A fault inversion method and device for a flexible direct current converter valve

Abstract

The application discloses a kind of flexible DC converter valve fault inversion method and device, it is related to DC transmission technical field, main purpose is to realize the fault inversion of flexible DC converter valve.The main technical scheme of the present application is: obtaining the multi-source operation data of flexible DC converter valve, data covers valve tower level, sub-module level and each functional component level inside sub-module level;According to the preset model construction strategy, the three-dimensional digital model of flexible DC converter valve is constructed, the model includes valve tower level model, sub-module level model and functional component level model, and there is hierarchical nested structure between each level model;According to the preset data fusion rule, the multi-source operation data is fused into three-dimensional digital model;According to the alarm time in multi-source operation data, the fusion data is time-sequenced, and the multi-source operation data with time sequence in model is obtained;Drive three-dimensional digital model to generate fault inversion sequence data for visual presentation based on the data.

Description

Technical Field

[0001] This invention relates to the field of DC power transmission technology, and in particular to a fault inversion method and apparatus for a flexible DC converter valve. Background Technology

[0002] High-voltage, high-capacity flexible direct current (DC) transmission has become a key technology for long-distance, high-capacity power transmission. As a core component of flexible DC transmission, the flexible DC converter valve operates under harsh conditions such as high voltage, high current, and strong electromagnetic interference, and its reliability directly affects the safety and stability of the entire power grid. Therefore, it is necessary to conduct fault inversion analysis on the flexible DC converter valve to help maintenance personnel gain a deeper understanding of the fault mechanisms and develop more effective prevention and handling measures.

[0003] However, due to the short operational time of flexible DC transmission projects, the long-term operating characteristics of flexible DC converter valves are still being explored. Currently, only operational status monitoring has been implemented, and a fault inversion method for flexible DC converter valves has not yet been developed. Therefore, a fault inversion method for flexible DC converter valves is urgently needed, enabling maintenance personnel to quickly locate the cause of a fault based on the inversion results after it occurs. Summary of the Invention

[0004] In view of the above problems, the present invention provides a fault inversion method and apparatus for flexible DC converter valves, the main purpose of which is to realize fault inversion of flexible DC converter valves.

[0005] To solve the above-mentioned technical problems, the present invention proposes the following solution: In a first aspect, the present invention provides a fault inversion method for a flexible DC converter valve, the method comprising: Acquire multi-source operating data of the flexible DC converter valve, which covers the valve tower level, sub-module level, and the level of each functional component within the sub-module; According to the preset model building strategy, a three-dimensional digital model of the flexible DC converter valve is constructed. The three-dimensional digital model includes a valve tower hierarchical model, a sub-module hierarchical model and a functional component hierarchical model. The valve tower hierarchical model, the sub-module hierarchical model and the functional component hierarchical model have a hierarchical nested structure. According to the preset data fusion rules, multi-source operating data are fused into the three-dimensional digital model of the flexible DC converter valve; Based on the alarm time in the multi-source operating data, the multi-source operating data fused into the three-dimensional digital model of the flexible DC converter valve is processed in a time sequence to obtain multi-source operating data with a time sequence relationship in the three-dimensional digital model of the flexible DC converter valve. The three-dimensional digital model driving the flexible DC converter valve generates fault inversion sequence data for visualization based on multi-source operating data with temporal relationships.

[0006] Secondly, the present invention provides a fault inversion device for a flexible DC converter valve, the device comprising: The data acquisition unit is used to acquire multi-source operating data of the flexible DC converter valve. The multi-source operating data covers the valve tower level, the sub-module level, and the level of each functional component within the sub-module. The model building unit is used to build a three-dimensional digital model of the flexible DC converter valve according to a preset model building strategy. The three-dimensional digital model includes a valve tower hierarchical model, a sub-module hierarchical model and a functional component hierarchical model. The valve tower hierarchical model, the sub-module hierarchical model and the functional component hierarchical model have a hierarchical nested structure. The data fusion unit is used to fuse the multi-source operating data acquired by the data acquisition unit into the three-dimensional digital model of the flexible DC converter valve constructed by the model building unit according to the preset data fusion rules. The data processing unit is used to perform time-series processing on the multi-source operating data fused into the three-dimensional digital model of the flexible DC converter valve by the data fusion unit according to the alarm time in the multi-source operating data, so as to obtain multi-source operating data with time-series relationship in the three-dimensional digital model of the flexible DC converter valve. The fault inversion unit, used to drive the three-dimensional digital model of the flexible DC converter valve, generates fault inversion sequence data for visualization based on the multi-source operating data with temporal relationships processed by the data processing unit.

