Intelligent gas pipe network valve remote control supervision Internet of Things system and method

Abstract

The invention provides an intelligent gas pipe network valve remote control supervision Internet of Things system and method, and relates to the field of intelligent gas control. The method is realized based on the Internet of Things system, and comprises the following steps: obtaining pipe network information and performance parameters of a control assembly, and uploading the performance parameters to a government safety supervision management platform; obtaining a parameter confirmation instruction, determining layout parameters, and uploading the layout parameters to a government safety supervision management platform; a layout confirmation instruction is obtained, and layout parameters are sent to a gas maintenance object platform; after the layout is completed, the regulation and control compensation amount of the control assembly is determined based on the correction period and uploaded to a government safety supervision management platform; and a correction confirmation instruction is obtained, the control assembly is corrected based on the regulation and control compensation amount, the control assembly is controlled to regulate and control the coverage valve based on the regulation and control parameter set in the correction period, a regulation and control gas data pair is obtained, and the regulation and control compensation amount is determined. The arrangement position of the control assembly can be reasonably determined, and the regulation and control deviation is accurately evaluated to ensure the remote control effectiveness of the valve.

Description

Technical Field

[0001] This manual relates to the field of intelligent gas control, and in particular to an IoT system and method for remote control and monitoring of intelligent gas pipeline valves. Background Technology

[0002] Gas pipelines are the primary carriers of gas. To ensure the safety of gas operations, gas pipeline networks are typically designed with valves at each node to control gas transmission and switching. Remote control components are also installed to enable remote valve control, allowing for valve adjustment in the event of a gas accident, reducing gas leakage time and mitigating safety risks.

[0003] Because the control components for pipeline valves have a maximum communication distance, it is necessary to determine the appropriate installation location and pairing relationship between the control components and the valves before installation to ensure effective coverage of the valves. Furthermore, after installation and during use, it is also necessary to assess the error of the actual control results of the components and make timely corrections to ensure the effectiveness of remote control.

[0004] Therefore, we hope to propose an IoT system and method for remote control and supervision of valves in intelligent gas pipeline networks. This system should be able to reasonably determine the placement of control components to cover the valves, accurately assess and correct control deviations in a timely manner, and ensure the accuracy and effectiveness of remote control and supervision of valves, thereby improving the level of intelligent monitoring and control of gas pipeline networks. Summary of the Invention

[0005] To address the challenges of determining the optimal placement of control components and accurately assessing control deviations to ensure the effectiveness of remote valve control, this invention provides an IoT system and method for remote control and monitoring of valves in a smart gas pipeline network.

[0006] The invention includes an IoT system for remote control and supervision of smart gas pipeline valves. The IoT system comprises: a government safety supervision and management platform, a government safety supervision object platform, a gas equipment object platform, and a gas maintenance object platform. The government safety supervision object platform includes a gas company management platform. The gas equipment object platform includes at least one control component, and the gas maintenance object platform includes at least one human interaction device. The gas company management platform is configured to execute a method for remote control and supervision of smart gas pipeline valves.

[0007] The invention includes a method for remote control and monitoring of valves in a smart gas pipeline network. The method is implemented based on an IoT system for remote control and monitoring of valves in a smart gas pipeline network. The IoT system includes a government safety supervision and management platform, a government safety supervision object platform, a gas equipment object platform, and a gas maintenance object platform. The government safety supervision object platform includes a gas company management platform, the gas equipment object platform includes at least one control component, and the gas maintenance object platform includes at least one human interaction device. The method is executed by the gas company management platform and includes: acquiring pipeline network information and performance parameters of the control component, and uploading the performance parameters to the government safety supervision and management platform; responding to a parameter confirmation command issued by the government safety supervision and management platform, determining deployment parameters based on the pipeline network information and the performance parameters, and uploading them to the government safety supervision and management platform. The system includes a management platform; the deployment parameters include the deployment location of the control component and the covering valve; in response to receiving a deployment confirmation instruction issued by the government safety supervision and management platform, the deployment parameters are sent to the gas maintenance object platform to arrange staff to deploy the component; after deployment is completed, the control compensation amount of the control component is determined based on the correction cycle and uploaded to the government safety supervision and management platform; in response to receiving a correction confirmation instruction issued by the government safety supervision and management platform, the control component is corrected based on the control compensation amount; wherein, determining the control compensation amount of the control component based on the correction cycle includes: within the correction cycle, performing: controlling the control component to regulate the covering valve based on the control parameter group to obtain a regulated gas data pair; and determining the control compensation amount based on the regulated gas data pair and the control parameter group.

[0008] The beneficial effects brought about by the above invention include, but are not limited to: (1) By uploading performance parameters and deployment parameters to the government safety management platform, the government can promote the supervision and control of the deployment process; Based on the pipeline network information and the performance parameters of the control components, the deployment parameters can be determined so that the control components can connect as many valves as possible, thereby improving resource utilization; Based on the correction cycle, the control component's regulation compensation amount can be determined, and the control component can be periodically corrected based on the regulation compensation amount, so as to avoid the problem of inaccurate valve regulation caused by control component failure or valve failure, thereby ensuring that parameters such as gas flow, pressure and temperature are within the set range, reducing the risk of gas runaway, thereby improving operational safety and realizing automated remote monitoring and intelligent control of gas; (2) Based on the valve position, valve Based on the type of pipe and valve, the valves can be grouped separately for specific functions or areas. The layout parameters are determined by combining the group and the performance parameters of the control components. This ensures that the control components can effectively regulate the valves they cover, while avoiding resource waste and improving the regulation accuracy and resource utilization efficiency of the gas pipeline network. (3) Based on the regulation of gas data, the regulation offset distribution can be determined, which can determine the deviation of the control components and lay the foundation for the correction process. By determining the regulation compensation amount through the regulation offset distribution, the Internet of Things system can accurately correct its own regulation deviation during operation, which can reduce the gas runaway problem caused by control component failure or valve failure. This is conducive to realizing the automated remote regulation of gas and improving the stability and safety of the gas pipeline network. Attached Figure Description

