Heat supply pipe network pressure adjusting device and adjusting method

Abstract

The invention relates to the technical field of heat supply pipe networks, in particular to a heat supply pipe network pressure adjusting device and method, which comprises a synchronous sensing module, a trend comparison module, a regulation and control calibration module, a target adjustment module and a parameter correction module, and analyzes pressure intensity monitoring data based on an inlet of a heat exchange station of a heat supply main pipe. According to the method, the consistency of data in space and time dimensions is improved through a real-time matching and synchronous discrimination method of multi-point pressure and flow information, early anomaly detection of the operation state of a key link is achieved based on node trend deviation judgment and dynamic parameter grading, and through self-adaptive configuration of regulation and control parameters, the detection accuracy of the operation state of the key link is improved. Parameter convergence and system state stability are promoted by combining automatic balance of a node cooperative relation, dynamic adjustment of a driving pressure difference boundary and an abnormal data processing mechanism, each section of a pipe network can adapt to continuous load fluctuation, and it is guaranteed that heating medium operation is in a coordinated balance state all the time, so that the safety and reliability of heating system operation are improved.

Description

Technical Field

[0001] This invention relates to the field of heating network technology, and in particular to a heating network pressure regulating device and regulating method. Background Technology

[0002] Heating networks fall under the field of urban infrastructure and energy management technology, primarily involving the transmission, distribution, and pressure balance control of thermal energy within urban networks. This encompasses multiple aspects, including heat source systems, heating networks, hydraulic balance regulation, heating stations, and terminal heating equipment. Traditional heating network pressure regulation devices utilize methods such as constant pressure water supply devices, pressure relief valves, pressure stabilizing tanks, and circulating pumps to regulate internal network pressure. This addresses pressure fluctuations caused by changes in heat load or network resistance. Mechanical pressure control valves or electric valves combined with pressure sensors are commonly used to ensure the stability of the heat medium flow and the continuous operation of the heating system.

[0003] In existing technologies, pressure and flow monitoring are often scattered across different collection points, lacking effective time coordination. Parameter status is difficult to reflect the actual connection between nodes when the load changes. Static regulating valves and pumps lack the ability to identify and respond to real-time anomalies. When data lag or loss of synchronization occurs between multiple nodes, it can easily lead to pipeline regulation failure, reduced response speed of the heating system, and risks to heating continuity and system balance when encountering severe load fluctuations. There is also the problem of not being able to achieve timely network-wide coordinated regulation. Summary of the Invention

[0004] To address the technical problems existing in the prior art, embodiments of the present invention provide a heating network pressure regulating device and method. The technical solution is as follows: On the one hand, a heating network pressure regulating device is provided, the device comprising: The synchronous sensing module analyzes pressure monitoring data based on the inlet of the heat exchange station of the main heating pipeline, synchronously compares the flow monitoring data of the primary side node of the heat exchanger of the heating station, removes asynchronous data through time tag consistency screening, and obtains the zonal rate characteristic group. Based on the partitioned rate feature group, the trend comparison module compares the flow change trend and pressure change trend of the monitoring nodes in the main water supply section to determine the synchronization status, identifies synchronization differences node by node and classifies the abnormality type to obtain the node synchronization offset index. Based on the node synchronization offset index, the control and calibration module analyzes abnormal node information, sorts out the related water pump adjustment action process, and adjusts the abnormal node parameters by comparing the recovery performance after the adjustment action to obtain the sensitivity control parameters. Based on the sensitivity control parameters, the target adjustment module determines the pressure monitoring data of the corresponding water pump at the regulating port of the heating return water branch, analyzes the parameter coordination in conjunction with the flow change trend, adjusts the boundary parameters, and obtains the differential pressure control range. Based on the differential pressure control range, the parameter correction module compares the current periodic pressure change with the boundary setting, identifies data points that do not meet the requirements, adjusts the correction coefficient, optimizes the flow change parameter processing, and obtains the closed-loop regulation correction amount.

[0005] On the other hand, the partition rate feature group includes a rate mapping table, node grouping code, and data synchronization marker; the node synchronization offset index includes offset type, offset period, and offset degree; the sensitivity control parameter includes sensitivity level, action trigger factor, and adjustment amplitude identifier; the differential pressure control interval includes interval boundary parameter and interval number; and the closed-loop adjustment correction amount includes correction factor, correction number, and iteration identifier.

[0006] On the other hand, the synchronous sensing module includes: The data tag extraction submodule is based on the inlet of the heat exchange station of the main heating pipe. It analyzes the pressure monitoring data and the flow monitoring data of the primary side node of the heat exchanger of the heating station, compares the time information of the data records, determines whether the time of each data item conforms to the unified sampling period, optimizes the time recording tagging method, and obtains the time synchronization tag set. The time tag matching submodule, based on the time synchronization tag set, filters the pairing of pressure monitoring data and flow monitoring data under each time tag, compares the pairing completeness of data at the same time node, and removes data that do not form a corresponding pair to obtain the synchronous monitoring dataset. The feature grouping generation submodule, based on the synchronous monitoring dataset, determines the spatial location and equipment partition code of each monitoring node, classifies and organizes the paired data, optimizes the comparison method of pressure change and flow rate change under continuous time nodes of each monitoring unit, and obtains partition rate feature groups.

[0007] On the other hand, the trend comparison module includes: The trend parameter extraction submodule analyzes the pressure monitoring data and flow monitoring data of each node in a continuous time period based on the partition rate feature group, compares the direction of pressure and flow change at adjacent times of each time node, calculates the trend characteristics of continuous change in the node sequence, and obtains the node trend feature sequence. The node synchronization judgment submodule compares the pressure trend and flow trend of each node based on the node trend feature sequence, analyzes the consistency of the two types of trend changes step by step in the time series, judges whether the trend fluctuations within the same period are synchronized, identifies the node segments with directional differences in trend changes, and obtains the synchronization difference dataset. The abnormal offset classification submodule, based on the synchronization difference dataset, determines the pressure and flow pairing behavior of each monitoring node during the offset period, identifies monitoring nodes that continuously experience offset, classifies synchronization anomaly types, and obtains node synchronization offset indices.

