which are connected in sequence. The processing module preprocesses the pipe network data and constructs a dynamic boundary area; the layering module generates operation parameters according to function classification; the identification module analyzes equipment fault features to obtain state data; the scheduling module formulates a preliminary scheme according to a time-sharing rule; the analysis module performs multi-target processing based on the dynamic weight to generate a scheduling instruction; and the evaluation module evaluates pressure, flow and water quality indexes to form a target strategy. The operation efficiency of the water supply network is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a digital water pipe network integrated dispatching system. Background Art

[0002] The existing water supply network scheduling method mainly relies on manual experience for regulation. This scheduling method usually adopts fixed scheduling rules, sets water supply parameters based on historical operating experience, and monitors the network operation status through manual observation and recording. The monitoring data of the water supply network includes pressure data, flow data and water quality data. These data are collected through decentralized monitoring equipment and then summarized and analyzed by the dispatcher. The operation scheduling of the network is mainly based on simple threshold control. When the monitoring data exceeds the preset range, the dispatcher adjusts the parameters based on experience. At the same time, the existing scheduling methods have also begun to introduce GIS technology for visual management and basic analysis of network equipment.

[0003] However, the existing technology has the following shortcomings: first, manual experience scheduling is difficult to cope with complex and changeable water supply demands, especially during peak water usage periods, and it is impossible to make accurate scheduling decisions quickly; second, decentralized data collection and isolated data analysis methods make it impossible to fully utilize the correlation between various types of monitoring data; third, simple threshold control methods are difficult to achieve overall optimization of the water supply system, often resulting in excessive local regulation and insufficient overall coordination; finally, although GIS technology has been introduced, it is limited to basic visualization and simple analysis, and has failed to give full play to its advantages in spatial analysis and decision support. Summary of the invention

[0004] The present application provides a digital water pipe network integrated dispatching system, which is used to improve the operating efficiency of the water supply network and significantly improve the operating stability and scientific dispatching of the water supply system.

[0005] In a first aspect, the present application provides a digital intelligent water pipe network integrated dispatching system, the digital intelligent water pipe network integrated dispatching system comprising: a processing module, a stratification module, an identification module, a dispatching module, an analysis module and an evaluation module; the output end of the processing module is connected to the input end of the stratification module, the output end of the stratification module is connected to the input end of the identification module, the output end of the identification module is connected to the input end of the dispatching module, the output end of the dispatching module is connected to the input end of the analysis module, and the output end of the analysis module is connected to the input end of the evaluation module;

[0006] A processing module is used to pre-process the pressure data, flow data and water quality data in the water supply network, construct a dynamic boundary area in combination with the spatial location information of the network, and screen the data in the dynamic boundary area according to the completeness, accuracy and timeliness indicators to obtain the basic data of the network;

[0007] A hierarchical module is used to perform hierarchical processing on the basic data of the pipe network, classify the monitoring sites according to the functions of water supply hubs, water distribution stations and terminal pipe networks, and generate operating parameters based on pipe section analysis, fire hydrant coverage radius query and valve closing impact range analysis;

[0008] An identification module is used to record and process the equipment operation status by using the operation parameters, identify the fault characteristics and propagation law by combining the equipment history records and the status of adjacent associated equipment, and obtain equipment status data;

[0009] A scheduling module is used to perform scheduling analysis based on the equipment status data, integrate water supply and flow information according to the time-sharing rules of peak period, off-peak period and valley period, and obtain a preliminary scheduling plan;

[0010] An analysis module is used to perform multi-objective processing on the preliminary scheduling plan, and obtain a scheduling instruction from the water supply pressure balance performance consumption efficiency analysis based on a dynamic weight allocation mechanism;

[0011] The evaluation module is used to analyze the effects according to the scheduling instructions, evaluate the pressure fluctuation range, flow distribution balance and water quality compliance rate indicators, and generate a target scheduling strategy.

[0012] In the technical solution provided by this application, by pre-processing the pressure data, flow data and water quality data in the water supply network, and combining the spatial location information of the network to build a dynamic boundary area, effective data screening and spatial correlation analysis are achieved; by layering the basic data of the network, the monitoring sites are classified according to the functions of water supply hubs, water distribution stations and terminal networks, a clear network hierarchy structure is established, and the safety and emergency response capabilities of the network are enhanced by combining pipe section analysis, fire hydrant coverage radius query and valve closing impact range analysis; by recording and processing the operating status of the equipment, combined with the equipment history By combining historical records and the status of adjacent and related equipment, accurate identification of fault characteristics and propagation laws is achieved; by integrating water supply and flow information according to the time-sharing rules of peak, off-peak and off-peak periods, the pertinence and effectiveness of the scheduling plan are improved; by conducting multi-objective analysis from aspects such as water supply pressure balance, system energy efficiency and service quality satisfaction based on the dynamic weight allocation mechanism, scientific optimization of scheduling instructions is achieved; by comprehensively evaluating the pressure fluctuation range, flow distribution balance and water quality compliance rate indicators, continuous improvement and optimization of the scheduling strategy is ensured, and the operating efficiency of the water supply network is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0014] Figure 1 This is a schematic diagram of an embodiment of a digital water pipe network integrated dispatching system in an embodiment of the present application. DETAILED DESCRIPTION

[0015] An embodiment of the present application provides a digital water pipe network integrated scheduling system. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way are interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0016] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 , an embodiment of the digital water pipe network integrated dispatching system in the embodiment of the present application includes:

[0017] Processing module 101 is used to pre-process the pressure data, flow data and water quality data in the water supply network, construct a dynamic boundary area based on the spatial location information of the network, and screen the data in the dynamic boundary area according to the completeness, accuracy and timeliness indicators to obtain the basic data of the network;

[0018] The hierarchical module 102 is used to hierarchically process the basic data of the pipe network, classify the monitoring sites according to the functions of water supply hubs, water distribution stations and terminal pipe networks, and generate operating parameters based on pipe section analysis, fire hydrant coverage radius query and valve closing impact range analysis;

[0019] Identification module 103, used to record and process the equipment operation status by using the operation parameters, identify the fault characteristics and propagation law by combining the equipment history records and the status of adjacent associated equipment, and obtain equipment status data;

[0020] The scheduling module 104 is used to perform scheduling analysis based on the equipment status data, integrate the water supply and flow information according to the time-sharing rules of peak period, flat period and valley period, and obtain a preliminary scheduling plan;

[0021] The analysis module 105 is used to perform multi-objective processing on the preliminary scheduling plan, and obtain the scheduling instructions from the water supply pressure balance performance consumption efficiency analysis based on the dynamic weight allocation mechanism;

[0022] The evaluation module 106 is used to perform effect analysis according to the scheduling instructions, evaluate the pressure fluctuation range, flow distribution balance and water quality compliance rate indicators, and generate a target scheduling strategy.

[0023] Specifically, the processing module 101 performs preprocessing operations on the data collected by the water supply network. The pressure data processed by this module includes the real-time pressure values ​​of each key node of the network, which is recorded in units of 0.1MPa and the collection frequency is once every 5 minutes; the flow data records the flow of the pipe section and the node flow, in units of cubic meters / hour, including the direction of the water flow and the size of the flow; the water quality data includes real-time monitoring data of key indicators such as turbidity (NTU value), residual chlorine content (mg / L), and pH value. The spatial location information of the network is obtained based on the GIS one-picture function, which records the longitude and latitude coordinates and altitude information of all equipment in the network. The dynamic boundary area is a functional partition constructed based on the physical connection relationship of the water supply network. The adjacent monitoring points are divided into several relatively independent water supply partitions according to the distribution of water supply pressure. These areas are not fixed, but will be dynamically adjusted as the water supply status changes. During the data screening process, the integrity index is evaluated by calculating the missing rate of data records. When the data missing rate of a monitoring point exceeds 10%, the data of the monitoring point will be marked as pending verification; the accuracy index sets upper and lower limits based on the statistical range of historical data. For pressure data, the normal range is set between 0.15MPa and 0.40MPa. Data outside this range requires secondary verification; the timeliness index requires that the data collection delay does not exceed 30 seconds, and expired data will be eliminated.