[0007] To achieve the above objectives, according to a third aspect of the present invention, a storage medium is provided, the storage medium including a stored program, wherein, when the program is executed, the device in which the storage medium is located is controlled to perform the fault inversion method of the flexible DC converter valve of the first aspect described above.

[0008] To achieve the above objectives, according to a fourth aspect of the present invention, a processor is provided for running a program, wherein the program executes the fault inversion method for the flexible DC converter valve described in the first aspect.

[0009] By employing the aforementioned technical solution, this invention provides a fault inversion method and apparatus for a flexible DC converter valve. By acquiring multi-source operational data covering the valve tower level, sub-module level, and the levels of functional components within each sub-module, the comprehensiveness of the data required for fault analysis is ensured. Based on this, a three-dimensional digital model of the flexible DC converter valve with a hierarchical nested structure, including valve tower level models, sub-module level models, and functional component level models, is constructed, allowing the structural hierarchy of the physical device to be realistically represented in digital space. Subsequently, according to preset data fusion rules, the multi-source operational data is fused into this three-dimensional digital model, forming a binding between the operational data and the corresponding model levels. Furthermore, using the alarm time in the multi-source operational data as the reference time, the fused multi-source operational data undergoes time-series processing, enabling the originally asynchronous and scattered data to form a time-series relationship under a unified time reference in the three-dimensional digital model. Finally, the three-dimensional digital model is driven to generate fault inversion sequence data for visualization based on the time-series multi-source operational data, thereby dynamically reconstructing the entire process of fault occurrence, development, and impact in chronological order. The above steps work together to ensure that the fault inversion results have both spatial hierarchical correspondence and temporal continuity and consistency, effectively improving the accuracy and interpretability of fault backtracking.

[0010] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0011] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart of a fault inversion method for a flexible DC converter valve provided by an embodiment of the present invention is shown; Figure 2 A flowchart of another fault inversion method for a flexible DC converter valve provided by an embodiment of the present invention is shown; Figure 3 This diagram shows a block diagram of a fault inversion device for a flexible DC converter valve provided in an embodiment of the present invention; Figure 4 A block diagram of another fault inversion device for a flexible DC converter valve provided in an embodiment of the present invention is shown. Detailed Implementation

[0012] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0013] It should be noted that the flexible DC converter valve has a clearly defined hierarchical structure: its top layer is the valve tower level, used to represent the complete converter valve unit containing all components; below the valve tower level are multiple key subsystems and structural components, such as submodules, water-cooled pipes, fiber optic channels, shielding covers, post insulators, and insulating supports; among them, the submodule, as the core functional unit, is further subdivided into multiple functional component levels, specifically including IGBTs, thyristors, bypass switches, DC capacitors, heat sinks, secondary boards, and internal cooling water pipes. This multi-level structure provides the physical basis for achieving refined modeling and fault location.

[0014] However, for the sake of clarity and highlighting the core technical logic of the present invention, only the valve tower level, the sub-module level, and the level of each functional component within the sub-module are described as exemplary hierarchical structures. This simplification does not exclude other actual components or levels mentioned above, nor should it be construed as a limitation on the scope of protection of the present invention.

[0015] Next, combined Figure 1 The present invention describes a fault inversion method for a flexible DC converter valve, the specific execution steps of which are as follows: Figure 1 As shown, it includes: 101. Obtain multi-source operating data of flexible DC converter valves.

[0016] In one embodiment of the present invention, the acquisition of multi-source operating data of the flexible DC converter valve in step 101 refers to collecting raw data related to the operating status of the equipment from sensors, measurement and control devices, and information systems deployed at different physical locations of the converter valve. Specifically, this includes: Valve tower level: Data such as temperature and humidity, cooling water flow, and total voltage / current waveform are collected through valve hall environmental sensors, water cooling system monitoring units, etc. Submodule level: Real-time operating data such as capacitor voltage, switch status, and communication status are collected through the submodule controller, and corresponding annual inspection data (such as insulation resistance, withstand voltage test results, etc.) are retrieved from the operation and maintenance system. The submodule's internal functional components are hierarchically structured as follows: electrical or thermal parameters are collected by current / temperature sensors or dedicated waveform recording devices deployed on key components such as IGBTs, bypass switches, and DC capacitors; at the same time, the converter valve control system generates alarm messages (such as "overcurrent", "overtemperature", "communication interruption") and corresponding fault waveform recording segments.

