A heat distribution pipe network scheduling monitoring method, a monitoring platform, a device and a storage medium

Abstract

The application discloses a heat distribution pipe network scheduling monitoring method and a monitoring platform, device and storage medium, and comprises the following steps: acquiring detection data from a sensor component; substituting each detection data into a pipe network topology model to form real-time state data of each position in the pipe network topology model; analyzing the real-time state data and a topology connection structure to obtain the operation conditions of each operation device in the heat distribution pipe network and deriving a scheduling strategy to perform feedback control on the corresponding operation device; diagnosing the real-time state data and the topology connection structure against preset fault judgment conditions, outputting alarm information when the real-time state data satisfies the fault judgment conditions, and analyzing fault causes according to a fault logic model; and visually outputting the real-time state data, the topology connection structure, the scheduling strategy, the alarm information and the fault causes; and the design improves the safety performance, fault tracking capability and service life of the heat distribution pipe network and reduces the maintenance cost.

Description

Technical Field

[0001] This invention relates to the field of computer control of thermal systems, and in particular to a method, monitoring platform, device, and storage medium for scheduling and monitoring thermal pipeline networks. Background Technology

[0002] Heating networks are an important component of urban heating systems, supplying heat to users for production or daily life through facilities such as heating pipe networks.

[0003] However, the current level of intelligence in my country's heating network is low, and there are many problems and challenges. For example, the lack of quality control in the heating network leads to poor pipe sealing, serious heat loss, and short service life of heating pipes, which can easily cause serious pipeline accidents, resulting in water loss and significant energy loss. The heating network lacks quality regulation and energy consumption metering methods, which not only cause hydraulic imbalance and uneven heating, but also lead to serious waste due to extensive operation without metering. The low efficiency of data acquisition and transmission in the heating network makes it difficult to achieve real-time monitoring and optimization analysis of the heating system, affecting heating efficiency and quality. The data security and traceability of the heating network are poor, making it difficult to achieve the characteristics of data encryption, distribution, immutability, and traceability. Summary of the Invention

[0004] This invention aims to solve at least one of the technical problems existing in the prior art. To this end, this invention proposes a method, monitoring platform, device, and storage medium for scheduling and monitoring of a heating pipe network. This method can detect the status of the heating pipe network, automatically provide feedback and adjustment, promptly report and analyze the causes of faults, improve the safety performance and fault tracing capabilities of the heating pipe network, extend its service life, and reduce maintenance costs.

[0005] A method for scheduling and monitoring a heat pipe network according to a first aspect of the present invention includes: acquiring detection data from sensor components disposed at various locations in the heat pipe network, wherein each detection data corresponds to a location in the pipe network and multiple detection data have multiple information categories; substituting each detection data into a pipe network topology model to form real-time status data for each location in the pipe network topology model, wherein the pipe network topology model is used to simulate the topological connection structure of the heat pipe network and the dynamic state changes caused by each detection data in the topological connection structure; and analyzing the real-time status data and the topological connection structure to determine the operating conditions of each location in the heat pipe network. The system monitors the equipment's operation and derives a scheduling strategy, which is then distributed to the controllers corresponding to each operating device. These controllers provide feedback control to the respective operating devices. Real-time status data and the topology are compared with preset fault judgment conditions for diagnosis. When the real-time status data meets the fault judgment conditions, an alarm message is output. This alarm message characterizes the occurrence of a fault event, and the fault event is analyzed based on a fault logic model to determine the cause of the fault. The fault logic model is a relationship model between fault events and fault causes. The system visually outputs real-time status data, topology, scheduling strategy, alarm message, and fault cause.