[0009] 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: Figure 1 This is a platform schematic diagram of an IoT system for remote control and monitoring of smart gas pipeline valves, as shown in some embodiments of this specification. Figure 2 This is an exemplary flowchart of a remote control and monitoring method for intelligent gas pipeline valves, as shown in some embodiments of this specification. Figure 3 This is an exemplary schematic diagram illustrating the determination of deployment parameters according to some embodiments of this specification; Figure 4 This is an exemplary schematic diagram illustrating the determination of the amount of regulatory compensation according to some embodiments of this specification. Detailed Implementation

[0010] The accompanying drawings used in the description of the embodiments will be briefly introduced below. The drawings do not represent all embodiments.

[0011] In the embodiments of the present invention, when describing the operations performed step by step, unless otherwise specified, the order of the steps is interchangeable, the steps can be omitted, and other steps may be included in the operation process.

[0012] Figure 1 This is a schematic diagram of the platform structure of an IoT system for remote control and monitoring of smart gas pipeline valves, as shown in some embodiments of this specification.

[0013] In some embodiments, such as Figure 1 As shown, the intelligent gas pipeline valve remote control and monitoring IoT system 100 may include a government safety supervision and management platform 110, a government safety supervision sensor network platform 120, a government safety supervision object platform 130, a gas company sensor network platform 140, a gas equipment object platform 150, and a gas maintenance object platform 160. The government safety supervision object platform 130 may include a gas company management platform 131, the gas equipment object platform 150 may include at least one control component, and the gas maintenance object platform 160 may include at least one human interaction device.

[0014] The government security supervision and management platform 110 refers to the platform used by the government for security supervision and management, which can be configured as a processor and / or server.

[0015] In some embodiments, the government safety supervision and management platform 110 can communicate with the gas company management platform 131 through the government safety supervision sensor network platform 120.

[0016] The government security supervision sensor network platform 120 refers to a platform for the government to supervise and manage the security of sensor network information, which can be configured as communication equipment and / or servers.

[0017] The government safety supervision object platform 130 refers to an object platform for generating sensing information and executing control information, and can be configured as a processor and / or a server. In some embodiments, the government safety supervision object platform 130 may include a gas company management platform 131.

[0018] The gas company management platform 131 refers to a comprehensive management platform for gas company information, which can be configured as a processor and / or server and storage.

[0019] In some embodiments, the gas company management platform 131 can be configured to execute a method for remote control and monitoring of smart gas pipeline valves. More details regarding this method can be found in [link to relevant documentation]. Figure 2 Related descriptions.

[0020] The gas company sensor network platform 140 refers to the comprehensive management platform for the gas company's sensor information, and can be configured as a communication device and / or a server. In some embodiments, the gas company sensor network platform 140 can be used for communication interaction between the gas company management platform 131 and the gas equipment object platform 150 and the gas maintenance object platform 160.

[0021] The gas equipment object platform 150 refers to a functional platform for real-time remote control of gas pipeline networks. In some embodiments, the gas equipment object platform 150 may include at least one control component.

[0022] A control component refers to a component used for remotely controlling valves in a pipeline network. In some embodiments, a control component can remotely regulate one or more valves on a gas pipeline to control the gas transmission within the pipeline by controlling the valve opening.

[0023] The process of the control component regulating the valve may include adjusting the valve opening from the current initial opening to the expected opening, and then restoring the valve opening to the initial opening after monitoring the gas data. The expected opening can be preset manually based on actual conditions.

[0024] The gas maintenance platform 160 refers to a platform for interaction with gas users. Gas users are individuals or businesses that use gas, such as gas pipeline workers (e.g., component installers, pipeline monitors). The gas maintenance platform 160 may include at least one user interaction device, such as a mobile phone or computer.

[0025] In some embodiments, the smart gas pipeline valve remote control and monitoring IoT system 100 may further include a processor. The processor can process data and / or information related to the smart gas pipeline valve remote control and monitoring IoT system 100. Based on this data, information, and / or processing results, the processor can execute program instructions to perform one or more functions described in this application. In some embodiments, the processor may include one or more sub-processing devices (e.g., a single-core processing device, a multi-core multi-chip processing device, etc.). By way of example only, the processor may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or any combination thereof.

[0026] In some embodiments, the processor can interact with multiple platforms included in the smart gas pipeline valve remote control and monitoring IoT system 100, or can be configured on multiple platforms.

[0027] In some embodiments of this specification, the IoT system for remote control and supervision of smart gas pipeline valves can form a closed loop of information operation between various functional platforms, and operate in a coordinated and regular manner under the unified management of the gas company's management platform, thereby realizing the informatization and intelligentization of remote control and supervision of smart gas pipeline valves.

[0028] Figure 2 This is an exemplary flowchart of a remote control and monitoring method for intelligent gas pipeline valves, as shown in some embodiments of this specification.

[0029] In some embodiments, process 200 can be implemented based on the smart gas pipeline valve remote control and monitoring IoT system 100, and can be executed by the gas company management platform 131 within the smart gas pipeline valve remote control and monitoring IoT system 100. For example, it can be executed by a processor within the gas company management platform 131. Figure 2 As shown, process 200 includes the following steps.

[0030] Step 210: Obtain pipeline information and performance parameters of control components from the gas equipment object platform via the gas company's sensor network platform, and upload the performance parameters to the government safety supervision and management platform via the government safety supervision sensor network platform.

[0031] Pipeline network information refers to information related to the gas pipeline network in the current area. Pipeline network information may include valve locations. Valves can be control valves installed inside gas pipelines within the current area to control the flow rate, velocity, and pressure of the gas within the pipeline. Valve locations can be represented by coordinates, etc.

