Converter station multi-class heterogeneous terminal data acquisition method and device based on collaborative information model

Abstract

The invention discloses a collaborative information model-based converter station multi-class heterogeneous terminal data acquisition method and device, and the method comprises the steps: obtaining the operation state parameters of multi-class heterogeneous terminals in a current detection period of a converter station, and the multi-class heterogeneous terminals comprise a transformer, a converter valve and a smoothing reactor; performing feature fusion on the plurality of types of operation state parameters, and calculating a current prediction value of the operation state of the converter station based on a collaborative information model; and adjusting the operation state of the converter station in the next detection period based on the current prediction value of the operation state. Through real-time acquisition and fusion of multi-equipment state parameters, comprehensive monitoring and accurate prediction of the operation state of the converter station are realized, the real-time performance and accuracy of converter station data acquisition are improved, the adaptability of the system is enhanced, the accuracy of understanding of the overall operation state information of the converter station by a user is improved, and the user experience is improved. And stable operation of the smart power grid is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of converter station data collection, and in particular to a method and device for collecting data of multiple types of heterogeneous terminals in a converter station based on a collaborative information model. Background Art

[0002] Converter stations are key facilities in high-voltage direct current transmission systems, mainly used to convert alternating current into direct current or vice versa, to achieve long-distance, large-capacity, low-loss power transmission, and to achieve interconnection between different power grids. Converter stations usually include core equipment such as converter transformers, converter valves, smoothing reactors, filters, control systems, etc., and are an important component of efficient and stable operation of power systems.

[0003] It is extremely important to understand the operating status of key equipment in converter stations, as this is not only related to the stable supply and efficient operation of the power system, but also plays a decisive role in preventing equipment failures, reducing maintenance costs, and improving system reliability and safety. It also provides important data support for the optimized scheduling and predictive maintenance of smart grids.

[0004] The current daily monitoring of converter stations only focuses on the status of individual devices, while ignoring the overall operating status, which makes it impossible for users to fully evaluate the operating efficiency and stability of the converter station, and it is difficult to timely discover and respond to complex faults and potential risks across devices, missing opportunities to optimize system performance and preventive maintenance, increasing the possibility of unexpected power outages and large-scale failures, thereby affecting the reliability of power supply and the safety of the power grid. In addition, focusing only on the operating status of a single device also makes it impossible for users to fully understand the mutual information and synergy between devices, limiting the ability to understand and predict the overall safety status of the converter station. Summary of the invention

[0005] The purpose of the embodiment of the present invention is to provide a method and device for collecting data from multiple types of heterogeneous terminals in a converter station based on a collaborative information model. By acquiring and fusing status parameters of multiple devices in real time, comprehensive monitoring and accurate prediction of the operating status of the converter station are achieved, the real-time and accuracy of data collection in the converter station are improved, the adaptability of the system is enhanced, the accuracy of the user's understanding of the overall operating status information of the converter station is improved, and the stable operation of the smart grid is ensured.

[0006] In order to solve the above technical problems, a first aspect of an embodiment of the present invention provides a method for collecting data of multiple types of heterogeneous terminals in a converter station based on a collaborative information model, comprising the following steps:

[0007] Acquire operation status parameters of multiple types of heterogeneous terminals in a current detection cycle of a converter station, wherein the multiple types of heterogeneous terminals include: transformers, converter valves, and smoothing reactors;

[0008] Performing feature fusion on several types of operating status parameters, and calculating a current predicted value of the operating status of the converter station based on a collaborative information model;

[0009] Based on the current predicted value of the operating state, the operating state of the converter station in the next detection cycle is adjusted.

[0010] Furthermore, the multiple types of heterogeneous terminals include: transformers, converter valves and smoothing reactors;

[0011] The operating state parameters of the transformer include: load current value and insulation resistance value;

[0012] The operating state parameters of the converter valve include: converter valve voltage value, converter valve current value, trigger angle and cut-off angle;

[0013] The operating state parameters of the smoothing reactor include: a reactor current value and a reactor voltage drop value.

