Iot big model-based intelligent city heating emergency regulation and control system and method

Abstract

The application provides an Internet of Things large model-based smart city heat supply emergency regulation and control system and method, and relates to the technical field of city heat supply regulation and control. The system comprises an emergency supervision and management platform. The emergency supervision and management platform is configured to acquire heat supply parameters of a heat supply pipe network to construct a heat supply change vector; in combination with an environmental temperature, in response to the existence of an abnormal heat exchange station and / or an abnormal pipe end, determine a heat exchange abnormality type according to the heat supply change vector; control heat supply pipe valves and / or circulating pumps to perform heat supply based on updated valve opening degrees and / or rotating speeds; and according to a plurality of historical change vectors, determine heat supply correlation characteristics, in combination with the heat supply change vector, predict potential abnormal areas at a future time, and perform heat supply after adjusting valve opening degrees and rotating speeds in the potential abnormal areas. Through the system, the valve opening degrees of the heat supply pipe valves and the rotating speeds of the circulating pumps can be reasonably determined and controlled, the risk of heat supply imbalance in the heat supply pipe network is reduced, and the stable balance of heat supply is ensured.

Description

Technical Field

[0001] This invention relates to the field of urban heating regulation technology, and in particular to a smart city heating emergency regulation system and method based on an Internet of Things (IoT) big data model. Background Technology

[0002] Heating systems are a crucial component of urban infrastructure. In practice, urban heating networks often experience heating imbalances due to a combination of factors, including design flaws, construction issues, and dynamic changes in user load. These imbalances can lead to overheating in some areas due to excessive flow, while other areas experience insufficient heating due to insufficient flow, severely impacting overall heating quality and resulting in significant energy waste. Traditional heating regulation methods typically involve technicians manually adjusting valves or circulating pump parameters in the heating pipelines to attempt to balance the system. This approach is not only inefficient but also ill-suited to the complex and dynamic nature of large-scale pipeline systems.

[0003] Therefore, there is a need to provide a smart city heating emergency control system and method based on the Internet of Things (IoT) big data model to improve the regulation efficiency of the heating system and optimize the operation quality of the heating system. Summary of the Invention

[0004] The invention includes a smart city heating emergency control system based on an Internet of Things (IoT) big data model. The system includes an emergency monitoring and management platform configured to execute a smart city heating emergency control method based on an IoT big data model.

[0005] The invention includes a smart city heating emergency control method based on an IoT big data model. The method is executed by the emergency monitoring and management platform of the smart city heating emergency control system based on the IoT big data model. The method includes: acquiring multiple sets of heating parameters of the heating network at multiple times to construct a heating change vector; determining whether there are abnormal heat exchange stations and / or abnormal pipeline ends based on the heating change vector and the ambient temperature of heat exchange stations and / or residential areas; in response to the existence of the abnormal heat exchange station and / or the abnormal pipeline end, determining the type of heat exchange anomaly based on the heating change vector; and updating the valves of the heating pipeline in the primary or secondary network according to the type of heat exchange anomaly. The valve opening degree and / or the rotational speed of the circulation pump are adjusted, and based on the updated valve opening degree and rotational speed, the heating pipeline valves and / or the circulation pump are controlled to provide heating, wherein heating includes hot water being delivered by the heating pipeline valves and / or hot water being circulated by the circulation pump; heating correlation characteristics are determined based on multiple historical change vectors; potential abnormal areas at future times are predicted based on the heating change vectors and the heating correlation characteristics; adjustment time points are determined based on the potential abnormal areas, and at the adjustment time points, the heating pipeline valves and the circulation pump in the secondary network within the potential abnormal areas are controlled to provide heating based on the valve opening degree and rotational speed after secondary adjustment.

[0006] Beneficial effects: Through the smart city heating emergency control system based on the Internet of Things big data model, the heating network can be monitored, and the valve opening degree of different heating pipeline valves and the speed of different circulating pumps in the heating network can be reasonably determined and controlled, reducing the risk of heating imbalance in the heating network, and upgrading the control of heating imbalance from passive emergency response to proactive prevention, thus ensuring stable and balanced heating. Attached Figure Description

[0007] The present invention will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, the same reference numerals denote the same structures, wherein:

[0008] Figure 1 This is a schematic diagram of the platform structure of a smart city heating emergency control system based on an Internet of Things (IoT) big data model, according to some embodiments of the present invention.

[0009] Figure 2 This is an exemplary flowchart of a smart city heating emergency control method based on an Internet of Things (IoT) big data model, according to some embodiments of the present invention.

[0010] Figure 3 This is an exemplary schematic diagram of a heating diagram structure according to some embodiments of the present invention;

[0011] Figure 4This is an exemplary schematic diagram illustrating the determination of adjustment time points according to some embodiments of the present invention;

[0012] Figure 5 This is an exemplary flowchart illustrating secondary adjustments to valve opening and rotation speed according to some embodiments of the present invention. Detailed Implementation

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of the present invention. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0014] It should be understood that the terms "system," "unit," and / or "module" used herein are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0015] Unless the context clearly indicates an exception, words such as "a," "an," "a kind," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0016] This invention uses flowcharts to illustrate the operations performed by the system according to embodiments of the invention. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0017] Figure 1 This is a schematic diagram of the platform structure of a smart city heating emergency control system based on an Internet of Things (IoT) big data model, according to some embodiments of the present invention.

[0018] In some embodiments, such as Figure 1 As shown, the smart city heating emergency control system 100 based on the Internet of Things big data model includes an emergency monitoring user platform 110, an emergency monitoring service platform 120, an emergency monitoring management platform 130, an emergency monitoring sensor network platform 140, and an emergency monitoring object platform 150.

[0019] The Emergency Monitoring User Platform 110 is a platform used for interaction with users.

[0020] In some embodiments, the emergency monitoring user platform 110 can be configured as a terminal for user use.

[0021] The Emergency Monitoring Service Platform 120 is a platform used to convey users' needs and control information.

[0022] In some embodiments, the emergency monitoring service platform 120 may be configured as a server for communication.

[0023] In some embodiments, the emergency monitoring service platform 120 can interact with the emergency monitoring user platform 110 and the emergency monitoring management platform 130.

[0024] The Emergency Supervision and Management Platform 130 is a platform for generating supervision information and executing control information.

[0025] In some embodiments, the emergency monitoring and management platform 130 may be configured as a processor or server that implements emergency control functions.

[0026] In some embodiments, the emergency monitoring and management platform 130 is configured to execute a smart city heating emergency control method based on an IoT big data model.

[0027] The Emergency Monitoring Sensor Network Platform 140 refers to a platform for the comprehensive management of sensor information.

[0028] In some embodiments, the emergency monitoring sensor network platform 140 can be configured as a communication device or server for communication, such as a 5G base station, a vehicle-to-everything (V2X) roadside unit, a fiber optic switch, etc.

[0029] In some embodiments, the emergency monitoring sensor network platform 140 can interact with the emergency monitoring management platform 130 and the emergency monitoring object platform 150.

[0030] Emergency monitoring object platform 150 refers to a functional platform that generates perception information and execution control information.

[0031] In some embodiments, the emergency monitoring object platform 150 may include heating pipeline valves and circulating pumps located at the ends of heat exchange stations, thermal power plants, and pipelines.

[0032] For a detailed explanation of the foregoing, please refer to Figures 2 to 5 Related descriptions.

[0033] In some embodiments of the present invention, the smart city heating emergency control system 100 based on the Internet of Things big data model can form an information operation closed loop between various functional platforms, realizing the informatization and intelligentization of emergency monitoring of abnormal operation.