[0008] On the other hand, the regulation and calibration module includes: The node information analysis submodule analyzes the synchronization deviation of each abnormal node based on the node synchronization offset index, determines the correlation with the water pump adjustment action, identifies nodes exhibiting abnormal behavior, analyzes the changing trend under each adjustment state, and obtains abnormal node feature data. The adjustment action comparison submodule analyzes the node recovery performance after each adjustment action based on the abnormal node feature data, compares the differences in the effects of each adjustment method during the recovery process, analyzes the impact on node recovery time and synchronization status, identifies the adjustment action with the best performance, and obtains action adjustment data. The control parameter adjustment submodule analyzes the pump adjustment effect based on the action adjustment data and adjusts the control parameters of abnormal nodes to obtain the sensitivity control parameters.

[0009] On the other hand, the target adjustment module includes: The pressure trend analysis submodule analyzes the pressure monitoring data of the water pump at the regulating port of the heating return water branch based on the sensitivity control parameters, compares the pressure changes in continuous cycles, identifies the pressure increase or decrease trend in each cycle, determines the difference in the change amplitude during the cycle, and obtains the pressure trend characteristics. Based on the pressure trend characteristics, the periodic synchronization comparison submodule performs synchronization analysis on the flow rate change trend and pressure change trend of the current period, compares the degree of coordination between the two changes, determines whether they are consistent, identifies asynchronous data segments, and obtains periodic synchronization difference data. The control boundary adjustment submodule analyzes the data on synchronicity discrepancies based on the aforementioned periodic synchronicity difference data, determines the impact on pump regulation, adjusts the control parameters of the discrepancy section, and obtains the differential pressure control range.

[0010] On the other hand, the parameter correction module includes: The pressure change analysis submodule analyzes the pressure change in the current cycle based on the pressure difference control range, compares the pressure fluctuation characteristics in each cycle, identifies the pressure increase and decrease trends of each data point in the time period, analyzes whether the fluctuation trend meets the set requirements, and obtains the pressure fluctuation characteristics. Based on the pressure fluctuation characteristics, the data point filtering submodule filters data points that do not meet the set requirements, checks the change range of each data point one by one, determines whether it meets the control standard, identifies data that does not meet the synchronization requirements, and obtains a set of abnormal data points. The correction coefficient adjustment submodule analyzes the deviation of each data point based on the abnormal data point set, corrects the data points, calculates the matching correction coefficient according to the node characteristics and the flow change trend within the period, optimizes the flow parameter processing method, and obtains the closed-loop adjustment correction amount.

[0011] On the other hand, the pressure monitoring data refers to the set of pressure values ​​collected in real time at the inlet of the heat exchange station of the main heating pipe through a pressure sensor. The primary side node refers to the primary water circulation system of the heat exchanger of the heat station, that is, the high-temperature side of the heating system, where a flow sensor is installed to collect flow data.

[0012] On the other hand, the flow rate change trend refers to the direction and pattern of flow rate change over time at a monitoring node within a continuous sampling period, and the pressure change trend refers to the direction and pattern of pressure change over time at a monitoring node within a continuous sampling period.

[0013] On the other hand, a method for regulating the pressure of a heating network is provided. This method is applied to a pressure regulating device for a heating network and includes the following steps: S1: Based on the inlet of the heat exchange station of the main heating pipeline, analyze the pressure monitoring data, synchronously compare the flow monitoring data of the primary side node of the heat exchanger of the heating station, remove asynchronous data through time tag consistency screening, and obtain the zonal rate characteristic group. S2: Based on the partitioned rate feature group, compare the flow rate change trend and pressure change trend of the monitoring nodes of the main water supply section, determine the synchronization status, identify the synchronization difference of each node and classify the abnormal type to obtain the node synchronization offset index. S3: Based on the node synchronization offset index, analyze the abnormal node information, sort out the related water pump adjustment action process, and adjust the abnormal node parameters by comparing the recovery performance after the adjustment action to obtain the sensitivity control parameters. S4: Based on the aforementioned sensitivity control parameters, determine the pressure monitoring data of the corresponding water pump at the regulating port of the heating return water branch, analyze the parameter coordination in conjunction with the flow rate change trend, adjust the boundary parameters, and obtain the differential pressure control range. S5: Based on the differential pressure control range, compare the current periodic pressure change with the boundary setting, identify data points that do not meet the requirements, adjust the correction coefficient, optimize the flow change parameter processing process, and obtain the closed-loop control correction amount.

[0014] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: By using real-time matching and synchronous identification methods for multi-point pressure and flow information, the consistency of data in spatial and temporal dimensions is improved. Based on node trend deviation judgment and dynamic parameter classification, early anomaly detection of the operating status of key links is achieved. Through adaptive configuration of control parameters and automatic balancing of node coordination relationships, dynamic adjustment of differential pressure boundaries is achieved. The abnormal data processing mechanism promotes parameter convergence and system stability. Each section of the pipeline network can adapt to continuous load fluctuations, ensuring that the operation of the heat medium is always in a coordinated and balanced state, thereby improving the safety and reliability of the heating system. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the device of the present invention; Figure 2 This is a schematic diagram of the device frame of the present invention; Figure 3 This is a flowchart of the synchronous sensing module of the present invention; Figure 4 This is a flowchart of the trend comparison module of the present invention; Figure 5 This is a flowchart of the calibration module of the present invention; Figure 6 A flowchart of the objective adjustment module of this invention; Figure 7 This is a flowchart of the parameter correction module of the present invention; Figure 8 This is a flowchart of the method steps of the present invention. Detailed Implementation

[0017] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0018] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0019] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0020] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0021] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0022] This invention provides a heating network pressure regulating device, such as... Figure 1 As shown, the device includes: The synchronous sensing module analyzes the pressure monitoring data at each time node based on the inlet of the heat exchange station of the main heating pipe, and performs synchronous comparison of the flow monitoring data of the primary side node of the heat exchanger of the heating station. By checking the consistency of the time tag of the collected data, it screens out all data that does not meet the synchronization requirements and adjusts the grouping method of the remaining valid data to obtain the partition rate characteristic group. The trend comparison module compares the flow rate change trend and pressure change trend of each monitoring node in the main water supply section based on the partition rate feature group, judges the synchronization between the two trends, analyzes whether the synchronization is obvious by analyzing the node-by-node, identifies the monitoring nodes with obvious synchronization differences, classifies the nodes into abnormal types, and obtains the node synchronization offset index. The control and calibration module analyzes abnormal node information based on node synchronization offset index, sorts out the adjustment action process of associated water pumps, and identifies the adjustment action that performs better than other actions by comparing the recovery state after each adjustment action. The control parameter configuration of abnormal nodes is then adjusted to obtain the sensitivity control parameters. The target adjustment module, based on the sensitivity control parameters, judges the pressure monitoring data of the corresponding water pump at the regulating port of the heating return water branch, and performs a synchronization analysis in combination with the current cycle flow change trend. It compares the coordination between parameter changes in continuous cycles. If the change trend is found to be inconsistent, the control boundary parameter setting is adjusted to obtain the differential pressure control range. The parameter correction module, based on the differential pressure control range, compares the pressure changes detected in the current cycle with the boundary settings, identifies data points that do not meet the settings, adjusts the correction coefficients for the data points, optimizes the processing of flow change parameters in the current cycle, and obtains the closed-loop regulation correction amount.

