Heating pipe network adjusting system based on digital twinning

Abstract

This invention belongs to the field of heating network monitoring technology, specifically a heating network regulation system based on digital twins. It includes a network holographic perception module, a twin dynamic modeling module, a fluid heat loss simulation output module, an intelligent regulation decision module, a linkage execution module, and a heating network monitoring terminal. The network holographic perception module collects comprehensive parameters of the heating network, including fluid operation, environmental impact, and structural status. The twin dynamic modeling module integrates BIM and GIS technologies with an improved Kalman filter algorithm to ensure consistency between the virtual model and the physical network. The fluid heat loss simulation prediction module accurately predicts heat loss. The intelligent regulation decision module scientifically calculates regulation targets based on simulation results and real-time parameters. The linkage execution module performs automated regulation, achieving precise, automated, and long-term monitoring of the heating network while balancing energy efficiency and user comfort, significantly improving the reliability and management efficiency of the heating network operation.

Description

Technical Field

[0001] This invention relates to the field of heating network monitoring technology, specifically a heating network regulation system based on digital twins. Background Technology

[0002] As the core infrastructure of urban energy supply, the operation efficiency and temperature control accuracy of centralized heating networks are directly related to energy conservation, environmental governance and user heating comfort. With the acceleration of urbanization, the scale of heating networks continues to expand and the network structure becomes increasingly complex. At the same time, it faces multiple challenges such as ambient temperature fluctuations, dynamic changes in user load, and network aging. The traditional control mode that relies on manual experience or single parameter feedback is no longer suitable for the needs of refined operation.

[0003] Chinese invention patent CN115013858A discloses "a method for individual household control of a secondary heating network based on lag time identification". This method involves constructing a digital twin model of the secondary heating network, combining heat metering data, room temperature data, and outdoor weather data to establish a load prediction model, identifying the control lag time, and generating individual household valve control strategies. This method is beneficial for solving the temperature fluctuation problem caused by the delay effect of secondary network control. However, the above-mentioned technical solutions lack a targeted correction mechanism for heat loss simulation prediction, fail to quantify the coupled impact of multiple factors such as ambient temperature and pipeline laying length on heat loss, and have limited accuracy in prediction results. They cannot provide accurate basis for decision-making on the whole-area pipeline network regulation and control. Moreover, they only focus on the generation and execution of valve regulation strategies, without setting up standard analysis of actuator actions and multi-dimensional evaluation of regulation effects. It is difficult to discover potential problems and cannot guarantee the stability and continuity of regulation effects. This is not conducive to achieving precise, automated and long-term supervision of heating pipeline networks. Therefore, a solution is proposed. Summary of the Invention

[0004] The purpose of this invention is to provide a heating network regulation system based on digital twins to address the technical deficiencies mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a heating network regulation system based on digital twins, comprising a network holographic perception module, a twin dynamic modeling module, a fluid heat loss simulation and prediction module, an intelligent regulation decision module, a linkage execution module, and a heating network monitoring terminal; The pipeline holographic perception module collects relevant parameters of the physical entity of the heating pipeline network in multiple dimensions and with high precision. The twin dynamic modeling module constructs a digital twin that is synchronized with the physical pipeline network in real time and outputs real-time twin data. The fluid heat loss simulation and prediction module predicts the heat loss of the heating network based on a dynamic digital twin. The intelligent regulation decision module generates comprehensive regulation commands based on the simulation prediction results and the real-time operating parameters of the physical network, and sends the comprehensive regulation commands to the linkage execution module and the heating network monitoring terminal. Based on the comprehensive regulation commands, the linkage execution module drives the actuators of the physical entities of the heating network to act, and feeds back the regulation execution information to the heating network monitoring terminal in real time.

[0006] Furthermore, the pipeline holographic sensing module deploys distributed fiber optic temperature sensors, ultrasonic Doppler flow sensors, and high-precision pressure transmitters at key nodes such as the main pipes, branch pipes, heat exchange station outlets, and user ends of the heating pipeline network, and deploys environmental temperature and humidity sensors and micro-deformation monitoring sensors in the pipeline laying area to form a full-node, multi-dimensional sensing network. The collected data includes fluid operation parameters, environmental impact parameters, and structural state parameters. After hardware filtering to remove pulse interference signals, the collected data is standardized through an edge computing gateway, uniformly converted into JSON format, and marked with a collection timestamp and node ID. It is then synchronously transmitted to the twin dynamic modeling module.