[0014] Furthermore, the feature fusion of several types of operating status parameters and calculation of the current predicted value of the operating status of the converter station based on the collaborative information model include:

[0015] Normalizing several types of operating status parameters;

[0016] Combined with several historical operating status detection values ​​of the converter station, characteristic value fusion is performed on several types of operating status parameters after normalization to calculate the current predicted value of the operating status of the converter station.

[0017] Furthermore, the current predicted value Z of the operating state t The calculation formula is:

[0018]

[0019] X t =[V value ,I value ,α,β,I transformer ,R insulation ,I reactor ,V drop ];

[0020] W=[ω1,ω2,ω3,ω4,ω5,ω6,ω7,ω8];

[0021] Among them, λ is the smoothing constant, X t is a one-dimensional operating state parameter matrix, W is a one-dimensional weight coefficient matrix, t is the serial number of the current detection cycle, ti is the serial number of the historical detection cycle, K is the number of historical detection cycles, θ t-i is the corresponding weight coefficient of the ti-th running status historical detection value, Zt-i is the historical detection value of the ti-th running state, V value is the voltage value of the converter valve, I value is the current value of the converter valve, α is the trigger angle, β is the cut-off angle, I transformer is the load current value, R insulation is the insulation resistance value, I reactor is the reactor current value, V drop is the weight coefficient of the reactor voltage drop, ω1 is the weight coefficient of the converter valve current value, ω2 is the weight coefficient of the converter valve current value, ω3 is the weight coefficient of the trigger angle, ω4 is the weight coefficient of the turn-off angle, ω5 is the weight coefficient of the load current value, ω6 is the weight coefficient of the insulation resistance value, ω7 is the weight coefficient of the reactor current value, and ω8 is the weight coefficient of the reactor voltage drop.

[0022] Furthermore, the current predicted value Z of the operating state t The calculation formula is:

[0023] Z t =σ1×V' value +σ2×I' value +σ3×α'+σ4×β'+σ5×I' transformer +σ6×R' insulation +σ7×I' reactor +σ8×V' drop ;

[0024]

[0025] α'=η 30 +η 31 ×α t-1 +η 32 ×α t-2 +…+η 3i ×α t-i +…+η 3K ×α t-K ;

[0026] β'=η 40 +η 41 ×β t-1 +η 42 ×β t-2 +…+η 4i ×β t-i +…+η 4K ×β t-K ;

[0027]

[0028] Among them, V v ' alueis the fitting value of the converter valve voltage, I' value is the fitting value of the converter valve current, α' is the fitting value of the trigger angle, β' is the fitting value of the turn-off angle, I t ' ransformer is the load current fitting value, R i ' nsulation is the insulation resistance fitting value, I' reactor is the reactor current fitting value, V d ' rop is the fitting value of the reactor voltage drop, σ1 to σ8 are the weight coefficients of the above parameters respectively, η 10 To 1K is the fitting coefficient of the real-time detection value and the historical detection value of the converter valve voltage value, η 20 To 2K is the fitting coefficient of the real-time detection value and the historical detection value of the converter valve current value, η 30 To 3K is the fitting coefficient of the real-time detection value and the historical detection value of the trigger angle, η 40 To 4K is the fitting coefficient of the real-time detection value and the historical detection value of the shut-off angle, η 50 To 5K is the fitting coefficient of the real-time detection value and the historical detection value of the load current value, η 60 To 6K is the fitting coefficient of the real-time detection value and the historical detection value of the insulation resistance value, η 70 To 7K is the fitting coefficient of the real-time detection value and the historical detection value of the reactor current value, η 80 To 8K is the fitting coefficient of the real-time detection value and the historical detection value of the reactor voltage drop value, ti is the serial number of the historical detection cycle, K is the number of the historical detection cycles, and t is the serial number of the current detection cycle.

[0029] Furthermore, the operating status parameters of the multiple types of heterogeneous terminals also include: equipment temperature values ​​and environmental humidity values ​​of transformers, equipment temperature values ​​and environmental humidity values ​​of converter valves, and equipment temperature values ​​and environmental humidity values ​​of smoothing reactors.