[0023] The partition rate characteristic group includes a rate mapping table, node group code, and data synchronization marker. The node synchronization offset index includes offset type, offset period, and offset degree. The sensitivity control parameters include sensitivity level, action trigger factor, and adjustment amplitude identifier. The differential pressure control range includes range boundary parameters and range number. The closed-loop control correction amount includes correction factor, correction number, and iteration identifier.

[0024] In the synchronous sensing module, each time node refers to every point in time recorded by the data acquisition system according to a predetermined sampling cycle during the heating operation; pressure monitoring data refers to the set of pressure values ​​collected in real time by pressure sensors at the inlet of the heating main pipeline heat exchange station; primary side node refers to the primary water circulation system of the heat exchanger in the heat station (i.e., the high-temperature side of the heating system), where flow sensors are installed to collect flow data; synchronous comparison refers to matching and comparing the collected data from different monitoring points (such as pressure and flow) according to time tags to ensure the consistency of data analysis time; time tag consistency refers to marking the data collected by all sensors at the same time point to ensure the effectiveness and synchronization of horizontal data analysis; synchronization requirement refers to the error between data acquisition time points being less than a certain range to ensure data time sequence alignment; effective data grouping method refers to classifying and organizing qualified data after synchronous screening according to spatial location, equipment zoning, etc., for subsequent feature analysis between nodes.

[0025] In the trend comparison module, the flow rate change trend refers to the direction and pattern of flow rate change over time at a monitoring node within a continuous sampling period; the pressure change trend refers to the direction and pattern of pressure change over time at a monitoring node within a continuous sampling period; synchronization refers to the coordination of the direction and magnitude of flow rate change trends and pressure change trends at the same monitoring node over time; synchronization status refers to whether the two trends show synchronous growth, synchronous decline, or asynchronous behavior within the same time period; significant difference in synchronicity refers to the fact that the synchronicity deviation between flow rate and pressure changes at some nodes is greater than the system's allowable range, indicating abnormal node operating characteristics; anomaly type classification refers to classifying monitoring nodes identified as having synchronicity anomalies into different types of anomaly labels based on characteristics such as offset direction, magnitude, and duration.

[0026] In the control and calibration module, abnormal node information refers to the detailed operation and characteristic parameters of monitoring nodes marked as having synchronous anomalies in the trend comparison module; the control action process refers to the entire process of automatic or manual control operations such as pump speed regulation and valve adjustment, including command issuance, equipment execution, and result feedback; the performance of the recovery state refers to the response speed, fluctuation, and other indicators of the system (such as node pressure and flow) reaching a stable state after the control action is completed; the control action that outperforms other actions refers to the action that enables the system to recover to the target state faster or more smoothly among various control actions; and the control parameter configuration refers to the specific settings made to the operating parameters (such as sensitivity and adjustment step) of equipment such as pumps based on the actual performance results of the control action.

[0027] In the target adjustment module, the heating return water branch refers to the key node in the return water pipeline of the heating system, which is usually an important part of heat recovery and differential pressure control; the synchronization analysis refers to pairing and comparing the changes in pressure and current flow rate of the return water branch within a continuous operating cycle to analyze the synergistic or lagging relationship between the two; parameter change refers to the changes and trends of operating parameters such as pressure and flow rate in different sampling cycles; coordination refers to whether the parameter changes show a consistent trend, that is, whether the changes between parameters can adapt to each other and support the stable operation of the system; inconsistent change trends refer to inconsistent trends of parameters such as pressure and flow rate, manifested as abnormal fluctuations, loss of synchronization, etc.; the setting of control boundary parameters refers to setting and adjusting the boundary range of parameter changes based on the coordination of trends.

[0028] In the parameter correction module, pressure change and boundary setting refers to comparing the actual pressure changes detected in the current cycle with the pre-set normal fluctuation range item by item; data points that do not meet the settings refer to specific moments or data records where the detected pressure or flow parameters exceed the normal boundaries; correction coefficient adjustment refers to automatically or manually adjusting the parameter correction factor after abnormal data points are detected, so that the system operation returns to a controllable range; the processing refers to recalculating and updating the trend of the flow change data in the current cycle in combination with the corrected parameters, to ensure the pertinence and effectiveness of subsequent control actions.

[0029] like Figure 2 and Figure 3 As shown, the synchronous sensing module includes: The data tag extraction submodule is based on the inlet of the heat exchange station of the main heating pipe. It analyzes the pressure monitoring data and the flow monitoring data of the primary side node of the heat exchanger of the heating station, compares the time information of the data records, determines whether the time of each data item conforms to the unified sampling period, optimizes the time recording tagging method, and obtains the time synchronization tag set. By retrieving data from the pressure sensor installed at the inlet and the flow sensor installed at the primary side node of the heat exchanger in the heating station, the two data sources are first decomposed into year-month-day-hour-minute-second format according to the time field. Following a preset sampling period (e.g., once every 5 seconds), the time interval between each record and its adjacent records is calculated. If the interval between two records exceeds a preset error range (e.g., a maximum error of 0.2 seconds), the record is considered to be inconsistent with the unified sampling period and is subsequently removed from the comparison data. The remaining data continues to the next step of processing, where the timestamps that have passed the screening are uniformly converted. The data is formatted in a standard way, such as using a format of accumulated seconds since 1970, to facilitate subsequent alignment. Timestamp lists are then extracted from both the pressure and flow datasets, and cross-checked one by one. Time points present in both lists are retained to form a new set of timestamps. Only the data at these times is used for subsequent analysis. A new structured table is then created, with each row representing a pressure and flow value record at a sampling moment. Simultaneously, all data acquisition devices undergo unified time source calibration, such as daily synchronization with an external high-precision network time server, ensuring that the internal clocks of each device are within the error range, thus generating a set of time synchronization markers.