[0024] The hierarchical module 102 performs hierarchical processing on the pre-processed basic data of the pipe network. In the water supply system, a water supply hub usually refers to a large water plant or a pressure pump station with a daily water supply capacity of more than 50,000 tons, which directly undertakes the task of regional water supply; a water distribution station is a medium-sized pressure facility with a daily water supply capacity between 5,000 tons and 50,000 tons, which is responsible for secondary pressurization and water quality regulation in the region; the terminal pipe network refers to the part of the pipe network directly connected to the user, and the pipe diameter is usually less than DN200. This hierarchical architecture can clearly reflect the hierarchical relationship of the water supply system. The pipe section analysis function can draw a cross section or a longitudinal section at any location on a GIS map, and intuitively display the spatial distribution of underground pipelines, including key information such as the buried depth, pipe diameter, and material of the pipeline. The fire hydrant coverage radius query function can quickly find fire hydrants within a radius with any point as the center, and display detailed information of the fire hydrants, such as the installation year, the last maintenance time, and the water outlet pressure. The valve closing impact range analysis can quickly locate the valve that needs to be closed when a pipeline failure occurs based on the pipeline network topology, and calculate the number of users within the valve closing impact range.

[0025] The identification module 103 monitors and analyzes the equipment operation status in real time. The equipment operation status data includes the speed, current, bearing temperature, vibration value and other operating parameters of the water pump motor, which are collected once every minute. The equipment history record includes the installation time, maintenance record, replacement record and other life cycle information of the equipment. Adjacent associated equipment refers to a group of equipment that has a direct pipeline connection or functional interdependence in the water supply system, such as a booster pump group running in series. By analyzing the state change rules of these equipment groups, the propagation path and potential impact range of equipment failure can be identified. The scheduling module 104 formulates a time-divided scheduling plan based on the equipment status data. In the water supply system, the peak period usually occurs from 6 to 9 in the morning and from 6 to 9 in the evening. The water consumption in these two periods may reach more than 150% of the daily average; the flat peak period is the working period, and the water consumption is basically maintained at the daily average level; the trough period is mainly from 23 o'clock at night to 5 o'clock in the morning of the next day, and the water consumption may drop to less than 50% of the daily average. The time-sharing rules will dynamically adjust the water supply and pipeline pressure according to the water usage characteristics in different time periods, reducing energy consumption while ensuring water supply safety.

[0026] The analysis module 105 performs multi-objective optimization processing on the preliminary scheduling plan. The balance of water supply pressure needs to ensure that the pressure value of each user point remains within a reasonable range. Generally, the terminal pressure is required to be between 0.20MPa and 0.35MPa, and the pressure difference does not exceed 0.10MPa. Energy efficiency takes into account the power consumption of the water pump and the hydraulic loss of the pipe network, and reduces the total energy consumption by adjusting the operating conditions of the water pump and the pressure distribution of the pipe network. The dynamic weight allocation mechanism will automatically adjust the weight coefficients of goals such as water supply pressure, energy consumption control, and water quality assurance according to the real-time operation situation. The evaluation module 106 conducts a comprehensive evaluation of the scheduling execution effect. The pressure fluctuation range reflects the stability of the water supply, and the pressure fluctuation at the same monitoring point within 24 hours is required to be no more than 0.05MPa. The flow distribution balance indicates whether the water supply between each water supply zone is balanced, and is evaluated by calculating the water supply per unit area of ​​each zone. The water quality compliance rate focuses on the stability of water quality indicators, including continuous monitoring data of key indicators such as turbidity, residual chlorine, and pH value. In actual applications, when a water supply zone has abnormal pressure, the system first locates the abnormal position through a GIS map and analyzes the pipe network topology and equipment operating status in the area. If it is found that the pump of a water distribution station has abnormal vibration, the system will immediately adjust the operating parameters of the adjacent water distribution station to ensure the safety of regional water supply. At the same time, the dynamic boundary area will automatically adjust according to the pressure distribution to minimize the affected area. This process shows the complete processing flow from abnormal monitoring, cause analysis to scheduling response, reflecting the intelligence level of the system. The generated target scheduling strategy will comprehensively consider water supply safety, economic benefits and service quality, and form a scheduling plan including specific parameters such as equipment start and stop time, operating conditions, and valve opening.

[0027] In the embodiment of the present application, by pre-processing the pressure data, flow data and water quality data in the water supply network, and combining the spatial location information of the network to build a dynamic boundary area, effective data screening and spatial correlation analysis are achieved; by layering the basic data of the network, the monitoring sites are classified according to the functions of water supply hubs, water distribution stations and terminal networks, a clear network hierarchy structure is established, and the safety and emergency response capabilities of the network are enhanced by combining the pipe section analysis, fire hydrant coverage radius query and valve closing impact range analysis; by recording and processing the equipment operation status, combined with the equipment history record By recording and recording the status of adjacent related equipment, accurate identification of fault characteristics and propagation laws is achieved; by integrating water supply and flow information according to the time-sharing rules of peak, off-peak and off-peak periods, the pertinence and effectiveness of the scheduling plan are improved; by conducting multi-objective analysis from aspects such as water supply pressure balance, system energy efficiency and service quality satisfaction based on the dynamic weight allocation mechanism, scientific optimization of scheduling instructions is achieved; by comprehensively evaluating the pressure fluctuation range, flow distribution balance and water quality compliance rate indicators, continuous improvement and optimization of the scheduling strategy is ensured, and the operating efficiency of the water supply network is improved.

[0028] In a specific embodiment, the processing module 101 is used to:

[0029] (1) Sort the pressure data, flow data, and water quality data according to timestamps to obtain a time series data sequence;

[0030] (2) Perform a range check on the time series data sequence, mark the data that exceeds the historical maximum and minimum values ​​as abnormal data, and obtain an abnormal mark sequence;

[0031] (3) Based on the physical connection relationship of the water supply network, the data of adjacent monitoring points in the time series data sequence are correlated and analyzed, and the abnormal marker sequence is combined to generate the correlation analysis results;

[0032] (4) Compare the data collection time in the correlation analysis results with the system time, filter out data records with delays exceeding the preset time, and obtain a valid data set;

[0033] (5) For valid data sets, calculate the data quality score based on the completeness index, accuracy index, and timeliness index;

[0034] (6) The data quality score is weighted with the valid data set, combined with the spatial location information of the pipeline network and the dynamic boundary area to generate the basic data of the pipeline network.

[0035] Specifically, the processing module 101 performs timestamp sorting on the collected pressure data, flow data and water quality data. The pressure data records the real-time pressure value of each node in the water supply network, and the collection frequency is once every 5 minutes. The data format includes the node number, pressure value (MPa) and collection timestamp; the flow data includes the pipe section flow and node flow information, and records the direction and flow size of the water flow (m 3 / h), also collected every 5 minutes; water quality data covers water quality indicators such as turbidity (NTU), residual chlorine content (mg / L), and pH value, and the collection frequency is once every 10 minutes. The timestamp sorting process organizes these three types of data according to a unified time reference, and forms a time series data sequence through time alignment to ensure the temporal consistency of the data.

[0036] During the range check phase, a reasonable range of variation is established based on historical data statistics. The normal operating range of pressure data is 0.15MPa to 0.40MPa, and data points outside this range are marked; flow data is marked as abnormal by calculating the rate of change between the two time points before and after, and when the rate of change exceeds 30%, it is marked as abnormal; water quality data sets thresholds according to national drinking water standards, such as turbidity not exceeding 1NTU, residual chlorine content between 0.30-0.80mg / L, and pH value between 6.5-8.5. All data points outside the range will be recorded in the abnormal marking sequence, including the specific time, location and degree of deviation of the abnormal data.

[0037] The correlation analysis phase is carried out using the physical connection relationship of the water supply network. According to the network topology information provided by a GIS map, the connection relationship between adjacent monitoring points is clarified. The data between adjacent monitoring points should have a certain correlation, such as the upstream and downstream pressure difference should comply with the hydraulic calculation law, and the flow data must meet the node balance. The data of adjacent monitoring points in the time series data sequence are compared and combined with the existing abnormal marker sequence to generate the correlation analysis results. This result reflects the spatial correlation characteristics of the data and helps to identify local anomalies.