[0006] A method for scheduling and monitoring a thermal pipeline network according to an embodiment of the present invention has at least the following beneficial effects:

[0007] This invention relates to a method for scheduling and monitoring thermal pipeline networks. Various types of sensor components are deployed at different locations within the thermal pipeline network to acquire the detection data generated by these components. Since the detection data corresponds to the location within the pipeline network, the data can be substituted into the network topology model to form real-time status data for each location. Given the known topology of the thermal pipeline network, the relationships between operating equipment at different locations can be determined. Using the real-time status data and the topology, the operating status of each piece of equipment can be analyzed, and a scheduling strategy can be derived. Based on this strategy, automatic feedback control can be applied to the corresponding operating equipment, ensuring the entire thermal pipeline network operates in a reasonable and stable state. Simultaneously, the real-time status data and topology are used to diagnose fault events. When a fault event occurs, an alarm is output, and the fault event is analyzed using a fault logic model to determine the cause and provide handling suggestions. This allows for timely maintenance and repair by staff. This design enables status monitoring of the thermal pipeline network and automatic feedback adjustment. It promptly reports and analyzes the causes of faults, improving the safety performance and fault tracking capabilities of the thermal pipeline network, extending its service life, and reducing maintenance costs.

[0008] According to some embodiments of the present invention, the pipeline topology model includes one or more of the following: convolutional neural network model, recurrent neural network model, and graph neural network model. The pipeline topology model is trained by multiple sets of data including detection data, real-time status data, topology connection structure, and scheduling strategy.

[0009] According to some embodiments of the present invention, the step of analyzing the operating status of each operating device in the thermal pipeline network based on real-time status data and topological connection structure and deriving a scheduling strategy includes: determining the optimization objective and constraints of the scheduling strategy based on a multi-objective genetic algorithm; performing optimization analysis on the scheduling strategy using a multi-objective genetic algorithm based on real-time status data and topological connection structure, and outputting the optimal solution set of the scheduling strategy.

[0010] According to some embodiments of the present invention, the step of diagnosing real-time status data and topology connection structure with preset fault judgment conditions, and outputting alarm information when the real-time status data meets the fault judgment conditions, includes: the fault judgment conditions include multiple fault thresholds corresponding to various positions and categories of parameters in the topology connection structure, each fault threshold corresponding to at least one fault event; the real-time status data is compared with the fault thresholds, and when the real-time status data exceeds the fault threshold, alarm information corresponding to the fault event is output.

[0011] According to some embodiments of the present invention, the step of analyzing the fault event based on the fault logic model to find the fault cause includes: the fault logic model is established based on the tree analysis method, and the fault event tends to at least one fault cause based on the fault logic relationship; the fault event is substituted into the fault logic model to analyze at least one fault cause.

[0012] According to some embodiments of the present invention, in the fault logic model, each fault event is listed as a first node, each fault cause is listed as a second node, and the occurrence probability and influence degree of the fault cause are set for each second node. The fault logic relationship includes multiple logic gates, each logic gate is used to characterize the relationship between each fault event and at least one fault cause, each logic gate is listed as an intermediate node, and each first node and each second node are associated through the corresponding intermediate nodes.

[0013] According to some embodiments of the present invention, the occurrence of a fault event is analyzed to obtain a minimum cut set based on a fault logic model. The minimum cut set is the minimum combination of fault causes that lead to the occurrence of the fault event. Based on the occurrence probability and influence of each fault cause in the minimum combination of events, the correlation index of each fault cause is calculated according to logic gates. The priority level of the fault cause is determined based on the correlation index, and a processing suggestion is derived.

[0014] According to a second aspect of the present invention, a monitoring platform includes: a sensor assembly for detecting the operation of a heating pipe network to generate detection data, each detection data corresponding to a location in the pipe network and multiple detection data having various information categories; a data processing module for acquiring the detection data and substituting each detection data into a pipe network topology model to form real-time status data for each location in the pipe network topology model, wherein the pipe network topology model is used to simulate the topological connection structure of the heating pipe network and the dynamic state changes caused by each detection data in the topological connection structure; and a feedback control module for analyzing the real-time status data and the topological connection structure to determine the operating conditions of each device in the heating pipe network. The system monitors the operation of the equipment and derives a scheduling strategy, which is then distributed to the controllers corresponding to each operating device. The controllers then provide feedback control to the corresponding operating devices. A diagnostic alarm module diagnoses real-time status data and topology connections against preset fault judgment conditions. When the real-time status data meets the fault judgment conditions, an alarm message is output. This alarm message characterizes the occurrence of a fault event, and the fault event is analyzed based on a fault logic model to determine the cause of the fault. The fault logic model is a relationship model between fault events and fault causes. A display module visually outputs real-time status data, topology connections, scheduling strategies, alarm messages, and fault causes.