[0007] Furthermore, the twin dynamic modeling module calls the basic geographic information database of the heating pipe network to extract basic parameters including pipe diameter, pipe material, laying depth and insulation layer thickness, and uses BIM and GIS fusion technology to construct the initial digital twin framework; The system receives standardized data transmitted from the pipeline holographic sensing module, fuses the multi-source sensing data through an improved Kalman filter algorithm, integrates real-time parameters into the twin model, dynamically corrects the fluid flow state, heat transfer path, and pipeline structure stress distribution in the twin, and synchronizes the dynamically updated real-time twin data to the fluid heat loss simulation and prediction module.

[0008] Furthermore, the fluid heat loss simulation prediction module receives real-time twin data transmitted by the twin dynamic modeling module, designs a heat loss correction formula, calculates the corrected actual heat loss Qc of the pipeline network based on the heat loss correction formula and substitutes relevant parameters, and sends the actual heat loss Qc of the pipeline network to the intelligent regulation decision module.

[0009] Furthermore, the intelligent regulation decision module acquires simulation prediction results and real-time operating parameters of the physical pipe network, designs the optimal water supply temperature regulation formula, and after calculating the target value Tad for water supply temperature regulation, generates and outputs a comprehensive regulation command for the heating pipe network based on the target value Tad.

[0010] Furthermore, the linkage execution module receives the comprehensive adjustment instructions from the intelligent adjustment decision module, parses the comprehensive adjustment instructions, and then establishes a communication connection with the actuators of the heat exchange station, which include temperature control valves, circulating pump groups, and electric regulating valves. The actuator is driven by a PID closed-loop control algorithm. After the actuator moves, the actual operating parameters of the actuator are collected in real time, including the actual opening degree of the temperature control valve, the actual frequency of the pump group and the actual opening degree of the electric regulating valve. The regulation and execution information is then transmitted to the heating network monitoring terminal via wireless communication.

[0011] Furthermore, the heating network monitoring terminal communicates with the action standard analysis module. The action standard analysis module analyzes the action performance of each actuator during the test period, generates a high-standard execution signal or a low-standard execution signal through analysis, and sends the high-standard execution signal or the low-standard execution signal to the heating network monitoring terminal. When the heating network monitoring terminal receives the low-standard execution signal, it issues a corresponding warning.

[0012] Furthermore, the specific analysis process of the motion standardization analysis module is as follows: If the execution action of the corresponding actuator does not meet the requirements of the corresponding instruction, the corresponding actuator is determined to be in a non-standard execution state. The duration of the corresponding actuator in the non-standard execution state within the test period is obtained and the ratio of it to the total test duration is calculated to obtain the execution time difference feature value. If the execution time difference feature value exceeds the preset execution time difference feature threshold, the corresponding actuator is marked as a non-standard actuator. If a non-standard mechanism exists, a low-standard execution signal is generated; if no non-standard mechanism exists, the ratio of the execution time-varying characteristic value of the corresponding execution mechanism to the corresponding preset execution time-varying characteristic threshold is calculated to obtain the action evaluation value, and the average of the action evaluation values ​​of all execution mechanisms is calculated to obtain the action standardization influence coefficient. If the action influence coefficient exceeds the preset action influence coefficient threshold, a low-standard execution signal is generated; if the action influence coefficient does not exceed the preset action influence coefficient threshold, a high-standard execution signal is generated.

[0013] Furthermore, the action standardization analysis module communicates with the regulation effectiveness early warning module. The action standardization analysis module sends the action high standard signal to the regulation effectiveness early warning module. When the regulation effectiveness early warning module receives the action high standard signal, it analyzes the regulation effect of the heating network within the test period. Through analysis, it determines whether to generate a network regulation effectiveness early warning signal. When a network regulation effectiveness early warning signal is generated, it is sent to the heating network monitoring terminal. When the heating network monitoring terminal receives the network regulation effectiveness early warning signal, it issues a corresponding early warning.