[0034] Figure 2 This is an exemplary flowchart of a smart city heating emergency control method based on an Internet of Things (IoT) big data model, according to some embodiments of the present invention. In some embodiments, process 200 is executed by an emergency monitoring and management platform. Process 200 includes the following steps.

[0035] Step 210: Obtain multiple sets of heating parameters of the heating network at multiple times to construct a heating change vector.

[0036] A heating network is a circulating heating system that delivers heat energy produced by a heat source to users through a pipeline system and returns the return water to the heat source for reheating.

[0037] In some embodiments, the heating network may include a primary network and a secondary network.

[0038] The primary network refers to the circulating heating pipeline from the heat source to the heat exchange station.

[0039] In some embodiments, the heat source includes a thermal power plant, etc. The thermal power plant can heat the hot water in the heating network to a preset temperature. It is understood that the preset temperature is typically a high temperature. The preset temperature can be preset by technicians based on experience.

[0040] A heat exchange station is a facility located between a thermal power plant and a user, used to convert high-temperature, high-pressure water from the thermal power plant into water with a lower temperature and pressure that is usable by the user.

[0041] In some embodiments, in a primary network, the power plant is mechanically connected to multiple heat exchange stations via circulating heating pipelines.

[0042] Multiple moments refer to multiple historical time points separated by a preset interval. For example, multiple moments can be multiple consecutive historical time points separated by a preset interval within 6 hours before the current moment.

[0043] The secondary network refers to the circulating heating pipeline between the heat exchange station and the end of the pipeline in the residential area.

[0044] Residential areas refer to the areas where users of the city's heating system reside. For example, a residential community or a factory.

[0045] The end of the pipeline refers to the section of the pipeline that directly supplies heat to residential areas.

[0046] In some embodiments, in a secondary network, the heat exchange station is mechanically connected to multiple pipeline ends via circulating heating pipelines.

[0047] In some embodiments, heating parameters include the heating temperature, heating pressure, and heating flow rate of the heat exchange stations in the primary network, and the return water temperature, terminal pressure, and terminal flow rate at the end of the pipeline in the residential area of ​​the secondary network. Heating temperature refers to the temperature of the hot water output from the heat exchange station. Heating pressure refers to the pressure of the hot water output from the heat exchange station. Heating flow rate refers to the flow rate of the hot water output from the heat exchange station. Return water temperature refers to the temperature of the water flow from the residential area. Terminal pressure refers to the pressure of the hot water at the end of the pipeline. Terminal flow rate refers to the flow rate of the hot water at the end of the pipeline.

[0048] The heating change vector is a quantitative representation of the fluctuation state of heating parameters.

[0049] In some embodiments, the emergency monitoring and management platform can collect multiple sets of heating parameters of the heating network at multiple times within a preset time period, and arrange the values ​​of each parameter in the multiple sets of heating parameters at different times according to parameter type to form a heating change vector.

[0050] Step 220: Based on the heating change vector and the ambient temperature of the heat exchange station and / or residential area, determine whether there are abnormal heat exchange stations and / or abnormal pipeline ends.

[0051] Ambient temperature refers to the air temperature in heat exchange stations and / or residential areas.

[0052] An abnormal heat exchange station refers to a heat exchange station that experiences operational abnormalities, resulting in a decrease in heat transfer efficiency.

[0053] Abnormal pipeline ends refer to pipeline ends that are malfunctioning, resulting in poor heating performance or other problems.

[0054] In some embodiments, the emergency monitoring and management platform can determine the existence of abnormal heat exchange stations and / or abnormal pipeline ends by using various methods based on the heating change vector and the ambient temperature of the heat exchange station and / or residential area. For example, the emergency monitoring and management platform can determine the existence of abnormal heat exchange stations and / or abnormal pipeline ends based on a search of the vector database using the heating change vector.

[0055] The emergency monitoring and management platform can construct a vector database based on historical data. This database includes multiple feature vectors and their corresponding feature labels. Specifically, the platform can obtain historical heating temperatures, historical ambient temperatures, and historical heating flow rates at the end of the pipelines of each heat exchange station and residential area when they were in normal operating conditions, and construct feature vectors based on these parameters. It can also obtain the actual historical heating pressure, historical return water temperature, historical terminal pressure, and historical terminal flow rate at the first historical point in time for each feature vector, using these as the feature labels for each feature vector. The historical heating temperatures, historical ambient temperatures, and historical heating flow rates at the end of the pipelines of each heat exchange station and residential area when they were in normal operating conditions, as well as the actual historical heating pressure, historical return water temperature, historical terminal pressure, and historical terminal flow rate at the first historical point in time, can be determined based on the daily maintenance records of staff.

[0056] Normal condition refers to the absence of any abnormalities at the ends of the pipelines in the heat exchange station and / or residential area. The presence of any abnormalities at the ends of the pipelines in the heat exchange station and / or residential area at any given time can be determined based on the daily maintenance records of the staff.

[0057] The first historical point in time refers to a historical point in time that occurs multiple times in advance.

[0058] The emergency monitoring and management platform can construct a target vector based on the heating temperature, heating flow rate, and ambient temperature in the current heating change vector; calculate the vector similarity between the target vector and multiple feature vectors in the vector database; select multiple feature vectors with a similarity greater than a preset similarity threshold, and use the heating parameter range of the feature labels corresponding to the multiple feature vectors as the normal heating parameter range corresponding to the target vector. The preset similarity threshold can be preset by technical personnel based on experience.

[0059] The emergency monitoring and management platform can compare the heating change vectors of each heat exchange station and the pipeline end of each residential area with the normal heating parameter range. If a heating parameter in the heating change vector exceeds the normal heating parameter range, the heat exchange station is judged to be an abnormal heat exchange station or the pipeline end of the residential area is judged to be an abnormal pipeline end.

[0060] There are two known scenarios: the presence of abnormal heat exchange stations and / or abnormal pipeline ends, and the absence of abnormal heat exchange stations and / or abnormal pipeline ends.

[0061] Step 230: In response to the presence of an abnormal heat exchange station and / or an abnormal pipeline end, determine the type of heat exchange anomaly based on the heat supply change vector.

[0062] In some embodiments, heat exchange anomalies may include abnormal heating temperature difference, abnormal hot water flow rate, and abnormal hot water pressure. Abnormal heating temperature difference refers to the phenomenon where the temperature difference between the hot water and return water at the end of the pipeline deviates from a preset temperature difference range. Abnormal hot water flow rate refers to the phenomenon where the outlet and / or return water flow rates at the heat exchange station and / or the end of the pipeline deviate from a preset flow rate range. Abnormal hot water pressure refers to the phenomenon where the outlet and / or return water pressure at the heat exchange station and / or the end of the pipeline deviate from a preset pressure range. The preset temperature difference range, preset flow rate range, and preset pressure range can be preset by technicians based on experience.

[0063] For more information on types of heat transfer anomalies, please refer to [link / reference]. Figure 4 And its related descriptions.

[0064] In some embodiments, in response to the presence of abnormal heat exchange stations and / or abnormal pipeline terminals, the emergency monitoring and management platform can determine the type of heat exchange anomaly based on the heat supply change vector through various methods. For example, the emergency monitoring and management platform can compare the heat supply change vectors of each heat exchange station and each residential area with the normal heating parameter range. If there are heating parameters outside the normal heating parameter range within the heat supply change vector, the corresponding heat exchange anomaly type can be determined. For example, if the return water temperature is outside the normal heating parameter range, it can be determined that there is a heating temperature difference anomaly; if the heating pressure or terminal pressure is outside the normal heating parameter range, it can be determined that there is a hot water pressure anomaly; if the terminal flow rate is outside the normal heating parameter range, it can be determined that there is a hot water flow rate anomaly.