[0032] The current area refers to the area where control components need to be deployed. One or more control components need to be deployed in the current area, and each control component can control one or more valves. In some embodiments, the control components to be deployed in the current area are control components with the same performance parameters.

[0033] Performance parameters may include maximum communication distance and maximum number of valve connections.

[0034] Maximum communication distance refers to the maximum distance at which the control component can communicate with the valve.

[0035] The maximum number of valve connections refers to the maximum number of valves that the control component can communicate with. The control component can control the valves that it communicates with.

[0036] In some embodiments, the gas equipment object platform can obtain the performance parameters of the control components based on the factory parameters of the control components, and obtain pipeline information based on the installation records; the gas company management platform can obtain the pipeline information and the performance parameters of the control components from the gas equipment object platform through the gas company sensor network platform, and upload the performance parameters to the government safety supervision management platform through the government safety supervision sensor network platform, so that the government safety supervision management platform can confirm the performance parameters.

[0037] Step 220: In response to receiving the parameter confirmation instruction issued by the government safety supervision and management platform, determine the deployment parameters based on the pipeline network information and performance parameters, and upload the deployment parameters to the government safety supervision and management platform via the government safety supervision sensor network platform.

[0038] A parameter confirmation command is a command that confirms that the performance parameters are correct.

[0039] In some embodiments, the parameter confirmation instruction can be generated by the government safety supervision and management platform after confirming the performance parameters, and then sent to the gas company's management platform through the government safety supervision sensor network platform.

[0040] Layout parameters may include the location of control components and the covered valves.

[0041] The placement location refers to the location where the control components are placed. The placement location can be represented by location coordinates, etc.

[0042] A covered valve refers to a valve that the control component can control at its designated location. The distance between the covered valve's location and the control component's location is less than the control component's maximum communication distance.

[0043] In some embodiments, the processor can determine the deployment parameters in various ways based on network information and performance parameters.

[0044] For example, the processor can construct multiple first reference vectors based on pipeline network information from other regions and performance parameters of control components in other regions; construct a first feature vector based on pipeline network information and performance parameters of control components in the current region; determine the first reference vector with the highest vector similarity to the first feature vector and use it as the first target vector; perform equivalent processing between the region corresponding to the first target vector and the current region, and project the actual deployment parameters of the region corresponding to the first target vector onto the current region as the deployment parameters of the current region. Here, "other regions" refers to regions where control components have already been deployed. Equivalent processing methods may include coordinate system overlap, etc.

[0045] In some embodiments, the processor can also determine the control association group based on the pipeline network information; and determine the deployment parameters based on the control association group and the performance parameters of the control components. For more information on this section, please refer to [link to relevant documentation]. Figure 3 And related descriptions.

[0046] Step 230: In response to receiving the deployment confirmation instruction issued by the government safety supervision and management platform, the deployment parameters are sent to the gas maintenance target platform via the gas company's sensor network platform so that staff can be arranged to deploy the components.

[0047] A deployment confirmation instruction is an instruction confirming that components have been deployed according to deployment parameters. In some embodiments, the deployment confirmation instruction may be generated by the government safety supervision and management platform after confirming the deployment parameters, and then sent to the gas company's management platform through the government safety supervision sensor network platform.

[0048] In some embodiments, after the gas company's management platform receives the deployment confirmation instruction, it can send the deployment parameters to the gas maintenance object platform via the gas company's sensor network platform. Staff can obtain the deployment parameters through the personnel interaction device and deploy the control components according to the deployment parameters.

[0049] Step 240: After the deployment is completed, the control compensation amount of the control component is determined based on the correction cycle, and the control compensation amount is uploaded to the government safety supervision and management platform via the government safety supervision sensor network platform.

[0050] The correction cycle refers to the time interval for periodically correcting the control components.

[0051] In some embodiments, due to control component failure or valve failure (e.g., control component calibration failure, valve rust, etc.), the control component may have an offset during valve regulation.

[0052] Offset refers to the deviation in valve control, which can be expressed as the difference between the actual valve opening after control component adjustment and the expected opening. Control compensation is the amount used to compensate for the offset during valve control. For example, if the expected valve opening is 20° and the actual opening after adjustment is 18°, the valve offset is -2°. Therefore, the expected valve opening needs to be set to 22° before control component adjustment to ensure the actual opening reaches 20°. Thus, the control compensation for this valve is +2°.

[0053] In some embodiments, the amount of regulation compensation of the control component can be represented by a sequence of the negative numbers of the offsets of all the covered valves of the control component.

[0054] For example, the offsets of cover valve 1, cover valve 2, ..., cover valve n of control component A are +1°, -3°, ..., +2°, respectively, where n represents the total number of cover valves of control component A. Then the adjustment compensation amount of control component A can be expressed as (-1, +3, ..., -2).

[0055] In some embodiments, the processor determining the amount of regulation compensation of the control component based on the correction cycle may include performing steps 241 and 242 below within the correction cycle.

[0056] Step 241: Based on the control parameter group, the control component controls the covering valve to obtain the control gas data pair.

[0057] A control component's parameter set can include the expected opening degrees of all covered valves of that control component. The parameter set can be preset manually based on actual conditions.

[0058] In some embodiments, the processor can control the control component based on the control parameter group to adjust the corresponding cover valve from the current initial opening to the expected opening, and after monitoring and acquiring the gas data after valve adjustment, restore the opening of the cover valve to the initial opening.

[0059] The controlled gas data pairs can include pipeline gas data before and after valve control. Pipeline gas data can include gas flow rate, gas velocity, and gas pressure within the pipeline. A single control action by one control component generates multiple controlled gas data pairs covering multiple valves of that control component.