[0014] Furthermore, the specific analysis process of the adjustment effectiveness early warning module is as follows: Get the actual temperature Tr and the target temperature Td at the user end. If |Tr-Td|≤1℃, the user end temperature is judged to meet the standard. The temperature compliance rate is calculated by the ratio of the compliance time of the user end temperature to the total test time within the test cycle. If the temperature compliance rate does not exceed the preset temperature compliance rate threshold, a pipeline efficiency adjustment early warning signal is generated. If the temperature compliance rate exceeds the preset temperature compliance rate threshold, the ratio of the preset temperature compliance rate threshold to the temperature compliance rate is calculated to obtain the compliance anomaly value. The temperature fluctuation amplitude and pressure fluctuation amplitude of the heating network during the test period are marked as fluid temperature wave value and fluid pressure wave value, respectively. The ratio of the actual regulation energy consumption to the traditional regulation energy consumption during the test period is calculated to obtain the regulation energy consumption detection value. The efficiency adjustment warning coefficient is calculated by weighting and summing the abnormal values, fluid temperature wave values, fluid pressure wave values, and energy consumption detection values. If the efficiency adjustment warning coefficient exceeds the preset efficiency adjustment warning coefficient threshold, a pipeline efficiency adjustment warning signal is generated.

[0015] Compared with the prior art, the beneficial effects of the present invention are: 1. In this invention, the operating parameters of the heating network are comprehensively collected by the pipeline holographic perception module, the twin dynamic modeling module ensures the consistency between the virtual model and the physical pipeline network, the fluid heat loss simulation prediction module accurately predicts heat loss, and the adjustment target is scientifically calculated and automatically controlled by combining the simulation results and real-time parameters. This achieves precise, automated and long-term supervision of the heating network, taking into account both energy saving and user comfort, and greatly improving the reliability and management efficiency of the heating network operation.

[0016] 2. In this invention, the action standardization analysis module evaluates the action performance of the actuator, promptly detects actuator malfunctions or non-standard operation problems, provides a basis for equipment maintenance and replacement, ensures the stability and reliability of control execution, and evaluates the control effect from multiple dimensions through the adjustment effectiveness early warning module, helping managers to quickly identify problems and optimize solutions, further improving the operation quality of the heating network. Attached Figure Description

[0017] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings; Figure 1 This is a system block diagram of Embodiment 1 of the present invention; Figure 2 This is a system block diagram of Embodiments 2 and 3 of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1: As Figure 1 As shown, the present invention proposes a heating network regulation system based on digital twin, which includes a network holographic perception module, a twin dynamic modeling module, a fluid heat loss simulation and prediction module, an intelligent regulation decision module, a linkage execution module, and a heating network monitoring terminal; The pipeline holographic perception module collects relevant parameters of the physical entity of the heating pipeline network in multiple dimensions and with high precision, realizing multi-dimensional holographic perception of fluid operation, environmental impact and structural status. It effectively avoids the deviation of twin modeling caused by data loss or inconsistent formats, and provides comprehensive and reliable data source support for subsequent dynamic modeling. Specifically, the pipeline holographic sensing module deploys distributed fiber optic temperature sensors, ultrasonic Doppler flow sensors, and high-precision pressure transmitters at key nodes such as the main pipes, branch pipes, heat exchange station outlets, and user ends of the heating pipeline network, and deploys environmental temperature and humidity sensors and micro-deformation monitoring sensors in the pipeline laying area to form a full-node, multi-dimensional sensing network. The collected data includes fluid operating parameters (supply water temperature Tin, return water temperature Tout, operating pressure P, and instantaneous flow rate F in the pipeline network), environmental impact parameters (temperature Ta and relative humidity Ha of the surrounding environment of the pipeline network), and structural state parameters (micro-deformation ε and corrosion state of the pipeline wall). It should be noted that the sensor adopts a hybrid wireless and wired transmission mode. Non-core parameters such as ambient temperature and humidity and micro-deformation of the pipeline are transmitted wirelessly via LoRa, while core parameters such as water supply temperature, pressure, and flow rate are transmitted wired via industrial Ethernet to ensure the real-time performance and stability of data transmission. Furthermore, after the collected data is filtered by hardware to remove pulse interference signals, it is processed by the edge computing gateway to standardize the data format, uniformly convert it into JSON format and mark the collection timestamp and node ID, and then synchronously transmit it to the twin dynamic modeling module.