[0065] In some embodiments, the emergency monitoring and management platform can also construct a heating map structure to determine whether there are abnormal heat exchange stations and / or abnormal pipeline ends, as well as the type of heat exchange anomaly. More information on this part can be found in [link to relevant documentation]. Figure 3 And its related descriptions.

[0066] Step 240: Based on the type of heat exchange anomaly, update the valve opening degree of the heating pipeline valves and / or the rotation speed of the circulating pump in the primary or secondary network, and control the heating pipeline valves and / or circulating pump to supply heat based on the updated valve opening degree and rotation speed.

[0067] The heating includes the delivery of hot water through valves in the heating pipeline and / or the circulation of hot water driven by a circulation pump.

[0068] A heating pipeline valve is a device installed in a heating pipeline to regulate the flow rate of hot water circulation within the pipeline.

[0069] The valve opening degree of a heating pipeline valve refers to the degree to which the valve is open. The valve opening degree of a heating pipeline valve is directly proportional to the hot water circulation flow rate within the heating pipeline. For example, the larger the valve opening degree, the larger the hot water circulation flow rate within the heating pipeline.

[0070] A circulating pump is a device installed in a heating pipeline to drive the flow of water and regulate the circulation speed of hot water in the heating pipeline.

[0071] In some embodiments, the rotational speed of the circulating pump is proportional to the circulation velocity of the hot water in the heating pipeline. For example, the higher the rotational speed of the circulating pump, the higher the circulation velocity of the hot water in the heating pipeline.

[0072] In some embodiments, the emergency monitoring and management platform can update the valve openings of heating pipeline valves and / or the rotational speed of circulating pumps in the primary or secondary network according to the type of heat exchange anomaly, using various methods. For example, the emergency monitoring and management platform can query a first preset table based on the type of heat exchange anomaly to determine the equipment in the primary or secondary network that needs to be regulated (e.g., heating pipeline valves and / or circulating pumps), and update the valve openings of the heating pipeline valves and / or the rotational speed of the circulating pumps. The first preset table includes preset relationships between the type of heat exchange anomaly and the equipment that needs to be regulated, the updated valve openings of the heating pipeline valves, and / or the rotational speed of the circulating pumps. The first preset table can be preset by technical personnel based on experience.

[0073] Step 250: Determine the heating-related characteristics based on multiple historical change vectors.

[0074] The historical change vector refers to the historical heating change vector at the corresponding historical moment when multiple heat exchange stations and multiple residential areas experience anomalies.

[0075] In some embodiments, the historical change vector may include a first abnormal heating parameter corresponding to a historical moment. The historical change vector can be obtained from the routine maintenance records of the staff.

[0076] In some embodiments, for each historical change vector, the emergency monitoring and management platform can, based on historical data, obtain other abnormal heat exchange stations / abnormal pipeline ends that occurred within a preset time period corresponding to the historical moment, as associated heat exchange stations and / or associated pipeline ends, obtain the second abnormal heating parameters corresponding to the associated heat exchange stations and / or associated pipeline ends, and determine the connection relationship between the associated heat exchange stations and / or associated pipeline ends and the heat exchange stations and / or pipeline ends corresponding to the historical change vector. For example, the connection relationship includes upstream relationships, downstream relationships, etc.

[0077] Heating correlation characteristics refer to the characteristics that reflect the correlation between abnormal heat exchange stations and / or abnormal pipeline ends in the heating network.

[0078] In some embodiments, the heating association features include a first abnormal heating parameter that occurs at a certain historical moment, a second abnormal heating parameter that occurs after that historical moment, and the connection relationship between the associated heat exchange station and / or the associated pipeline end and the heat exchange station and / or pipeline end corresponding to the historical change vector.

[0079] In some embodiments, the emergency monitoring and management platform can construct heating correlation characteristics based on the first abnormal heating parameter in the aforementioned historical change vector, the associated heat exchange stations and / or associated pipeline ends and the corresponding second abnormal heating parameters, and the aforementioned connection relationships. The preset time period refers to a historical period of preset duration, which can be set by technical personnel based on experience.

[0080] Step 260: Based on the heating change vector and heating correlation characteristics, predict potential anomaly areas at future times.

[0081] A future time refers to a point in time after the current time. Future times can be set by technicians based on experience. For example, one hour after the current time, or one day after the current time.

[0082] Potentially abnormal areas refer to urban areas where abnormal heat exchange stations and / or abnormal pipeline ends may exist in the future.

[0083] In some embodiments, the preset interval may be negatively correlated with the area of ​​the potential anomalous region at a future time; for example, the larger the predicted area of ​​the potential anomalous region at a future time, the smaller the preset interval. It is understood that, since the potential anomalous region is predicted at any time, the preset interval may also change dynamically.

[0084] In some embodiments, the emergency monitoring and management platform can predict potential abnormal areas in the future using various methods based on heating change vectors and heating correlation features. For example, the platform can compare the current heating change vector with the normal heating parameter range to obtain abnormal heating parameters in the current heating change vector; match these abnormal heating parameters with heating correlation features; and predict potential abnormal areas in the future based on the corresponding connection relationships in the matched heating correlation features. Matching refers to comparing the current abnormal heating parameters with a first abnormal heating parameter; a successful match occurs when the parameter types match. When a successful match occurs, the platform can determine the connection relationships based on the first abnormal heating parameter, identify associated heat exchange stations and / or associated pipeline ends based on the connection relationships, and designate the areas where the associated heat exchange stations and / or associated pipeline ends are located as potential abnormal areas in the future.

[0085] In some embodiments, the emergency monitoring and management platform can also predict potential anomalous areas based on an anomaly propagation model. For more information on this section, please refer to [link to relevant documentation]. Figure 5 And its corresponding description.

[0086] For more information on the normal heating parameter range, please refer to step 220 and its related content.

[0087] Step 270: Based on the potential abnormal area, determine the adjustment time point. At the adjustment time point, control the heating pipeline valves and circulation pumps in the secondary network within the potential abnormal area, and provide heating based on the valve opening and speed after the secondary adjustment.

[0088] The adjustment time point refers to the time point at which the operating equipment of the heating network (such as heating pipeline valves and circulating pumps) is adjusted for a second time.

[0089] In some embodiments, the emergency monitoring and management platform can determine the adjustment time point based on potentially abnormal areas using various methods. For example, the platform can determine the adjustment time point based on the distance between the potentially abnormal area and the current abnormal heat exchange station and / or abnormal pipeline end, using a preset rule table. The preset rule table is a table that includes the correspondence between the distance and the adjustment time point. This table can be preset by technical personnel based on experience. It is understood that the smaller the distance, the earlier the adjustment time point.

[0090] In some embodiments, the emergency monitoring and management platform can also determine the adjustment timing based on regulatory fluctuation information. For more information on this section, please refer to... Figure 4 And its corresponding description.

[0091] In some embodiments, the valve opening and rotation speed after secondary adjustment refer to the adjusted values ​​of the valve opening and rotation speed of the heating pipeline valves and circulating pumps that require secondary adjustment in the potential abnormal area.