[0015] The monitoring platform according to embodiments of the present invention has at least the following beneficial effects:

[0016] The monitoring platform of this invention can detect the status of the heating network and automatically provide feedback and adjustment. When a fault occurs, it can report and analyze the cause in a timely manner, thereby improving the safety performance of the heating network, fault tracking capability, extending the service life of the heating network, and reducing maintenance costs.

[0017] According to a third aspect of the present invention, a control device includes: one or more memories; one or more processors, configured to execute one or more computer programs stored in the one or more memories, and further configured to execute the thermal pipeline network scheduling and monitoring method disclosed in any of the above embodiments.

[0018] A computer-readable storage medium according to a fourth aspect of the present invention includes instructions that, when executed on a computer, cause the computer to perform the thermal pipeline network scheduling and monitoring method disclosed in any of the above embodiments.

[0019] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0020] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0021] Figure 1 This is a schematic diagram illustrating the principle structure of one embodiment of the monitoring platform of the present invention;

[0022] Figure 2 This is a flowchart of one embodiment of the scheduling and monitoring method of the present invention;

[0023] Figure 3 This is a schematic diagram of the control device of the present invention in one embodiment.

[0024] Figure label:

[0025] Sensor assembly 210; data processing module 220; feedback control module 230; diagnostic alarm module 240; display module 250; network link 260; data storage and sharing module 270; controller 280; control device 300; memory 310; processor 320. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0027] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0029] First, according to a first aspect embodiment of the present invention, a method for scheduling and monitoring a thermal pipeline network, such as... Figure 2 As shown, it includes:

[0030] S110. Acquire detection data from sensor assemblies installed at various locations in the thermal pipeline network, wherein each detection data corresponds to a location in the pipeline network and multiple detection data have various information categories;

[0031] S120. Substitute each detection data into the pipeline topology model to form real-time status data at each location in the pipeline topology model, wherein the pipeline topology model is used to simulate the topological connection structure of the heating pipeline and the dynamic state changes caused by each detection data in the topological connection structure.

[0032] S130. Analyze the real-time status data and topology connection structure to determine the operating status of each operating device in the heat pipe network and derive a scheduling strategy. Distribute the scheduling strategy to the controllers corresponding to each operating device, and the controllers provide feedback control to the corresponding operating devices.

[0033] S140. Diagnose the real-time status data and topology connection structure with the preset fault judgment conditions. When the real-time status data meets the fault judgment conditions, output alarm information. The alarm information is used to characterize the fault event that has occurred. Analyze the fault event according to the fault logic model to find the cause of the fault. The fault logic model is a relationship model between the fault event and the cause of the fault.

[0034] S150 provides a visual output of real-time status data, topology connection structure, scheduling strategy, alarm information, and fault causes.

[0035] It should be noted that multiple sensor components can be installed at various locations in the heating network. There are various types of sensor components, such as temperature sensors, pressure sensors, and flow sensors. The detected data includes various information categories, such as collecting data on temperature, pressure, and flow rate in the network.

[0036] Sensor components can send data to a cloud server via wireless communication chips such as RS485. The monitoring platform then retrieves the relevant data from the cloud server for processing. Specifically, the wireless communication methods can be, but are not limited to, Bluetooth, Wi-Fi, ZigBee, and LoRa.