[0030] The time tag matching submodule filters the pairing of pressure monitoring data and traffic monitoring data under each time tag based on the time synchronization tag set, compares the pairing completeness of data at the same time node, removes data that do not form a corresponding pair, and obtains the synchronous monitoring dataset. Pressure and flow data records are read separately from each time point. It is checked whether valid data exists for both at the same time. For example, at 10:00 AM, are there both pressure and flow values? If a record at a certain time contains only one type of data or invalid values ​​such as negative values, zero values, or anomaly markers, that time point is removed from the set. Only records with complete and reasonable values ​​are retained. After further filtering, a list of valid time points is formed, called the valid synchronization tag set. Using this set as an index, corresponding complete data pairs are extracted from the original data to establish a synchronization data set with a structure of time, pressure, and flow. The numerical range of all records is then judged. For example, pressure values ​​are limited to 0.3 to 1.6 MPa, and flow values ​​are limited to 0.1 to 120 cubic meters per hour. Any record outside this range is marked as invalid and removed from the dataset. The number of synchronized data after filtering is recorded and compared with the number in the original time set. If the ratio is lower than a set threshold, such as less than 85% of the total, it is marked as insufficient data integrity and an alarm is triggered. Only synchronized monitoring data at valid time points are retained, forming a standard data set for subsequent analysis.

[0031] The feature grouping generation submodule is based on the synchronous monitoring dataset. It determines the spatial location and equipment partition code of each monitoring node, classifies and organizes the paired data, optimizes the comparison method of pressure change and flow change under continuous time nodes of each monitoring unit, and obtains partition rate feature groups. The system identifies the monitoring node number, physical location coordinates, and functional zone code of each record. For example, node number 001 is located on the main branch pipe on the east side of the heating network, and its equipment code indicates that it belongs to the primary side system. After obtaining the identification information, the system performs the first round of classification based on the node number, gathering all time point data under the same number into one set. Then, it divides the physical regions of each node based on spatial coordinates. For example, it sets region A to all nodes with coordinate values ​​within 100, and others to region B. Subsequently, it further refines the classification based on the equipment code. For example, codes starting with HT01 are classified as high-temperature systems, and codes starting with HT02 are classified as return water sections. After completing the two-level zoning, it iterates through each... The pressure and flow rate changes at consecutive time points in the node data set are formed into a continuous change sequence by calculating the difference between the changes in pairs. The correspondence between flow rate changes and pressure changes is then observed in the change sequence to determine the speed of the response. For example, if the flow rate changes greatly while the pressure remains basically unchanged, the node is considered to be sensitive to the heating system. Conversely, if the two changes are not coordinated, it is classified as low response. The response range is set into three types: normal, slow, and sudden. The results of different types of changes are labeled in each data set to form a structured feature group set. This set also includes node number, region division, equipment classification, and flow and pressure response characteristic records, which facilitates subsequent status identification and difference analysis by region and node granularity.

[0032] like Figure 2 and Figure 4 As shown, the trend comparison module includes: The trend parameter extraction submodule analyzes the pressure monitoring data and flow monitoring data of each node in a continuous time period based on the partition rate feature group, compares the direction of pressure and flow change between adjacent times of each time node, calculates the trend characteristics of continuous change in the node sequence, and obtains the node trend feature sequence. For each partition, all monitoring nodes are processed. During execution, the pressure and flow data sequences of each node within a continuous time period are first extracted from the feature group. Based on time sorting, the pressure values ​​at every two adjacent time points are compared to determine whether the pressure is rising, falling, or remaining constant. Simultaneously, adjacent flow values ​​are processed in the same way, and each difference direction is numbered and marked. For example, a pressure increase is marked as +1, a decrease as -1, and no change as 0. The same applies to flow data. For instance, if node number N001 samples once per minute from 10:00 to 10:10, collecting 11 data points, it forms 10 pairs of adjacent difference values. If the pressure changes from 0.92 to 0.95 from the first minute to the second minute, it indicates an upward trend; similarly, if the flow rate changes from 32.0 to 33.8, it also indicates an upward trend. The trend is recorded as +1 and +1 respectively. Then, the difference direction is judged for subsequent time points to form a set of trend direction sequences. On this basis, the pressure and flow trend directions in each time period are combined to form trend label pairs. For example, the first group is (+1, +1), the second group is (-1, -1), and the third group is (+1, -1). This trend direction pair is used as the basic unit of the trend feature sequence. The entire time axis is traversed and the trend sequence length and change frequency of each node are recorded. Then, the node's partition code, spatial location, and time window number are combined to form a complete trend structure group. If a node has a consistent trend direction in at least 7 out of 10 consecutive cycles, the node is marked as having strong trend continuity. If there are less than 3 consistent cycles, the trend is marked as unstable. The node trend feature sequence is established.

[0033] The node synchronization judgment submodule compares the pressure trend and flow trend of each node based on the node trend feature sequence, analyzes the consistency of the two types of trend changes step by step in the time series, judges whether the trend fluctuations within the same period are synchronized, identifies the node segments with directional differences in trend changes, and obtains the synchronization difference dataset. First, select the trend sequence of each monitoring node within a given time period, decompose it into a pressure trend sequence and a flow trend sequence, and compare the two sequences position by position according to the time alignment method. If the pressure trend is rising and the flow trend is also rising within a certain time period, it is considered that the trends at that time point are synchronous. If the two are not in the same direction, such as pressure decreasing and flow increasing, it is considered that the trends at that time point are inconsistent, and the time point is recorded as asynchronous. Then, accumulate the number of all synchronous and asynchronous time points in chronological order. For example, if there are 15 synchronous points and 5 asynchronous points in 20 sampling points, the synchronization ratio is 75%. If the synchronization ratio is lower than a set threshold, such as lower than 60%, the segment where the node is located is marked. The abnormal segment is marked as a trend synchronization anomaly. Further, the trend difference of the abnormal segment is judged directionally. If most abnormal points show a decrease in pressure and an increase in flow, the directional difference type is recorded as reverse offset. If the pressure remains unchanged and the flow changes, it is recorded as non-corresponding offset. Then, the trend fluctuation path of each node is statistically analyzed to determine its trend consistency in multiple consecutive time periods. If the number of consecutive asynchronous points exceeds a set number, such as more than 5 consecutive time points of asynchronousity, the segment is recorded as a structural synchronization anomaly. Through the above comparison and trend direction difference marking, a synchronization difference dataset is formed that records the trend consistency of each node, the abnormal direction type, and the abnormal segment identifier.