[0092] In some embodiments, the emergency monitoring and management platform can determine the valve opening and rotation speed after secondary adjustment using various methods. For example, the platform can determine the valve opening and rotation speed after secondary adjustment by querying a second preset table based on the heating parameters of the potentially abnormal area. The second preset table includes the correlation between the heating parameters of the potentially abnormal area and the valve openings of the heating pipeline valves in the secondary network, as well as the rotation speed of the circulating pumps in the secondary network. The second preset table can be preset by technicians based on experience. In the second preset table, the heating parameters of the potentially abnormal area are the average values ​​of multiple different types of heating parameters, such as the average heating temperature, the average heating pressure, and the average heating flow rate.

[0093] In some embodiments, the emergency monitoring and management platform can also determine the valve opening and rotation speed after secondary adjustment based on the safe heating coefficient. For more information on this section, please refer to... Figure 4 And its corresponding description.

[0094] In some embodiments of the present invention, multiple heating parameters are monitored in real time to identify and address current problems. Historical data is used to analyze the correlations between these problems to predict and proactively intervene in future potential anomalies. This elevates heating regulation from a passive emergency response to a proactive prevention approach, ensuring stable and balanced heating. On the other hand, a larger potential anomaly area indicates poorer stability of the current heating network. Increasing the monitoring frequency of the heating network for large potential anomaly areas can improve the accuracy of detecting heating anomalies.

[0095] Figure 3 This is an exemplary schematic diagram of a heating diagram structure according to some embodiments of the present invention.

[0096] In some embodiments, the emergency monitoring and management platform can construct a heating map structure; based on the heating map structure, it can determine whether there are abnormal heat exchange stations and / or abnormal pipeline ends, as well as the type of heat exchange abnormality.

[0097] A heating network diagram structure is a graphical model used to describe the components and their interrelationships within a heating network. In some embodiments, the heating network diagram structure includes three node types: power plants, heat exchange stations, and pipeline terminals. Node attributes include multiple heating parameters from each set of heating parameters. The edges of the heating network diagram structure represent heating pipelines, and edge attributes include pipeline length and pipeline roughness value. Node attributes also include ambient temperature, and these attributes are updated based on changes in sensor monitoring data. Specifically, the node attributes of a power plant include a preset temperature. The node attributes of a heat exchange station include heating temperature, heating pressure, heating flow rate, and the ambient temperature of the heat exchange station. The node attributes of the pipeline terminals include return water temperature, terminal pressure, terminal flow rate, and the ambient temperature of the residential area.

[0098] In some embodiments, node attributes can be obtained through sensor monitoring. Exemplary sensors include temperature sensors, pressure sensors, flow sensors, etc.

[0099] In some embodiments, such as Figure 3 As shown, the thermal power plant may include thermal power plant 310, the heat exchange station may include heat exchange station 321 and heat exchange station 322, and the pipeline end may include pipeline end 331, pipeline end 332, pipeline end 333, pipeline end 334, pipeline end 335 and pipeline end 336. The edges of the heating diagram structure are heating pipelines, and the black boxes on the edges represent heating pipeline valves and / or circulation pumps.

[0100] For more information on thermal power plants, heat exchange stations, pipeline terminals, heating parameters, heating pipelines, heating pipeline valves, circulating pumps, and ambient temperature, please refer to [link to relevant documentation]. Figure 2 And its corresponding description.

[0101] Pipeline length refers to the physical length of a heating pipeline, that is, the distance from the beginning to the end of the pipeline. For example, the pipeline length is 8km, 10km, etc. The pipeline length can be obtained directly from the design drawings or construction drawings of the heating network.

[0102] Pipe roughness value refers to the roughness of the inner wall of a heating pipe, usually expressed as a roughness coefficient or equivalent roughness. For example, pipe roughness values ​​are 0.01 mm, 0.03 mm, etc. Pipe roughness values ​​can be obtained by consulting relevant standards or manuals based on the pipe material (such as steel pipe, plastic pipe, etc.).

[0103] Monitoring data refers to various parameters and indicators collected by sensors that reflect the operating status of the heating network. For example, monitoring data includes the monitored values ​​of attributes of each node.

[0104] In some embodiments, as sensor monitoring data changes, the emergency monitoring and management platform can update the values ​​of node attributes accordingly.

[0105] There are two scenarios for updating known node attributes: satisfying preset conditions and not satisfying preset conditions.

[0106] In some embodiments, in response to the node attribute update meeting preset conditions, the emergency monitoring and management platform can obtain the abnormal nodes and abnormal diffusion nodes corresponding to the abnormal heat exchange station and / or the abnormal pipeline end according to the heating diagram structure and through the abnormal diffusion model; and make secondary adjustments to the valve opening degree of the heating pipeline valve and / or the speed of the circulating pump in the primary or secondary network according to the abnormal nodes and abnormal diffusion nodes.

[0107] For more information on abnormal heat exchange stations, abnormal pipeline ends, primary networks, and secondary networks, please refer to [link / reference needed]. Figure 2 And its corresponding description.

[0108] Preset conditions refer to the pre-defined conditions for judging node attributes. For example, preset conditions may include the node attribute update frequency exceeding a preset frequency threshold and the update magnitude exceeding a preset magnitude threshold. The update frequency refers to the number of times a node attribute changes per unit of time. For example, an update frequency of 2 times / min or 4 times / min.

[0109] Update magnitude refers to the degree or range of change of a node attribute within a unit of time. For example, update magnitude could be 0.1 MPa, 0.2 MPa, etc. In some embodiments, update magnitude can be represented by the average of the absolute values ​​of the differences between the node attributes before and after the update. The preset frequency threshold and preset magnitude threshold refer to pre-set critical values ​​for update frequency and update magnitude, respectively. The preset frequency threshold and preset magnitude threshold can be set by technical personnel based on experience.

[0110] An anomaly propagation model is a model used to identify anomalous nodes and anomalous propagation nodes. In some embodiments, the anomaly propagation model is a machine learning model. For example, the anomaly propagation model is a graph neural network (GNN) model or any other feasible model.

[0111] In some embodiments, the input to the abnormal diffusion model is a heating diagram structure, and the output includes abnormal nodes and abnormal diffusion nodes corresponding to abnormal heat exchange stations and / or the ends of abnormal pipelines.

[0112] In some embodiments, the emergency monitoring and management platform can train an anomaly propagation model based on a large number of first training samples with first labels.

[0113] In some embodiments, the first training sample includes historical heating map structures at multiple second historical time points when anomalies exist in different heating pipe networks. The first label includes actual anomalous nodes in the historical heating map structure corresponding to the first training sample and newly emerging anomalous nodes within a subsequent period of time at the corresponding multiple second historical time points. Here, anomalies in the heating pipe network refer to the presence of abnormal heat exchange stations and / or abnormal pipeline ends in the heating pipe network. Multiple second historical time points refer to past time points corresponding to multiple moments when heating parameters are acquired. Actual anomalous nodes refer to nodes where abnormal heat exchange stations and / or abnormal pipeline ends currently occur. Newly emerging anomalous nodes refer to nodes in the historical heating map structure where abnormal heat exchange stations and / or abnormal pipeline ends actually occur within a subsequent period of time.

[0114] As an example, the emergency monitoring and management platform can input the first training sample into the initial anomaly propagation model, construct a loss function using the output of the initial anomaly propagation model and the first label, and iteratively update the parameters of the initial anomaly propagation model based on the loss function using gradient descent or other methods. The model training is complete when the iteration termination conditions are met, resulting in a trained anomaly propagation model. These iteration termination conditions include loss function convergence and the number of iterations reaching a threshold.

[0115] An abnormal node refers to a node where a heating anomaly has been detected at the current moment. A heating anomaly means that the heating parameters are not within the normal range. For more information on the normal range of heating parameters, please refer to [link to relevant documentation]. Figure 2 The corresponding description.

