Intelligent heat supply network operation analysis system based on multi-information fusion

Abstract

The application discloses an intelligent heat network operation analysis system based on multi-information fusion and relates to the technical field of intelligent heat network operation. The system mainly aims at the problem that different model constructions cannot be performed at different stages in the intelligent heat network operation analysis process and targeted supply analysis cannot be performed in combination with an actual heat supply process. Specifically, when entering a first stage, pipe network basic modeling is performed and non-steady state characteristic detection is performed, temperature, pressure and flow are taken as three dimensions of data collection, continuous monitoring and collection are performed according to the data type of the current dimension, a temperature field and a pressure field are constructed according to the collected values, when entering a second stage, the pipe network in the heat supply network is divided into pipe sections, valves and heat exchanger pipeline components, a hardware network model of the heat supply network is constructed, a distribution cloud map is constructed in the hardware network model, a medium flow trajectory is obtained according to the heat supply medium in the heat supply network, and analysis is performed in combination with a use scene, so that operation control is performed.

Description

Technical Field

[0001] This invention relates to the field of intelligent heating network operation technology, specifically to an intelligent heating network operation analysis system based on multi-information fusion. Background Technology

[0002] Heating network operation refers to the full-process management and control of the heat source, pipeline network, heat exchange station and user terminal of the centralized heating system in order to achieve the goal of safe, efficient and economical heating. The core tasks include data monitoring, operation control, equipment maintenance, user service and energy efficiency optimization, involving knowledge from multiple fields such as thermodynamics, fluid mechanics, automatic control and information technology.

[0003] However, existing technologies cannot divide the operation of the heating network into stages, making it impossible to carry out targeted operation control in stages. Furthermore, different models cannot be built for different stages, and it is also impossible to conduct targeted supply analysis based on the actual heating process, which reduces the operating efficiency of the heating network. To address the above-mentioned technical deficiencies, a solution is proposed. Summary of the Invention

[0004] The purpose of this invention is to solve the problems mentioned above by proposing an intelligent heating network operation analysis system based on multi-information fusion.

[0005] The objective of this invention can be achieved through the following technical solution: a smart heating network operation analysis system based on multi-information fusion, including a heating network operation analysis platform, used to perform heating network operation analysis, and to divide the supply end into stable supply end, low demand supply end and low demand supply end during the operation phase, and to divide the real-time heating phase according to the type of supply end, namely the first phase and the second phase.

[0006] In the first stage, the pipeline network is modeled and non-steady-state characteristics are detected. Temperature, pressure, and flow rate are used as the three dimensions for data collection. The data is continuously monitored and collected according to the data type of the current dimension. Temperature and pressure fields are constructed based on the collected values, and the influence characteristics are detected through the data of each dimension.

[0007] In the second stage, an additional data collection dimension is added: humidity. The heating network is divided into pipe sections, valves, and heat exchanger pipe components. A hardware network model of the heating network is constructed, and a distribution cloud map is built within the hardware network model. At the same time, the flow trajectory of the heating medium within the heating network is obtained, and analysis is performed in conjunction with the usage scenarios to enable operational control.

[0008] In a preferred embodiment of the present invention, a temperature field and a pressure field are constructed at various locations in the current heating network based on the numerical range of temperature or pressure. The distribution of the temperature field and the pressure field are detected. When the fluctuation of the heating task is lower than the fluctuation range, the numerical fluctuation of the temperature field or the pressure field is collected. If the frequency of the numerical fluctuation exceeds the frequency threshold, a supply environment fluctuation signal is generated and uploaded to the heating network operation analysis platform. If the frequency of the numerical fluctuation does not exceed the frequency threshold, a supply environment temperature signal is generated and uploaded to the heating network operation analysis platform.

[0009] In a preferred embodiment of the present invention, when numerical fluctuations occur, that is, after the numerical values ​​of the corresponding dimension data of consecutive adjacent positions in the temperature field or pressure field fluctuate, the numerical fluctuation delay time deviation between different position intervals in the temperature field or pressure field is collected. If the numerical fluctuation delay time deviation exceeds the set time deviation threshold, a hysteresis monitoring signal is generated and uploaded to the heating network operation analysis platform. After receiving the hysteresis monitoring signal, the heating network operation analysis platform extends the monitoring cycle of each dimension data and adds monitoring time.