[0030] Further, adjusting the operating state of the converter station in the next detection cycle based on the current predicted value of the operating state includes:

[0031] When the current predicted value of the operating state is greater than a first preset threshold, it is determined that the converter station is in a normal operating state;

[0032] When the current predicted value of the operating state is less than or equal to the first preset threshold and greater than the second preset threshold, it is determined that the converter station is in an abnormal operating state and an abnormal alarm signal is issued;

[0033] When the current predicted value of the operating status is less than or equal to the second preset threshold, it is determined that the converter station is in a fault state and a fault alarm signal is issued.

[0034] Accordingly, a second aspect of an embodiment of the present invention provides a data collection device for multiple types of heterogeneous terminals in a converter station based on a collaborative information model, and data collection is performed on the converter station based on the data collection method for multiple types of heterogeneous terminals in a converter station based on a collaborative information model, including:

[0035] A data acquisition module, which is used to obtain operating status parameters of multiple types of heterogeneous terminals in the current detection cycle of the converter station, wherein the multiple types of heterogeneous terminals include: transformers, converter valves and smoothing reactors;

[0036] A feature fusion module, which is used to perform feature fusion on several types of operating status parameters and calculate the current predicted value of the operating status of the converter station based on a collaborative information model;

[0037] A state control module is used to adjust the operating state of the converter station in the next detection cycle based on the current predicted value of the operating state.

[0038] Correspondingly, a third aspect of an embodiment of the present invention provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the above-mentioned method for collecting data from multiple types of heterogeneous terminals in a converter station based on a collaborative information model.

[0039] Accordingly, a fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-mentioned method for collecting data from multiple types of heterogeneous terminals in a converter station based on a collaborative information model.

[0040] The above technical solution of the embodiment of the present invention has the following beneficial technical effects:

[0041] 1. Comprehensive acquisition of operating status parameters of different equipment and sensors in the converter station ensures the comprehensiveness of data collection and can reflect the operating status of the converter station from multiple angles;

[0042] 2. Through the rapid processing of real-time data and the fusion analysis of historical data, this method can not only monitor the current status of the converter station in real time, but also predict the short-term operation trend;

[0043] 3. Using collaborative information models, this method can effectively integrate data from different sources and types, achieve complementarity and collaboration between data, and improve data utilization efficiency and analysis accuracy;

[0044] 4. Through feature fusion and model calculation, the operating status of the converter station can be accurately evaluated, providing a scientific basis for operation and maintenance decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of a method for collecting data of multiple types of heterogeneous terminals in a converter station based on a collaborative information model provided by an embodiment of the present invention;

[0046] Figure 2 It is a module block diagram of a data collection device for multiple types of heterogeneous terminals in a converter station based on a collaborative information model provided by an embodiment of the present invention;

[0047] Figure 3 is a block diagram of a data acquisition module provided by an embodiment of the present invention;

[0048] Figure 4 It is a block diagram of a state control module provided by an embodiment of the present invention.

[0049] Reference numerals:

[0050] 1. Data acquisition module, 2. Feature fusion module, 21. Preprocessing unit, 22. Feature fusion unit, 3. State control module, 31. First determination unit, 32. Second determination unit, 33. Third determination unit. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0052] Please refer to Figure 1 A first aspect of an embodiment of the present invention provides a method for collecting data of multiple types of heterogeneous terminals in a converter station based on a collaborative information model, comprising the following steps:

[0053] Step S100, obtaining operating status parameters of multiple types of heterogeneous terminals in a current detection cycle of the converter station, where the multiple types of heterogeneous terminals include: transformers, converter valves and smoothing reactors.

[0054] In one implementation of an embodiment of the present invention, multiple types of heterogeneous terminals may include: transformers, converter valves and smoothing reactors; the operating status parameters of the transformers include: load current value and insulation resistance value; the operating status parameters of the converter valves include: converter valve voltage value, converter valve current value, trigger angle and shut-off angle; the operating status parameters of the smoothing reactors include: reactor current value and reactor voltage drop value.