[0116] In some embodiments, the anomalous diffusion nodes include nodes that are predicted to have heating anomalies at future times. In some embodiments, the potential anomalous region includes multiple anomalous diffusion nodes.

[0117] In some embodiments, for abnormal nodes, the emergency monitoring and management platform can construct a heating change vector based on the node attributes of the abnormal node; determine the heat exchange anomaly type based on the abnormal node and the heating change vector; and update the valve opening degree of the heating pipeline valves and / or the rotation speed of the circulating pump in the primary or secondary network according to the heat exchange anomaly type. More information on constructing the heating change vector, determining the heat exchange anomaly type, and updating according to the heat exchange anomaly type can be found in [link to relevant documentation]. Figure 2 The corresponding description.

[0118] In some embodiments, for abnormal diffusion nodes, the emergency monitoring and management platform can determine the spatial location and upstream / downstream connections of the abnormal diffusion nodes based on the heating diagram structure; cluster the abnormal diffusion nodes according to their spatial location or upstream / downstream connections to form multiple potential abnormal regions; determine the adjustment time point based on the potential abnormal regions; determine the valve opening and speed for secondary adjustment based on multiple heating parameters of the potential abnormal regions through a second preset table; and at the adjustment time point, perform secondary adjustments on the valve opening and / or the speed of the circulating pump in the heating pipeline corresponding to the abnormal diffusion node. Here, the upstream / downstream connection refers to the upstream and downstream relationship between abnormal diffusion nodes. Clustering can use K-means clustering algorithms or community detection algorithms based on graph structures, etc. More information on determining the adjustment time point and the second preset table can be found in [link to relevant documentation]. Figure 2 And its corresponding description.

[0119] In some embodiments of the present invention, a graph neural network model is used to analyze the heating diagram structure, thereby enabling more intelligent and accurate prediction of current heating anomalies and their spread, achieving precise early warning of potential fault areas.

[0120] In some embodiments, the emergency monitoring and management platform can determine whether there are abnormal heat exchange stations and / or abnormal pipeline ends, as well as the type of heat exchange anomaly, based on the heating map structure. For example, for a pipeline end, the emergency monitoring and management platform can identify the upstream heat exchange station through the heating map structure and obtain the difference between the heating temperature of the heat exchange station and the return water temperature of the pipeline end, the difference between the heating pressure of the heat exchange station and the end pressure of the pipeline end, and the network resistance factor of the edge between the heat exchange station and the pipeline end. Based on the node attributes of the pipeline end, the aforementioned two differences, and the network resistance factor, a first feature vector is constructed. For a heat exchange station, the emergency monitoring and management platform can find all multiple downstream pipeline ends through the heating map structure and obtain the average return water temperature, total downstream demand flow, and maximum temperature difference of the aforementioned multiple pipeline ends. Based on the node attributes of the heat exchange station, the aforementioned average return water temperature, total downstream demand flow, and maximum temperature, a second feature vector is constructed. Based on cluster analysis, abnormal heat exchange stations and / or abnormal pipeline ends in the heating map structure and the corresponding heat exchange anomaly types are obtained.

[0121] The pipeline resistance factor is a parameter used to describe the resistance to fluid flow in heating pipelines, reflecting the degree to which the heating pipelines impede fluid flow. In some embodiments, the emergency monitoring and management platform normalizes the pipeline length and pipeline roughness value, then performs a weighted sum, using this weighted sum as the pipeline resistance factor. Normalization can be implemented in various ways, such as Min-Max normalization. The weighting coefficients for the weighted sum can be set by technical personnel based on experience.

[0122] The average return water temperature refers to the average return water temperature of all pipe ends downstream of the heat exchange station. For example, the average return water temperature of all pipe ends downstream of heat exchange station 321, including pipe ends 331 to 333, is the average return water temperature of pipe ends 331 to 333.

[0123] Total downstream demand flow refers to the sum of the flow rates at the ends of all pipelines downstream of the heat exchange station.

[0124] The maximum temperature difference refers to the difference between the heating temperature of the heat exchange station and the lowest value among the return water temperatures at the ends of all downstream pipelines.

[0125] An exemplary clustering analysis process includes: constructing multiple clustering vectors based on multiple historical first vectors and multiple historical second vectors corresponding to the historical heating map structures of different heating networks at multiple historical moments; using historically abnormal heat exchange stations, historically abnormal pipeline ends, and corresponding historical heat exchange anomaly types existing in the heating network at the historical moments corresponding to the clustering vectors as labels corresponding to the clustering vectors; constructing target vectors based on multiple first feature vectors and multiple second feature vectors corresponding to the current heating map structure; using the multiple clustering vectors and target vectors as objects to be clustered; clustering the objects to be clustered, and using the cluster where the target vector is located as the target cluster; obtaining the union set of nodes corresponding to historically abnormal heat exchange stations and historically abnormal pipeline ends in the historical heating map structures corresponding to multiple clustering vectors in the target cluster, using the nodes corresponding to the aforementioned nodes in the current heating map structure as abnormal heat exchange stations and / or abnormal pipeline ends, and using the historical heat exchange anomaly types corresponding to the clustering vectors as the heat exchange anomaly types corresponding to each node in the current heating map structure.

[0126] In some embodiments of the present invention, by constructing the entire heating network into a heating diagram structure that includes physical connection relationships and real-time operating parameters, the system can combine the topological relationship of the network when judging anomalies, thereby more accurately locating abnormal nodes and identifying the type of heat exchange anomaly.

[0127] Figure 4 This is an exemplary schematic diagram illustrating the determination of adjustment time points according to some embodiments of the present invention.

[0128] In some embodiments, such as Figure 4 As shown, the emergency monitoring and management platform can predict control fluctuation information 420 based on the ambient temperature 411 and the heating temperature 412, heating pressure 413, heating flow rate 414 and adjustment parameters 415 of the heat exchange station; based on the control fluctuation information 420, it can determine the adjustment time point 430, and at the adjustment time point 430, make secondary adjustments to the valve opening degree of the heating pipeline valves and / or the speed of the circulating pump in the secondary network.

[0129] More information regarding ambient temperature, heating temperature of the heat exchange station, heating pressure, heating flow rate, adjustment time point, secondary network, heating pipeline valves, valve opening degree, circulating pump and speed can be found in [link to relevant documentation]. Figure 2 And its corresponding description.

[0130] Regulation parameters refer to parameters related to the properties of heating pipeline valves and circulating pumps. For example, regulation parameters include the number of heating pipeline valves being regulated, the valve opening adjustment amount, the number of circulating pumps being regulated, and the speed adjustment amount.

[0131] The adjustment parameters can be set by technicians based on experience.

[0132] Control fluctuation information refers to information related to fluctuations in heating parameters.

[0133] In some embodiments, the regulation fluctuation information 420 includes the fluctuation amplitude 420-1 and fluctuation duration 420-2 of multiple heating parameters in each group of heating parameters at multiple future times after updating the valve opening degree of the heating pipeline valves in the primary network or secondary network and / or the rotation speed of the circulating pump.

[0134] Multiple future moments refer to multiple points in time within a certain period of time in the future.

[0135] Fluctuation amplitude refers to the change or deviation range of heating parameters after adjustment relative to before adjustment. For example, fluctuation amplitude can be the difference between the actual values ​​of multiple heating parameters monitored by sensors and the corresponding ranges of normal heating parameters. Normal heating parameters refer to the reasonable range of each heating parameter under stable operating conditions of the heating network. Normal heating parameters can be set by technicians based on experience.