[0017] It should be noted that although the above data acquisition has a clear physical orientation (e.g., a certain waveform recording channel is dedicated to monitoring the current of a specific IGBT branch), the generated raw data usually only contains parameter names, values, timestamps and possible logical addresses, and does not directly carry semantic labels indicating which submodule or functional component the data belongs to.

[0018] This is because valve towers and submodules, as basic management units with independent device codes and communication addresses in the system, can automatically associate their operating data with unique valve tower IDs or submodule numbers during the acquisition or retrieval process, thus possessing clear hierarchical attribution identifiers; while the monitoring data of functional components inside submodules (such as IGBTs, capacitors, heat sinks, etc.) are mostly raw data, and their physical attribution cannot be directly determined, so it needs to be determined later according to preset data fusion rules.

[0019] For example, a waveform record might only be described as "t=10:05:23.120, current=150A", and an alarm message might only be described as "t=10:05:23.125, overcurrent alarm (threshold 3200A)", neither specifying the exact component originating from. Furthermore, non-real-time data such as annual inspection data and historical fault cases may only contain vague location information (e.g., "Pole I upper bridge arm submodule abnormal"), lacking precise identification down to the functional component.

[0020] 102. Construct a three-dimensional digital model of the flexible DC converter valve according to the preset model construction strategy.

[0021] In one embodiment of the present invention, a three-dimensional digital model with a hierarchical nesting relationship can be constructed based on the topological parameters and electrical performance parameters of the device. This model consists of a valve tower hierarchical model, a sub-module hierarchical model, and a functional component hierarchical model. The valve tower hierarchical model, as the outermost container, contains one or more sub-module hierarchical models. Each sub-module hierarchical model further contains several functional component hierarchical models, such as IGBTs, DC capacitors, bypass switches, heat sinks, secondary circuit boards, and internal water pipes.

[0022] It should be noted that the above three-level division is merely an exemplary expression for the convenience of describing the core idea of ​​this invention. In reality, the flexible DC converter valve also includes other key components such as water-cooled pipes, optical fiber channels, shielding covers, post insulators, and insulating supports, and their corresponding digital models can also be included in this framework, embedded into the corresponding level according to their actual physical affiliation. The scope of protection of this invention is not limited to the model types listed.

[0023] Furthermore, during the model building phase, the hierarchical structure and data access interfaces of the model can be specifically designed to meet the actual application of subsequent fault inversion, thereby achieving a precise match between inversion requirements and model functionality. For targeted inversion of a single alarm event, independent dedicated data interfaces can be configured for each level of the model, including the valve tower, sub-modules, and functional components, based on the alarm time interval of that alarm event. These interfaces only allow data writing and retrieval permissions for the corresponding time interval. During inversion, it is not necessary to load data for the entire time period; the focus can be directly placed on the time period in which the alarm event occurred, thus reproducing the entire state evolution process of the converter valve.

[0024] If full-time operational status retrospective is required, the time of the first alarm can be used as the time axis reference origin, and a universal data interface for all valve towers, sub-modules, and core functional components can be uniformly configured for all time periods. This type of interface does not have time range limitations, ensuring that data from every moment of the converter valve's operation can be written to the corresponding level of the model location, thereby supporting continuous and complete playback from the initial operational state to the occurrence and development of various alarm events.

[0025] The core differences between the two modeling and inversion strategies are mainly reflected in four aspects: First, they are applicable to different scenarios. The single alarm event directional inversion strategy is suitable for the cause analysis of specific alarm events and the precise investigation of fault locations, focusing on the in-depth exploration of single-point problems; while the all-time operation status backtracking strategy is suitable for analyzing the chain reaction of multiple alarm events, or for restoring the complete evolution link of the converter valve from the bud to the outbreak over a period of time.

[0026] Second, there are differences in the interface design logic. The former uses the time interval of alarm events as the basis for division, configuring a dedicated interface for each level model that is strongly bound to a single event. Its permission scope is strictly limited to the corresponding target time interval. By default, each model can have multiple independent interfaces facing different time intervals. The latter does not set any time range restrictions, adopts a unified all-time universal interface, covers the entire process of converter valve operation, and is applicable to all models at all levels.