[0038] Data timeliness check is achieved by comparing the data collection time with the current system time. The preset time threshold is set to 30 seconds, and any data record with a collection delay exceeding this threshold will be screened out. This step ensures the real-time nature of the data and provides a reliable data basis for subsequent real-time scheduling. The screened data forms a valid data set, which includes pressure, flow and water quality data with qualified timeliness.

[0039] The calculation of data quality score comprehensively considers three dimensions: integrity index, accuracy index and timeliness index. The integrity index reflects the completeness of data records and is obtained by calculating the data missing rate within a specific time period; the accuracy index is based on the abnormal mark sequence and calculates the efficiency of data; the timeliness index is scored according to the data delay. The weights of these three indicators are 0.3, 0.4 and 0.3 respectively, and the final data quality score is obtained by weighted average. The data quality score is used as the weight coefficient and weighted with the valid data set. At the same time, the spatial location information of the pipeline network from a GIS map, including the latitude and longitude coordinates and altitude of the equipment, and the dynamic boundary area information are combined to form the final basic data of the pipeline network. The dynamic boundary area is a functional zoning based on the distribution of water supply pressure, and these areas will be dynamically adjusted according to the water supply status.

[0040] Take the data processing of a water supply network node as an example: the pressure value recorded at monitoring point A at 7:00 in the morning is 0.45MPa, which is obviously beyond the normal operating range. Checking the data of its adjacent monitoring points B and C during the same period, it was found that their pressure values ​​were 0.28MPa and 0.27MPa respectively. The pressure difference between the three points obviously exceeded the hydraulic calculation expectations. At the same time, the data collection delay is only 5 seconds, and the timeliness is good. Through the calculation of completeness, accuracy and timeliness indicators, the data quality score of this monitoring point is low. Considering that this point is located at the boundary of the water supply zone, combined with the pipe network connection relationship shown in a GIS map, the abnormal data is finally marked as a data point that needs further verification.

[0041] In a specific embodiment, the layering module 102 is used to:

[0042] (1) The basic data of the pipe network is divided into monitoring areas according to the spatial location, and the monitoring sites are hierarchically marked to obtain the marking data of the water supply hub, the water distribution station and the terminal pipe network;

[0043] (2) Analyze the distribution of monitoring points based on the water supply hub tag data, water distribution station tag data, and terminal pipe network tag data, and generate site-level data based on the pipe segment connection relationship;

[0044] (3) Cut the pipe sections in the site-level data into sections, extract the depth information, diameter information, and material information of the pipe sections, and obtain the pipe section feature data;

[0045] (4) With the preset fire point as the center, search for the location of fire hydrants in the site-level data, calculate the distance from each fire hydrant to the preset fire point, and generate fire hydrant coverage data;

[0046] (5) Based on the site-level data and pipe section characteristic data, the water supply network is analyzed for valve closing in different regions, the influence range and closing sequence of each valve are calculated, and valve control data is generated;

[0047] (6) Integrate and analyze the pipe section characteristic data, fire hydrant coverage data, and valve control data to generate operating parameters.

[0048] Specifically, the hierarchical module 102 processes and analyzes the basic data of the pipe network in a hierarchical manner. First, the monitoring area is divided based on the spatial location information contained in the basic data of the pipe network. The spatial location information comes from the GIS one-picture system, which contains the latitude and longitude coordinates and altitude data of each monitoring site. The monitoring sites are divided into three levels: water supply hubs, water distribution stations, and terminal pipe networks. A water supply hub refers to a large water plant or pressure pump station with a daily water supply capacity of more than 50,000 tons, which directly undertakes the task of regional water supply; a water distribution station is a medium-sized pressure facility with a daily water supply capacity between 5,000 tons and 50,000 tons, responsible for secondary pressurization and water quality regulation in the region; the terminal pipe network is the part of the pipe network directly connected to the user, and the pipe diameter is usually less than DN200mm. The hierarchical marking process will add corresponding hierarchical identification to each monitoring site, forming water supply hub marking data, water distribution station marking data, and terminal pipe network marking data. When performing monitoring point distribution analysis for these three types of marking data, it is necessary to consider the spatial distribution relationship between the sites and the pipe network connection relationship. The connection matrix between sites is established through the pipe network topology information provided by a GIS map. The connection matrix reflects the pipe connection between sites at different levels, including information such as the length, direction and diameter of the connecting pipes. Combined with this information, site-level data is generated, which clearly shows the hierarchical structure of the water supply system and the connection relationship between sites.

[0049] In a GIS map, you can draw a cross section or longitudinal section at any location to obtain the spatial distribution information of the pipeline at that location. The depth information of the pipe section reflects the buried depth of the pipeline, which is usually between 1.2 meters and 3 meters; the pipe diameter information includes the inner diameter and outer diameter data of the pipeline, which is an important parameter for calculating the water delivery capacity; the material information records the material of the pipeline, such as ductile iron, PE plastic, etc. These information together constitute the pipe section feature data. The generation process of fire hydrant coverage data is an important analysis for fire safety. In the event of a fire, it is necessary to quickly locate the available fire hydrants around the fire point. With the preset fire point as the center, search for the surrounding fire hydrant locations in the site level data, and calculate the actual distance from each fire hydrant to the fire point. The distance calculation here needs to take into account the actual situation of the road network, rather than a simple straight-line distance. The fire hydrant coverage data contains information such as the location of each fire hydrant, water discharge capacity, and distance from the fire point.

[0050] Based on the site-level data and pipe section characteristic data, the water supply network is divided into regions. When an accident such as a pipe rupture occurs in a certain area, it is necessary to quickly determine the range of valves that need to be closed. By analyzing the pipe network topology, the minimum valve closing range is first determined, and then the valve closing sequence is formulated according to the location of the valve and the difficulty of operation. This information forms valve control data to provide support for rapid emergency response. Finally, the pipe section characteristic data, fire hydrant coverage data and valve control data are integrated and analyzed. The integration process needs to consider the correlation between these three types of data, such as which fire hydrants will be affected by the closure of a valve, and how the characteristics of the pipe section will affect the fire water supply capacity. Through this multi-dimensional analysis, operating parameters are generated to provide a basis for subsequent scheduling decisions.

[0051] For example, a pipeline burst accident occurred in a certain area. First, the location of the accident point was located through a GIS one-map. The location was located on a DN400mm ductile iron pipeline with a buried depth of 2.5 meters. Analysis of the site-level data revealed that the pipeline connected a water distribution station with a daily water supply capacity of 30,000 tons and multiple terminal pipe network nodes. Through regional valve closing analysis, it was determined that a total of 4 valves upstream and downstream needed to be closed to effectively isolate the fault section. At the same time, 3 fire hydrants in the area would be affected, of which the nearest fire hydrant was located 150 meters north of the fault point. Considering the fire safety needs, the backup water supply plan was analyzed, and the minimum water outlet pressure requirement of the fire hydrant was maintained by adjusting the water outlet pressure of the adjacent water distribution station. This example shows how to combine various types of data for comprehensive analysis and decision support. Each processing step of the hierarchical module 102 is closely related to the GIS one-map function. When dividing the monitoring area, a division method based on pressure partitioning is adopted. The boundary of the pressure partition is usually set on the pipe section where the water supply pressure is relatively stable. The area of ​​each partition is determined according to the water supply scale and is generally controlled within 2-5 square kilometers. At least one flow metering point and one pressure monitoring point are set up in each pressure zone to monitor the water supply status of the zone in real time.

[0052] The connection relationship analysis of the water supply network adopts the graph theory method. The water supply hub, water distribution station and terminal pipe network nodes are taken as the vertices of the graph, and the pipeline connection is taken as the edge to establish the network topology graph. The water flow path is analyzed by the depth-first search algorithm to identify the key water supply channels and weak links. For example, when a water distribution station needs to be shut down for maintenance, by analyzing the network topology structure, an alternative water supply path can be quickly found to ensure the safety of regional water supply. The section analysis of the pipe section adopts multi-point surveying and mapping data. For important pipe sections, a section sampling point is set every 50 meters to record the spatial coordinates and buried depth data of the pipeline. These data points are interpolated in three dimensions to form a continuous pipeline space curve, which intuitively shows the buried status of the pipeline. Section analysis is not only used for engineering construction and maintenance, but also provides an important reference for pipeline network transformation and expansion.