[0055] The calculation process in this embodiment takes the above three key devices as an example to explain the entire data collection method and the subsequent control process in detail. The object protected by the present invention is the data collection method and the corresponding processing process of the converter station. The equipment of the converter station is not limited to the above three devices and their corresponding parameter types.

[0056] Step S200, feature fusion is performed on several types of operating status parameters, and the current predicted value of the operating status of the converter station is calculated based on the collaborative information model.

[0057] In the operation and maintenance management of converter stations, it is crucial to conduct real-time monitoring and data analysis of the operating status of multiple types of heterogeneous terminal equipment (e.g., transformers, converter valves, and smoothing reactors); by collecting the key operating parameters of these devices, such as the load current and insulation resistance of the transformer, the voltage and current of the converter valve and the trigger and shutdown angles, and the current and voltage drop of the smoothing reactor, a comprehensive feature set can be constructed. Using the collaborative information model, these features are fused and analyzed to calculate the current operating status prediction value of the converter station. This approach not only improves the monitoring capability of the individual status of the equipment, but also enhances the understanding and prediction of the overall operating status of the converter station, providing data support and decision-making basis for more efficient and reliable power system management.

[0058] Step S300: adjusting the operating state of the converter station in the next detection cycle based on the current predicted value of the operating state.

[0059] Based on the current predicted values ​​of the data operation status of various heterogeneous terminals, the operation status adjustment of the converter station in the next detection cycle is a dynamic optimization process; this process involves real-time monitoring and analysis of the status parameters of key equipment such as transformers, converter valves and smoothing reactors, and the use of collaborative information models to integrate these multi-source heterogeneous data to generate predicted values. These predicted values ​​guide users to make scientific decisions, such as adjusting loads, optimizing equipment parameters, arranging preventive maintenance or taking risk mitigation measures to ensure the stability and efficiency of the converter station in the future operation cycle. Through this data-driven approach, the converter station can achieve more accurate and efficient operation status management and improve the reliability and economy of the overall power system.

[0060] Specifically, in step S200, the features of several types of operating status parameters are fused, and the current predicted value of the operating status of the converter station is calculated based on the collaborative information model, including:

[0061] Step S210, normalizing several types of operating status parameters.

[0062] The purpose of normalizing several types of operating status parameters is to convert equipment status data of different dimensions and magnitudes into a unified and comparable range, usually between 0 and 1 or -1 to 1. This standardization process eliminates the impact of data scale differences, allowing status parameters from different equipment such as transformers, converter valves, and smoothing reactors to be analyzed and compared under the same standards. Normalization is an important step in data preprocessing, which helps to improve the accuracy of data analysis and the generalization ability of machine learning models, and ensures the reliability and effectiveness of condition monitoring and prediction models. In this way, equipment performance can be evaluated and compared more accurately, providing a reliable data basis for the operation, maintenance, and fault diagnosis of converter stations.

[0063] Step S220, combining several historical operating status detection values ​​of each converter station, performing feature value fusion on several types of operating status parameters after normalization, and calculating the current predicted value of the operating status of the converter station.

[0064] Combining multiple historical operating status detection values ​​of each converter station, the current predicted value of the converter station's operating status can be calculated by fusing the feature values ​​of the normalized state parameters. This involves collecting multiple types of heterogeneous data from key equipment (such as transformers, converter valves, and smoothing reactors), normalizing them to eliminate the impact of different dimensions, and then integrating them using feature fusion technology. Through the collaborative information model, these fused features are used to generate a comprehensive prediction value, thereby making an accurate assessment of the current operating status of the converter station and improving the accuracy of monitoring the converter station's operating status.