[0037] This invention relates to a method for scheduling and monitoring thermal pipeline networks. Various types of sensor components are deployed at different locations within the thermal pipeline network to acquire the detection data generated by these components. Since the detection data corresponds to the location within the pipeline network, the data can be substituted into the network topology model to form real-time status data for each location. Given the known topology of the thermal pipeline network, the relationships between operating equipment at different locations can be determined. Using the real-time status data and the topology, the operating status of each piece of equipment can be analyzed, and a scheduling strategy can be derived. Based on this strategy, automatic feedback control can be applied to the corresponding operating equipment, ensuring the entire thermal pipeline network operates in a reasonable and stable state. Simultaneously, the real-time status data and topology are used to diagnose fault events. When a fault event occurs, an alarm is output, and the fault event is analyzed using a fault logic model to determine the cause and provide handling suggestions. This allows for timely maintenance and repair by staff. This design enables status monitoring of the thermal pipeline network and automatic feedback adjustment. It promptly reports and analyzes the causes of faults, improving the safety performance and fault tracking capabilities of the thermal pipeline network, extending its service life, and reducing maintenance costs.

[0038] In some embodiments of the present invention, the pipeline topology model includes one or more of the following: convolutional neural network model, recurrent neural network model, and graph neural network model. The pipeline topology model is trained from multiple sets of data including detection data, real-time status data, topology connection structure, and scheduling strategy.

[0039] Before training, the received detection data usually needs to be cleaned to remove outliers, noise, missing values, etc., to ensure the quality and integrity of the data. At the same time, the cleaned data can also be verified to check the consistency, validity, and accuracy of the data, so as to ensure the credibility and usability of the data.

[0040] When a convolutional neural network model is selected for the pipeline topology model, the fused detection data can be used as input. Through multi-layer convolution, pooling, full connection and other operations, the feature vectors of each node and edge in the thermal pipeline network can be extracted and combined into a matrix to represent the state parameters of the thermal pipeline network.

[0041] When a recurrent neural network is used for the pipeline topology model, the fused detection data can be used as input in chronological order. Through multiple recurrent units (such as LSTM, GRU, etc.), the characteristics of each node and edge in the thermal pipeline network as a function of time can be captured, and the output can be a sequence representing the state parameters of the thermal pipeline network.

[0042] When a graph neural network is used for the pipeline topology model, the fused detection data can be used as the attributes of nodes and edges. Through multi-layer graph convolution, graph attention, graph pooling and other operations, the neighbor information of each node and edge in the heating pipeline network can be aggregated and output as a graph representing the state parameters of the heating pipeline network.

[0043] Taking a graph neural network as an example, specifically, it can be simplified to consider a heating pipe network with N nodes and M edges. Each node has K control parameters (such as temperature, pressure, flow rate, etc.), and each edge has L attribute parameters (such as length, resistance, direction, etc.). Then, in the pipe network topology model, the input is: The output is: The pipeline network topology model is as follows: .

[0044] in, It is a graph neural network function, where W and b are trainable weights and biases, and A is the adjacency matrix of the thermal pipeline network.

[0045] In some embodiments of the present invention, the step of analyzing real-time status data and topological connection structure to determine the operating status of each operating device in the thermal pipeline network and deriving a scheduling strategy includes:

[0046] The optimization objectives and constraints of the scheduling strategy are determined based on a multi-objective genetic algorithm.

[0047] Based on real-time status data and topology connection structure, a multi-objective genetic algorithm is used to optimize and analyze the scheduling strategy, and output the optimal solution set of the scheduling strategy.

[0048] In formulating scheduling strategies based on the operating status of equipment, staff can pre-set optimization objectives and constraints. Then, by using a multi-objective genetic algorithm to optimize and analyze the scheduling strategy based on real-time status data and topological connection structure, the optimal solution set that satisfies the optimization objectives and constraints can be obtained. This enables feedback control of each operating device and maintains the stable operation of the heating network.