[0010] As a preferred embodiment of the present invention, after determining the data monitoring cycle of each dimension, the flow rate in the heating network is collected, and the instantaneous increase stage of the flow rate is marked as the instantaneous process. After the instantaneous process occurs, the area covered by the floating point of the dimensional data of the temperature field or pressure field is collected and marked as the temperature wave propagation range or pressure wave propagation range.

[0011] When the instantaneous process occurs, the area fluctuation of the propagation range and the frequency of the propagation range are recorded. If the frequency of the propagation range continues to increase and the area fluctuation of the propagation range continues to increase, an instantaneous high impact signal is generated and uploaded to the heating network operation analysis platform. After receiving the instantaneous high impact signal, the heating network operation analysis platform controls the flow rate by adjusting the fluctuation.

[0012] If the frequency of the propagation range fluctuates back and forth, and the area of ​​the propagation range fluctuates back and forth, a hardware maintenance signal is generated and uploaded to the heating network operation analysis platform. After receiving the signal, the heating network operation analysis platform maintains the heating network and takes the location where the flow rate fluctuates continuously as the maintenance starting point and the propagation range as the direction for pipeline maintenance.

[0013] If the frequency of propagation range generation is consistently lower than the set frequency threshold, and the area fluctuation of propagation range is consistently lower than the set area threshold, a normal signal for impact characteristic detection will be generated and uploaded to the heating network operation analysis platform.

[0014] In a preferred embodiment of the present invention, based on a hardware network model, the local pressure peak value at the transient impact position during the propagation of pressure waves in the fluid medium transient process is collected. At the same time, based on the continuous generation of the transient impact position, the deviation value of the increase in floating velocity of deformation at each position in the pipeline is collected. The local pressure peak value at the transient impact position and the deviation value of the increase in floating velocity of deformation at each position in the pipeline during the propagation of pressure waves in the fluid medium transient process are analyzed.

[0015] As a preferred embodiment of the present invention, if the local pressure peak at the transient impact position exceeds the pressure peak during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation value of the increase in floating velocity of the deformation at each position in the pipeline exceeds the deviation threshold, a transient control signal is generated and sent to the heating network operation analysis platform. After receiving the signal, the heating network operation analysis platform controls the transmission of the fluid medium and performs regular maintenance at the transient position of the fluid medium transmission.

[0016] If the local pressure peak at the transient impact point exceeds the pressure peak during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation value of the increase in floating speed of the deformation at each position in the pipeline does not exceed the deviation threshold, then a transient satisfaction signal is generated and sent to the heating network operation analysis platform. After receiving the signal, the heating network operation analysis platform reduces the limit on the fluid medium transmission speed, that is, according to the actual heating demand, the fluid medium transmission speed is increased. When a transient occurs, the fluid medium is still transmitted according to the current heating rules.

[0017] If the local pressure peak at the transient impact point does not exceed the pressure peak during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation value of the increase in floating velocity of the deformation at each position in the pipeline exceeds the deviation threshold, a transient resistance signal is generated and sent to the heating network operation analysis platform. After receiving the transient resistance signal, the heating network operation analysis platform will control the fluid medium transportation of the current pipeline to reduce the number of transients.

[0018] If the local pressure peak at the transient impact point does not exceed the pressure peak during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation value of the increase in floating velocity of the deformation at each position in the pipeline does not exceed the deviation threshold, then a transient smoothing signal is generated and sent to the heating network operation analysis platform. After receiving the signal, the heating network operation analysis platform controls the current pipeline to continuously deliver heat according to the existing delivery rules.

[0019] As a preferred embodiment of the present invention, the irregular insulation structure is analyzed, and the ambient humidity value at the location of the irregular insulation structure in the hardware network model during the operation of the heating network is collected.

[0020] When the ambient humidity value changes, the rate at which the temperature difference between the inside and outside of the irregular insulation structure decreases is obtained;

[0021] When the ambient humidity remains unchanged, the humidity variation deviation of the environment near and far from the structure is obtained.

[0022] As a preferred embodiment of the present invention, if the rate at which the temperature difference between the inside and outside of the irregular insulation structure decreases exceeds the rate of decrease, or if the humidity change deviation of the corresponding positions near and far from the structure in the environment where the irregular insulation structure is located exceeds the deviation threshold, a heat transfer control signal for the structure is generated and sent to the heat network operation analysis platform.