[0053] The fire hydrant coverage analysis takes into account the actual situation of the road network. When calculating the distance from the fire hydrant to the fire point, the road network shortest path algorithm is used instead of a simple straight-line distance. At the same time, considering the water supply capacity of the fire hydrant, it is generally required that the water outlet pressure of the outdoor fire hydrant is not less than 0.10MPa and the flow rate is not less than 15L / s. Through analysis, it is ensured that there are available fire hydrants within 150 meters of any fire point. When determining the valve closing range, it is necessary to balance the two factors of impact range and operation difficulty. Priority is given to valve combinations that are easy to operate and have a small impact range, while considering the maintenance status and reliability of the valve. The valve closing sequence needs to take into account the direction of water flow, usually closed from downstream to upstream in sequence to avoid water hammer.

[0054] In a specific embodiment, the identification module 103 is used to:

[0055] (1) Record the pressure data, flow data, and water quality data in the operating parameters in time segments, establish a data association table according to the equipment location, and obtain the equipment operation record;

[0056] (2) Extract the operating time, maintenance cycle, and failure frequency information of each device from the equipment operation records, organize them in chronological order, and generate a device historical data sequence;

[0057] (3) Compare and analyze the equipment historical data sequence with the equipment operation record, mark the equipment operation abnormal points and equipment status mutation points, and form equipment characteristic data;

[0058] (4) Based on the equipment feature data, extract the operating status change rules of adjacent related equipment and generate an equipment association map;

[0059] (5) Analyze the abnormal propagation path in the equipment association map, extract the temporal relationship and spatial distribution of the fault occurrence, and form a fault propagation chain;

[0060] (6) Integrate and analyze equipment feature data, equipment association graphs, and fault propagation chains to generate equipment status data.

[0061] Specifically, the identification module 103 records the pressure data, flow data and water quality data in the operating parameters in time segments. The pressure data includes the pressure value (MPa) of each monitoring point, which is collected every 5 minutes; the flow data records the instantaneous flow rate (m 3 / h) and cumulative flow, also every 5 minutes; water quality data includes indicators such as turbidity, residual chlorine, pH value, etc., which are collected every 10 minutes. According to the spatial location of the equipment, a data association table is established to associate different types of data at the same location to form an equipment operation record. The data association table contains the equipment number, location coordinates, collection time and corresponding monitoring values. Next, the key operation information of each device is extracted from the equipment operation record. The operating time refers to the cumulative working time of the equipment, recorded in hours; the maintenance cycle records the regular maintenance time and maintenance content of the equipment; the fault frequency information counts the number and type of equipment failures. This information is sorted in chronological order to generate a historical data sequence for the equipment. The historical data sequence reflects the operating rules and health status change trends of the equipment.

[0062] Compare and analyze the historical data sequence of the equipment with the current equipment operation record, and identify abnormal conditions by setting thresholds. Operation abnormality points refer to the moment when the equipment parameters exceed the normal operating range, such as a sudden increase in pump current, a sudden drop in pressure, etc.; state mutation points refer to the moment when the equipment parameters change significantly in a short period of time, such as a sharp fluctuation in flow, a sudden change in water quality indicators, etc. These abnormal points and mutation points constitute the equipment characteristic data, reflecting the operating characteristics of the equipment.

[0063] Based on the equipment feature data, analyze the changing rules of the operating status of adjacent and associated equipment. Adjacent and associated equipment refers to a group of equipment that has a direct physical connection or functional dependency in the water supply system, such as a series of pump groups and adjacent water distribution stations. By analyzing the changing relationship of the operating parameters of these equipment, the association pattern between equipment is established, and an equipment association map is generated. The association map shows the influence relationship and linkage rules between equipment. In-depth analysis of the abnormal propagation path in the equipment association map. When a device fails, the impact of the failure will spread to the surrounding equipment through the pipeline network. By analyzing the time sequence and spatial distribution characteristics of the failure, the propagation law of the failure is identified and a fault propagation chain is formed. The fault propagation chain records the origin point, propagation path and impact range of the fault, which helps to quickly locate the source of the fault and take targeted measures.

[0064] The equipment characteristic data, equipment association map and fault propagation chain are integrated and analyzed. The integration process takes into account the equipment's operating characteristics, associations and fault patterns to form a comprehensive equipment status assessment result. These analysis results are recorded in the equipment status data to provide a basis for scheduling decisions.

[0065] Take a group of water pumps in a water supply network as an example: the water pump group consists of three water pumps running in series, responsible for regional booster water supply. By analyzing the operation records of the water pumps, it was found that the current value of water pump No. 1 began to fluctuate after 8 hours of continuous operation, and the fluctuation amplitude gradually increased. Looking at the historical data of the equipment, it was found that this situation had occurred twice in the past three months, and both were related to the increase in bearing temperature. At the same time, the operating parameters of water pumps No. 2 and No. 3 also changed accordingly, and the flow and pressure showed a fluctuating trend. Through correlation analysis, it was found that the abnormality of water pump No. 1 would be transmitted to water pump No. 2 within 15-20 minutes, and then affect water pump No. 3 after 10-15 minutes. This fault propagation law is recorded in the fault propagation chain, and corresponding preventive measures are formulated.

[0066] In a specific embodiment, the scheduling module 104 is used to:

[0067] (1) Divide the water supply and flow information in the equipment status data into peak time periods, off-peak time periods, and off-peak time periods according to a 24-hour cycle to obtain time-divided data;

[0068] (2) Compare the time-divided data with the historical data of the same period, analyze the changing trends of water supply and flow information, and generate water use pattern data;

[0069] (3) Statistic the pressure fluctuations in each period of the water use pattern data, and combine them with the equipment operation information in the equipment status data to form pressure distribution data;

[0070] (4) Group the pressure distribution data by water supply area, analyze the supply-demand balance relationship of each area during peak, off-peak and trough periods, and obtain regional balance data;

[0071] (5) For the supply-demand contradiction areas appearing in the regional balance data, the water use pattern data and pressure distribution data are combined to perform adjustment calculations and generate adjustment plan data;

[0072] (6) Match and analyze the adjustment plan data with the equipment status data to generate a preliminary scheduling plan.

[0073] Specifically, the water supply and flow information in the equipment status data are divided according to a 24-hour cycle. The water supply is in cubic meters, recording the water output in each period; the flow information includes instantaneous flow and cumulative flow, recording the size and direction of the water flow. A day is divided into three periods: peak period, off-peak period and trough period. The peak period occurs from 6 to 9 in the morning and 6 to 9 in the evening, which is the main period for residents to use water; the off-peak period is from 9 to 18 during working hours, and the water consumption is relatively stable; the trough period is from 23 o'clock at night to 5 o'clock in the morning of the next day, and the water consumption is the lowest. This division forms time-divided data. When comparing and analyzing the time-divided data with the historical data of the same period, seasonal factors, climate conditions and user habits need to be considered. The historical data of the same period is the water supply and flow records of the same period in the past 30 days. Through comparative analysis, the trend of water use changes is extracted, such as the weekly increase in water use during the morning peak, or the regularity of flow fluctuations in a specific period. These trend information is recorded in the water use pattern data, reflecting the water use characteristics of the water supply area.

[0074] Pressure fluctuations reflect the stability of water supply and record the pressure change range and change rate of each measuring point. Combined with equipment operation information, such as pump operation status, valve opening, etc., pressure distribution data is formed. Pressure distribution data shows the pressure distribution status of the entire water supply network.

[0075] After grouping the pressure distribution data by water supply area, the supply and demand balance relationship of each area at different time periods is analyzed. The supply and demand balance relationship includes the matching degree of water supply capacity and water demand, and whether the pressure distribution meets the user's requirements. This analysis produces regional balance data, which reflects the operating status of each water supply zone. For the supply and demand contradiction areas appearing in the regional balance data, adjustment calculations are required. The contradiction between supply and demand is manifested in insufficient water supply capacity or uneven pressure distribution. The process of adjustment calculation can be expressed by the following formula:

[0076]

[0077] Where: W i is the water use rule weight of the i-th period; P i is the pressure adjustment coefficient of the i-th period; Y i is the supply and demand balance index of the ith region; F i is the flow regulation factor of the ith region; K i is the time period correction coefficient; n is the total number of time periods; A is the adjustment optimization value.