[0049] In a multi-objective genetic algorithm, the following steps can be performed: Randomly generate a certain number of individuals, each representing a possible heating parameter and scheduling strategy, such as valve opening, pump speed, and water temperature; calculate the fitness value of each individual based on the optimization objective and constraints, such as heating cost, heating efficiency, and heating quality; select a subset of superior individuals as parents based on the fitness values ​​using methods such as non-dominated sorting and crowding distance; perform mutation operations on each parent individual with a certain probability, such as randomly changing the value of a parameter, to generate new individuals as offspring; perform crossover operations on each pair of adjacent individuals in the parent generation with a certain probability, such as exchanging the values ​​of certain parameters, to generate new individuals as offspring; select a subset of the best individuals from the parent and offspring generations as the next generation; determine whether the termination condition is met, such as reaching the maximum number of iterations or convergence degree. If yes, output the optimal solution set; otherwise, return to the step of calculating the fitness value of each individual based on the optimization objective and constraints.

[0050] Specifically, using the example of a heating pipe network with N nodes and M edges, the optimization problem of the multi-objective genetic algorithm can be set as follows:

[0051] Decision variables: ;in Let i represent the parameter vector of the i-th node. The parameter vector representing the j-th edge;

[0052] Objective function: ;in This represents the P-th optimization objective;

[0053] Constraints: ;in This represents the q-th constraint.

[0054] Optimal solution set: Where X represents the feasible solution space. This indicates Pareto dominance.

[0055] In some embodiments of the present invention, the step of diagnosing real-time status data and topology connection structure against preset fault judgment conditions, and outputting alarm information when the real-time status data meets the fault judgment conditions, includes:

[0056] The fault judgment conditions include multiple fault thresholds corresponding to various positions and categories of parameters in the topology connection structure, and each fault threshold corresponds to at least one fault event.

[0057] The real-time status data is compared with the fault threshold. When the real-time status data exceeds the fault threshold, an alarm message corresponding to the fault event is output.

[0058] It should be noted that when certain locations or operating equipment in the heating network malfunction, the detection data generated by certain sensor components at those locations will become abnormal. By setting a fault threshold, the occurrence of the fault event can be quickly determined, so that the fault can be handled in a timely manner.

[0059] In some embodiments of the present invention, the step of analyzing the fault event to determine the cause of the fault based on the fault logic model includes:

[0060] The fault logic model is established based on the tree analysis method, and the fault events tend to be at least one fault cause based on the fault logic relationship.

[0061] Substitute the fault event into the fault logic model to analyze at least one fault cause.

[0062] Since each fault event may be caused by one or more fault causes, staff can enter the fault event and fault cause into the system in advance, and use tree analysis to guide the fault event to each fault cause. After a fault event occurs, the system can tend to at least one fault cause according to the fault logic relationship, thereby generating an alarm message.

[0063] Specifically, in the fault logic model, each fault event is listed as a first node, each fault cause is listed as a second node, and the occurrence probability and impact degree of the fault cause are set for each second node. The fault logic relationship includes multiple logic gates, each logic gate is used to characterize the relationship between each fault event and at least one fault cause, each logic gate is listed as an intermediate node, and each first node and each second node are associated through the corresponding intermediate nodes. Thus, the system can reasonably and accurately analyze the fault cause based on the fault event.

[0064] In some embodiments of the present invention, the occurrence of a fault event is analyzed to obtain a minimum cut set according to the fault logic model. The minimum cut set is the minimum combination of fault causes that cause the fault event. Based on the occurrence probability and influence of each fault cause in the minimum combination of fault events, the correlation index of each fault cause is calculated according to the logic gate. The priority level of the fault cause is determined based on the correlation index, and a processing suggestion is derived.