[0020] The twin dynamic modeling module constructs a digital twin that is synchronized with the physical pipeline network in real time and outputs real-time twin data. It builds an initial framework through the integration of BIM and GIS technologies and combines an improved Kalman filter algorithm to achieve multi-source data fusion, which solves the problem of asynchronous traditional static modeling and dynamic changes of physical entities. Specifically, the twin dynamic modeling module first calls the basic geographic information database of the heating pipe network to extract basic parameters such as pipe diameter D, pipe material M, laying depth Hl, and insulation layer thickness δ, and uses BIM and GIS fusion technology to construct the initial digital twin framework; Subsequently, the system receives standardized data transmitted from the pipeline holographic sensing module and fuses the multi-source sensing data using an improved Kalman filter algorithm. Real-time parameters such as Tin, Tout, P, F, Ta, and ε are integrated into the twin model to dynamically correct the fluid flow state, heat transfer path, and pipeline stress distribution in the twin. At the same time, the dynamically updated real-time twin data is synchronized to the fluid heat loss simulation and prediction module.

[0021] The fluid heat loss simulation and prediction module, based on a dynamic digital twin, predicts the heat loss of the heating network, quantifies the impact of ambient temperature and laying length on heat loss, significantly improves the accuracy of simulation results, and provides accurate prediction basis for intelligent regulation decisions. Specifically, the fluid heat loss simulation and prediction module receives real-time twin data transmitted from the twin dynamic modeling module, designs a heat loss correction formula, calculates the corrected actual heat loss Qc of the pipeline network based on the heat loss correction formula and substituting relevant parameters, and sends the actual heat loss Qc of the pipeline network to the intelligent regulation decision module; the heat loss correction formula is as follows: Wherein, Qs: initial simulated heat loss based on standard environmental parameters (preferred, 20℃); α: Ambient temperature influence coefficient, ranging from 0.001 to 0.003, obtained by fitting the ambient temperature and actual heat loss monitoring data over the past 3 years using the least squares method; ΔTa: The difference between the actual ambient temperature and the standard simulation temperature. Preferably, ΔTa = Ta − 20. L: Actual length of pipeline.

[0022] The intelligent regulation decision module, based on simulation prediction results and real-time operating parameters of the physical pipeline network, generates comprehensive regulation commands through analysis and sends them to the linkage execution module and the heating pipeline network monitoring terminal. It quantifies the impact of temperature deviation and heat loss on the regulation commands, which is more scientific and accurate than traditional experience-based regulation. It effectively reduces pipeline heat loss and pump energy consumption, while ensuring the temperature compliance rate at the user end. Specifically, the intelligent regulation decision module acquires simulation prediction results and real-time operating parameters of the physical pipe network, designs the optimal water supply temperature regulation formula, calculates the target value Tad for water supply temperature regulation, and generates and outputs a comprehensive regulation command for the heating pipe network based on the target value Tad. The specific formula is as follows: Where, Tad: the optimized target value for water supply temperature regulation; Tac: Current water supply temperature; Td: Target temperature for the user, default 20℃; Tr: Actual temperature at the user end; β: Temperature deviation adjustment coefficient, with a value ranging from 0.3 to 0.5, obtained through training with historical adjustment data to ensure rapid correction of temperature deviation; γ: Heat loss correction factor, with a value range of 0.1 to 0.2, determined according to the thermal insulation performance of the pipeline network (0.1 when the insulation layer thickness δ≥50mm, and 0.2 when δ<50mm). Qc: Actual heat loss in the pipeline network; Qn: Rated heat loss of the pipeline design, derived from the pipeline basic parameter database of the twin dynamic modeling module.