[0078] Based on the calculation results, the regulation plan data is generated, including the start and stop time of the pump, operating parameters and valve regulation strategy. Finally, the regulation plan data is matched and analyzed with the equipment status data to ensure that the regulation plan is compatible with the equipment operating status, thereby generating a preliminary scheduling plan.

[0079] Take a water supply zone as an example: through analysis, it is found that the water consumption in this area increases significantly from 7 to 8 in the morning, and the water supply pressure shows a downward trend. Comparing historical data, it is found that this situation is more common on weekdays. The pressure distribution data shows that the pressure of the terminal pipe network during this period drops to 0.18MPa, which is lower than the normal operation requirement. Combining the water use pattern and pressure distribution, it is calculated that the booster pump needs to be started in advance at 6:30 and the water outlet pressure needs to be gradually adjusted. At the same time, considering the pressure balance of adjacent areas, a valve adjustment scheme is designed. This scheduling process fully reflects the scientificity and effectiveness of time-sharing scheduling. The scheduling module 104 needs to consider multiple influencing factors when performing specific scheduling. In the analysis of water use pattern data, in addition to the basic water supply and flow information, the influence of weather factors needs to be considered. For example, in hot weather, residents' water consumption will increase significantly, and the peak of water use will appear in advance; on rainy days, water consumption will be relatively reduced. These factors need to be included in the analysis of water use patterns. Pressure sensors are arranged at key nodes of the pipe network to collect pressure data in real time. After filtering, these data form a continuous pressure curve. The pressure fluctuation is evaluated by sliding time window method, which calculates the pressure change amplitude and change rate within a specified time period. When the pressure fluctuation of a node exceeds the set threshold, an early warning mark will be triggered.

[0080] The division of water supply areas is based on the principle of pressure zoning, and each zone is equipped with independent flow metering devices and pressure monitoring points. For each zone, a supply and demand balance model is established, taking into account factors such as the number of users, water use characteristics, and time characteristics. Through real-time monitoring data, the supply and demand differences in each zone are calculated to identify areas with large supply and demand contradictions. Energy consumption factors also need to be considered during the adjustment calculation process. The optimized scheduling plan must not only meet the water supply requirements, but also minimize energy consumption. This involves the start-stop strategy and operating condition selection of the water pump. During periods of high electricity prices, minimize the operation of high-power equipment; during periods of low electricity prices, appropriately increase water storage to prepare for peak water supply.

[0081] In a specific embodiment, the analysis module 105 is used to:

[0082] (1) Divide the water supply pressure data in the preliminary scheduling plan by region, calculate the pressure difference in each region, mark the area where the pressure fluctuation exceeds the threshold, and generate pressure balance data;

[0083] (2) Extract the running time and power parameters of the water pump from the preliminary scheduling plan, calculate the energy consumption cost based on the real-time electricity price information, and form the system energy consumption data;

[0084] (3) Based on the water supply pressure balance data and system energy consumption data, the water supply security level and operating cost ratio of each area are calculated to obtain service evaluation data;

[0085] (4) Group the service evaluation data by different time periods and regions, calculate the supply-demand matching degree and energy consumption distribution, and generate dynamic weight coefficients;

[0086] (5) Perform weighted combination of dynamic weight coefficient, pressure balance data, and system energy consumption data to generate comprehensive scoring data;

[0087] (6) Sort the scheduling priorities based on the comprehensive scoring data and generate scheduling instructions.

[0088] Specifically, the analysis module 105 performs regional analysis on the water supply pressure data in the preliminary scheduling plan. The water supply pressure data contains the real-time pressure value of each monitoring point, recorded in MPa. These data are classified according to the water supply partitions, and the maximum, minimum and average pressures in each area are calculated to obtain the pressure difference. When the pressure difference within a region exceeds a preset threshold (usually 0.15MPa), the region will be marked as an abnormal pressure fluctuation region. These analysis results form pressure balance data, which reflects the pressure distribution of the water supply network.

[0089] The operating time (hours) and power parameters (kW) of each water pump are extracted from the preliminary scheduling plan, and the energy consumption cost is calculated in combination with the time-of-use electricity price information. The time-of-use electricity price is usually divided into two periods, peak and valley, and the difference between peak and valley electricity prices is large. By calculating the energy consumption cost of each period, the system energy consumption data is formed. The system energy consumption data includes the energy consumption of each device and the overall operating cost. In-depth analysis is conducted on the pressure balance data and system energy consumption data to calculate the water supply guarantee situation in each area. The degree of water supply guarantee takes into account factors such as the pressure compliance rate and water supply continuity. At the same time, the operating cost ratio of each area is calculated, and the cost is allocated to different water supply areas. These analysis results are recorded in the service evaluation data. The service evaluation data is grouped according to time periods (peak period, flat peak period, valley period) and water supply areas, and the supply and demand balance in different time periods and areas is analyzed. For each time period, the matching degree of water supply capacity and water demand is calculated, while considering the distribution characteristics of energy consumption. These calculation results are used to generate dynamic weight coefficients, reflecting the water supply priority in different time periods and areas.

[0090] The weighted combination process of dynamic weight coefficients can be expressed by the following formula:

[0091]

[0092] Where: H j is the pressure balance weight of the jth region; R j is the pressure rating coefficient of the jth area; N j is the energy consumption weight of the jth period; E j is the efficiency coefficient of the jth period; Zj is the regional adjustment factor; m is the total number of regions; S is the comprehensive score.

[0093] The calculation result of this formula forms a comprehensive scoring data, which comprehensively reflects the balance of water supply pressure and the energy efficiency of the system. Finally, based on the comprehensive scoring data, the scheduling tasks of each area and time period are prioritized and specific scheduling instructions are generated. The scheduling instructions include equipment start and stop time, operating parameters and adjustment strategies. Take the scheduling optimization of a certain water supply area as an example: the pressure balance data of a certain area during the morning peak period shows that the pressure difference in the area reaches 0.20MPa, exceeding the preset threshold. At the same time, the energy consumption data shows that the water pump operation during this period is in a high electricity price period. By calculating the matching degree of supply and demand, it is found that the pressurization demand during the peak period can be reduced by appropriately raising the water level in advance during the low electricity price period. After dynamic weight calculation and comprehensive scoring, a new scheduling strategy is formed: starting at 3 am to gradually increase the water level and reduce the number of water pumps during the morning peak period, which not only ensures the water supply pressure but also reduces the energy consumption cost.

[0094] In a specific embodiment, the evaluation module 106 includes:

[0095] A comparison unit, used to compare the pressure data before and after the execution of the dispatch instruction, calculate the pressure change value of each monitoring point, and generate pressure fluctuation data;

[0096] A statistical unit is used to perform statistical analysis on the fluctuation values ​​in the pressure fluctuation data, divide the pressure fluctuation range of each monitoring point according to the water supply area, and obtain regional pressure distribution data;

[0097] A calculation unit, used to calculate the flow data of each water supply area, compare the flow differences at corresponding positions of the regional pressure distribution data, and generate flow balance data;

[0098] An analysis unit is used to correlate and analyze the flow values ​​of each region of the flow balance data with the water quality monitoring data, calculate the water quality changes under different flow rates, and obtain water quality analysis data;

[0099] A generation unit, used to comprehensively analyze the pressure fluctuation data, flow balance data and water quality analysis data to generate scheduling effect data;

[0100] The optimization unit is used to optimize the water supply scheduling plan based on the scheduling effect data to obtain the target scheduling strategy.