[0023] After receiving the data, the heating network operation analysis platform monitors the temperature of the irregular insulation structure in real time and controls the real-time heat transfer. If the rate of decrease of the temperature difference between the inside and outside of the irregular insulation structure does not exceed the rate of decrease threshold, and the humidity change deviation of the corresponding positions near and far from the structure in the environment where the irregular insulation structure is located does not exceed the change deviation threshold, a normal heat transfer signal for the structure is generated and sent to the heating network operation analysis platform.

[0024] Compared with the prior art, the beneficial effects of the present invention are:

[0025] 1. In this invention, the heating network operation analysis platform performs basic modeling of the pipeline network. Based on the basic modeling, it infers whether the current operating condition of the heating pipeline network meets the demand, thereby conducting supply detection of the heating pipeline network. The heating pipeline network is detected under low-intensity supply conditions, which improves the accuracy of real-time assessment of the operating status of the heating pipeline network. This facilitates targeted control decisions by the operation platform, avoids supply anomalies that reduce heating efficiency, and promptly detects and adjusts abnormal operating parameters of the heating pipeline network, thereby reducing heating risks.

[0026] 2. In this invention, after the hardware network model is constructed, heating network scenario detection is performed. That is, the hardware network model is tested for various usage scenarios during heating operation. Based on the detection of each usage scenario and the synchronous operation analysis of the hardware network model, it is inferred whether the real-time heating network supply status is qualified. Thus, the heating network status can be adjusted in a timely manner during network operation. Combined with the hardware network model, the supply network can be regulated in a timely manner according to the impact of the real-time supply status. The hardware network model can also monitor the impact of hardware operation status on heating in real time, which facilitates timely and targeted maintenance and reduces the adverse effects of heating network hardware. Attached Figure Description

[0027] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0028] Figure 1 This is a schematic diagram of the system of the present invention;

[0029] Figure 2 This is a flowchart of the method in Embodiment 2 of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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.

[0031] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0032] Please see Figure 1 As shown, the intelligent heating network operation analysis system based on multi-information fusion includes a heating network operation analysis platform, which is used to perform operation analysis on the heating network and conduct targeted analysis and detection according to the operation stage of the heating network.

[0033] It needs to be explained that the operation phase of the heating network is analyzed, and the supply end of the heating network during the heating phase is collected. The supply end refers to the user end that has heating. The supply is divided according to the amount of heat received and the frequency of heat received. That is, if the amount of heat received or the frequency of heat received exceeds the corresponding set threshold, the current supply end is marked as a stable supply end.

[0034] If both the received heat supply and the received heat supply frequency exceed the corresponding set threshold, the current supplier is marked as a high-demand supplier; if neither the received heat supply nor the received heat supply frequency exceeds the corresponding set threshold, the current supplier is marked as a low-demand supplier.

[0035] During the operation of the heating network, if the ratio of heat supply from the low-demand supply side to the high-demand supply side continues to increase, it is inferred that the heat demand from the low-demand supply side exceeds the demand from the high-demand supply side. That is, the heat demand from the low-demand supply side is continuously increasing, or the cumulative heat supply from the stable supply side is continuously increasing. The current stage is then marked as the second stage.

[0036] If the ratio of heat supply from low-demand supply side to high-demand supply side continues to decrease, it is inferred that the heat demand from low-demand supply side has not exceeded the demand from high-demand supply side. That is, the heat demand from low-demand supply side has not continued to increase, and the cumulative heat supply from stable supply side has not continued to increase. The current stage is marked as the first stage.

[0037] It should be explained that when collecting the heat supply ratio, it is also necessary to combine and analyze the actual heat supply of each type of supply to eliminate the error caused by comparing the heat supply values. That is, when the ratio does not change, if the heat supply of the corresponding low-demand supply side exceeds the set threshold, it is also judged as an increase in demand. Different models are made according to different stages to ensure the targeting of heat supply detection in the corresponding stage and to ensure the accuracy of heat network operation analysis.

[0038] Example 1: In the first stage, the heating network operation analysis platform performs basic network modeling. Based on the basic modeling, it infers whether the current operating condition of the heating network meets the demand, thereby conducting supply detection on the heating network. The heating network is detected under low-intensity supply conditions, which improves the accuracy of real-time assessment of the operating status of the heating network. This facilitates targeted control decisions by the operation platform, avoids supply anomalies that reduce heating efficiency, and promptly detects and adjusts abnormal operating parameters of the heating network, thereby reducing heating risks.