[0027] Third, the data retrieval methods are different. The former only needs to retrieve relevant data within the target alarm time interval, which is small in volume and fast in retrieval speed, and can effectively avoid redundant loading of irrelevant data; the latter needs to retrieve all the operating data of the converter valve from beginning to end, which is complete in data dimensions and can support a global review and analysis of the overall operating status.

[0028] Fourth, the inversion presentation effects have different focuses. The former focuses on a local close-up of the time period when a single alarm event occurs, without involving the operating status of other unrelated time periods, which makes it easier for technicians to quickly pinpoint the cause of the fault; the latter provides a full playback from normal operation to the successive occurrence of various alarms, which can show the temporal relationship and correlation path between different alarm events, and helps to thoroughly sort out the propagation chain and root cause of the fault.

[0029] 103. According to the preset data fusion rules, the multi-source operating data is fused into the three-dimensional digital model of the flexible DC converter valve.

[0030] 104. Based on the alarm time in the multi-source operation data, perform time-series processing on the multi-source operation data integrated into the three-dimensional digital model of the flexible DC converter valve to obtain multi-source operation data with time-series relationship in the three-dimensional digital model of the flexible DC converter valve.

[0031] 105. The three-dimensional digital model of the driving flexible DC converter valve generates fault inversion sequence data for visualization based on multi-source operating data with temporal relationships.

[0032] In step 103, the multi-source operating data can be standardized. Then, according to the preset fusion rules, these data are written into the corresponding model entity components in the three-dimensional digital model of the flexible DC converter valve.

[0033] Quantifiable parameters such as temperature, voltage, and status codes can be written into the component's attribute fields, while descriptive information such as annual inspection results and alarm numbers can be attached as tags to the corresponding components. This writing operation is not arbitrary but is accomplished through the data interfaces configured during the model's construction phase. Each interface explicitly defines the target components that can be written to, the types of attributes / tags that can be updated, and the valid time window or data source range.

[0034] The configuration method of this interface depends directly on the inversion target: if the analysis is targeted at a single alarm event, a dedicated interface is configured for the corresponding components at each level, allowing only data within the corresponding time period to be written, thereby ensuring that the data of different events are isolated from each other; if full-time operation status backtracking is required, a unified general interface is configured for all components, without limiting the time range, so that data from every moment since commissioning can be continuously written to the attributes of the corresponding component to form a complete state evolution record.

[0035] Step 104 allows for time-series organization of the data written to component attributes. Under the dedicated interface strategy, since each component attribute only contains data within the target alarm window, the system can directly extract and align multi-source signals (e.g., interpolating millisecond-level electrical quantities and second-level temperature data onto a unified time axis). Under the general interface strategy, the analysis interval needs to be extracted from the full historical data stored in the component attributes, all alarm-related times need to be marked, time-series synchronization needs to be completed, and finally a set of multi-source operational data sequences with a time base needs to be output.

[0036] In step 105, a fault inversion sequence can be generated based on the aforementioned time-series data to drive the 3D model. For scenarios using a dedicated interface strategy, since the attribute data of each component is focused and small in size, each frame within the alarm time window is usually traversed when the inversion task starts. The current attribute values ​​of the components are read (e.g., valve tower temperature = 42℃, IGBT voltage drop anomaly = true). Combined with visualization rules, a model state snapshot containing rendering instructions and label descriptions (e.g., annual inspection qualified, insulation aging excluded) is generated. Then, it is organized in chronological order and made available for the front end to call as needed to realize the playback of local close-up shots. In scenarios employing a generic interface strategy, the entire process data is stored in the component properties. A real-time driven approach can be selected, meaning that when the front end requests a specified time for each frame, the back end retrieves the corresponding state from the component properties and dynamically returns instructions such as highlighting, color, pop-ups, and data, thereby completely reconstructing the entire process of the fault's development.

[0037] Of course, the above methods are not the only options. Under the general interface strategy, the entire process of fault development can be fully reproduced by pre-generating model snapshots, or data can be dynamically displayed in real time as needed for specific fault evolution stages, flexibly adapting to the needs of different analysis scenarios. Regardless of the method used, the inversion process can be exported as animation, video, or structured interactive files and archived in the fault case library, forming traceable and reusable typical inversion cases for maintenance personnel to review and replay repeatedly, improving fault handling efficiency.