[0101] Among them, the evaluation module 106 is composed of six functional units, which jointly complete the evaluation and optimization of the scheduling effect. The comparison unit first obtains the pressure monitoring data before and after the execution of the scheduling instruction, and pairs these data according to the time series. For each monitoring point, the pressure value before scheduling and the pressure value after scheduling are recorded, and the difference between the two is the pressure change value. The frequency of collecting pressure monitoring data is once every 5 minutes, and 24 hours of data are collected before and after scheduling for comparison. By calculating the pressure change value of each monitoring point in different time periods, a pressure fluctuation data set is formed. The statistical unit conducts an in-depth analysis of the pressure fluctuation data. First, the monitoring points are classified according to the water supply partitions, and each partition contains multiple pressure monitoring points. The pressure fluctuation values ​​of each monitoring point are statistically processed, and the mean, standard deviation and coefficient of variation of the fluctuation are calculated. According to these statistical indicators, the pressure fluctuation range in each partition is determined, and the regional pressure distribution data is generated. The regional pressure distribution data reflects the pressure change characteristics of each water supply partition.

[0102] The calculation unit handles the data analysis work related to flow. Balance calculation is performed for the flow data of each water supply zone, including the inlet flow and outlet flow. At the same time, the flow data is spatially matched with the regional pressure distribution data to analyze the flow change pattern under different pressure conditions. By comparing the flow differences between each zone, it is determined whether the water supply is balanced and the flow balance data is generated.

[0103] The analysis unit is responsible for the analysis of water quality monitoring. The flow balance data of each partition is associated with the water quality monitoring data of the area. The water quality monitoring data includes key indicators such as turbidity, residual chlorine, and pH value. By analyzing the trend of water quality changes under different flow conditions, the impact of flow changes on water quality is evaluated to form water quality analysis data. This process needs to consider the impact of water age changes on water quality.

[0104] The generation unit conducts a comprehensive analysis of the three types of data obtained previously (pressure fluctuation data, flow balance data, and water quality analysis data). During the comprehensive analysis, it is necessary to weigh the three goals of water supply pressure stability, flow distribution balance, and water quality assurance. By establishing a multi-objective evaluation system, calculating the comprehensive score, and generating scheduling effect data, the scheduling effect data fully reflects the execution effect of the scheduling plan.

[0105] The optimization unit optimizes and adjusts the water supply scheduling plan based on the scheduling effect data. The optimization process takes into account multiple factors, including pressure balance, energy efficiency, water quality safety, etc. By analyzing the compliance of each indicator, identifying the links that need improvement, and formulating optimization plans. The final target scheduling strategy is a comprehensive solution that takes into account multiple goals.

[0106] Take the dispatch evaluation of a water supply zone as an example: after executing the boost dispatch instruction, the comparison unit found that the pressure at monitoring point A in the area increased by 0.12MPa after the dispatch, while the pressure at monitoring point B only increased by 0.05MPa. The statistical unit analysis showed that this pressure difference exceeded the normal fluctuation range. The calculation unit then analyzed the flow data and found that the flow at monitoring point A increased significantly, while the flow at monitoring point B did not change significantly. The analysis unit analyzed the water quality data of the area and found that the increase in flow led to a slight decrease in the residual chlorine content. After the generation unit conducted a comprehensive analysis of these data, it was concluded that the dispatch plan had the problem of uneven pressure distribution. Finally, the optimization unit suggested improving the uneven pressure distribution by adjusting the opening of the pipeline valve.

[0107] In a specific embodiment, the statistical unit is used to:

[0108] (1) The pressure fluctuation data is segmented according to the time series, and the fluctuation values ​​in each period are accumulated to obtain the fluctuation statistical data;

[0109] (2) The fluctuation statistical data are grouped according to the water supply area, and the maximum and minimum fluctuation values ​​of the monitoring points in each area are calculated to form the fluctuation range data;

[0110] (3) Analyze the distribution characteristics of the fluctuation range data, calculate the fluctuation median and fluctuation frequency of each region, and generate fluctuation characteristic data;

[0111] (4) matching the fluctuation characteristic data with the geographical boundaries of the water supply area, dividing the pressure fluctuation zones, and obtaining zone data;

[0112] (5) Classifying the pressure fluctuation values ​​of each monitoring point according to the partition data, calculating the pressure fluctuation density of each partition, and generating density distribution data;

[0113] (6) The density distribution data and the fluctuation characteristic data are correlated and sorted to generate regional pressure distribution data.

[0114] Specifically, the statistical unit processes the pressure fluctuation data in segments according to the time series. The pressure fluctuation data comes from the output of the comparison unit, which records the pressure change value of each monitoring point before and after the dispatch. The time series segmentation adopts the fixed time window method to divide 24 hours into multiple time periods, each of which is 2 hours. In each time period, the pressure fluctuation values ​​of all monitoring points are counted, the cumulative fluctuation amount is calculated, and the fluctuation statistical data is obtained. The fluctuation statistical data reflects the intensity of pressure change in different time periods. The fluctuation statistical data is grouped by region. The division of water supply areas is based on the physical connection relationship of the pipe network and the principle of pressure zoning. The data of the monitoring points in each area are counted to find the maximum and minimum fluctuation values ​​in the area. The maximum fluctuation value reflects the location where the pressure changes most violently in the area, and the minimum fluctuation value indicates the location where the pressure is most stable. These data constitute the fluctuation interval data, which describes the pressure fluctuation range of each area. The distribution characteristics of the fluctuation interval data are analyzed in depth. First, the median fluctuation value of each area is calculated, which can better reflect the typical fluctuation level of the area and is not affected by extreme values. At the same time, the fluctuation frequency, that is, the number of times the pressure change exceeds a specific threshold, is counted. The fluctuation frequency reflects the activeness of the pressure change. These analysis results form fluctuation characteristic data, which comprehensively describe the pressure fluctuation characteristics of each area.

[0115] Matching the fluctuation characteristic data with the geographic boundaries of the water supply area is a spatial analysis process. The geographic boundary information comes from a GIS map, which contains the specific scope of each water supply zone. Through spatial overlay analysis, the fluctuation characteristics are associated with the geographical location to divide the pressure fluctuation zones. The boundaries of the pressure fluctuation zones may be different from the original water supply zones. It is a functional zone determined based on the actual pressure fluctuation characteristics. Classifying the monitoring points according to the zone data is an important data sorting step. Each monitoring point is assigned to the corresponding pressure fluctuation zone according to its spatial location. In each zone, the pressure fluctuation amplitude per unit area is calculated, that is, the pressure fluctuation density. The pressure fluctuation density reflects the spatial concentration of pressure changes and helps to identify the hot spots of pressure fluctuations. These calculation results form density distribution data. The density distribution data is associated and sorted with the fluctuation characteristic data. This process combines spatial distribution information with statistical characteristic information to form regional pressure distribution data. Regional pressure distribution data contains not only the numerical characteristics of pressure changes, but also the spatial distribution laws of these changes.

[0116] Take the pressure fluctuation analysis of a water supply network as an example: after the pressure of a water supply zone is adjusted, the statistical unit analyzes the pressure fluctuation data of the area. First, the 24-hour data is divided into 2-hour periods, and the cumulative fluctuation in each period is calculated. It is found that the pressure fluctuation is most obvious during the 6-8 am period. After analyzing the 20 monitoring points in the area, the maximum fluctuation value appears at the monitoring point close to the booster pump station, and the minimum fluctuation value appears at the end of the pipe network. By calculating the median value and frequency of the fluctuation, three areas with different pressure fluctuation characteristics are identified. After matching these areas with the geographic boundaries, it is found that the originally divided water supply zone actually contains three sub-areas with different pressure fluctuation characteristics. The pressure fluctuation density of each sub-area is calculated, and it is found that the area close to the booster pump station has the highest fluctuation density.

[0117] In a specific embodiment, the computing unit is used to:

[0118] (1) The flow data of each water supply area is divided according to the time dimension, and the flow values ​​in each time period are accumulated to obtain the flow summary data;

[0119] (2) Mark the flow peaks and valleys in the flow summary data, calculate the flow change trend, and form flow trend data;

[0120] (3) Positionally match the flow trend data with the regional pressure distribution data, calculate the pressure-flow correlation, and obtain the associated data;

[0121] (4) Calculate the traffic difference value of each area in the associated data, mark the traffic imbalance point, and generate difference mark data;

[0122] (5) Calculate the flow balance adjustment amount based on the difference mark data, calculate the flow distribution ratio of each area, and obtain the balance calculation data;

[0123] (6) Organize and analyze the balance accounting data to generate flow balance data.