[0065] In a specific implementation of the embodiment of the present invention, the current predicted value Z of the running state t The calculation formula is:

[0066]

[0067] X t =|V value ,I value ,α,β,I transformer ,R insulation ,I reactor ,V drop |;

[0068] W=[ω1,ω2,ω3,ω4,ω5,ω6,ω7,ω8];

[0069] Among them, λ is the smoothing constant, X t is a one-dimensional operating state parameter matrix, W is a one-dimensional weight coefficient matrix, t is the serial number of the current detection cycle, ti is the serial number of the historical detection cycle, K is the number of historical detection cycles, θ t-i is the corresponding weight coefficient of the ti-th running status historical detection value, Z t-i is the historical detection value of the ti-th operating state, V value is the voltage value of the converter valve, I value is the current value of the converter valve, α is the trigger angle, β is the cut-off angle, I transformer is the load current value, R insulation is the insulation resistance value, I reactor is the reactor current value, V drop is the weight coefficient of the reactor voltage drop, ω1 is the weight coefficient of the converter valve current value, ω2 is the weight coefficient of the converter valve current value, ω3 is the weight coefficient of the trigger angle, ω4 is the weight coefficient of the turn-off angle, ω5 is the weight coefficient of the load current value, ω6 is the weight coefficient of the insulation resistance value, ω7 is the weight coefficient of the reactor current value, and ω8 is the weight coefficient of the reactor voltage drop.

[0070] Based on the current parameter values ​​of each device, the current predicted value of the operating status is calculated in combination with the weight coefficient and the historical value of the operating status. This can comprehensively consider multiple dimensions of equipment operation, reflect the importance of different parameters through the weight coefficient, and enhance the accuracy of the prediction. The use of historical data can reveal the long-term trends and potential patterns of equipment operation, thereby improving the reliability of the prediction. The data-driven approach can adapt to the dynamic changes in the operating status of the equipment, achieve real-time monitoring and rapid response, and thus optimize the operating efficiency and safety of the converter station.

[0071] In a specific implementation of the embodiment of the present invention, the current predicted value Z of the running state t The calculation formula is:

[0072] Z t =σ1×V' value +σ2×I' value +σ3×α'+σ4×β'+σ5×I' transformer +σ6×R' insulation +σ7×I' reactor +σ8×V' drop ;

[0073]

[0074] α'=η 30 +η 31 ×α t-1 +η 32×α t-2 +…+η 3i ×α t-i +…+η 3K ×α t-K ;

[0075] β'=η 40 +η 41 ×β t-1 +η 42 ×β t-2 +…+η 4i ×β t-i +…+η 4K ×β t-K ;

[0076]

[0077] Among them, V v ' alue is the fitting value of the converter valve voltage, I' value is the fitting value of the converter valve current, α' is the fitting value of the trigger angle, β' is the fitting value of the turn-off angle, I t ' ransformer is the load current fitting value, R i ' nsulation is the insulation resistance fitting value, I' reactor is the reactor current fitting value, V' drop is the fitting value of the reactor voltage drop, σ1 to σ8 are the weight coefficients of the above parameters respectively, η 10 To 1K is the fitting coefficient of the real-time detection value and the historical detection value of the converter valve voltage, η 20 To 2K is the fitting coefficient of the real-time detection value and the historical detection value of the converter valve current, η 30 To 3K is the fitting coefficient of the real-time detection value and the historical detection value of the trigger angle, η 40 To 4K is the fitting coefficient of the real-time detection value and the historical detection value of the turn-off angle, η 50 To 5K is the fitting coefficient of the real-time detection value and the historical detection value of the load current value, η 60 To 6K is the fitting coefficient of the real-time detection value and the historical detection value of the insulation resistance, η 70 To 7K is the fitting coefficient of the real-time detection value and the historical detection value of the reactor current value, η 80 To 8Kis the fitting coefficient of the real-time detection value and the historical detection value of the reactor voltage drop, ti is the serial number of the historical detection cycle, K is the number of historical detection cycles, and t is the serial number of the current detection cycle.

[0078] In the operation status management of the converter station, the fitting values ​​of each equipment parameter are calculated through comprehensive analysis of real-time monitoring data and historical data, and these fitting values ​​are further used to predict the overall operation status of the converter station, which improves the accuracy of fault prediction, enhances the system's response capability to abnormal situations, optimizes the adjustment of equipment operation parameters, reduces maintenance costs, and improves the reliability and safety of the converter station through preventive maintenance strategies.

[0079] In addition, the operating status parameters of the various types of heterogeneous terminals further include: equipment temperature values ​​and ambient humidity values ​​of transformers, equipment temperature values ​​and ambient humidity values ​​of converter valves, and equipment temperature values ​​and ambient humidity values ​​of smoothing reactors.