[0038] Based on the above Figure 1As can be seen from the implementation method, the fault inversion method for a flexible DC converter valve provided by this invention ensures the comprehensiveness of the data required for fault analysis by acquiring multi-source operational data covering the valve tower level, sub-module level, and the levels of functional components within each sub-module. Based on this, a three-dimensional digital model of the flexible DC converter valve with a hierarchical nested structure, including valve tower level models, sub-module level models, and functional component level models, is constructed, allowing the structural hierarchy of the physical device to be realistically represented in digital space. Subsequently, according to preset data fusion rules, the multi-source operational data is fused into this three-dimensional digital model, achieving a binding between the operational data and the corresponding model levels. Furthermore, using the alarm time in the multi-source operational data as the reference time, the fused multi-source operational data undergoes time-series processing, enabling the originally asynchronous and scattered data to form a time-series relationship under a unified time reference in the three-dimensional digital model. Finally, the three-dimensional digital model is driven to generate fault inversion sequence data for visualization based on the multi-source operational data with time-series relationships, thereby dynamically reconstructing the entire process of fault occurrence, development, and impact in chronological order. The above steps work together to ensure that the fault inversion results have both spatial hierarchical correspondence and temporal continuity and consistency, effectively improving the accuracy and interpretability of fault backtracking.

[0039] Furthermore, as a response to Figure 1 Further refinement and extension of the illustrated embodiment, this invention also provides another fault inversion method for flexible DC converter valves, such as... Figure 2 As shown, the specific steps are as follows: 201. Obtain multi-source operating data of flexible DC converter valves.

[0040] The implementation method of step 201 is the same as that of step 101, and can achieve the same technical effect and solve the same technical problem, so it will not be repeated here.

[0041] 202. Construct a three-dimensional digital model of the flexible DC converter valve according to the preset model construction strategy.

[0042] In this embodiment, the physical topology parameters, electrical performance parameters, and hierarchical division rules of the flexible DC converter valve are first obtained. The hierarchical division rules are used to define the boundaries and nesting relationships between the valve tower level, the sub-module level, and the functional component level.

[0043] Subsequently, based on geometric and electrical performance parameters, valve tower hierarchical models, submodule hierarchical models, and functional component hierarchical models are constructed sequentially. Independent attribute interfaces and control interfaces are configured for each hierarchical model: the attribute interface is used to mount the corresponding multi-source operating data, that is, to bind operating parameters such as temperature, voltage, and status codes to specific components in the model (such as valve tower housing, submodule shell, IGBT chip, etc.) in the form of attributes; the control interface is used to independently drive the visualization status of the hierarchical model, such as highlighting, color changing, pop-up windows, or animation feedback.

[0044] Finally, based on the hierarchical division rules, the valve tower hierarchical model, submodule hierarchical model, and functional component hierarchical model are assembled and associated according to their physical nesting relationship to form a three-dimensional digital model of a flexible DC converter valve with complete topological semantics.

[0045] 203. According to the preset data fusion rules, the multi-source operating data is fused into the three-dimensional digital model of the flexible DC converter valve.

[0046] In this embodiment, multi-source operational data is first acquired, including temperature and humidity data, real-time operational data, annual inspection data, alarm messages, fault waveform data, and historical fault case data. Subsequently, based on the fault time, fault content, handling process, and corresponding fault waveform data recorded in the fault case database, a structured correlation relationship is established between fault types, fault causes, and typical fault manifestation data in the functional component level of the flexible DC converter valve, which is used for subsequent fault location and data fusion.

[0047] Based on this, and according to the data identifiers at each level (such as device ID, location code, or topology path), different types of data are integrated into the corresponding level of the digital model: Valve tower level: Match the data identifier of temperature and humidity data with the data identifier of valve tower level model. When they match, the temperature and humidity data is attached to the corresponding valve tower level model component and stored as an attribute. Submodule level: Match the data identifiers of the running data and annual inspection data with the data identifiers of the submodule level model respectively. After a successful match, merge the corresponding data into the corresponding submodule level model. Functional component hierarchy: Trend analysis is performed on the electrical parameters (such as IGBT on-state voltage drop, capacitor terminal voltage, etc.) in the fault waveform data, and characteristic change patterns are extracted as the first data analysis result. This result is compared with the fault performance data in the aforementioned correlation to match the most likely fault cause and its corresponding functional component. Thus, the fault waveform data is associated and integrated into the specific device model (such as a certain IGBT or capacitor) in the functional component hierarchical model. Simultaneously, the alarm reason field in the alarm message is parsed and semantically or rule-matched with the fault reason entries in the association relationship to determine the specific functional component it points to. The alarm message is then integrated into the corresponding functional component model in the functional component hierarchy model as an event label or state trigger basis.