[0124] Specifically, the calculation unit processes the flow data of each water supply area in the time dimension. The flow data includes the real-time readings of each flow meter in the pipe network, which records the direction and size of the water flow. The time dimension is segmented using the same time window as the pressure data, that is, every 2 hours is a period. In each period, the flow value is accumulated and calculated, and the total water supply and average flow are recorded to form flow summary data. This time dimension processing helps to identify water use patterns. Marking the peak and valley values ​​of the flow summary data is an important step in flow feature analysis. Flow peaks usually occur during peak water use periods in the morning and evening, while valley values ​​occur during low water use periods at night. By marking these feature points and calculating the flow change rate between adjacent time periods, the flow change trend is obtained. This information is recorded in the flow trend data, reflecting the dynamic change characteristics of water consumption.

[0125] The process of spatial correlation analysis is to match the flow trend data with the regional pressure distribution data. Each flow monitoring point establishes a spatial correlation relationship with the surrounding pressure monitoring points. By calculating the correlation coefficient between the pressure change and the flow change at the same or similar location, the degree of mutual influence between pressure and flow is evaluated. This analysis produces correlation data, which reveals the interaction between pressure and flow. Analyzing the flow difference in the correlation data is the key to identifying water supply imbalance. The flow difference value between adjacent areas is calculated, and when the difference exceeds the preset threshold, the location is marked as a flow imbalance point. These imbalance points often reflect problems such as insufficient water supply capacity or unreasonable pipe network layout. These analysis results are recorded in the difference marking data.

[0126] Calculate the flow balance adjustment amount based on the difference mark data. The calculation of the adjustment amount needs to take into account the carrying capacity of the pipe network and user needs. For each imbalance point, calculate the flow that needs to be increased or decreased, and verify whether the water supply requirements of each area are met after adjustment. At the same time, calculate the flow distribution ratio of each area after adjustment to ensure the rationality of the distribution plan. These calculation results form the balance accounting data. The balance accounting data is sorted and analyzed to generate flow balance data. The flow balance data contains the target flow value and adjustment suggestions for each area, providing a basis for subsequent scheduling optimization.

[0127] Take the flow balance analysis of a water supply network as an example: a flow analysis is performed on a water supply area with three partitions. After segmentation in the time dimension, it is found that the cumulative flow of partition A from 7 to 9 in the morning is significantly higher than that of the other two partitions. Further analysis of the flow trend shows that when the flow peak of partition A occurs, the pressure drops sharply. Correlating the flow trend with the pressure distribution, it is found that the water supply pipe diameter of partition A is too small, resulting in insufficient water supply pressure during peak hours. By calculating the flow difference, it is determined that part of the flow needs to be transferred from partition A to partition B. The balance calculation shows that the balanced distribution of flow can be achieved by adjusting the opening of the connecting valve between partitions.

[0128] In a specific embodiment, the generating unit is used to:

[0129] (1) Align the pressure fluctuation data, flow balance data, and water quality analysis data along the time axis, establish a data association table, and obtain a comprehensive data sequence;

[0130] (2) Standardize each indicator in the comprehensive data series, calculate the indicator weight, and form weight data;

[0131] (3) Apply the weight data to the comprehensive data series, calculate the comprehensive score of each indicator, and generate scoring data;

[0132] (4) Perform multi-dimensional statistics on the scoring data, calculate the dispatch effect index of each area, and obtain effect index data;

[0133] (5) Conduct time series analysis on the effect index data, identify the changing patterns of the scheduling effect, and generate pattern analysis data;

[0134] (6) Organize and summarize the regularity analysis data to generate scheduling effect data.

[0135] Specifically, the generation unit first performs time alignment on the three types of core data (pressure fluctuation data, flow balance data, and water quality analysis data). The three types of data are collected at different frequencies: pressure data is collected every 5 minutes, flow data is collected every 5 minutes, and water quality data is collected every 10 minutes. Through the time interpolation algorithm, all data are unified to the same time scale, and a unified data association table is established. Each row in the data association table represents a time point, containing the pressure, flow, and water quality index values ​​at that moment, forming a comprehensive data sequence. Standardizing the comprehensive data sequence is a key step in eliminating the dimensional differences of different indicators. The unit of pressure data is MPa, and the unit of flow data is m 3 / h, water quality data contains multiple indicators in different units. Through standardization, each indicator is converted to a unified dimensionless scale. At the same time, according to the importance of each indicator to the operation of the water supply system, the corresponding weight coefficient is calculated. These coefficients are recorded in the weight data, reflecting the relative importance of different indicators.

[0136] The weight data is applied to the standardized comprehensive data sequence to calculate the comprehensive score of each indicator. The calculation of the comprehensive score takes into account not only the current value of the indicator, but also its changing trend. For example, the pressure indicator not only looks at whether the absolute value meets the standard, but also whether the fluctuation range is within the allowable range. These calculation results form the scoring data, which fully reflects the operating status of the water supply system. Multi-dimensional statistical analysis is performed on the scoring data to calculate the scheduling effect index of each water supply area. The scheduling effect index is a comprehensive indicator to measure the execution effect of the scheduling plan, which includes three dimensions: pressure stability, flow balance, and water quality compliance rate. Through multi-dimensional analysis, the strengths and weaknesses of the scheduling effect can be identified and the effect index data can be generated.

[0137] Perform time series analysis on the effect index data, focusing on the change pattern of the scheduling effect over time. By analyzing the change of the effect index in different time periods, identify the key factors affecting the scheduling effect. For example, the scheduling effect in some time periods is obviously better than that in other time periods. Through analysis, the reasons for this difference can be found. These analysis results are recorded in the regularity analysis data. The regularity analysis data is sorted and summarized to generate the scheduling effect data. The scheduling effect data not only contains the evaluation results of the current scheduling plan, but also includes improvement suggestions and optimization directions.

[0138] Take the evaluation of the dispatching effect of a water supply zone as an example: the operation data of the zone within one week is analyzed. The pressure, flow and water quality data are time-aligned to establish a comprehensive data sequence containing 36 monitoring points. After standardization, it is found that the pressure stability is the best at night and the water quality compliance rate is the highest, but the balance of flow distribution is poor. Through weight calculation, determine the indicators that should be given priority in different time periods. Multi-dimensional analysis shows that the dispatching effect index of this zone during the morning and evening peak hours is low, mainly due to excessive pressure fluctuations.

[0139] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A digital water pipe network integrated dispatching system, characterized in that: The digital water pipe network integrated dispatching system includes: a processing module, a stratification module, an identification module, a dispatching module, an analysis module and an evaluation module; the output end of the processing module is connected to the input end of the stratification module, the output end of the stratification module is connected to the input end of the identification module, the output end of the identification module is connected to the input end of the dispatching module, the output end of the dispatching module is connected to the input end of the analysis module, and the output end of the analysis module is connected to the input end of the evaluation module; A processing module is used to pre-process the pressure data, flow data and water quality data in the water supply network, construct a dynamic boundary area in combination with the spatial location information of the network, and screen the data in the dynamic boundary area according to the completeness, accuracy and timeliness indicators to obtain the basic data of the network; A hierarchical module is used to perform hierarchical processing on the basic data of the pipe network, classify the monitoring sites according to the functions of water supply hubs, water distribution stations and terminal pipe networks, and generate operating parameters based on pipe section analysis, fire hydrant coverage radius query and valve closing impact range analysis; An identification module is used to record and process the equipment operation status by using the operation parameters, identify the fault characteristics and propagation law by combining the equipment history records and the status of adjacent associated equipment, and obtain equipment status data; A scheduling module is used to perform scheduling analysis based on the equipment status data, integrate water supply and flow information according to the time-sharing rules of peak period, off-peak period and valley period, and obtain a preliminary scheduling plan; An analysis module is used to perform multi-objective processing on the preliminary scheduling plan, and obtain a scheduling instruction from the water supply pressure balance performance consumption efficiency analysis based on a dynamic weight allocation mechanism; The evaluation module is used to analyze the effects according to the scheduling instructions, evaluate the pressure fluctuation range, flow distribution balance and water quality compliance rate indicators, and generate a target scheduling strategy.