[0080] Optionally, the detection range of operating status parameters of multiple types of heterogeneous terminals is further expanded, including not only the basic electrical performance indicators of transformers, converter valves and smoothing reactors, such as load current, insulation resistance, voltage value, current value, trigger angle, turn-off angle and voltage drop, but also the temperature value of the equipment itself and the humidity value of the environment. This comprehensive parameter monitoring can more accurately reflect the operating status and environmental impact of the equipment, and provide richer and more detailed data support for the stable operation and preventive maintenance of the converter station.

[0081] In order to further detect the overall operating status of the converter station, the detection and consideration of corresponding parameters of other equipment (such as: DC switch, AC switch, filter group, reactive power compensation equipment, etc.) can also be added.

[0082] Specifically, the step S300 of adjusting the operating state of the converter station in the next detection cycle based on the current predicted value of the operating state includes:

[0083] Step S310: When the current predicted value of the operating state is greater than a first preset threshold, it is determined that the converter station is in a normal operating state.

[0084] Step S310: When the current predicted value of the operating state is less than or equal to the first preset threshold and greater than the second preset threshold, it is determined that the converter station is in an abnormal operating state and an abnormal alarm signal is issued.

[0085] Step S330: When the current predicted value of the operating status is less than or equal to the second preset threshold, it is determined that the converter station is in a fault state and a fault alarm signal is issued.

[0086] In the operation status management of the converter station, the current prediction value calculated based on real-time monitoring data and historical data is used to dynamically adjust the status of the converter station in the next detection cycle, which has the advantages of improving system response speed, enhancing fault prediction accuracy, optimizing equipment operating parameters, reducing operation and maintenance costs, and improving grid stability and reliability. The above data-driven approach allows users to identify and respond to potential anomalies and faults in a timely manner, thereby achieving more intelligent and automated power system management.

[0087] Accordingly, please refer to Figure 2 A second aspect of an embodiment of the present invention provides a data collection device for multiple types of heterogeneous terminals in a converter station based on a collaborative information model, and data collection is performed on the converter station based on the data collection method for multiple types of heterogeneous terminals in a converter station based on a collaborative information model, including:

[0088] A data acquisition module 1 is used to obtain operating status parameters of multiple types of heterogeneous terminals in the current detection cycle of the converter station, and the multiple types of heterogeneous terminals include: transformers, converter valves and smoothing reactors;

[0089] A feature fusion module 2 is used to perform feature fusion on several types of operating status parameters and calculate the current predicted value of the operating status of the converter station based on the collaborative information model;

[0090] The state control module 3 is used to adjust the operation state of the converter station in the next detection cycle based on the current predicted value of the operation state.

[0091] For further information, please refer to Figure 3 , the feature fusion module 2 includes:

[0092] A preprocessing unit 21, which is used to normalize several types of operating status parameters;

[0093] The feature fusion unit 22 is used to combine several historical operating status detection values ​​of the converter station, fuse the feature values ​​of several types of operating status parameters after normalization, and calculate the current predicted value of the operating status of the converter station.

[0094] For further information, please refer to Figure 4 , the state control module 3 includes:

[0095] A first determination unit 31, which is used to determine that the converter station is in a normal operating state when the current predicted value of the operating state is greater than a first preset threshold;

[0096] A second determination unit 32, which is used to determine that the converter station is in an abnormal operation state and send an abnormal alarm signal when the current predicted value of the operation state is less than or equal to the first preset threshold and greater than the second preset threshold;

[0097] The third determination unit 33 is used to determine that the converter station is in a fault state and send a fault alarm signal when the current predicted value of the operating state is less than or equal to the second preset threshold.

[0098] Accordingly, a third aspect of an embodiment of the present invention provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the above-mentioned method for collecting data from multiple types of heterogeneous terminals in a converter station based on a collaborative information model.

[0099] Accordingly, a fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-mentioned method for collecting data from multiple types of heterogeneous terminals in a converter station based on a collaborative information model.