[0048] Through the above method, data from different sources and at different granularities are injected into the model hierarchy that is consistent with its logical affiliation, realizing full-scale data fusion from macroscopic valve towers to microscopic functional components, laying a structured data foundation for subsequent time series inversion and fault visualization.

[0049] 204. Based on the alarm time in the multi-source operation data, perform time-series processing on the multi-source operation data integrated into the three-dimensional digital model of the flexible DC converter valve to obtain multi-source operation data with time-series relationship in the three-dimensional digital model of the flexible DC converter valve.

[0050] This step adopts a global, full-time backtracking mode. For scenarios where there are multiple alarm messages in multi-source operational data, the time-series processing flow is as follows: First, extract the alarm timestamp from all alarm messages, determine the earliest triggered alarm timestamp as the global base time, and set it as the time zero point (t=0).

[0051] Subsequently, based on the preset fault inversion accuracy requirements (such as milliseconds or seconds), a time axis composed of discrete time points with fixed time granularity is constructed (for example, when the accuracy is 1 millisecond, the time axis nodes are t=0, t=1ms, t=2ms, etc.). Finally, for the multi-source operational data that has been associated with the valve tower, sub-module, and functional component hierarchical model through the attribute interface, it is mapped to the corresponding interval of the unified time axis according to the original timestamp of each data. For data that does not directly hit the discrete time point, the corresponding data values ​​of each discrete time point are completed by linear interpolation or nearest neighbor matching, and finally, multi-source operational data that is bound to each component of the three-dimensional digital model and has a continuous temporal relationship is formed.

[0052] Specifically, in practical applications, the raw data of flexible DC converter valves may exhibit a non-uniform distribution over time. Directly using such data for fault inversion in 3D digital models can easily lead to state jumps, animation stutters, or inversion distortion, affecting the accuracy of fault analysis and visualization. Therefore, it is advisable to first determine whether the time interval between the timestamps corresponding to two adjacent discrete time points of the raw data to be interpolated meets the preset fault inversion accuracy requirements. If the time interval is not greater than the time threshold corresponding to the fault inversion accuracy requirement (for example, if the inversion accuracy is set to 20ms, then the time threshold is 20ms), then the original data density is considered to be high enough. In this case, the nearest neighbor matching method is used to directly take the original data value closest to the discrete time point to be interpolated as the corresponding data value of that time point. If the time interval is greater than the time threshold, it indicates that the original data is too sparse and cannot accurately reflect the dynamic process. In this case, linear interpolation is used to calculate the interpolation result of the discrete time point based on the two adjacent original data values ​​and their timestamps before and after the discrete time point to be interpolated. In practice, the time difference between the time point to be interpolated and the previous original data point can be calculated, and the time difference can be divided by the time interval between the two original data points to obtain a normalized time scaling factor. Then, the difference between the two original data values ​​can be weighted according to the scaling factor to calculate the estimated data value of the time point to be interpolated. Finally, the estimated value is used as the corresponding data value of the discrete time point on a unified time axis.

[0053] The above strategy enables the adaptive selection of the optimal data completion method while ensuring the time resolution of fault inversion: in data-dense areas, real measurements are used first to avoid distortion introduced by interpolation, while in data-sparse areas, linear interpolation is used to maintain the continuity of state changes.

[0054] This timing processing step is performed after the data has been integrated into the model components. The core is to organize the data that the components have been attached to according to the time axis. That is, first confirm that the model components such as valve towers, sub-modules, and functional parts have completed data binding through the attribute interface (for example, the components in the IGBT model have been attached to the on-state voltage drop data, and the sub-modules have been attached to the operating voltage data), and all data carry the original acquisition timestamp, and then the timing processing is performed.

[0055] It should be noted that data and model fusion involves binding multi-source operational data to the backend data layer of model components such as valve towers, sub-modules, and functional parts through model attribute interfaces. The core is to solve the problem of which component the data belongs to, turning scattered data into structured data bound to specific components (for example, writing the IGBT's on-state voltage drop data into the attribute field of the corresponding IGBT model). All data carries the original timestamp, which is the basis for subsequent operations. The frontend model displays the corresponding data after the data has undergone time-series processing. The visualization rules are triggered through the model control interface to transform the abstract data bound to the backend into a visual form that users can intuitively perceive, thereby reproducing the fault evolution process.