[0034] The abnormal offset classification submodule is based on the synchronization difference dataset. It judges the pressure and flow pairing behavior of each monitoring node during the offset period, identifies the monitoring nodes that continuously offset, classifies the synchronization anomaly type, and obtains the node synchronization offset index. Read the pressure and flow values ​​of each node during the time period recorded as a synchronization anomaly, and establish a pressure-flow paired dataset for that period. Then, re-verify the trend direction of the paired data to confirm whether the abnormal direction is a continuous offset. Then, determine the degree of offset persistence based on the number of paired data and the length of continuous offset for each node in the abnormal segment. For example, if a node shows an increase in flow and a decrease in pressure for 10 consecutive minutes, and the trend direction does not return to the synchronization state even once, then the node is marked as a continuous offset type. If the offset direction changes occasionally within 3 to 5 minutes, it is marked as an intermittent offset. Nodes are classified into different offset types according to different offset patterns. At the same time, the offset cycle length and the number of offsets are recorded. The historical offset count of nodes is accumulated. If the same node has more than 3 consecutive offsets in different cycles, its offset level is further upgraded to severe anomaly. Then, generate a node offset record table based on the node number, the partition it is located in, the offset type, and the offset level. Finally, form a set of node synchronization offset indicators.

[0035] like Figure 2 and Figure 5 As shown, the adjustment and calibration module includes: The node information analysis submodule analyzes the synchronization deviation of each abnormal node based on the node synchronization offset index, determines the correlation with the water pump adjustment action, identifies nodes exhibiting abnormal behavior, analyzes the changing trends under each adjustment state, and obtains abnormal node characteristic data. For each node marked as abnormal, processing begins. First, basic information such as the offset type, duration, and magnitude of each node is extracted from the synchronization offset index. Then, this information is compared line by line with the adjustment records of the pump to which the node belongs. Operation records such as pump speed changes, start-up / stop actions, and valve opening adjustments within the corresponding time period are retrieved. The offset time period of each node is matched with the adjustment time points of the pump to determine if there is a temporal overlap. For example, if a node continuously offsets between 10:05 and 10:10, and the pump increases its speed at 10:06, and the flow rate suddenly changes direction between 10:07 and 10:08, a preliminary correlation can be established. Further trend comparison is performed on the node's flow rate and pressure change sequences before and after the pump adjustment. If the pressure before adjustment... The pressure shows a decreasing trend while the flow rate shows an increasing trend. After adjustment, the pressure quickly recovers and the flow rate tends to stabilize, indicating that the adjustment behavior has an intervention effect on the node. It is judged to be a correlated action. Then, the same matching operation is performed on all abnormal nodes. The correlation strength is divided according to the degree of influence. If the node state stabilizes quickly after the adjustment and the trend direction consistency is greater than 75%, it is recorded as a strong correlation. If the stabilization time is longer than 10 minutes or the consistency is less than 50%, it is recorded as a weak correlation. Finally, a list of abnormal nodes with strong correlation to the pump action is compiled. Combining their historical trend offset records and changes before and after adjustment, the feature data of each node is extracted. The data fields include node number, associated pump number, offset period, change time after adjustment, trend response direction, and stabilization time, thus obtaining the feature data of abnormal nodes.

[0036] The adjustment action comparison submodule analyzes the node recovery performance after each adjustment action based on the abnormal node feature data, compares the differences in the effects of each adjustment method during the recovery process, analyzes the impact on node recovery time and synchronization status, identifies the adjustment action with the best performance, and obtains the action adjustment data. Feature records are extracted from each node identified as strongly correlated with the adjustment action. Then, each instance of pump adjustment is mapped to its corresponding action, including the start time, action type, duration, and adjustment amplitude parameters, which are recorded as an adjustment action sequence. The pressure and flow changes of the node after each action are evaluated in time intervals. The pressure and flow fluctuation ranges of the node within the first, third, and fifth minutes after adjustment are statistically analyzed, recording the maximum amplitude and direction of change. The time required for the node to return to a stable state is then marked. For example, if the node's pressure fluctuation is less than 0.02 MPa for three consecutive samplings after adjustment, and the flow fluctuation is less than 0.5 cubic meters per hour with a consistent trend direction, the node is considered to have recovered. To restore a stable state, the recovery time is recorded. For example, if a node reaches a stable state within 6 minutes after the pump speed is increased, the recovery time is 6 minutes. The recovery time and trend consistency of the same node under different adjustment actions are compared. If action A has a recovery time of 6 minutes and a trend consistency of 90%, while action B has a recovery time of 4 minutes but a consistency of only 55%, then action A is considered to be more stable. If action C has a recovery time of 3 minutes and a consistency of 85%, then it is recorded as the optimal adjustment action. All adjustment actions are sorted according to the recovery time, trend change direction, and stable state duration of each action. The optimal action type, action amplitude, and action duration are extracted as action adjustment data.

[0037] The control parameter adjustment submodule analyzes the pump control effect based on the action control data and adjusts the control parameters of abnormal nodes to obtain the sensitivity control parameters. The action type, adjustment range, trigger time period, and pump response data are extracted from the optimal adjustment action record. Then, a normalized score is applied to the node's recovery effect based on the action. The scoring dimensions include recovery time, trend consistency, and fluctuation amplitude, with weights of 0.4, 0.4, and 0.2 respectively. Each indicator is standardized; for example, shorter recovery time, higher consistency, and smaller fluctuations result in higher scores. These three scores are combined to form the adjustment action score. Action parameters with a total score higher than 80 can be used as the preferred parameter source for sensitivity control. The pump adjustment range setting value under this action is extracted. For example, if the speed adjustment range is 150 revolutions per minute, it is recorded as the adjustment step size. If the adjustment duration is 90 seconds, it is recorded as the adjustment time period. If the action trigger point is a node pressure change greater than 0.15 MPa, this value is recorded as the trigger factor. These three parameters are integrated to form the node sensitivity control parameters. Subsequently, all abnormal nodes are traversed, and their associated optimal action parameters are called and written into their control parameter setting table to obtain the sensitivity control parameters.