[0100] The embodiment of the present invention aims to protect a method and device for collecting data of multiple types of heterogeneous terminals in a converter station based on a collaborative information model, wherein the method includes: obtaining the operating status parameters of multiple types of heterogeneous terminals in the current detection cycle of the converter station; performing feature fusion on several types of operating status parameters, and calculating the current predicted value of the operating status of the converter station based on the collaborative information model; and adjusting the operating status of the converter station in the next detection cycle based on the current predicted value of the operating status. The above technical solution has the following effects:

[0101] 1. Comprehensive acquisition of operating status parameters of different equipment and sensors in the converter station ensures the comprehensiveness of data collection and can reflect the operating status of the converter station from multiple angles;

[0102] 2. Through the rapid processing of real-time data and the fusion analysis of historical data, this method can not only monitor the current status of the converter station in real time, but also predict the short-term operation trend;

[0103] 3. Using collaborative information models, this method can effectively integrate data from different sources and types, achieve complementarity and collaboration between data, and improve data utilization efficiency and analysis accuracy;

[0104] 4. Through feature fusion and model calculation, the operating status of the converter station can be accurately evaluated, providing a scientific basis for operation and maintenance decisions.

[0105] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0106] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0107] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0108] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for collecting data from multiple heterogeneous terminals in a converter station based on a collaborative information model, characterized in that: The steps include: Acquire operation status parameters of multiple types of heterogeneous terminals in a current detection cycle of a converter station, wherein the multiple types of heterogeneous terminals include: transformers, converter valves, and smoothing reactors; Performing feature fusion on several types of operating status parameters, and calculating a current predicted value of the operating status of the converter station based on a collaborative information model; Based on the current predicted value of the operating state, the operating state of the converter station in the next detection cycle is adjusted.

2. The method for collecting data from multiple types of heterogeneous terminals in a converter station based on a collaborative information model according to claim 1, characterized in that: The operating state parameters of the transformer include: load current value and insulation resistance value; The operating state parameters of the converter valve include: converter valve voltage value, converter valve current value, trigger angle and cut-off angle; The operating state parameters of the smoothing reactor include: a reactor current value and a reactor voltage drop value.

3. The method for collecting data from multiple types of heterogeneous terminals in a converter station based on a collaborative information model according to claim 2 is characterized in that: The step of fusing the characteristics of the operating status parameters of the plurality of categories and calculating the current predicted value of the operating status of the converter station based on the collaborative information model includes: Normalizing several types of operating status parameters; Combined with several historical operating status detection values ​​of the converter station, characteristic value fusion is performed on several types of operating status parameters after normalization to calculate the current predicted value of the operating status of the converter station.

4. The method for collecting data from multiple types of heterogeneous terminals in a converter station based on a collaborative information model according to claim 3 is characterized in that: The current predicted value Z of the operating state t The calculation formula is: W=[ω1,ω2,ω3,ω4,ω5,ω6,ω7,ω8]; Among them, λ is the smoothing constant, X t is a one-dimensional operating state parameter matrix, W is a one-dimensional weight coefficient matrix, t is the serial number of the current detection cycle, ti is the serial number of the historical detection cycle, K is the number of historical detection cycles, θ t-i is the corresponding weight coefficient of the ti-th running status historical detection value, Z t-i is the historical detection value of the ti-th running state, V value is the voltage value of the converter valve, I value is the current value of the converter valve, α is the trigger angle, β is the cut-off angle, I transformer is the load current value, R insulation is the insulation resistance value, I reactor is the reactor current value, V drop is the weight coefficient of the reactor voltage drop, ω1 is the weight coefficient of the converter valve current value, ω2 is the weight coefficient of the converter valve current value, ω3 is the weight coefficient of the trigger angle, ω4 is the weight coefficient of the turn-off angle, ω5 is the weight coefficient of the load current value, ω6 is the weight coefficient of the insulation resistance value, ω7 is the weight coefficient of the reactor current value, and ω8 is the weight coefficient of the reactor voltage drop.