[0136] The duration of fluctuation refers to the time required for heating parameters to reach a new stable state after adjustment. For example, the duration of fluctuation can be the time it takes for the actual values ​​of multiple heating parameters monitored by N consecutive sensors to stabilize within the corresponding range of normal heating parameters from the start of adjustment. The value of N can be set by technicians based on experience.

[0137] In some embodiments, the emergency monitoring and management platform can predict regulation fluctuation information by retrieving a heating database based on ambient temperature and the heating temperature, heating pressure, heating flow rate, and regulation parameters of the heat exchange station. The heating database refers to a database that stores the correspondence between ambient temperature, heating temperature, heating pressure, heating flow rate, regulation parameters, and regulation fluctuation information of the heating network. As an example, the emergency monitoring and management platform can construct a feature vector based on the historical ambient temperature, historical heating temperature, historical heating pressure, historical heating flow rate, and historical regulation parameters of the heating network; use the historical fluctuation amplitude and duration of the actual historical heating parameters at multiple subsequent moments in the historical regulation corresponding to the feature vector as labels for the feature vector; repeat the above operation multiple times to obtain the heating database.

[0138] In some embodiments, the emergency monitoring and management platform can construct a target vector based on the current ambient temperature, heating temperature, heating pressure, heating flow rate, and regulation parameters of the heat exchange station; calculate the vector similarity between the target vector and multiple feature vectors in the heating database; select the feature vector with the highest vector similarity to the target vector, and use the label corresponding to this feature vector as the regulation fluctuation information corresponding to the target vector. Vector similarity can be represented by cosine similarity, Euclidean distance, etc.

[0139] In some embodiments, the emergency monitoring and management platform can determine the adjustment time points in various ways based on the control fluctuation information. For example, if the duration of the fluctuation exceeds a preset duration threshold, the emergency monitoring and management platform will use multiple future moments when the fluctuation amplitude exceeds a preset amplitude threshold as adjustment time points to make secondary adjustments to the heating network.

[0140] The preset duration threshold and preset amplitude threshold refer to the pre-set critical values ​​for the duration and amplitude of the fluctuation, respectively. These thresholds can be set by technical personnel based on experience.

[0141] In some embodiments, the emergency monitoring and management platform can determine the safe heating coefficient based on the control fluctuation information and the node type; and control the valves and circulating pumps in the heating pipeline in the secondary network according to the pre-determined valve opening and / or circulating pump speed and safe heating coefficient, and provide heating based on the valve opening and speed after the secondary adjustment.

[0142] The safety heating coefficient is a quantitative indicator used to assess the safety and stability of a heating network under current control conditions. For example, the safety heating coefficient can be a value between 0 and 1.

[0143] In some embodiments, the emergency monitoring and management platform can determine the safe heating coefficient through various methods based on the control fluctuation information and node type. For example, the platform can determine the safe heating coefficient using a third preset table, based on the average fluctuation amplitude and node type at multiple future times in the control fluctuation information. The third preset table is a table that includes the correspondence between the average fluctuation amplitude, node type, and safe heating coefficient. This third preset table can be set by technical personnel based on experience.

[0144] In some embodiments, heat exchange anomaly types include abnormal heating temperature difference, abnormal hot water flow rate, and abnormal hot water pressure. The emergency monitoring and management platform can determine the safe heating coefficient based on the heat exchange anomaly type corresponding to the control fluctuation information and the node type.

[0145] In some embodiments, further information regarding abnormal heating temperature differences, abnormal hot water flow rates, and abnormal hot water pressures can be found at [link to relevant documentation]. Figure 2 The corresponding description.

[0146] In some embodiments, abnormal heating temperature, abnormal hot water flow, and abnormal hot water pressure each correspond to a proportionality coefficient. After determining the safe heating coefficient through a third preset table, the emergency monitoring and management platform can use the product of the safe heating coefficient and the proportionality coefficient corresponding to the heat exchange anomaly type in the control fluctuation information as the current safe heating coefficient. The proportionality coefficient can be determined in various ways. For example, it can be set by technicians based on experience. Another example is that the proportionality coefficient is positively correlated with the frequency of occurrence of this type of heat exchange anomaly in the heating network. The frequency of occurrence refers to the number of times this type of heat exchange anomaly occurs within a certain period (e.g., one day, one week, or one month).

[0147] In some embodiments of the present invention, by combining the safe heating coefficient with specific heat exchange anomaly types (such as temperature difference, pressure, flow rate) and their historical occurrence frequency, differentiated adjustment strategies with different intensities are implemented for faults of different natures, making the control measures more precise.

[0148] It is understood that the predetermined valve opening and / or circulating pump speed after secondary adjustment refers to the valve opening and / or circulating pump speed determined by the second preset table. More information about the second preset table can be found at [link to relevant documentation]. Figure 2 The corresponding description.

[0149] In some embodiments, the emergency monitoring and management platform can use the product of the pre-determined secondary adjusted valve opening and / or circulation pump speed and the safe heating coefficient as the secondary adjusted valve opening and speed; and control the heating pipeline valves and circulation pumps in the secondary network to provide heating based on the secondary adjusted valve opening and speed.

[0150] In some embodiments of the present invention, the magnitude of the adjustment command is corrected by introducing a safety heating coefficient that combines the expected fluctuations after adjustment and the importance of the area, thereby ensuring the safety of the control operation and avoiding excessive impact on sensitive areas.

[0151] In some embodiments of the present invention, by using a heating database to predict the parameter fluctuations that the adjustment operation itself will bring before the secondary adjustment, the adjustment time point can be selected more scientifically, avoiding new system oscillations caused by blind adjustment and making the control process more stable.

[0152] Figure 5 This is an exemplary flowchart illustrating the control of heating pipeline valves and circulating pumps for heating according to some embodiments of the present invention.

[0153] In some embodiments, such as Figure 5 As shown, process 500 includes the following steps. Process 500 can be executed by the emergency monitoring and management platform.

[0154] Step 510: Based on the safe heating coefficient, iteratively update the valve opening degree of the heating pipeline valves and / or the rotation speed of the circulating pump in the secondary network.

[0155] The initial parameters for the first iteration are the valve opening and rotation speed after secondary adjustments, determined based on the safe heating coefficient. After the first iteration, step 520 is executed. Once an abnormal heat exchange station, abnormal pipeline end, or potential abnormal area is identified, step 530 is executed, and the process returns to step 510 to begin the second iteration. The initial parameters for the second iteration are the valve opening and rotation speed after secondary adjustments, determined based on the safe heating coefficient redefined in the first iteration. Step 520 is executed again, and so on, for multiple iterations. This continues until no abnormal heat exchange station, abnormal pipeline end, or potential abnormal area exists, at which point step 540 is executed, ending the iteration. For more information on adjusting the valve opening and / or circulation pump rotation speed of heating pipeline valves in the secondary network based on the safe heating coefficient, please refer to [link to relevant documentation]. Figure 4 The corresponding description.

[0156] For more information on secondary networks, heating pipeline valves, valve opening, circulating pumps, and speeds, please refer to [link to relevant documentation]. Figure 2 And its corresponding description.

[0157] Step 520: Predict whether there are abnormal heat exchange stations, abnormal pipeline ends, and potential abnormal areas in the heating network after each iteration update.

[0158] For more information on abnormal heat exchange stations, abnormal pipeline ends, and potentially abnormal areas, please refer to [link / reference needed]. Figure 2 And its corresponding description.