[0023] The linkage execution module, based on comprehensive adjustment commands, drives the actuators of the physical entities in the heating network to move, and feeds back the adjustment execution information to the heating network monitoring terminal in real time, realizing automated and precise control of the heating network, which significantly reduces the difficulty of monitoring and controlling the heating network and the workload of management personnel. Specifically, the linkage execution module receives the comprehensive adjustment instructions from the intelligent adjustment decision module, parses the comprehensive adjustment instructions, and then establishes a communication connection with the actuators of the heat exchange station. The actuators of the heat exchange station include temperature control valves, circulating pump groups, and electric regulating valves, etc. The actuator is driven by a PID closed-loop control algorithm. After the actuator moves, the actual operating parameters of the actuator are collected in real time, such as the actual opening degree of the temperature control valve, the actual frequency of the pump group, and the actual opening degree of the electric regulating valve. The adjustment and execution information is transmitted to the heating network monitoring terminal via wireless communication, which makes it convenient for managers to have a detailed understanding of the operation and adjustment information of the heating network. This is conducive to manual intervention and adjustment to ensure the safe and stable operation of the heating network.

[0024] Example 2: Figure 2 As shown, the difference between this embodiment and Embodiment 1 is that the heating network monitoring terminal is connected to the action standard analysis module. The action standard analysis module analyzes the action performance of each actuator during the test period, generates a high standard execution signal or a low standard execution signal through analysis, and sends the high standard execution signal or the low standard execution signal to the heating network monitoring terminal. When the heating network monitoring terminal receives a signal indicating substandard operation, it issues a corresponding early warning. This allows for timely detection of actuator malfunctions or non-standard operational issues, providing a basis for equipment maintenance and replacement. It also reminds management personnel to promptly repair or replace the corresponding actuators, ensuring the stability and reliability of control execution and further guaranteeing the efficient and safe operation of the heating network. The specific analysis process of the action standardization analysis module is as follows: The system receives adjustment and execution information from each actuator from the linkage execution module. If the execution action of the corresponding actuator does not meet the corresponding instruction requirements, it is determined that the corresponding actuator is in a non-standard execution state (for example, if the actual frequency of the pump group is not within the corresponding preset threshold range, it is determined that the circulating pump group is in a non-standard execution state). The system obtains the duration of the corresponding actuator in a non-standard execution state within the test cycle and calculates the ratio with the total test duration to obtain the execution time-varying characteristic value. The system compares the execution time-varying characteristic value with the preset execution time-varying characteristic threshold. If the execution time-varying characteristic value exceeds the preset execution time-varying characteristic threshold, it indicates that the execution performance of the corresponding actuator is poor within the test cycle, and the corresponding actuator is marked as a non-standard actuator. If a non-standard mechanism exists, it indicates that there is a potential control execution risk in the heating network, and a low-standard execution signal is generated; if no non-standard mechanism exists, the ratio of the execution time-varying characteristic value of the corresponding execution mechanism to the corresponding preset execution time-varying characteristic threshold is calculated to obtain the action evaluation value, and the average of the action evaluation values ​​of all execution mechanisms is calculated to obtain the action standardization influence coefficient. The action impact coefficient is compared with the preset action impact coefficient threshold. If the action impact coefficient exceeds the preset action impact coefficient threshold, it indicates that the overall control stability of the heating network during the test period is poor, and a low standard execution signal is generated. If the action impact coefficient does not exceed the preset action impact coefficient threshold, it indicates that the overall control stability of the heating network during the test period is good, and a high standard execution signal is generated.