[0039] Pipeline network basic modeling and non-steady-state characteristic detection are performed. The heating network is constructed according to the distribution of pipelines, and data is collected on the heating network during the heating phase. Specifically, based on the sensors set at various locations in the heating network, the temperature, pressure, and flow rate at the corresponding collection points are collected. Temperature, pressure, and flow rate are used as the three dimensions of data collection, and continuous monitoring and collection are performed through the data type of the current dimension. Temperature field and pressure field are constructed based on the collected values.

[0040] Based on the numerical range of temperature or pressure, the temperature field and pressure field of each location in the current heating network are constructed. The distribution of the temperature field and pressure field is detected. When the fluctuation of the heating task is lower than the fluctuation range, the numerical fluctuation of the temperature field or pressure field is collected. If the numerical fluctuation frequency exceeds the frequency threshold, it is inferred that the supply environment of the heating network is unstable, and a supply environment fluctuation signal is generated and uploaded to the heating network operation analysis platform. After receiving the signal, the heating network operation analysis platform detects and controls the corresponding fluctuation position of the heating network. If the numerical fluctuation frequency does not exceed the frequency threshold, it is inferred that the supply environment of the heating network is stable, and a supply environment temperature signal is generated and uploaded to the heating network operation analysis platform.

[0041] When numerical fluctuations occur, i.e., after the numerical values ​​of corresponding dimensions at consecutive adjacent positions within the temperature or pressure field fluctuate, the deviation of the numerical fluctuation delay between different intervals in the temperature or pressure field is collected. If the deviation of the numerical fluctuation delay exceeds the set time deviation threshold, it is inferred that there is a lag effect in the collected dimensional data. That is, there is a lag in the numerical collection of data in each dimension when the heating network is operating. Data delay assessment is required to avoid data statistical deviation. A lag monitoring signal is generated and uploaded to the heating network operation analysis platform. After receiving the lag monitoring signal, the heating network operation analysis platform extends the monitoring cycle of each dimension data and adds monitoring time to ensure that the data collection of the heating network during the analysis by the heating network operation analysis platform is in line with the actual needs and reduces data errors.

[0042] After determining the data monitoring cycle for each dimension, flow is collected within the heating network, and the instantaneous increase in flow is marked as an instantaneous process. After the instantaneous process occurs, the area covered by the floating points of the dimensional data of the temperature field or pressure field is collected and marked as the temperature wave propagation range or pressure wave propagation range.

[0043] When the instantaneous process occurs, the area fluctuation of the propagation range and the frequency of the propagation range are recorded. If the frequency of the propagation range continues to increase and the area fluctuation of the propagation range continues to increase, it is inferred that the instantaneous impact characteristic detection is abnormal, an instantaneous high impact signal is generated and uploaded to the heating network operation analysis platform. After receiving the instantaneous high impact signal, the heating network operation analysis platform controls the flow rate by fluctuation.

[0044] If the frequency of the propagation range fluctuates back and forth, and the area of ​​the propagation range fluctuates back and forth, it is inferred that the fault tolerance rate of the pipeline equipment of the heating network to instantaneous impact is decreasing. A hardware maintenance signal is generated and uploaded to the heating network operation analysis platform. After receiving the signal, the heating network operation analysis platform maintains the heating network and takes the location where the flow rate fluctuates continuously as the maintenance starting point and performs pipeline maintenance in the direction of the propagation range.

[0045] If the frequency of propagation range generation is consistently lower than the set frequency threshold, and the area fluctuation of propagation range is consistently lower than the set area threshold, it is inferred that the impact characteristic detection of the heating network is normal, and an impact characteristic detection normal signal is generated and uploaded to the heating network operation analysis platform.

[0046] Example 2: Please refer to Figure 2 As shown, in the second stage, the data collection dimension is increased to humidity data, and the heating network is discretized and modeled. The pipe network within the heating network is divided into pipe sections, valves and heat exchangers and other pipe components to build a hardware network model of the heating network.

[0047] Combining the temperature field and pressure field of the heating network in the previous embodiment, a distribution cloud map is constructed within the hardware network model, and the flow trajectory of the medium is obtained based on the heating medium within the heating network.

[0048] After the hardware network model is built, heating network scenario detection is performed. This involves detecting various usage scenarios during the operation of the hardware network model for heating. Based on the detection of each usage scenario and the synchronous operation analysis of the hardware network model, it is inferred whether the real-time heating network supply status is qualified. This allows for timely adjustments to the heating network status during network operation. Combined with the hardware network model, the supply network can be regulated in a timely manner based on the impact of the real-time supply status. The hardware network model can also monitor the impact of hardware operation status on heating in real time, facilitating timely and targeted maintenance and reducing the adverse effects of heating network hardware.