[0038] like Figure 2 and Figure 6 As shown, the target adjustment module includes: The pressure trend analysis submodule analyzes the pressure monitoring data of the water pump at the regulating port of the heating return water branch based on the sensitivity control parameters, compares the pressure changes in continuous cycles, identifies the pressure increase and decrease trend in each cycle, determines the difference in the change amplitude during the cycle, and obtains the pressure trend characteristics. The pressure sensor data collected by the regulating inlet of the heating return water branch is periodically processed. First, according to a set time period, such as every 30 minutes, an analysis cycle is defined. All pressure records within the current cycle are extracted from the sensor dataset and arranged chronologically. The pressure values ​​between any two adjacent sampling points are compared. If the pressure at a later time is higher than the previous time, it is marked as an upward trend; if it is lower, it is marked as a downward trend; if they are equal, it is marked as no change. This judgment is performed sequentially within the cycle to generate a trend sequence. Simultaneously, the cumulative difference between the increases and decreases is accumulated. For example, if the pressure increases from 0.32 MPa to 0.48 MPa in one cycle, the increment for this cycle is 0.16 MPa. In the next cycle, the pressure increases from 0.48 MPa... If the pressure drops to 0.41 MPa, the change is 0.07 MPa. Then, the increase or decrease of two adjacent cycles is compared, the difference is calculated, and it is determined whether it is outside the set change threshold. The threshold is set to 0.1 MPa. If the difference in change between two cycles exceeds this value, it is judged as an abnormal trend change. For example, if the increase in cycle one is 0.16 and the decrease in cycle two is 0.07, the difference is 0.09. If it is below the threshold, it is considered that there is no abnormal trend fluctuation. If the difference between adjacent cycles is 0.15 MPa, it is recorded as a significant trend change. By comparing the trend direction and fluctuation amplitude of each cycle in turn, the increase or decrease direction, cumulative change, and trend deviation value of each cycle are marked. The above results are written into the cycle trend characteristic table to form pressure trend characteristic data.

[0039] The periodic synchronization comparison submodule analyzes the synchronization of the flow rate change trend and the pressure change trend in the current period based on the pressure trend characteristics, compares the degree of coordination between the two changes, determines whether they are consistent, identifies asynchronous data segments, and obtains periodic synchronization difference data. To determine the consistency between flow and pressure trends within the same period, the process first extracts a set of flow records aligned with the pressure data from the flow sensor records for that period. The direction of flow change is then determined based on the magnitude of values ​​at adjacent time points, generating a flow trend direction sequence. This sequence is then compared one-to-one with the pressure trend direction sequence. If both change in the same direction within any time period, they are marked as trend-synchronized. If the directions are opposite, or one remains unchanged while the other changes, they are marked as trend-asynchronized. The number of synchronized and asynchronous points within the period is then counted, and the synchronization percentage is calculated. For example, if there are 10 trend comparison points within a period, with 7 synchronized and 3 asynchronous, the synchronization rate is 70%. If the value is lower than the set synchronization benchmark, for example, 80%, it is determined that there is insufficient coordination between flow and pressure within that cycle. Further, the asynchronous points are located, the start and end times are recorded, and the time period is marked as the synchronization difference segment. Then, combined with the trend fluctuation of this cycle and adjacent cycles, it is determined whether the asynchronous segment has continuity. For example, if the asynchronous segments of two cycles are adjacent and the time coverage is greater than 50% of the cycle, they are merged into a continuous synchronization anomaly segment. The pressure change direction, flow change direction, duration, and the maximum difference between pressure and flow within this segment are recorded in the synchronization difference dataset. Through the above processing, structured periodic synchronization difference data is generated.

[0040] The control boundary adjustment submodule analyzes the data on periodic synchronization difference, determines the impact on pump regulation, and adjusts the control parameters of the uncoordinated section to obtain the differential pressure control range. Extract all data segments marked as asynchronous, and independently analyze the pressure change trend and flow response trend within each segment. Within each asynchronous segment, determine whether there are phenomena such as large flow fluctuations with relatively constant pressure, or continuous pressure increases with decreasing flow. If such characteristics exist, record this segment as a highly sensitive segment to regulation influence. Then, read the pump regulation execution records within this segment and analyze the parameter response before and after the regulation action. For example, if a certain regulation action was executed before this segment, and the pressure change exceeded the normal range within 3 minutes after execution (e.g., exceeding 0.2 MPa), then... If the adjustment action has a strong impact on the segment, it is determined that the change is weak. If the change is less than 0.05 MPa, it is determined that the impact is weak. After performing the above operation on all asynchronous segments, they are classified into "strong response segment", "weak response segment" and "medium response segment" according to the response intensity. Then, the corresponding differential pressure control boundary parameters are set according to the segment classification results. For example, the differential pressure adjustment range is set to ±0.1 MPa for the strong response segment, ±0.05 MPa for the medium response segment, and the original value is kept unchanged for the weak response segment. The upper and lower limit boundaries of the control are reset for each segment, and the differential pressure control interval data is output.

[0041] like Figure 2and Figure 7 As shown, the parameter correction module includes: The pressure change analysis submodule analyzes the pressure change in the current cycle based on the differential pressure control range, compares the pressure fluctuation characteristics in each cycle, identifies the pressure increase and decrease trends of each data point in the time period, analyzes whether the fluctuation trend meets the set requirements, and obtains the pressure fluctuation characteristics. Extract the pressure monitoring data set at the regulating port within the current cycle, sort the pressure values ​​at each time point chronologically, then calculate the pressure change between adjacent time points and mark the increasing or decreasing trend. If the value at a later time point is greater than that at a previous time point, the data point is recorded as rising; otherwise, it is recorded as falling; if they are equal, it is marked as stable. Then, statistically analyze the changing trends of all data points within the same cycle, calculate the proportion of rising, falling, and stable trends within the cycle, and compare and judge each data point in conjunction with the upper and lower limits set in the differential pressure control range. For example, if the current cycle control range is set to 0.3 MPa to 0.6 MPa, then... The system reads the value of each pressure point and determines whether it is within the range. It also determines whether the pressure change between adjacent data points exceeds the upper limit of the allowable fluctuation. For example, if the fluctuation amplitude threshold is set to 0.08 MPa, then when the pressure difference between any two points exceeds this value, it is recorded as an abnormal fluctuation. If multiple consecutive data points fluctuate in the same direction, the number of direction changes is further calculated. If the number of direction changes exceeds 40% of the total number of data points in the cycle, it is determined to be a trend unstable cycle. By systematically analyzing the change amplitude, trend continuity, and direction switching frequency of the pressure value in each cycle, the pressure fluctuation characteristic data in that cycle is formed.