[0025] Example 3: Figure 2 As shown, the difference between this embodiment and Embodiment 1 and Embodiment 2 is that the action standard analysis module is communicatively connected to the regulation effectiveness early warning module. The action standard analysis module sends the action high standard signal to the regulation effectiveness early warning module. When the regulation effectiveness early warning module receives the action high standard signal, it analyzes the regulation effect of the heating network within the test period and determines whether to generate a network regulation effect early warning signal through analysis. When a network performance adjustment early warning signal is generated, it is sent to the heating network monitoring terminal. Upon receiving the signal, the monitoring terminal issues a corresponding warning, helping managers quickly identify problems and optimize solutions, improving the operational quality of the heating network, further ensuring its operational effectiveness, and significantly reducing the difficulty of its operation and monitoring. The specific analysis process of the adjustment effectiveness early warning module is as follows: Get the actual temperature Tr and the target temperature Td at the user end. If |Tr-Td|≤1℃, the user end temperature is judged to meet the standard. The temperature compliance rate is calculated by the ratio of the compliance time of the user end temperature to the total test time within the test cycle. The temperature compliance rate is compared with the preset temperature compliance rate threshold. If the temperature compliance rate does not exceed the preset temperature compliance rate threshold, a pipeline efficiency adjustment early warning signal is generated. If the temperature compliance rate exceeds the preset temperature compliance rate threshold, the ratio of the preset temperature compliance rate threshold to the temperature compliance rate is calculated to obtain the compliance anomaly value. The temperature fluctuation amplitude and pressure fluctuation amplitude of the heating network during the test period are marked as fluid temperature wave value and fluid pressure wave value, respectively. The ratio of the actual regulation energy consumption to the traditional regulation energy consumption during the test period is calculated to obtain the regulation energy consumption detection value. The efficiency improvement warning coefficient is calculated by weighting and summing the abnormal compliance values, fluid temperature wave values, fluid pressure wave values, and energy consumption detection values. Specifically, the abnormal compliance values, fluid temperature wave values, fluid pressure wave values, and energy consumption detection values ​​are each assigned a corresponding preset weight coefficient. The abnormal compliance values, fluid temperature wave values, fluid pressure wave values, and energy consumption detection values ​​are then multiplied by their respective preset weight coefficients, and the sum of the four product results is marked as the efficiency improvement warning coefficient. It should be noted that the larger the value of the adjustment and control early warning coefficient, the worse the overall performance of the heating network adjustment and control during the test period. The adjustment and control early warning coefficient is compared with the preset adjustment and control early warning coefficient threshold. If the adjustment and control early warning coefficient exceeds the preset adjustment and control early warning coefficient threshold, it indicates that the overall performance of the heating network adjustment and control during the test period is poor, and a network adjustment and control early warning signal is generated.

[0026] The working principle of this invention is as follows: During use, the holographic perception module collects comprehensive parameters such as fluid operation, environmental impact, and structural status of the heating network. The twin dynamic modeling module integrates BIM and GIS technologies and an improved Kalman filter algorithm to ensure the consistency between the virtual model and the physical network. The fluid heat loss simulation and prediction module accurately predicts heat loss. The intelligent adjustment decision module combines simulation results and real-time parameters to scientifically calculate adjustment targets, effectively reducing network heat loss and energy consumption while ensuring that user-end temperatures meet standards. The linkage execution module performs automated control, significantly reducing the difficulty and workload of manual supervision. Overall, it achieves precise, automated, and long-term supervision of the heating network, taking into account both energy conservation and user comfort, and greatly improving the reliability and management efficiency of the heating network operation.

[0027] In this invention, the threshold, preset value, or preset range settings are for result comparison and analysis to determine whether the result is good or bad. The magnitude of these values ​​is determined by a combination of large-scale model analysis of sample data and human experience, and can also be appropriately adjusted based on seasonal or common-sense influence conditions. Similarly, the preset weight coefficients and influence factors are assigned specific values ​​based on the magnitude of each parameter's influence on the result, ultimately reflecting the impact on the result. These settings are also determined by a combination of large-scale model analysis of sample data and human experience, and can also be appropriately adjusted based on seasonal or common-sense influence conditions.

[0028] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, enabling those skilled in the art to better understand and utilize it. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A heating network regulation system based on digital twin, characterized in that, It includes a pipeline holographic perception module, a twin dynamic modeling module, a fluid heat loss simulation and prediction module, an intelligent regulation decision module, a linkage execution module, and a heating pipeline monitoring terminal; The pipeline holographic perception module collects relevant parameters of the physical entity of the heating pipeline network in multiple dimensions and with high precision. The twin dynamic modeling module constructs a digital twin that is synchronized with the physical pipeline network in real time and outputs real-time twin data. The fluid heat loss simulation and prediction module is based on a dynamic digital twin to predict the heat loss of the heating network. The intelligent regulation decision module generates comprehensive regulation commands based on simulation prediction results and real-time operating parameters of the physical pipeline network. The linkage execution module drives the actuators of the physical entities of the heating pipeline network to act based on the comprehensive regulation commands and feeds back the regulation execution information to the heating pipeline network monitoring terminal in real time.