[0060] In some embodiments, the processor can acquire pipeline gas data before valve regulation and pipeline gas data after valve regulation based on sensors deployed in the pipeline, thereby obtaining a regulated gas data pair.

[0061] Step 242: Determine the control compensation amount based on the control gas data pair and control parameter group.

[0062] In some embodiments, the processor can determine the amount of control compensation in various ways based on the control gas data pair and the control parameter group.

[0063] For example, the processor can construct multiple second reference vectors based on historical control gas data pairs and historical control parameter sets corresponding to multiple historical control components in multiple historical controls; for a control component under current control, a second feature vector is constructed based on the control gas data pairs and control parameter sets corresponding to that control component; the second reference vector with the highest vector similarity to the second feature vector is determined and used as the second target vector; the historical actual control compensation amount corresponding to the second target vector is used as the control compensation amount of the current control component.

[0064] In some embodiments, the processor can also determine the control offset distribution of the control component based on the controlled gas data pairs and the control parameter set; and determine the control compensation amount based on the control offset distribution. Further details on this part can be found in [link to relevant documentation]. Figure 4 And related descriptions.

[0065] In some embodiments, the gas company's management platform can upload the control compensation amount to the government safety supervision and management platform via the government safety supervision sensor network platform. Staff on the government safety supervision and management platform confirm the control compensation amount to generate a correction confirmation instruction, which is then sent to the gas company's management platform via the government safety supervision sensor network platform.

[0066] Step 250: In response to the correction confirmation instruction issued by the government safety supervision and management platform, the correction control component is adjusted based on the compensation amount.

[0067] A correction confirmation instruction is an instruction that confirms the correctness of the adjustment compensation amount and corrects the control components.

[0068] In some embodiments, in response to receiving a correction confirmation command, the processor can correct the control component based on the adjustment compensation amount. For example, if the adjustment compensation amount corresponding to the cover valve 1 of control component A is +2°, then the expected opening degree of the cover valve 1 of control component A will be increased by 2°.

[0069] In some embodiments of this specification, uploading performance parameters and deployment parameters to the government's safety management platform can facilitate government supervision and control of the deployment process. Determining deployment parameters based on pipeline information and the performance parameters of the control components allows the control components to connect as many valves as possible, improving resource utilization. Determining the control component's regulation compensation amount based on the correction cycle, and periodically correcting the control component based on the regulation compensation amount, can promptly avoid inaccurate valve regulation caused by control component or valve failures. This ensures that parameters such as gas flow, pressure, and temperature are within the set range, reducing the risk of gas runaway, thereby improving operational safety and realizing automated remote monitoring and intelligent control of gas.

[0070] Figure 3 This is an exemplary schematic diagram illustrating the determination of layout parameters according to some embodiments of this specification.

[0071] In some embodiments, the pipeline information may also include valve type and valve-pipe type. For example... Figure 3 As shown, the processor can determine the control association group 320 based on the pipeline network information 310; and determine the deployment parameters 340 based on the control association group 320 and the performance parameters 330 of the control components.

[0072] Valve types can include ball valves, gate valves, pressure reducing valves, etc. Valve pipeline type refers to the type of gas pipeline in which the valve is located. Pipeline types can be classified in several ways. For example, based on the pipeline's purpose, pipeline types can be classified as gas transmission pipelines, gas distribution pipelines, and user access pipelines.

[0073] Control association grouping refers to the grouping category corresponding to the valve. In some embodiments, each control association grouping may include one or more valves.

[0074] In some embodiments, the processor can determine control-related groups based on pipeline network information using a clustering algorithm. The processor can construct multiple cluster vectors based on the pipeline network information, where each cluster vector consists of the valve location, valve pipeline type, and valve type. The processor then clusters these multiple vectors using a clustering algorithm to form a predetermined number of clusters. Valves within a cluster are then grouped into a control-related group. The clustering algorithm can be one with a predetermined number of clusters, such as the K-means clustering algorithm.

[0075] In some embodiments, the preset number of clusters may be related to the maximum communication distance performance parameter. The processor can mesh the current region with the maximum communication distance as the grid edge length, and determine the number of meshed grids as the preset number of clusters. For information on the current region, maximum communication distance performance parameter, etc., please refer to [link to relevant documentation]. Figure 2 And related content.

[0076] In some embodiments, the processor may determine the deployment parameters in various ways based on the performance parameters of the control and association groups and control components.

[0077] For example, the processor can count the number of valves in each control association group. For a control association group: in response to the number of valves in the control association group being greater than the maximum number of valve connections of the control component, the area corresponding to the control association group is divided into multiple sub-regions according to preset division conditions. The center of each sub-region is set as the deployment location of multiple control components, and the valves in each sub-region are respectively used as the covered valves of their respective control components. The preset division condition is to minimize the number of sub-regions while ensuring that the number of valves in each sub-region does not exceed the maximum number of valve connections of the control component.

[0078] For a control association group: in response to the number of valves in the control association group being less than or equal to the maximum number of valve connections of the control component, the center of the area corresponding to the control association group is set as the placement location of a control component, and the valves in the area are used as the covered valves of the corresponding control component; based on the placement location and covered valves of each control association group, the placement parameters are determined.

[0079] The region corresponding to a control association group can refer to an area that can cover all valves within the control association group. The region selection method can be set manually or by the system. For example, the smallest rectangle that can cover all valves within a control association group can be used as the region corresponding to that control association group.

[0080] In some embodiments, such as Figure 3 As shown, the processor can generate a deployment location group 350 based on the control association group 320; construct a valve map 360 based on the deployment location group 350 and performance parameters 330; and determine the deployment parameters 340 based on the valve map 360 through a parameter determination model 370, where the parameter determination model is a machine learning model.

[0081] In some embodiments, a deployment location group may include multiple deployment locations corresponding to multiple control components.