[0042] The data point filtering submodule filters data points that do not meet the set requirements based on pressure fluctuation characteristics. It checks the change range of each data point one by one to determine whether it meets the control standard, identifies data that does not meet the synchronization requirements, and obtains a set of abnormal data points. Each monitoring data point within each cycle is checked item by item. First, the position and change value of each data point recorded in the pressure fluctuation characteristics are retrieved from the trend sequence. This data point is then compared with its preceding and following adjacent data points to calculate the local fluctuation gradient formed by the three points. For example, if the previous value of a certain point is 0.45 MPa, the current value is 0.52 MPa, and the subsequent value is 0.43 MPa, then the point is determined to have abnormal fluctuation spike behavior, and the fluctuation amplitude of this point is recorded as 0.09 MPa. This is then compared with the control standard. If the control standard is set to a maximum allowable jump amplitude of 0.06 MPa for a single point, then the current data point exceeds this standard. If a data point is marked as non-compliant, it is then determined whether it conforms to the direction of a continuous trend. For example, if a single upward point appears in a continuous downward trend, it is recorded as a trend interruption point. All identified non-compliant data points are numbered and their attributes such as offset magnitude, trend conflict type, and whether they appear consecutively are recorded. At the same time, their start timestamp and the node number they belong to in that period are recorded. If the number of abnormal data points in a single period exceeds 30% of the total number of sampling points, that period is recorded as a data abnormal period. The data point numbers in the abnormal period are uniformly written into the abnormal data point set to obtain a clearly identified and complete abnormal data point set.

[0043] The correction coefficient adjustment submodule analyzes the deviation of each data point based on the abnormal data point set, corrects the data points, calculates the matching correction coefficient according to the node characteristics and the flow change trend within the period, optimizes the flow parameter processing method, and obtains the closed-loop adjustment correction amount. For each abnormal data point, extract basic information such as the original pressure value, adjacent values, fluctuation direction, and offset amplitude. Then, retrieve the historical regulation response parameters of the node to which the data point belongs and match them with the corresponding flow rate trend data within the same period. If the node's historical performance shows abnormally high pressure accompanied by a decrease in flow rate, it is initially determined that the current pressure deviation is caused by a lag in the regulation response. The correction benchmark is set as the average difference between two adjacent normal trend data points. For example, if the adjacent normal data points are 0.47 MPa and 0.46 MPa, and the average is 0.465 MPa, then if the current abnormal value is 0.53 MPa... If the pressure is in megapascals (MPa), it needs to be corrected downwards by approximately 0.065 MPa. The correction coefficient level is set based on the node response level. If the node sensitivity is high, the corresponding correction coefficient is set to 0.9; if the sensitivity is medium, it is set to 0.6; and if the sensitivity is low, it is set to 0.3. This coefficient is applied to scale the current point offset value to obtain the correction amount. The original data is then adjusted using this correction amount. The corrected pressure value of each abnormal data point is calculated, and the value before correction, the correction amount, the correction coefficient, and the value after adjustment are recorded. The number of corrected data points and the total correction magnitude within the cycle are combined to form the closed-loop regulation correction amount dataset for this cycle.

[0044] like Figure 8 As shown, a method for regulating the pressure of a heating network includes the following steps: S1: Based on the inlet of the heat exchange station of the main heating pipeline, analyze the pressure monitoring data, synchronously compare the flow monitoring data of the primary side node of the heat exchanger of the heating station, remove asynchronous data through time tag consistency screening, and obtain the zonal rate characteristic group. S2: Based on the zonal rate feature group, compare the flow rate change trend and pressure change trend of the monitoring nodes in the main water supply section to determine the synchronization status, identify the synchronization difference of each node and classify the abnormal type to obtain the node synchronization offset index. S3: Based on the node synchronization offset index, analyze the abnormal node information, sort out the related water pump adjustment action process, and adjust the abnormal node parameters by comparing the recovery performance after the adjustment action to obtain the sensitivity control parameters. S4: Based on the sensitivity control parameters, determine the pressure monitoring data of the corresponding water pump at the regulating port of the heating return water branch, analyze the parameter coordination in combination with the flow change trend, adjust the boundary parameters, and obtain the differential pressure control range; S5: Based on the differential pressure control range, compare the current cycle pressure change with the boundary setting, identify data points that do not meet the requirements, adjust the correction coefficient, optimize the flow change parameter processing process, and obtain the closed-loop control correction amount.

[0045] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A heating network pressure regulating device, characterized in that, The device comprises: The synchronization awareness module analyzes the pressure monitoring data based on the heat supply main pipe heat exchange station entrance, synchronously compares the flow monitoring data of the heat station heat exchanger primary side node, removes the out-of-sync data through time tag consistency screening, and obtains the partition rate feature group; The trend comparison module compares the flow change trend and the pressure change trend of the water supply main section monitoring node based on the partition rate feature group, judges the synchronization situation, identifies the synchronization difference node by node and classifies the abnormal type, and obtains the node synchronization offset index; The regulation and calibration module analyzes the abnormal node information based on the node synchronization offset index, sorts out the associated water pump regulation action process, adjusts the abnormal node parameters by comparing the recovery performance after the regulation action, and obtains the sensitivity regulation parameter; The target adjustment module judges the pressure monitoring data of the corresponding water pump at the regulation port of the heat supply return branch based on the sensitivity regulation parameter, analyzes the parameter coordination by combining the flow change trend, adjusts the boundary parameter, and obtains the pressure difference regulation interval; The parameter correction module compares the current period pressure change and the boundary setting based on the pressure difference regulation interval, identifies the data points that do not meet the requirements, adjusts the correction coefficient, optimizes the flow change parameter processing process, and obtains the closed-loop regulation correction amount.

2. The heating network pressure regulating device according to claim 1, characterized in that The partition rate feature group includes a rate mapping table, a node grouping code, and a data synchronization mark. The node synchronization offset index includes an offset type, an offset period, and an offset degree. The sensitivity regulation parameter includes a sensitivity level, an action trigger factor, and a regulation amplitude identifier. The pressure difference regulation interval includes interval boundary parameters and interval serial numbers. The closed-loop regulation correction amount includes a correction factor, a correction number, and an iteration identifier.