[0049] Based on the hardware network model, the local pressure peak at the transient impact point during pressure wave propagation in the fluid medium transient process is collected. Simultaneously, based on the continuous generation of the transient impact point, the deviation value of the floating velocity increase in deformation at each position within the pipe is collected. The local pressure peak at the transient impact point and the deviation value of the floating velocity increase in deformation at each position within the pipe during pressure wave propagation in the fluid medium transient process are analyzed.

[0050] If the local pressure peak at the transient impact point exceeds the pressure peak during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation value of the increase in floating velocity of the deformation at each position in the pipeline exceeds the deviation threshold, it is inferred that the transient process of the fluid medium has caused a deviation in the wear progress of the pipe section. A transient control signal is generated and sent to the heating network operation analysis platform. After receiving the signal, the heating network operation analysis platform controls the transmission of the fluid medium and performs regular maintenance at the location where the transient occurs in the transmission of the fluid medium.

[0051] If the local pressure peak at the transient impact point exceeds the pressure peak during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation value of the increase in floating velocity of the deformation at each position in the pipeline does not exceed the deviation threshold, it is inferred that the transient process of the fluid medium has little impact on the pipe section, and a transient satisfaction signal is generated and sent to the heating network operation analysis platform. After receiving the signal, the heating network operation analysis platform reduces the limit on the fluid medium transmission speed, that is, according to the actual heating demand, the fluid medium transmission speed is increased, and the fluid medium is still transmitted according to the current heating rules when a transient occurs.

[0052] If the local pressure peak at the transient impact point does not exceed the pressure peak during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation value of the increase in floating velocity of the deformation at each position in the pipeline exceeds the deviation threshold, it is inferred that the transient process of the fluid medium has a significant impact on the pipe section, generating a transient resistance signal and sending it to the heating network operation analysis platform. After receiving the transient resistance signal, the heating network operation analysis platform will implement fluid medium transportation control for the current pipeline to reduce the number of transient events.

[0053] If the local pressure peak at the transient impact point does not exceed the pressure peak during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation value of the increase in floating speed of the deformation at each position in the pipeline does not exceed the deviation threshold, it is inferred that the fluid medium is transported stably, a transient smoothing signal is generated and sent to the heating network operation analysis platform. After receiving the signal, the heating network operation analysis platform controls the current pipeline to continue to transport heat according to the existing transport rules.

[0054] In the hardware network model, in addition to pipes, irregular insulation structures are analyzed. Irregular insulation structures are represented by components such as valves and elbows. The ambient humidity values ​​at the locations of irregular insulation structures in the hardware network model are collected during the operation of the heating network.

[0055] When the ambient humidity changes, the rate at which the temperature difference between the inside and outside of the irregular insulation structure decreases is obtained. When the ambient humidity does not change, the humidity change deviation of the corresponding positions near and far from the structure in the environment where the irregular insulation structure is located is obtained.

[0056] If the rate of decrease of the temperature difference between the inside and outside of the irregular insulation structure exceeds the rate of decrease, or if the humidity change deviation of the corresponding positions of the environment near and far from the structure exceeds the deviation threshold, then it is inferred that the heat conduction of the corresponding irregular insulation structure in the hardware network model is abnormal, and a structural heat transfer control signal is generated and sent to the heat network operation analysis platform.

[0057] After receiving the data, the heating network operation analysis platform monitors the temperature of the irregular insulation structure in real time and controls the real-time heat transfer. If the rate of decrease of the temperature difference between the inside and outside of the irregular insulation structure does not exceed the rate of decrease threshold, and the humidity change deviation of the corresponding positions near and far from the structure in the environment where the irregular insulation structure is located does not exceed the change deviation threshold, it is inferred that the heat conduction of the corresponding irregular insulation structure in the hardware network model is normal, and a normal heat transfer signal is generated and sent to the heating network operation analysis platform.

[0058] When this invention is used, the heating network operation analysis platform performs heating network operation analysis and divides the supply end into stable supply end, low demand supply end and low demand supply end during the operation phase. According to the type of supply end, the real-time heating phase is divided into the first phase and the second phase.