[0082] In some embodiments, for a control association group, the processor can randomly select multiple points from the area corresponding to the control association group as multiple deployment positions of the control component corresponding to the control association group, randomly select one from the multiple deployment positions corresponding to each control association group to form a deployment position group, and generate multiple deployment position groups based on multiple random selections.

[0083] A valve diagram is a graphical model that shows valves and their interrelationships. In some embodiments, a valve diagram may include multiple nodes and multiple edges.

[0084] The nodes in the valve diagram include the first node, the second node, and the third node.

[0085] The first node is the valve. The node characteristics of the first node may include the valve location, valve type, and the pipe type of the pipeline it is located in.

[0086] The second node is the deployment location.

[0087] The third node is a communication device. The node characteristics of the third node can include the location of the communication device and communication parameters. The communication device can be used for pipeline network communication, as well as for remote communication between control components and remote equipment (such as a gas company management platform). The communication device can be a network base station, etc. The location of the communication device is a manually uploaded known location (e.g., the construction location of a network base station), and the communication parameters can include communication range, communication bandwidth, signal strength, etc.

[0088] In some embodiments, the edges of the valve map may include first-type edges, second-type edges, third-type edges, and fourth-type edges. The edge features of the first-type edges and second-type edges include the communication distance between connected nodes, and the edge features of the third-type edges include pipeline gas data, valve pipeline type, and pipeline fluctuation characteristics.

[0089] The first type of edge is used to connect a first node and a second node that satisfy a preset connection condition. The preset connection condition is that the communication distance between the first node and the second node is less than the maximum communication distance. In some embodiments, if the communication distance between the first node and multiple second nodes is less than the maximum communication distance, then the first node is connected to the second node with the shortest communication distance, and the resulting edge is called a first type edge. Each first node corresponds to only one first type edge. The communication distance between connected nodes can be represented by the straight-line distance between the nodes.

[0090] In some embodiments, when there is no first type edge between the first node M1 and any second node, but the first node M2 ​​in the same control association group as the first node M1 has a first type edge with the second node W1, the first node M1 and the second node W1 are connected to form a second type edge.

[0091] The third type of edge is used to connect two first nodes that have an actual pipeline connection.

[0092] Type 4 edges are used to connect the third node to the second nodes within the communication range of the third node. The communication range of the communication device corresponding to the third node is generally large, so it can be assumed that the third node in a valve diagram is connected to all second nodes by Type 4 edges.

[0093] Pipeline fluctuation characteristics refer to features that reflect the fluctuation of gas data within a pipeline. In some embodiments, the processor can use the ratio of the standard deviation to the mean of gas flow rate at multiple time points over a period of time as the pipeline fluctuation characteristic; the smaller the ratio, the higher the pipeline stability.

[0094] In some embodiments of this specification, the information range covered by the valve map is expanded by constructing four types of edges, so that the valve map can not only include the location information of the valves, but also show the communication distance between valves and the pipeline information connected to each valve. This is beneficial for more accurately evaluating the communication efficiency between the control components and the valves and the pipeline status, thereby optimizing the layout and control strategy of the control components.

[0095] In some embodiments, the processor can determine the edges and nodes of the valve map based on pipeline network information, deployment location groups, and performance parameters. One deployment location group corresponds to one valve map.

[0096] A parameter determination model is a model used to determine the layout parameters. In some embodiments, the parameter determination model can be a machine learning model, such as a graph neural network (GNN).

[0097] In some embodiments, the input to the parameter determination model may include a valve graph, and the output may include the communication delay of the first type of edge and the communication delay of the second type of edge in the valve graph.

[0098] In some embodiments, communication delay can be represented by the time required for signal transmission.

[0099] In some embodiments, the parameter determination model can be obtained through training in various ways. For example, it can be obtained by training multiple training samples with training labels.

[0100] Training samples and training labels can be obtained based on historical data. For example, training samples can be sample valve maps constructed based on historical data (including historical pipeline network information, historical deployment location groups, and historical performance parameters of historical control components). The construction method for sample valve maps can be found in the valve map construction process described above. The training labels corresponding to the training samples are the historical actual communication delays of the first type of edges and the second type of edges corresponding to the sample valve maps. Training labels can be manually labeled.

[0101] In some embodiments, the processor can input the sample valve map into the initial parameter determination model, determine the communication delay of the first type of edge and the second type of edge based on the output of the initial parameter determination model, construct a loss function with the training labels, update the initial parameter determination model based on the loss function, and complete the training of the initial parameter determination model when a preset condition is met, thus obtaining a trained parameter determination model. The preset condition may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0102] In some embodiments, training of the parameter determination model may include training based on a training set, validating based on a validation set, and testing based on a test set; the training set, validation set, and test set are datasets composed of historical pipeline information, historical deployment location groups, and historical performance parameters of historical control components; the data volume of the training set, validation set, and test set constitutes a preset ratio, and there is no data overlap between the training set, validation set, and test set; the sample learning rate in model training is related to the sample accident probability.

[0103] The training set refers to the dataset used to train the internal parameters of a model.

[0104] A validation set is a dataset used to validate the model's state and convergence during training. Validation sets can be used to determine hyperparameters, monitor for overfitting, and determine when to stop training.

[0105] A test set is a dataset used to test a model's generalization ability. After using the validation set to determine hyperparameters and the training set to tune intrinsic parameters, the test set can be used to determine whether the model is running and its performance.

[0106] In some embodiments, historical pipeline network information, historical deployment location groups, and historical performance parameters of historical control components can constitute a data set for obtaining corresponding sample valve profiles. The training set, validation set, and test set each consist of multiple data sets.

[0107] The preset ratio refers to the preset proportion of data included in the training set, validation set, and test set. In some embodiments, the preset ratio can be set by system default or by technical personnel based on experience. For example, the preset ratio can be 8:1:1.