[0065] It should be noted that since each fault cause has a probability of occurrence and a degree of influence, the degree of influence means the likelihood that the fault cause will lead to a fault event. Therefore, when a fault event occurs, the system can deduce the correlation index involving the fault cause based on the fault event. For example, fault cause A has a 60% probability of occurrence and a high degree of influence on the occurrence of a certain fault event (the degree of influence can be set by level or percentage). Fault cause B has a 30% probability of occurrence and a medium degree of influence on the occurrence of the same fault event. Then, when the fault event occurs, the minimum cut set contains both fault cause A and fault cause B, but the correlation index of fault cause A is higher than that of fault cause B. This can be expressed numerically.

[0066] Specifically, the following model can be established for the above problems using tree-based analysis:

[0067] Fault event: ,in =1 indicates a fault has occurred. =0 indicates that no fault occurred;

[0068] Cause of the malfunction: ,in, =1 indicates that the i-th node or edge has an anomaly or is damaged. = 0 indicates that the i-th node or edge is normal;

[0069] Failure probability: ,in, This represents the probability that the i-th node or edge is abnormal or damaged;

[0070] Impact of the fault: ,in, This indicates the degree of impact of an anomaly or damage to the heating network caused by the i-th node or edge.

[0071] Fault tree: , where T is a logical function that represents the logical relationship between the fault event and the fault cause;

[0072] Minimal cut set: Where C(F) is the set of basic events, representing the smallest combination of basic events that can lead to a failure event;

[0073] Minimum cut set probability: Where P(C(F)) represents the probability of the minimum cut set occurring;

[0074] Minimal cut set effect: Wherein, I(C(F)) represents the degree of influence of the minimum cut set on the heating network;

[0075] Minimal cut set importance: Where R(C(F)) represents the importance index of the minimum cut set, reflecting the priority of the cause of the failure.

[0076] According to a second aspect of the present invention, a monitoring platform, such as Figure 1 As shown, it includes:

[0077] Sensor assembly 210 is used to detect the operation of the heating pipe network to generate detection data, each of the detection data corresponds to a location in the pipe network and multiple detection data have multiple information categories;

[0078] The data processing module 220 is used to acquire detection data and substitute each detection data into the pipeline network topology model to form real-time status data at each location in the pipeline network topology model. The pipeline network topology model is used to simulate the topological connection structure of the heating pipeline network and the dynamic state changes caused by each detection data in the topological connection structure.

[0079] The feedback control module 230 is used to analyze the real-time status data and topology connection structure to determine the operating status of each operating device in the heat pipe network and to derive a scheduling strategy. The scheduling strategy is then distributed to the controller 280 corresponding to each operating device, and the controller 280 performs feedback control on the corresponding operating device.

[0080] The diagnostic alarm module 240 is used to diagnose the real-time status data and topology connection structure with preset fault judgment conditions. When the real-time status data meets the fault judgment conditions, it outputs alarm information. The alarm information is used to characterize the fault event that has occurred, and the fault event is analyzed to find the fault cause based on the fault logic model. The fault logic model is a relationship model between the fault event and the fault cause.

[0081] Display module 250 is used to visually output real-time status data, topology connection structure, scheduling strategy, alarm information and fault causes.

[0082] The monitoring platform of this invention can detect the status of the heating network and automatically provide feedback and adjustment. When a fault occurs, it can report and analyze the cause in a timely manner, thereby improving the safety performance of the heating network, fault tracking capability, extending the service life of the heating network, and reducing maintenance costs.

[0083] In some embodiments of the present invention, the monitoring platform also includes a network 260 constructed by upstream and downstream users of the heating pipeline. Based on the blockchain encryption consensus mechanism, the real-time status data, topology connection structure, scheduling strategy, alarm information and fault causes of the heating pipeline are encrypted and securely uploaded to the blockchain. Storage contracts, data access contracts and data sharing contracts are deployed in the network 260 to realize secure access and sharing of data.

[0084] First, the data storage and sharing module 270 encrypts real-time status data, topology connection structure, scheduling strategy, alarm information and fault causes to generate encrypted data;

[0085] Secondly, the data storage and sharing module 270 packages the encrypted data into blocks and broadcasts the blocks to the blockchain network. User nodes in the blockchain network perform consensus verification. After successful verification, the block is added to the blockchain, realizing distributed and tamper-proof storage of data.