[0059] In the first stage, the pipeline network is modeled and its unsteady-state characteristics are detected. Temperature, pressure, and flow rate are used as the three dimensions for data collection, and continuous monitoring and collection are carried out according to the data type of the current dimension. Temperature and pressure fields are constructed based on the collected values, and the influence characteristics are detected through the data of each dimension. In the second stage, an additional dimension is added for collection, namely humidity. Combining the temperature and pressure fields of the heating network in the previous embodiment, the pipeline network within the heating network is divided into pipe sections, valves, and heat exchanger pipe components. A hardware network model of the heating network is constructed, and a distribution cloud map is built within the hardware network model. At the same time, the flow trajectory of the heating medium within the heating network is obtained, and analysis is performed in conjunction with the usage scenario for operation control.

[0060] Thresholds, preset values, or preset ranges are set for result comparison and analysis to determine whether they are good or bad. The magnitude of these values ​​is determined by a combination of large-scale model analysis of the sample data and human experience. They can also be adjusted appropriately based on seasonal or common-sense influence conditions. Similarly, the weighting ratio coefficients and influence factors are set based on the magnitude of each parameter's influence on the results. These values ​​are assigned to reflect the overall impact on the results. They are also determined by a combination of large-scale model analysis of the sample data and human experience. They can also be adjusted appropriately based on seasonal or common-sense influence conditions.

[0061] 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, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A smart heating network operation analysis system based on multi-information fusion, characterized in that, This includes a heating network operation analysis platform, which is used to analyze the operation of the heating network and divide the supply side into stable supply side, low demand supply side and low demand supply side during the operation phase. Based on the type of supply side, the real-time heating phase is divided into the first phase and the second phase. In the first stage, the pipeline network is modeled and non-steady-state characteristics are detected. Temperature, pressure, and flow rate are used as the three dimensions for data collection. The data is continuously monitored and collected according to the data type of the current dimension. Temperature and pressure fields are constructed based on the collected values, and the influence characteristics are detected through the data of each dimension. In the second stage, an additional data collection dimension is added: humidity. The heating network is divided into pipe sections, valves, and heat exchanger pipe components. A hardware network model of the heating network is constructed, and a distribution cloud map is built within the hardware network model. At the same time, the flow trajectory of the heating medium within the heating network is obtained, and analysis is performed in conjunction with the usage scenarios to enable operational control.

2. The intelligent heating network operation analysis system based on multi-information fusion according to claim 1, characterized in that, Based on the numerical range of temperature or pressure, the temperature and pressure fields at various locations in the current heating network are constructed. The distribution of the temperature and pressure fields is detected. When the fluctuation of the heating task is lower than the fluctuation range, the numerical fluctuation of the temperature or pressure field is collected. If the frequency of the numerical fluctuation exceeds the frequency threshold, a supply environment fluctuation signal is generated and uploaded to the heating network operation analysis platform. If the frequency of the numerical fluctuation does not exceed the frequency threshold, a supply environment temperature signal is generated and uploaded to the heating network operation analysis platform.

3. The intelligent heating network operation analysis system based on multi-information fusion according to claim 2, characterized in that, When numerical fluctuations occur, i.e., after the numerical values ​​of corresponding dimensions at consecutive adjacent positions in the temperature or pressure field fluctuate, the deviation of the numerical fluctuation delay time between different positions in the temperature or pressure field is collected. If the deviation of the numerical fluctuation delay time exceeds the set time deviation threshold, a hysteresis monitoring signal is generated and uploaded to the heating network operation analysis platform. After receiving the hysteresis monitoring signal, the heating network operation analysis platform extends the monitoring cycle of each dimension of data and adds monitoring time.

4. The intelligent heating network operation analysis system based on multi-information fusion according to claim 3, characterized in that, After determining the data monitoring cycle for each dimension, flow is collected within the heating network, and the instantaneous increase in flow is marked as an instantaneous process. After the instantaneous process occurs, the area covered by the floating points of the dimensional data of the temperature field or pressure field is collected and marked as the temperature wave propagation range or pressure wave propagation range. When a transient process occurs, the area fluctuation of the propagation range and the frequency of the propagation range are recorded. If the frequency of the propagation range continues to increase and the area fluctuation of the propagation range continues to increase, a transient high impact signal is generated and uploaded to the heating network operation analysis platform. After receiving the transient high impact signal, the heating network operation analysis platform controls the flow rate by adjusting the fluctuation.