[0108] Data overlap refers to the presence of the same data in different sets, meaning the same data is used in multiple sets. In some embodiments, there is no data overlap between the training set, validation set, and test set; that is, a data set is included in only one of the training set, validation set, and test set.

[0109] In some embodiments, the sample learning rate during model training can be correlated with the sample accident probability. For example, the higher the sample accident probability, the higher the sample learning rate.

[0110] In some embodiments, for each sample valve pattern, the processor can calculate the interval between the occurrence time and the control time of each accident occurring in the region corresponding to the sample valve pattern, and determine the sample story probability by normalizing the ratio of the average of the intervals corresponding to multiple accidents to a preset time length.

[0111] The accident occurrence time refers to the point in time when an accident occurs in the area corresponding to the sample valve map. The control time refers to the point in time when the valves in the sample valve map are controlled after the accident occurs. In some embodiments, the processor can directly obtain the accident occurrence time and control time of each accident corresponding to the sample valve map from historical data. The preset time length can be set by the processor by default or manually based on experience. For example, the preset time length can be the average of the time intervals between the occurrence times of multiple historical accidents in the historical data.

[0112] In some embodiments of this specification, the model is trained in stages by dividing historical data into training, validation and test sets, and the learning rate of the samples is dynamically adjusted according to the probability of sample accidents. This avoids overfitting caused by data crossover and improves the accuracy and adaptability of the model's prediction parameters.

[0113] In some embodiments, the processor can input multiple valve maps corresponding to multiple deployment location groups into parameters to determine the model, output the communication delay of the first type of edge and the communication delay of the second type of edge respectively, filter out valve maps that meet the filtering conditions according to the model output results, determine the second nodes included in them as the deployment locations of the control components, determine the first nodes connected to each second node through the first type of edge or the second type of edge as the covering valves of the corresponding control components, and merge the deployment locations and covering valves into deployment parameters.

[0114] The filtering criteria can be that, in the valve diagram, the communication latency of the first type of edges exceeding a preset proportion is less than a communication latency threshold, and the communication latency of the second type of edges exceeding a preset proportion is less than a communication latency threshold. The preset proportion and communication latency threshold can be set by the processor by default or by technicians based on experience.

[0115] In some embodiments of this specification, valve maps are constructed by combining the performance parameters of the control components with the control association groups, so that the valve relationships and characteristics in the pipeline network can be graphically presented. This helps to enhance the understanding of the overall structure of the pipeline network when carrying out control work, and then the machine learning model can be used to accurately determine the layout parameters, improve the level of intelligent decision-making, and ensure the scientificity and effectiveness of the layout of control components.

[0116] In some embodiments of this specification, valves are grouped based on their valve location, valve pipeline type, and valve type. This allows for independent management of valves for specific functions or areas. The deployment parameters are determined by combining this grouping with the performance parameters of the control components. This ensures that the control components can effectively regulate the covered valves while avoiding resource waste, thereby improving the regulation accuracy and resource utilization efficiency of the gas pipeline network.

[0117] Figure 4 This is an exemplary schematic diagram illustrating the determination of the amount of regulatory compensation according to some embodiments of this specification.

[0118] In some embodiments, such as Figure 4 As shown, the processor can determine the control offset distribution 430 of the control component based on the control gas data pair 410 and the control parameter group 420; and determine the control compensation amount 440 based on the control offset distribution 430. The control offset distribution includes the offset of at least one control component's covering valve. More information on the control gas data pair, control parameter group, and control compensation amount can be found in [link to relevant documentation]. Figure 2 Related descriptions.

[0119] In some embodiments, the control offset distribution may include the offset of a control component covering a valve. Further details regarding offset can be found in [link to relevant documentation]. Figure 2 Related descriptions.

[0120] In some embodiments, the processor can determine the control offset distribution of the control component in a variety of ways based on the control gas data pair and the control parameter group.

[0121] For example, for each covered valve of the control component, the processor can determine the rate of change of gas flow rate and the rate of change of gas velocity before and after valve adjustment based on the controlled gas data pair. The rate of change of gas flow rate is represented by the ratio of the absolute value of the difference between the pipe gas flow rate before and after adjustment to the pipe gas flow rate before adjustment; the rate of change of gas velocity is similarly determined. Based on the rate of change of gas flow rate and the rate of change of gas velocity, the actual change amplitude of the covered valve is determined by querying a preset relationship table. The actual change amplitude refers to the actual change in valve opening before and after adjustment, represented by the actual opening of the covered valve after adjustment minus the initial opening of the covered valve before adjustment. The actual opening of the valve after adjustment is obtained by adding the actual change amplitude to the current opening of the valve. The expected opening of the valve is obtained based on the control parameter set. The difference between the actual opening and the expected opening is determined as the offset of the covered valve. The offset of each covered valve of each control component is calculated to determine the control offset distribution.

[0122] The preset relationship table can be constructed manually through experiments. For example, technicians can introduce gas into the experimental pipeline and repeatedly adjust the opening of the experimental valve (the experimental valve must be rust-free, non-aging, and functioning correctly). During each experiment, the valve change range (e.g., valve rotation angle) is recorded, along with the gas flow rate and velocity before and after adjustment. Based on the gas flow rate before and after adjustment, the gas flow rate change rate is calculated, and the gas velocity change rate can be obtained similarly. Based on the correspondence between the gas flow rate change rate, gas velocity change rate, and valve change range in each experiment, a preset relationship table is constructed.

[0123] In some embodiments, such as Figure 4As shown, for each control component, the processor can determine the actual control degree 450 of the control component based on the controlled gas data pair 410 and the control parameter group 420; in response to the actual control degree 450 being less than the control threshold 460, a fault command 470 is determined and sent to at least one human interaction device; in response to the actual control degree 450 being greater than or equal to the control threshold 460, the processor can determine the control offset component 480 of the control component based on the controlled gas data pair 410 and the control parameter group 420; and determine the control offset distribution 430 based on the control offset component 480 of at least one control component.