[0056] 205. The three-dimensional digital model of the driving flexible DC converter valve generates fault inversion sequence data for visualization based on multi-source operating data with temporal relationships.

[0057] In this step, the multi-source operational data that has been integrated into the 3D digital model of the flexible DC converter valve and has completed time-series alignment is traversed in timestamp order. For each time point, the operational status data (such as temperature, voltage, alarm flags, etc.) associated with each component in the valve tower level, sub-module level, and functional component level at that time are extracted and integrated to form a full-level operational status snapshot at that time point.

[0058] Subsequently, based on the state data in the snapshot, the system calls the preset visualization rules (e.g., yellow highlighting for temperature exceeding limits, red flashing for IGBT voltage drop anomalies, and overlaying icons for submodule faults), driving the 3D model to render the corresponding visualization state at that moment, generating a complete model state snapshot.

[0059] The state snapshots at all points in time are organized in chronological order to form structured fault inversion sequence data, which can be saved as JSON sequences, video files, or interactive playback formats.

[0060] On the front end, after loading the basic 3D model, users control the inversion progress using playback controls (such as play, pause, and drag the timeline). Based on the current time point, the front end reads the corresponding snapshot data from the inversion sequence and updates the display status of each component of the model in real time—including color, transparency, highlight effects, and pop-up information—thus presenting the static snapshots as a dynamic fault reproduction process. This entire process allows technicians to clearly observe the entire process of a fault from its occurrence and development to its chain reaction.

[0061] In summary, this invention achieves the reproduction of the fault evolution process of converter valves through a process of multi-source data acquisition—layered construction of a three-dimensional model—data fusion and time-series processing—visual inversion. First, multi-source operational data covering three levels—valve tower, submodule, and functional component—is collected. Data at the valve tower and submodule levels includes built-in device or location identifiers, allowing for direct attribution. However, data at the functional component level (such as fault recordings and alarm messages) is typically raw information without a clear attribution, requiring further parsing and matching.

[0062] Subsequently, based on the actual inversion requirements—whether to perform targeted analysis on a single alarm event or to retrospectively analyze the operational status throughout the entire period—a three-dimensional digital model with a hierarchical nested structure is constructed, and corresponding data interfaces are configured for different levels: For single alarms, a dedicated interface with a time window is used, while for full-process analysis, a general interface without time constraints is used. Furthermore, the model can select between high-precision or lightweight modeling strategies as needed to adapt to different hardware environments and usage scenarios.

[0063] During the data fusion phase, a hierarchical matching mechanism is adopted: valve tower and sub-module data are directly bound to the corresponding model components through their built-in identifiers; functional component data are attached to specific functional component models after trend analysis or semantic matching, based on the pre-established fault manifestation-fault cause-related component mapping relationship in the fault case library.

[0064] After fusion is completed, a unified timeline is constructed using the earliest triggered alarm time as the global reference point, and discrete time points are divided according to the preset inversion accuracy. The running data of all levels are time-aligned accordingly, and through interpolation or nearest neighbor completion, a time-series dataset that strictly corresponds to the model components is formed.

[0065] Finally, the system traverses the dataset chronologically, extracting the full-level state of the valve tower, sub-modules, and functional components frame by frame at each time point. Combining this with preset visualization rules (such as high-brightness overheating, abnormal pressure drop flashing, and pop-up prompts), it generates model state snapshots for the corresponding time points and organizes all snapshots into a structured fault inversion sequence. This sequence can be exported as a video, an interactive file, or stored in a case library.

[0066] After the front end loads the basic 3D model, the progress is controlled by playback controls (such as play, pause, and drag the timeline). The corresponding snapshots are read in real time and the display status of each component of the model is updated. This allows for a dynamic and coherent reproduction of the entire process of a fault from its initial occurrence to its gradual development and triggering of a chain response, providing maintenance personnel with an intuitive and accurate basis for fault location and cause analysis.