[0159] In some embodiments, after iteratively updating the valve opening degree of the heating pipeline valves and / or the rotational speed of the circulating pump in the secondary network, the emergency monitoring and management platform can update the node attributes of the heating map structure based on changes in sensor monitoring data, and simultaneously construct a heating change vector; based on the heating map structure, determine whether there are abnormal heat exchange stations and / or abnormal pipeline ends in the heating network; and predict potential abnormal areas based on the heating change vector. For details on constructing the heating change vector, determining whether there are abnormal heat exchange stations and / or abnormal pipeline ends in the heating network based on the heating map structure, and predicting potential abnormal areas based on the heating change vector, please refer to [link to relevant documentation]. Figure 2 The corresponding description. For more information on heating diagram structures, please refer to... Figure 3 And its corresponding description.

[0160] In some embodiments, the emergency monitoring and management platform can control the heating pipeline valves and circulating pumps after each iteration update, and provide heating based on the valve opening degree of the heating pipeline valves and / or the rotation speed of the circulating pumps determined in this iteration update; monitor the heating parameters after providing heating based on the valve opening degree and / or rotation speed after this iteration update through sensors, and update the node attributes in the heating map structure; process the heating map structure through an anomaly diffusion model to predict whether there are abnormal heat exchange stations, abnormal pipeline ends, and potential abnormal areas in the heating network after each iteration update.

[0161] For more information on the anomalous diffusion model, please refer to [link / reference]. Figure 3 And its corresponding description.

[0162] In some embodiments of the present invention, a graph neural network model is applied to each step of the iterative update. By performing real-time simulation prediction after each fine-tuning, the system can more intelligently evaluate the effect of each adjustment, significantly improving the efficiency and accuracy of the iterative optimization process.

[0163] There are two known scenarios: one where there are abnormal heat exchange stations, abnormal pipeline ends, and potentially abnormal areas in the heating network, and another where there are no abnormal heat exchange stations, abnormal pipeline ends, or potentially abnormal areas in the heating network.

[0164] Step 530: In response to the presence of abnormal heat exchange stations, abnormal pipeline ends, and potentially abnormal areas in the heating network, the safe heating coefficient is re-determined in the next iteration update.

[0165] In some embodiments, in response to the presence of abnormal heat exchange stations, abnormal pipeline ends, or potentially abnormal areas in the heating network, the emergency monitoring and management platform can predict regulation fluctuation information based on the ambient temperature of the current iteration and the heating temperature, heating pressure, heating flow rate, and regulation parameters of the heat exchange stations; based on the regulation fluctuation information and in conjunction with the node type, it can determine the safe heating coefficient. More information on regulation parameters, predicting regulation fluctuation information, and determining the safe heating coefficient can be found in [link to relevant documentation]. Figure 4 And its corresponding description.

[0166] In some embodiments, after performing step 530, the emergency monitoring and management platform returns to performing step 510.

[0167] Step 540: In response to the absence of abnormal heat exchange stations, abnormal pipeline ends, and potential abnormal areas in the heating network, stop iterative updates, control the heating pipeline valves and circulation pumps, and provide heating based on the valve opening degree of the heating pipeline valves and / or the rotation speed of the circulation pumps in the secondary network determined by the last iterative update.

[0168] In some embodiments, in response to the absence of abnormal heat exchange stations, abnormal pipeline ends, and potential abnormal areas in the heating network, the emergency monitoring and management platform can stop iterative updates, control the heating pipeline valves and circulation pumps, and provide heating based on the valve opening degree of the heating pipeline valves and / or the rotation speed of the circulation pumps in the secondary network determined by the last iterative update.

[0169] In some embodiments of the present invention, by re-predicting the system state after each adjustment and determining whether further adjustment is needed based on the prediction results, an iterative optimization closed-loop control is formed, thereby gradually and stably adjusting the system to the optimal state and avoiding the risk of one-step adjustment.

[0170] The basic concepts have been described above. It is clear that the detailed disclosure above is merely illustrative and does not constitute a limitation of the present invention. Although not explicitly stated herein, various modifications, improvements, and corrections may be made to the present invention by those skilled in the art. Such modifications, improvements, and corrections are suggested in this invention and therefore remain within the spirit and scope of the exemplary embodiments of the present invention.

[0171] Furthermore, this invention uses specific terms to describe embodiments of the invention. For example, "some embodiments" refers to a particular feature, structure, or characteristic associated with at least one embodiment of the invention. Additionally, certain features, structures, or characteristics in one or more embodiments of the invention can be appropriately combined.

[0172] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this invention are not intended to limit the order of the processes and methods of this invention. Although the foregoing disclosure has discussed some currently considered useful embodiments of the invention through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments of this invention. For example, while the system components described above can be implemented by hardware devices, they can also be implemented solely by software solutions, such as installing the described system on existing servers or mobile devices.

[0173] Finally, it should be understood that the embodiments described in this invention are merely illustrative of the principles of the invention. Other modifications may also fall within the scope of this invention. Therefore, alternative configurations of the embodiments of this invention are considered as examples and not limitations, and are regarded as consistent with the teachings of this invention. Accordingly, the embodiments of this invention are not limited to those explicitly described and illustrated herein.

Claims

1. A smart city heating emergency control system based on an Internet of Things (IoT) big data model, characterized in that, The emergency control system includes an emergency monitoring and management platform, which is configured as follows: Multiple sets of heating parameters of the heating network at multiple times are obtained, and the values ​​of each heating parameter in the multiple sets of heating parameters at different times are arranged according to parameter type to construct a heating change vector; the heating change vector refers to the quantitative representation of the fluctuation state of the heating parameter. Based on the heating change vector, and in conjunction with the ambient temperature of the heat exchange station and / or residential area, it is determined whether there are abnormal heat exchange stations and / or abnormal pipeline ends. In response to the presence of the abnormal heat exchange station and / or the abnormal pipeline end, the type of heat exchange abnormality is determined based on the heat supply change vector; According to the heat exchange anomaly type, update the valve opening degree of the heating pipeline valve and / or the rotation speed of the circulating pump in the primary or secondary network, and control the heating pipeline valve and / or the circulating pump to supply heat based on the updated valve opening degree and rotation speed, wherein the heat supply includes the delivery of hot water by the heating pipeline valve and / or the circulation of hot water driven by the circulating pump. Heating correlation characteristics are determined based on multiple historical change vectors. The historical change vectors refer to the historical heating change vectors corresponding to historical moments when anomalies occur at multiple heat exchange stations and multiple residential areas. Each historical change vector includes a first abnormal heating parameter at the corresponding historical moment. The heating correlation characteristics reflect the correlation between the abnormal heat exchange stations and / or the abnormal pipeline ends in the heating network. These characteristics include a first abnormal heating parameter occurring at a certain historical moment, a second abnormal heating parameter occurring after that historical moment, and the connection relationship between the associated heat exchange station and / or the associated pipeline end and the heat exchange station and / or pipeline end corresponding to the historical change vector. Determining the heating correlation characteristics based on multiple historical change vectors includes: constructing heating correlation characteristics based on the first abnormal heating parameter in the historical change vector, the associated heat exchange station and / or the associated pipeline end and the corresponding second abnormal heating parameter, and the connection relationship. Based on the heating change vector and the heating correlation characteristics, predict potential anomaly areas at future times; Based on the potential abnormal area, an adjustment time point is determined. At the adjustment time point, the heating pipeline valves and the circulating pump in the secondary network within the potential abnormal area are controlled to provide heating based on the valve opening and rotation speed after the secondary adjustment.