5. The method for collecting data from multiple types of heterogeneous terminals in converter stations based on a collaborative information model according to claim 3 is characterized in that: The current predicted value Z of the operating state t The calculation formula is: WITH t =σ1×V′ value +σ2×I' value +σ3×α'+σ4×β'+σ5×I′ transformer +σ6×R′ insulation +σ7×I' reactor +σ8×V′ drop ; a'=n 30 +n 31 ×a t-1 +n 32 ×a t-2 +…+h 3i ×a t-i +…+h 3K ×a t-K ; b'=n 40 +n 41 ×b t-1 +n 42 ×b t-2 +…+h 4i ×b t-i +…+h 4K ×b t-K ; Among them, V v ' alue is the fitting value of the converter valve voltage, I' value is the fitting value of the converter valve current, α' is the fitting value of the trigger angle, β' is the fitting value of the turn-off angle, I t ' ransformer is the load current fitting value, R i ' nsulation is the insulation resistance fitting value, I' reactor is the reactor current fitting value, V d ' rop is the fitting value of the reactor voltage drop, σ1 to σ8 are the weight coefficients of the above parameters respectively, η 10 To 1K is the fitting coefficient of the real-time detection value and the historical detection value of the converter valve voltage value, η 20 To 2K is the fitting coefficient of the real-time detection value and the historical detection value of the converter valve current value, η 30 To 3K is the fitting coefficient of the real-time detection value and the historical detection value of the trigger angle, η 40 To 4K is the fitting coefficient of the real-time detection value and the historical detection value of the shut-off angle, η 50 To 5K is the fitting coefficient of the real-time detection value and the historical detection value of the load current value, η 60 To 6K is the fitting coefficient of the real-time detection value and the historical detection value of the insulation resistance value, η 70 To 7K is the fitting coefficient of the real-time detection value and the historical detection value of the reactor current value, η 80 To 8K is the fitting coefficient of the real-time detection value and the historical detection value of the reactor voltage drop value, ti is the serial number of the historical detection cycle, K is the number of the historical detection cycles, and t is the serial number of the current detection cycle.

6. The method for collecting data from multiple types of heterogeneous terminals in a converter station based on a collaborative information model according to claim 2, characterized in that: The operating status parameters of the multiple types of heterogeneous terminals also include: equipment temperature value and environmental humidity value of the transformer, equipment temperature value and environmental humidity value of the converter valve, and equipment temperature value and environmental humidity value of the smoothing reactor.

7. The method for collecting data of multiple types of heterogeneous terminals in a converter station based on a collaborative information model according to any one of claims 1 to 6, characterized in that: The adjusting the operating state of the converter station in the next detection cycle based on the current predicted value of the operating state includes: When the current predicted value of the operating state is greater than a first preset threshold, it is determined that the converter station is in a normal operating state; When the current predicted value of the operating state is less than or equal to the first preset threshold and greater than the second preset threshold, it is determined that the converter station is in an abnormal operating state and an abnormal alarm signal is issued; When the current predicted value of the operating status is less than or equal to the second preset threshold, it is determined that the converter station is in a fault state and a fault alarm signal is issued.

8. A data collection device for multiple types of heterogeneous terminals in a converter station based on a collaborative information model, characterized in that: The method for collecting data from multiple types of heterogeneous terminals in a converter station based on a collaborative information model according to claims 1 to 7 is used to collect data from the converter station, including: A data acquisition module, which is used to obtain operating status parameters of multiple types of heterogeneous terminals in the current detection cycle of the converter station, wherein the multiple types of heterogeneous terminals include: transformers, converter valves and smoothing reactors; A feature fusion module, which is used to perform feature fusion on several types of operating status parameters and calculate the current predicted value of the operating status of the converter station based on a collaborative information model; A state control module is used to adjust the operating state of the converter station in the next detection cycle based on the current predicted value of the operating state.

9. An electronic device, characterized in that: include: at least one processor; And a memory connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the method for collecting data from multiple types of heterogeneous terminals in a converter station based on a collaborative information model as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed by the processor, the method for collecting data of multiple types of heterogeneous terminals in a converter station based on a collaborative information model as described in any one of claims 1 to 7 is implemented.

Images