[0124] Actual controllability refers to a parameter used to measure the control effect of a control component. The larger the actual controllability, the better the control effect of the control component on the covered valve.

[0125] In some embodiments, the processor can determine the actual change range of the covered valve of the control component based on the controlled gas data pair; determine the expected change range of the covered valve of the control component based on the control parameter set; and determine the actual control degree of the control component based on the actual change range and the expected change range, with the weights related to the pipeline fluctuation characteristics of the pipeline where the valve is located.

[0126] For an explanation of how to determine the actual magnitude of change based on controlled gas data, please refer to the relevant description above.

[0127] The expected change range refers to the expected change in valve opening before and after regulation.

[0128] In some embodiments, the processor can obtain the expected opening degree of the covered valve after adjustment based on the adjustment parameter group, and use the difference between the expected opening degree after adjustment and the current actual opening degree before adjustment as the expected change range.

[0129] In some embodiments, the processor can determine the actual degree of control of the control component by weighting the actual and expected changes in the multiple covered valves of the control component. For example, the actual degree of control of control component A can be calculated using the following formula (1): (1) in, To control the actual degree of control of component A, For the first control component A The weight of each covered valve, For the first control component A The actual variation range of each covered valve For the first control component A The expected range of change for each covered valve, The number of valves covering the control components.

[0130] In some embodiments, the weight of a covered valve is related to the pipe ripple characteristics of the pipeline containing the valve. The greater the pipe ripple characteristics of the pipeline containing the valve, the smaller the weight of the covered valve. For further explanation of pipe ripple characteristics, see [link to relevant documentation]. Figure 3 The relevant description in the document.

[0131] In some embodiments of this specification, based on the controlled gas data pairs and the pairing relationship between the controlled gas data pairs and the valve opening, the actual change range of the covered valve can be accurately determined; the actual control degree of the control component is determined by weighting the actual change range and the expected change range, thereby quantifying the control effectiveness; and the weights are determined based on the pipeline fluctuation characteristics, which can reduce the impact of gas pipelines with large gas fluctuations on the gas data, thereby improving the overall reliability of the actual control degree.

[0132] In some embodiments, the control threshold may be determined by the average valve criticality of multiple covered valves of the control component, wherein the higher the average valve criticality, the higher the control threshold.

[0133] Valve criticality refers to the degree of importance of a valve. In some embodiments, the valve criticality of a covered valve can be calculated using the following formula (2): (2) in, To cover the criticality of valves. To cover the number of associated downstream branches of the valve, To cover the valve's historical maintenance timeliness, , This is a preset constant.

[0134] The number of associated downstream branches refers to the number of downstream valves directly connected to the covered valve. Historical maintenance timeliness can be negatively correlated with the average response time. The average response time refers to the average response time from the generation of the fault command to the commencement of maintenance across multiple historical faults of the covered valve.

[0135] Fault commands may include control components that trigger fault alarms and their corresponding overriding valves.

[0136] In some embodiments, in response to the actual control degree of the control component being less than the control threshold, the processor can determine that there is a control abnormality or a performance degradation of the control component, generate a fault command, and send the fault command to the personnel interaction device of the gas maintenance object platform via the gas company's sensor network platform, so as to arrange staff to carry out fault investigation and repair.

[0137] The control offset component refers to the component corresponding to each control component in the control offset distribution.

[0138] In some embodiments, in response to the actual degree of control of the control component being greater than or equal to a control threshold, the processor can determine the actual and expected opening degrees of each covering valve of the control component based on the controlled gas data pair and the control parameter set; determine the difference between the actual and expected opening degrees as the offset of the covering valve; and calculate the offset of each covering valve of the control component to determine the control offset component. Further details regarding the above process can be found in the relevant description above.

[0139] In some embodiments, the processor may combine the control offset components of all control components that have not generated fault instructions to determine a control offset distribution.

[0140] In some embodiments of this specification, the actual control degree is determined by adjusting gas data pairs and control parameter groups, thereby quantifying the control effect of the control components. Simultaneously, by comparing the actual control degree with the control threshold, anomalies can be quickly identified when the actual control degree is too low, allowing for timely issuance of fault commands. This accelerates fault response and maintenance processes, reducing potential safety hazards. For components that meet or exceed the control threshold, the control strategy is optimized by calculating the control offset component, ensuring control accuracy and improving the overall operating efficiency and reliability of the gas pipeline network.

[0141] In some embodiments, the processor can determine the offset of each covered valve of each control component based on the control offset distribution; and use the inverse of the offset as the control compensation amount.

[0142] In some embodiments of this specification, the deviation of the control component can be determined based on the control gas data, laying the foundation for the correction process. By determining the control compensation amount through the control deviation distribution, the Internet of Things system can accurately correct its own control deviation during operation, which can reduce the gas runaway problem caused by control component failure or valve failure, which is conducive to realizing automated remote control of gas and improving the stability and safety of gas pipeline network.

[0143] The embodiments described in this invention are merely illustrative and do not limit the scope of the invention. Various modifications and alterations that can be made by those skilled in the art under the guidance of this invention are still within its scope.

[0144] Furthermore, certain features, structures, or characteristics in one or more embodiments of the present invention can be appropriately combined.

[0145] If there is any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the appended materials of this invention and the content described in this invention, the descriptions, definitions, and / or terminology used in this invention shall prevail.