2. The emergency control system as described in claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: A heating map structure is constructed, wherein the heating map structure includes three types of nodes: thermal power plant, heat exchange station and pipeline end. The node attributes include multiple heating parameters in each group of heating parameters. The edges of the heating map structure are heating pipelines, and the edge attributes include pipeline length and pipeline roughness value. The node attributes also include the ambient temperature. The node attributes are updated as the sensor monitoring data changes. Based on the heating diagram structure, determine whether the abnormal heat exchange station and / or the abnormal pipeline end exist, and the type of heat exchange abnormality.

3. The emergency control system as described in claim 2, characterized in that, The emergency monitoring and management platform is further configured as follows: In response to node attribute updates meeting preset conditions, Based on the heating diagram structure, the abnormal nodes and abnormal diffusion nodes corresponding to the abnormal heat exchange station and / or the abnormal pipeline end are obtained through the abnormal diffusion model. The abnormal diffusion nodes include nodes that are predicted to have heating abnormalities in the future. The abnormal diffusion model is a machine learning model. Based on the abnormal node and the abnormal diffusion node, the valve opening degree of the heating pipeline valve and / or the rotation speed of the circulating pump in the primary network or the secondary network are adjusted a second time.

4. The emergency control system as described in claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: Based on the ambient temperature and the heating temperature, heating pressure, heating flow rate and regulation parameters of the heat exchange station, predict regulation fluctuation information, wherein the regulation fluctuation information includes the fluctuation amplitude and fluctuation duration of multiple heating parameters in each group of heating parameters after updating the valve opening degree of the heating pipeline valve in the primary network or the secondary network and / or the rotation speed of the circulating pump; Based on the control fluctuation information, the adjustment time point is determined, and at the adjustment time point, the valve opening degree of the heating pipeline valve in the secondary network and / or the rotation speed of the circulating pump are adjusted a second time.

5. The emergency control system as described in claim 4, characterized in that, The emergency monitoring and management platform is further configured as follows: Based on the aforementioned regulation fluctuation information and in conjunction with the node type, a safe heating coefficient is determined; the safe heating coefficient refers to a quantitative indicator used to assess the safety and stability of the heating network under the current regulation state. The valve opening and speed after secondary adjustment are determined based on the product of the predetermined valve opening and / or the speed of the circulating pump and the safe heating coefficient, and the heating pipeline valves and the circulating pump in the secondary network are controlled to supply heat based on the valve opening and speed after secondary adjustment.

6. A smart city heating emergency control method based on an Internet of Things (IoT) big data model, characterized in that, The method is executed by the emergency monitoring and management platform of the smart city heating emergency control system, and the method includes: Multiple sets of heating parameters of the heating network at multiple times are obtained, and the values ​​of each heating parameter in the multiple sets of heating parameters at different times are arranged according to parameter type to construct a heating change vector; the heating change vector refers to the quantitative representation of the fluctuation state of the heating parameter. Based on the heating change vector, and in conjunction with the ambient temperature of the heat exchange station and / or residential area, it is determined whether there are abnormal heat exchange stations and / or abnormal pipeline ends. In response to the presence of the abnormal heat exchange station and / or the abnormal pipeline end, the type of heat exchange abnormality is determined based on the heat supply change vector; According to the heat exchange anomaly type, update the valve opening degree of the heating pipeline valve and / or the rotation speed of the circulating pump in the primary or secondary network, and control the heating pipeline valve and / or the circulating pump to supply heat based on the updated valve opening degree and rotation speed, wherein the heat supply includes the delivery of hot water by the heating pipeline valve and / or the circulation of hot water driven by the circulating pump. Heating correlation characteristics are determined based on multiple historical change vectors. The historical change vectors refer to the historical heating change vectors corresponding to historical moments when anomalies occur at multiple heat exchange stations and multiple residential areas. Each historical change vector includes a first abnormal heating parameter at the corresponding historical moment. The heating correlation characteristics reflect the correlation between the abnormal heat exchange stations and / or the abnormal pipeline ends in the heating network. These characteristics include a first abnormal heating parameter occurring at a certain historical moment, a second abnormal heating parameter occurring after that historical moment, and the connection relationship between the associated heat exchange station and / or the associated pipeline end and the heat exchange station and / or pipeline end corresponding to the historical change vector. Determining the heating correlation characteristics based on multiple historical change vectors includes: constructing heating correlation characteristics based on the first abnormal heating parameter in the historical change vector, the associated heat exchange station and / or the associated pipeline end and the corresponding second abnormal heating parameter, and the connection relationship. Based on the heating change vector and the heating correlation characteristics, predict potential anomaly areas at future times; Based on the potential abnormal area, an adjustment time point is determined. At the adjustment time point, the heating pipeline valves and the circulating pump in the secondary network within the potential abnormal area are controlled to provide heating based on the valve opening and rotation speed after the secondary adjustment.

7. The emergency control method as described in claim 6, characterized in that, The step of determining whether there are abnormal heat exchange stations and / or abnormal pipeline ends based on the heat supply change vector and the ambient temperature of the heat exchange station and / or residential area includes: A heating map structure is constructed, wherein the heating map structure includes three types of nodes: thermal power plant, heat exchange station and pipeline end. The node attributes include multiple heating parameters in each group of heating parameters. The edges of the heating map structure are heating pipelines, and the edge attributes include pipeline length and pipeline roughness value. The node attributes also include the ambient temperature. The node attributes are updated as the sensor monitoring data changes. Based on the heating diagram structure, determine whether the abnormal heat exchange station and / or the abnormal pipeline end exist, and the type of heat exchange abnormality.

8. The emergency control method as described in claim 7, characterized in that, The node attributes are updated as the sensor monitoring data changes, including: In response to node attribute updates meeting preset conditions, Based on the heating diagram structure, the abnormal nodes and abnormal diffusion nodes corresponding to the abnormal heat exchange station and / or the abnormal pipeline end are obtained through the abnormal diffusion model. The abnormal diffusion nodes include nodes that are predicted to have heating abnormalities in the future. The abnormal diffusion model is a machine learning model. Based on the abnormal node and the abnormal diffusion node, the valve opening degree of the heating pipeline valve and / or the rotation speed of the circulating pump in the primary network or the secondary network are adjusted a second time.

9. The emergency control method as described in claim 6, characterized in that, The step of determining the adjustment time point based on the potential abnormal region includes: Based on the ambient temperature and the heating temperature, heating pressure, heating flow rate and regulation parameters of the heat exchange station, predict regulation fluctuation information, wherein the regulation fluctuation information includes the fluctuation amplitude and fluctuation duration of multiple heating parameters in each group of heating parameters after updating the valve opening degree of the heating pipeline valve in the primary network or the secondary network and / or the rotation speed of the circulating pump; Based on the control fluctuation information, the adjustment time point is determined, and at the adjustment time point, the valve opening degree of the heating pipeline valve in the secondary network and / or the rotation speed of the circulating pump are adjusted a second time.

10. The emergency control method as described in claim 9, characterized in that, The step of determining the adjustment time point based on the control fluctuation information, and then making secondary adjustments to the valve opening degree of the heating pipeline valves in the secondary network and / or the rotation speed of the circulating pump at the adjustment time point, includes: Based on the aforementioned regulation fluctuation information and in conjunction with the node type, a safe heating coefficient is determined; the safe heating coefficient refers to a quantitative indicator used to assess the safety and stability of the heating network under the current regulation state. The valve opening and speed after secondary adjustment are determined based on the product of the predetermined valve opening and / or the speed of the circulating pump and the safe heating coefficient, and the heating pipeline valves and the circulating pump in the secondary network are controlled to supply heat based on the valve opening and speed after secondary adjustment.

Images