[0086] Furthermore, the data storage and sharing module 270 writes corresponding smart contracts based on the identity and permissions of different user nodes, defines the rules for data access and sharing, such as access conditions, access scope, access fees, etc., and deploys the smart contracts to the blockchain network.

[0087] Finally, when a user node needs to access or share data, it can send a request to the data storage and sharing module 270 by invoking the smart contract, providing corresponding proof and payment. The data storage and sharing module 270 automatically verifies the legality and validity of the user node's request according to the rules of the smart contract. If the verification passes, the data storage and sharing module 270 will return the corresponding encrypted data and decrypt it to restore the original data. If the verification fails, the data storage and sharing module 270 will reject the user node's request and return an error message. In this way, secure data access and sharing are achieved.

[0088] Specifically, the consortium blockchain network is used to run a data storage and sharing module 270 based on blockchain technology. This consortium blockchain network is composed of upstream and downstream users of the heating network, including: the heat source side, the heating network side, and heat users (various factories, enterprises, units, residential communities, etc.); it can be further categorized as follows:

[0089] Heating network operators are responsible for the operation, management, and maintenance of the heating network. They can access and share data and information of the heating network through the blockchain network, thereby improving operational efficiency and quality.

[0090] The heating network regulatory department, responsible for supervising and inspecting the heating network, can access and share data and information of the heating network through the blockchain network, thereby improving regulatory efficiency and credibility.

[0091] Heating network users, i.e. end users of heating, can access and share data and information of the heating network through the blockchain network, thereby improving heating satisfaction and participation;

[0092] Heating network service providers, namely third-party organizations that provide heating network-related services, such as equipment suppliers, maintenance companies, and consultants, can access and share heating network data and information through blockchain networks to improve service efficiency and quality.

[0093] The data storage and sharing module 270 is used to store the real-time status data, topology connection structure, scheduling strategy, alarm information and fault causes of the thermal pipeline network generated by the data processing module 220 in the consortium blockchain network in an encrypted, distributed and tamper-proof manner, and realize secure access and sharing of data through smart contracts.

[0094] According to a third aspect embodiment of the present invention, the control device 300, such as Figure 3 As shown, the control device 300 includes a memory 310 and a processor 320. The memory 310 stores a computer program, and the processor 320 executes the computer program to implement the thermal pipeline network scheduling and monitoring method disclosed in any of the above embodiments.

[0095] The control device can be any intelligent terminal, including a central computer, a remote equipment terminal computer, or any other intelligent terminal.

[0096] According to a fourth aspect of the present invention, a computer-readable storage medium stores a computer program, characterized in that, when executed by a processor, the computer program implements the thermal pipeline network scheduling and monitoring method disclosed in any of the above embodiments.