Claims

1. A smart gas pipeline network valve remote control and monitoring IoT system, characterized in that, The Internet of Things system includes a government safety supervision and management platform, a government safety supervision object platform, a gas equipment object platform, and a gas maintenance object platform. The government safety supervision platform includes a gas company management platform, the gas equipment platform includes at least one control component, and the gas maintenance platform includes at least one human interaction device. The gas company management platform is configured as follows: Obtain pipeline network information and performance parameters of the control components, and upload the performance parameters to the government safety supervision and management platform; In response to receiving a parameter confirmation instruction from the government safety supervision and management platform, the deployment parameters are determined based on the pipeline information and the performance parameters, and uploaded to the government safety supervision and management platform. The deployment parameters include the deployment location of the control components and the covered valves; In response to receiving the deployment confirmation instruction issued by the government safety supervision and management platform, the deployment parameters are sent to the gas maintenance target platform to arrange staff to deploy the components; After deployment is completed, the adjustment compensation amount of the control component is determined based on the correction cycle and uploaded to the government safety supervision and management platform. In response to receiving a correction confirmation instruction issued by the government safety supervision and management platform, the control component is corrected based on the adjustment compensation amount; The gas company management platform performs the following during the correction period: Based on the set of control parameters, the control component is controlled to regulate the covering valve to obtain a pair of regulated gas data. Based on the controlled gas data pair and the controlled parameter group, the controlled compensation amount is determined.

2. The system according to claim 1, characterized in that, The pipeline information also includes valve type and valve-pipe type, and the gas company management platform is further configured as follows: Based on the pipeline network information, determine the control-related groups; The deployment parameters are determined based on the regulation association group and the performance parameters of the control component.

3. The system according to claim 2, characterized in that, The gas company management platform is further configured as follows: Based on the aforementioned control association grouping, a deployment location group is generated; Based on the deployment location group and the performance parameters, a valve map is constructed; Based on the valve diagram, the layout parameters are determined by a parameter determination model, which is a machine learning model.

4. The system according to claim 1, characterized in that, The gas company management platform is further configured as follows: Based on the controlled gas data pair and the controlled parameter group, the controlled offset distribution of the control component is determined; the controlled offset distribution includes the offset of the covering valve of the at least one control component; The amount of regulatory compensation is determined based on the aforementioned regulatory offset distribution.

5. The system according to claim 4, characterized in that, The gas company management platform is further configured as follows: For each of the aforementioned control components, Based on the controlled gas data pair and the controlled parameter group, the actual control degree of the control component is determined; In response to the actual control degree being less than the control threshold, a fault command is determined and the fault command is sent to the at least one human interaction device; In response to the actual degree of regulation being greater than or equal to the control threshold, the regulation offset component of the control component is determined based on the regulated gas data pair and the regulation parameter group. The control offset distribution is determined based on the control offset component of the at least one control component.

6. A method for remote control and monitoring of valves in a smart gas pipeline network, characterized in that, The method is based on a smart gas pipeline valve remote control and monitoring IoT system, which includes a government safety supervision and management platform, a government safety supervision object platform, a gas equipment object platform, and a gas maintenance object platform. The government safety supervision platform includes a gas company management platform, the gas equipment platform includes at least one control component, and the gas maintenance platform includes at least one human interaction device. The method is executed by the gas company's management platform and includes: Obtain pipeline network information and performance parameters of the control components, and upload the performance parameters to the government safety supervision and management platform; In response to receiving a parameter confirmation instruction from the government safety supervision and management platform, the system determines the deployment parameters based on the pipeline network information and the performance parameters, and uploads them to the government safety supervision and management platform; the deployment parameters include the deployment location of the control components and the covered valves; In response to receiving the deployment confirmation instruction issued by the government safety supervision and management platform, the deployment parameters are sent to the gas maintenance target platform to arrange staff to deploy the components; After deployment is completed, the adjustment compensation amount of the control component is determined based on the correction cycle and uploaded to the government safety supervision and management platform. In response to receiving a correction confirmation instruction issued by the government safety supervision and management platform, the control component is corrected based on the adjustment compensation amount; The step of determining the adjustment compensation amount of the control component based on the correction cycle includes: Performed during the said correction cycle: Based on the set of control parameters, the control component is controlled to regulate the covering valve to obtain a pair of regulated gas data. Based on the controlled gas data pair and the controlled parameter group, the controlled compensation amount is determined.

7. The method according to claim 6, characterized in that, The pipeline network information also includes valve type and valve-pipe type. The step of determining the layout parameters based on the pipeline network information and the performance parameters includes: Based on the pipeline network information, determine the control-related groups; The deployment parameters are determined based on the regulation association group and the performance parameters of the control component.

8. The method according to claim 7, characterized in that, Determining the deployment parameters based on the regulation association group and the performance parameters of the control component includes: Based on the aforementioned control association grouping, a deployment location group is generated; Based on the deployment location group and the performance parameters, a valve map is constructed; Based on the valve diagram, the layout parameters are determined by a parameter determination model, which is a machine learning model.

9. The method according to claim 6, characterized in that, The step of determining the regulation compensation amount based on the regulated gas data pair and the regulated parameter group includes: Based on the controlled gas data pair and the controlled parameter group, the controlled offset distribution of the control component is determined; the controlled offset distribution includes the offset of the covering valve of the at least one control component; The amount of regulatory compensation is determined based on the aforementioned regulatory offset distribution.

10. The method according to claim 9, characterized in that, Determining the control offset distribution of the control component based on the controlled gas data pair and the control parameter group includes: For each of the aforementioned control components, Based on the controlled gas data pair and the controlled parameter group, the actual control degree of the control component is determined; In response to the actual control degree being less than the control threshold, a fault command is determined and the fault command is sent to the at least one human interaction device; In response to the actual degree of regulation being greater than or equal to the control threshold, the regulation offset component of the control component is determined based on the regulated gas data pair and the regulation parameter group. The control offset distribution is determined based on the control offset component of the at least one control component.

Images