2. A heating network regulation system based on digital twins according to claim 1, characterized in that, The data collected by the pipeline holographic perception module includes fluid operation parameters, environmental impact parameters, and structural state parameters. After hardware filtering to remove pulse interference signals, the collected data is standardized through the edge computing gateway, uniformly converted into JSON format, and marked with the collection timestamp and node ID. Then, it is synchronously transmitted to the twin dynamic modeling module.

3. A heating network regulation system based on digital twins according to claim 2, characterized in that, The twin dynamic modeling module calls the basic geographic information database of the heating network, extracts the basic parameters of the heating network, and uses BIM and GIS fusion technology to construct the initial digital twin framework; The system receives standardized data transmitted from the pipeline holographic sensing module, fuses the multi-source sensing data through an improved Kalman filter algorithm, integrates real-time parameters into the twin model, dynamically corrects the fluid flow state, heat transfer path, and pipeline structure stress distribution in the twin, and synchronizes the dynamically updated real-time twin data to the fluid heat loss simulation and prediction module.

4. A heating network regulation system based on digital twins according to claim 3, characterized in that, The fluid heat loss simulation and prediction module receives real-time twin data transmitted from the twin dynamic modeling module, designs a heat loss correction formula, calculates the corrected actual heat loss of the pipeline network based on the heat loss correction formula and substitutes relevant parameters, and sends the actual heat loss of the pipeline network to the intelligent regulation decision module.

5. A heating network regulation system based on digital twins according to claim 4, characterized in that, The intelligent regulation decision module acquires simulation prediction results and real-time operating parameters of the physical pipe network, designs the optimal water supply temperature regulation formula, and after calculating the target value of water supply temperature regulation, generates and outputs a comprehensive regulation command for the heating pipe network based on the target value of water supply temperature regulation.

6. A heating network regulation system based on digital twins according to claim 1, characterized in that, The linkage execution module receives the comprehensive adjustment instructions from the intelligent adjustment decision module, parses the comprehensive adjustment instructions, and then establishes a communication connection with the actuator of the heat exchange station. It uses a PID closed-loop control algorithm to drive the actuator to act. After the actuator acts, the actual operating parameters of the actuator are collected in real time, and the adjustment execution information is transmitted to the heating network monitoring terminal via wireless communication.

7. A heating network regulation system based on digital twins according to claim 6, characterized in that, The heating network monitoring terminal is connected to the action standard analysis module. The action standard analysis module analyzes the action performance of each actuator during the test period and generates high-standard or low-standard execution signals through analysis. When the heating network monitoring terminal receives a low-standard execution signal, it issues a corresponding warning.

8. A heating network regulation system based on digital twin according to claim 7, characterized in that, The specific analysis process of the motion standardization analysis module is as follows: if there is a non-standard mechanism, a low-standard execution signal is generated; if there is no non-standard mechanism, the motion evaluation values ​​of all actuators are averaged to obtain the motion standardization influence coefficient. If the motion influence coefficient exceeds the preset motion influence coefficient threshold, a low-standard execution signal is generated; otherwise, a high-standard execution signal is generated.

9. A heating network regulation system based on digital twins according to claim 8, characterized in that, The action standard analysis module communicates with the regulation effectiveness early warning module. When the regulation effectiveness early warning module receives the action high standard signal, it analyzes the regulation effect of the heating network within the test period and sends it to the heating network supervision terminal when generating the network regulation effectiveness early warning signal.

10. A heating network regulation system based on digital twins according to claim 9, characterized in that, The specific analysis process of the adjustment effectiveness early warning module is as follows: If the temperature compliance rate does not exceed the preset temperature compliance rate threshold, a pipeline efficiency adjustment warning signal is generated; if the temperature compliance rate exceeds the preset temperature compliance rate threshold, an efficiency adjustment warning coefficient is calculated by weighted summation of compliance anomaly values, fluid temperature wave values, fluid pressure wave values, and energy consumption detection values; if the efficiency adjustment warning coefficient exceeds the preset efficiency adjustment warning coefficient threshold, a pipeline efficiency adjustment warning signal is generated.

Images