3. The heating network pressure regulating device according to claim 1, characterized in that, The synchronization awareness module comprises: The data tag extraction submodule analyzes the pressure monitoring data and the heat station heat exchanger primary side node flow monitoring data based on the heat supply main pipe heat exchange station entrance, compares the time information of the data records, judges whether the time of each data meets the unified sampling period, optimizes the time record mark method, and obtains the time synchronization mark set; The time tag matching submodule screens the pairing of pressure monitoring data and flow monitoring data under each group of time tags based on the time synchronization mark set, compares the pairing integrity of the data at the same time node, eliminates the data that does not form a corresponding pair, and obtains the synchronization monitoring data set; The feature grouping generation submodule judges the spatial position and equipment partition code of each monitoring node based on the synchronization monitoring data set, classifies and organizes the paired data, optimizes the comparison method of pressure change and flow change of each monitoring unit at consecutive time nodes, and obtains the partition rate feature group.

4. The heating network pressure regulating device according to claim 1, characterized in that The trend comparison module comprises: The trend parameter extraction submodule analyzes the pressure monitoring data and flow monitoring data of each node in the continuous time period based on the partition rate feature group, compares the pressure and flow change direction of each time node adjacent moment, calculates the trend feature of continuous change in the node sequence, and obtains the node trend feature sequence; The node synchronization judgment submodule compares the pressure trend and the flow trend of each node based on the node trend feature sequence, gradually analyzes the consistency of the two types of trend changes under the time sequence, judges whether the trend fluctuations in the same cycle are synchronized, identifies the node section with directional difference in trend change, and obtains a synchronization difference dataset; The abnormal offset classification submodule judges the pressure and flow pairing behavior of each monitoring node during the offset period based on the synchronization difference dataset, identifies the monitoring node that continuously appears offset, classifies the synchronization abnormal type, and obtains a node synchronization offset indicator.

5. The heating network pressure regulating device according to claim 1, characterized in that, The regulation and calibration module comprises: The node information analysis submodule analyzes the synchronization deviation of each abnormal node based on the node synchronization offset indicator, judges the correlation between the synchronization deviation and the pump regulation action, identifies the node that performs abnormally, analyzes the change trend under each regulation state, and obtains abnormal node feature data; The regulation action comparison submodule analyzes the performance of the node recovery after each regulation action based on the abnormal node feature data, compares the effect difference of each regulation mode in the recovery process, analyzes the influence on the node recovery time and synchronization state, identifies the optimal regulation action, and obtains action regulation data; The regulation parameter adjustment submodule analyzes the pump regulation effect based on the action regulation data, adjusts the regulation parameters of the abnormal node, and obtains sensitivity regulation parameters.

6. The heating network pressure regulating device according to claim 1, characterized in that The target adjustment module comprises: The pressure trend analysis submodule analyzes the pressure monitoring data of the pump at the regulation port of the heating return water branch based on the sensitivity regulation parameters, compares the changes of the pressure in the consecutive cycles, identifies the pressure increase and decrease trend of each cycle, determines the change amplitude difference between the cycles, and obtains pressure trend features; The cycle synchronization comparison submodule performs synchronization analysis on the flow change trend and the pressure change trend of the current cycle based on the pressure trend features, compares the coordination degree of the changes of the two, judges whether they are consistent, identifies the out-of-sync data section, and obtains cycle synchronization difference data; The regulation boundary adjustment submodule analyzes the synchronization incoordination data based on the cycle synchronization difference data, judges the influence on the pump regulation, adjusts the regulation parameters of the incoordination section, and obtains a differential pressure regulation interval.

7. The heating network pressure regulating device according to claim 1, characterized in that, The parameter correction module comprises: The pressure change analysis submodule analyzes the pressure change in the current cycle based on the differential pressure regulation interval, compares the fluctuation features of the pressure in each cycle, identifies the pressure increase and decrease trend of each data point in the time period, analyzes whether the fluctuation trend meets the set requirements, and obtains pressure fluctuation features; The data point screening submodule screens the data points that do not meet the set requirements based on the pressure fluctuation features, checks the change amplitude of each data point one by one, judges whether it meets the regulation standard, identifies the data that does not meet the synchronization requirements, and obtains an abnormal data point set; The correction coefficient adjustment submodule analyzes the deviation of each data point based on the abnormal data point set, corrects the data points, calculates the matching correction coefficient according to the node characteristics and the flow change trend in the cycle, optimizes the flow parameter processing mode, and obtains a closed-loop regulation correction amount.

8. The heat supply network pressure regulating device according to claim 1, characterised in that The pressure monitoring data refers to a set of pressure values collected in real time by a pressure sensor at the inlet of a heat exchange station of a heat supply main pipe, and the first-level side node refers to a first-level water circulation system of a heat exchanger of a heat station, i.e., a high-temperature side of a heat supply system, at which a flow sensor is installed to collect flow data.

9. The heat supply network pressure regulating device according to claim 1, characterised in that The flow change trend refers to a change trend and change rule of flow of a monitoring node over time within a continuous sampling period, and the pressure change trend refers to a change trend and change rule of pressure of a monitoring node over time within a continuous sampling period.

10. A method for regulating pressure in a heating network, said method being used for implementing a device for regulating pressure in a heating network according to any one of claims 1-9, characterized in that, The method comprises the following steps: S1: Based on the inlet of the heat exchange station of the heat supply main pipe, the pressure monitoring data is analyzed, the flow monitoring data of the first-level side node of the heat exchanger of the heat station is synchronously compared, and through time tag consistency screening, out-of-sync data is removed to obtain a partition rate feature group; S2: Based on the partition rate feature group, the flow change trend and the pressure change trend of the monitoring node of the water supply main section are compared, the synchronization condition is judged, the synchronization difference is identified node by node and classified into abnormal types to obtain a node synchronization offset index; S3: Based on the node synchronization offset index, abnormal node information is analyzed, an associated water pump regulation action process is combed, a recovery performance after regulation action is compared, abnormal node parameters are adjusted, and a sensitivity control parameter is obtained; S4: Based on the sensitivity control parameter, pressure monitoring data of a corresponding water pump at a regulation port of a heat return branch section of the heat supply is judged, parameter coordination is analyzed in combination with a flow change trend, a boundary parameter is adjusted, and a pressure difference control interval is obtained; S5: Based on the pressure difference control interval, current period pressure changes and boundary settings are compared, data points that do not meet the requirements are identified, a correction coefficient is adjusted, a flow change parameter processing process is optimized, and a closed-loop regulation correction amount is obtained.

Images