[0097] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0098] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0099] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0100] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0101] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0102] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0103] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for scheduling and monitoring a heating network, characterized in that, include: Detection data is acquired from sensor assemblies located at various locations in the heating network, wherein each piece of detection data corresponds to a location in the network and the multiple pieces of detection data have various information categories; Each detection data is substituted into the pipeline topology model to form real-time status data at each location in the pipeline topology model, wherein the pipeline topology model is used to simulate the topological connection structure of the heating pipeline and the dynamic state changes caused by each detection data in the topological connection structure. The real-time status data and topology connection structure are analyzed to determine the operating status of each operating device in the heating network and to derive a scheduling strategy. The scheduling strategy is then distributed to the controllers corresponding to each operating device, and the controllers provide feedback control to the corresponding operating devices. The real-time status data and topology connection structure are diagnosed against preset fault judgment conditions. When the real-time status data meets the fault judgment conditions, an alarm message is output. The alarm message is used to characterize the fault event that has occurred. The fault event is analyzed to find the cause of the fault based on the fault logic model. The fault logic model is a relationship model between the fault event and the cause of the fault. It can visually output real-time status data, topology connection structure, scheduling strategy, alarm information and fault causes; The process of diagnosing real-time status data and topology connections against preset fault judgment conditions, and outputting alarm information when the real-time status data meets the fault judgment conditions, includes: The fault judgment conditions include multiple fault thresholds corresponding to various positions and categories of parameters in the topology connection structure, and each fault threshold corresponds to at least one fault event. The real-time status data is compared with the fault threshold. When the real-time status data exceeds the fault threshold, an alarm message corresponding to the fault event is output. The process of analyzing the fault event to determine the cause of the fault based on the fault logic model includes: The fault logic model is established based on the tree analysis method, and the fault events tend to be at least one fault cause based on the fault logic relationship. Substitute the fault event into the fault logic model to analyze at least one fault cause; In the fault logic model, each fault event is listed as a first node, each fault cause is listed as a second node, and the occurrence probability and impact of the fault cause are set for each second node. The fault logic relationship includes multiple logic gates, each logic gate is used to characterize the relationship between each fault event and at least one fault cause, each logic gate is listed as an intermediate node, and each first node and each second node are associated through the corresponding intermediate nodes. The occurrence of a fault event is analyzed using a fault logic model to obtain a minimum cut set. The minimum cut set is the minimum combination of fault causes that lead to the fault event. Based on the occurrence probability and impact of each fault cause in the minimum combination of fault events, the correlation index of each fault cause is calculated using logic gates. The priority level of the fault cause is determined based on the correlation index, and a handling suggestion is derived.

2. The method for scheduling and monitoring a heating network according to claim 1, characterized in that: The pipeline topology model includes one or more of the following: convolutional neural network model, recurrent neural network model, and graph neural network model. The pipeline topology model is trained from multiple sets of data including detection data, real-time status data, topology connection structure, and scheduling strategy.

3. The method for scheduling and monitoring a heating network according to claim 1, characterized in that, The process of analyzing real-time status data and topology connections to determine the operating status of each piece of equipment in the heating network and deriving a scheduling strategy includes: The optimization objectives and constraints of the scheduling strategy are determined based on a multi-objective genetic algorithm. Based on real-time status data and topology connection structure, a multi-objective genetic algorithm is used to optimize and analyze the scheduling strategy, and output the optimal solution set of the scheduling strategy.

4. A monitoring platform for executing the thermal pipeline network scheduling and monitoring method as described in any one of claims 1 to 3, characterized in that, include: A sensor assembly is used to detect the operation of a thermal pipeline network to generate detection data, each of which corresponds to a location in the pipeline network and the multiple detection data have various information categories. The data processing module is used to acquire detection data and substitute each detection data into the pipeline network topology model to form real-time status data at each location in the pipeline network topology model. The pipeline network topology model is used to simulate the topological connection structure of the heating pipeline network and the dynamic state changes caused by each detection data in the topological connection structure. The feedback control module is used to analyze the real-time status data and topology connection structure to determine the operating status of each operating device in the heat pipe network and derive a scheduling strategy. The scheduling strategy is then distributed to the controllers corresponding to each operating device, and the controllers perform feedback control on the corresponding operating devices. The diagnostic alarm module is used to diagnose real-time status data and topology connection structure against preset fault judgment conditions. When the real-time status data meets the fault judgment conditions, an alarm message is output. The alarm message is used to characterize the fault event that has occurred, and the fault event is analyzed to find the cause of the fault based on the fault logic model. The fault logic model is a relationship model between the fault event and the fault cause. The display module is used to visually output real-time status data, topology connection structure, scheduling strategy, alarm information, and fault causes.

5. A control device, characterized in that, include: One or more memory units; One or more processors are configured to execute one or more computer programs stored in the one or more memories, and to execute the thermal pipeline network scheduling and monitoring method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The instructions, when executed on a computer, cause the computer to perform the thermal pipeline network scheduling and monitoring method as described in any one of claims 1-3.

Images