5. The intelligent heating network operation analysis system based on multi-information fusion according to claim 4, characterized in that, If the frequency of the propagation range fluctuates back and forth, and the area of ​​the propagation range fluctuates back and forth, a hardware maintenance signal is generated and uploaded to the heating network operation analysis platform. After receiving the signal, the heating network operation analysis platform maintains the heating network and takes the location where the flow rate fluctuates continuously as the maintenance starting point and the propagation range as the direction for pipeline maintenance. If the frequency of propagation range generation is consistently lower than the set frequency threshold, and the area fluctuation of propagation range is consistently lower than the set area threshold, a normal signal for impact characteristic detection will be generated and uploaded to the heating network operation analysis platform.

6. The intelligent heating network operation analysis system based on multi-information fusion according to claim 5, characterized in that, Based on the hardware network model, the local pressure peak at the transient impact position during the propagation of pressure waves in the fluid medium transient process is collected. At the same time, based on the continuous generation of the transient impact position, the deviation value of the floating velocity of the deformation increase at each position in the pipeline is collected. The local pressure peak at the transient impact position and the deviation value of the floating velocity of the deformation increase at each position in the pipeline during the propagation of pressure waves in the fluid medium transient process are analyzed.

7. The intelligent heating network operation analysis system based on multi-information fusion according to claim 6, characterized in that, If the local pressure peak at the transient impact point exceeds the pressure peak during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation of the floating velocity caused by the increase in deformation at each position in the pipeline exceeds the deviation threshold, a transient control signal is generated and sent to the heating network operation analysis platform. If the local pressure peak at the transient impact point exceeds the pressure peak during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation of the floating velocity of the deformation at each position in the pipeline does not exceed the deviation threshold, then a transient satisfaction signal is generated and sent to the heating network operation analysis platform. If the local pressure peak at the transient impact point does not exceed the pressure peak during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation of the floating velocity caused by the increase in deformation at each position in the pipeline exceeds the deviation threshold, a transient collision signal is generated and sent to the heating network operation analysis platform. If the local pressure peak at the transient impact point does not exceed the pressure peak value during the propagation of the pressure wave during the transient process of the fluid medium, and the deviation value of the increase in floating velocity of the deformation at each position in the pipeline does not exceed the deviation threshold, then a transient smoothing signal is generated and sent to the heating network operation analysis platform.

8. The intelligent heating network operation analysis system based on multi-information fusion according to claim 7, characterized in that, After receiving transient control signals, the heating network operation analysis platform controls the transmission of fluid media and performs regular maintenance at the locations where transients occur in the transmission of fluid media. After receiving transient satisfaction signals, the heating network operation analysis platform reduces the limit on the transmission speed of fluid media. That is, based on actual heating demand, the transmission speed of fluid media is increased. Even when transients occur, the transmission of fluid media is still carried out according to the current heating rules. After receiving a transient conflict signal, the heating network operation analysis platform controls the fluid medium transport in the current pipeline to reduce the number of transients. After receiving a transient smoothing signal, the heating network operation analysis platform controls the current pipeline to continue transporting heat according to the existing transport rules.

9. The intelligent heating network operation analysis system based on multi-information fusion according to claim 8, characterized in that, Analyze irregular insulation structures and collect ambient humidity values ​​at the locations of irregular insulation structures within the hardware network model during the heating network operation phase. When the ambient humidity value changes, the rate at which the temperature difference between the inside and outside of the irregular insulation structure decreases is obtained; When the ambient humidity remains unchanged, the humidity variation deviation of the environment near and far from the structure is obtained.

10. The intelligent heating network operation analysis system based on multi-information fusion according to claim 9, characterized in that, If the rate of decrease of the temperature difference between the inside and outside of the irregular insulation structure exceeds the rate of decrease, or if the humidity change deviation of the corresponding positions near and far from the structure in the environment where the irregular insulation structure is located exceeds the deviation threshold, a heat transfer control signal for the structure will be generated and sent to the heat network operation analysis platform. After receiving the data, the heating network operation analysis platform monitors the temperature of the irregular insulation structure in real time and controls the real-time heat transfer. If the rate of decrease of the temperature difference between the inside and outside of the irregular insulation structure does not exceed the rate of decrease threshold, and the humidity change deviation of the corresponding positions near and far from the structure in the environment where the irregular insulation structure is located does not exceed the change deviation threshold, a normal heat transfer signal for the structure is generated and sent to the heating network operation analysis platform.

Images