2. The digital water pipe network integrated dispatching system according to claim 1 is characterized in that: The processing module is used for: Sorting the pressure data, the flow data and the water quality data according to timestamps to obtain a time series data sequence; Performing a range check on the time series data sequence, marking data exceeding the historical maximum and minimum values ​​as abnormal data, and obtaining an abnormal marking sequence; Based on the physical connection relationship of the water supply network, the data of adjacent monitoring points in the time series data sequence are subjected to association analysis, and combined with the abnormal mark sequence to generate a correlation analysis result; Compare the data collection time in the correlation analysis result with the system time, filter out data records delayed beyond a preset time, and obtain a valid data set; For the valid data set, the data quality score is obtained by calculating the completeness index, the accuracy index and the timeliness index; The data quality score and the valid data set are weighted and combined with the spatial location information of the pipe network and the dynamic boundary area to generate the pipe network basic data.

3. The digital water pipe network integrated dispatching system according to claim 1 is characterized in that: The layered module is used to: Divide the basic data of the pipe network into monitoring areas according to spatial positions, mark the monitoring sites in layers, and obtain water supply hub marking data, water distribution station marking data, and terminal pipe network marking data; Performing monitoring point distribution analysis on the water supply hub mark data, the water distribution station mark data and the terminal pipe network mark data, and generating site level data in combination with the pipe segment connection relationship; Performing cross-section cutting on the pipe segments in the site-level data, extracting the depth information, pipe diameter information and material information of the pipe segments, and obtaining pipe segment feature data; Taking the preset fire point as the center, searching for the location of fire hydrants in the site-level data, calculating the distance from each fire hydrant to the preset fire point, and generating fire hydrant coverage data; Based on the site level data and the pipe section characteristic data, the water supply network is subjected to regional valve closing analysis, the influence range and closing sequence of each valve are calculated, and valve control data is formed; The pipe section characteristic data, the fire hydrant coverage data and the valve control data are integrated and analyzed to generate the operating parameters.

4. The digital water pipe network integrated dispatching system according to claim 1 is characterized in that: The identification module is used to: Record the pressure data, flow data and water quality data in the operating parameters in time segments, establish a data association table according to the equipment location, and obtain the equipment operation record; Extracting the operation time, maintenance cycle and failure frequency information of each device from the device operation records, arranging them in chronological order, and generating a device historical data sequence; Compare and analyze the equipment historical data sequence with the equipment operation record, mark equipment operation abnormal points and equipment status mutation points, and form equipment characteristic data; Based on the device characteristic data, extract the change rules of the operating status of adjacent associated devices and generate a device association map; Analyze the abnormal propagation path in the device association map, extract the temporal relationship and spatial distribution of the fault occurrence, and form a fault propagation chain; The device characteristic data, the device association map and the fault propagation chain are integrated and analyzed to generate the device status data.

5. The digital water pipe network integrated dispatching system according to claim 1 is characterized in that: The scheduling module is used to: The water supply and flow information in the equipment status data is divided into peak period, off-peak period and off-peak period according to a 24-hour cycle to obtain time-divided data; Compare the time-divided data with historical data of the same time period, analyze the change trend of the water supply and flow information, and generate water use regularity data; The pressure fluctuations in each time period in the water use pattern data are counted, and combined with the equipment operation information in the equipment status data to form pressure distribution data; The pressure distribution data are grouped according to water supply areas, and the supply-demand balance relationship of each area during the peak period, the flat peak period and the valley period is analyzed to obtain regional balance data; For the supply-demand contradiction area appearing in the regional balance data, adjusting calculation is performed in combination with the water use rule data and the pressure distribution data to generate adjustment plan data; The adjustment plan data is matched and analyzed with the equipment status data to generate the preliminary scheduling plan.

6. The digital water pipe network integrated dispatching system according to claim 1 is characterized in that: The analysis module is used to: Divide the water supply pressure data in the preliminary scheduling plan by region, calculate the pressure difference in each region, mark the region where the pressure fluctuation exceeds the threshold, and generate pressure balance data; Extracting the running time and power parameters of the water pump from the preliminary scheduling plan, calculating the energy consumption cost in combination with the real-time electricity price information, and forming system energy consumption data; Based on the water supply pressure balance data and the system energy consumption data, the water supply guarantee degree and operating cost ratio of each area are calculated to obtain service evaluation data; The service evaluation data is grouped according to different time periods and regions, the supply-demand matching degree and energy consumption distribution are calculated, and a dynamic weight coefficient is generated; Performing a weighted combination on the dynamic weight coefficient, the pressure balance data, and the system energy consumption data to generate comprehensive scoring data; The scheduling priorities are sorted based on the comprehensive scoring data to generate the scheduling instruction.

7. The digital water pipe network integrated dispatching system according to claim 1 is characterized in that: The evaluation module comprises: A comparison unit, used to compare the pressure data before and after the execution of the scheduling instruction, calculate the pressure change value of each monitoring point, and generate pressure fluctuation data; A statistical unit, used to perform statistical analysis on the fluctuation values ​​in the pressure fluctuation data, divide the pressure fluctuation range of each monitoring point according to the water supply area, and obtain regional pressure distribution data; A calculation unit, used to calculate the flow data of each water supply area, compare the flow differences at corresponding positions of the regional pressure distribution data, and generate flow balance data; An analysis unit, used to correlate and analyze the flow values ​​of each region of the flow balance data with the water quality monitoring data, calculate the water quality changes under different flow rates, and obtain water quality analysis data; A generating unit, used for comprehensively analyzing the pressure fluctuation data, the flow balance data and the water quality analysis data to generate scheduling effect data; An optimization unit is used to optimize the water supply scheduling plan based on the scheduling effect data to obtain the target scheduling strategy.

8. The digital water pipe network integrated dispatching system according to claim 7 is characterized in that: The statistical unit is used for: The pressure fluctuation data is segmented according to the time series, and the fluctuation values ​​in each time period are accumulated to obtain fluctuation statistical data; The fluctuation statistical data are grouped according to the water supply area, and the maximum fluctuation value and the minimum fluctuation value of the monitoring points in each area are calculated to form fluctuation range data; Performing distribution characteristic analysis on the fluctuation range data, calculating the fluctuation median and fluctuation frequency of each region, and generating fluctuation characteristic data; Matching the fluctuation characteristic data with the geographical boundaries of the water supply area, dividing the pressure fluctuation into zones, and obtaining zone data; Classifying the pressure fluctuation value of each monitoring point according to the partition data, calculating the pressure fluctuation density of each partition, and generating density distribution data; The density distribution data and the fluctuation characteristic data are associated and sorted to generate the regional pressure distribution data.

9. The digital water pipe network integrated dispatching system according to claim 7 is characterized in that: The computing unit is used for: The flow data of each water supply area is divided according to the time dimension, and the flow values ​​in each time period are accumulated to obtain the flow summary data; Marking the flow peaks and valleys in the flow summary data, calculating the flow change trend, and forming flow trend data; Positionally correspond the flow trend data with the regional pressure distribution data, calculate the pressure-flow correlation, and obtain correlation data; Calculating the flow difference value of each area in the associated data, marking the flow imbalance point, and generating difference marking data; Calculate the flow balance adjustment amount according to the difference mark data, calculate the flow distribution ratio of each area, and obtain the balance calculation data; The balance accounting data is sorted and analyzed to generate the flow balance data.

10. The digital water pipe network integrated dispatching system according to claim 7 is characterized in that: The generating unit is used for: Align the pressure fluctuation data, the flow balance data and the water quality analysis data according to the time axis, establish a data association table, and obtain a comprehensive data sequence; Standardizing each indicator in the comprehensive data sequence, calculating the indicator weight, and forming weight data; Applying the weight data to the comprehensive data sequence, calculating the comprehensive score of each indicator, and generating scoring data; Perform multi-dimensional statistics on the scoring data, calculate the scheduling effect index of each area, and obtain effect index data; Performing time series analysis on the effect index data, identifying the changing pattern of the scheduling effect, and generating pattern analysis data; The regularity analysis data is sorted and summarized to generate the scheduling effect data.

Images