[0067] Furthermore, as a response to the above Figure 1 In addition to the implementation of the method shown, this embodiment of the invention also provides a fault inversion device for a flexible DC converter valve, used for the above-mentioned... Figure 1 The method shown is implemented accordingly. This device embodiment corresponds to the foregoing method embodiment. For ease of reading, this device embodiment will not repeat the details of the foregoing method embodiment, but it should be clear that the device in this embodiment can implement all the contents of the foregoing method embodiment. Figure 3 As shown, the device includes: Data acquisition unit 301 is used to acquire multi-source operating data of flexible DC converter valve, the multi-source operating data covering valve tower level, sub-module level and the level of each functional component inside the sub-module; The model building unit 302 is used to build a three-dimensional digital model of the flexible DC converter valve according to a preset model building strategy. The three-dimensional digital model includes a valve tower hierarchical model, a sub-module hierarchical model and a functional component hierarchical model. The valve tower hierarchical model, the sub-module hierarchical model and the functional component hierarchical model have a hierarchical nested structure. The data fusion unit 303 is used to fuse the multi-source operating data acquired by the data acquisition unit 301 into the three-dimensional digital model of the flexible DC converter valve constructed by the model building unit 302 according to the preset data fusion rules. The data processing unit 304 is used to perform time-series processing on the multi-source operating data fused by the data fusion unit 303 into the three-dimensional digital model of the flexible DC converter valve according to the alarm time in the multi-source operating data, so as to obtain multi-source operating data with time-series relationship in the three-dimensional digital model of the flexible DC converter valve. The fault inversion unit 305 is used to generate fault inversion sequence data for visualization based on the three-dimensional digital model of the flexible DC converter valve, which is generated from the multi-source operating data with temporal relationship processed by the data processing unit 304.

[0068] Furthermore, as a response to the above Figure 2 In addition to the method shown, this embodiment of the invention also provides another fault inversion device for flexible DC converter valves, used for the above-mentioned... Figure 2 The method shown is implemented accordingly. This device embodiment corresponds to the foregoing method embodiment. For ease of reading, this device embodiment will not repeat the details of the foregoing method embodiment, but it should be clear that the device in this embodiment can implement all the contents of the foregoing method embodiment. Figure 4 As shown, the device includes: Data acquisition unit 301 is used to acquire multi-source operating data of flexible DC converter valve, the multi-source operating data covering valve tower level, sub-module level and the level of each functional component inside the sub-module; The model building unit 302 is used to build a three-dimensional digital model of the flexible DC converter valve according to a preset model building strategy. The three-dimensional digital model includes a valve tower hierarchical model, a sub-module hierarchical model and a functional component hierarchical model. The valve tower hierarchical model, the sub-module hierarchical model and the functional component hierarchical model have a hierarchical nested structure. The data fusion unit 303 is used to fuse the multi-source operating data acquired by the data acquisition unit 301 into the three-dimensional digital model of the flexible DC converter valve constructed by the model building unit 302 according to the preset data fusion rules. The data processing unit 304 is used to perform time-series processing on the multi-source operating data fused by the data fusion unit 303 into the three-dimensional digital model of the flexible DC converter valve according to the alarm time in the multi-source operating data, so as to obtain multi-source operating data with time-series relationship in the three-dimensional digital model of the flexible DC converter valve. The fault inversion unit 305 is used to generate fault inversion sequence data for visualization based on the three-dimensional digital model of the flexible DC converter valve, which is generated from the multi-source operating data with temporal relationship processed by the data processing unit 304.

[0069] In one optional implementation, the data fusion unit 303 is specifically used for: Acquire the temperature and humidity data, operation data, annual inspection data, alarm messages, fault waveform data and fault case data included in the multi-source operation data; Based on the fault time, fault content, fault handling process, and fault waveform data in the fault case library, determine the correlation between the fault type, fault cause, and fault performance data at the functional component level of the flexible DC converter valve. Based on the data identifiers corresponding to the temperature and humidity data, operation data, and annual inspection data, as well as the data identifiers corresponding to the valve tower level and sub-module level, the temperature and humidity data, operation data, and annual inspection data are respectively integrated into the valve tower level model and sub-module level model corresponding to the valve tower level and sub-module level, respectively. The alarm messages and fault recording data are fused into the functional component hierarchical model based on the aforementioned relationship.

[0070] In one optional implementation, when the data fusion unit 303 fuses the temperature and humidity data, operating data, and annual inspection data into the valve tower level model and submodule level model respectively, based on the data identifiers corresponding to the temperature and humidity data, operating data, and annual inspection data, and the data identifiers corresponding to the valve tower level and submodule level, respectively, it is specifically used for: The data identifier corresponding to the temperature and humidity data is matched with the data identifier corresponding to the valve tower level, and when the matching results are the same, the temperature and humidity data is merged into the valve tower level model corresponding to the valve tower level. The data identifiers corresponding to the operation data and annual inspection data are matched with the data identifiers corresponding to the sub-module level, and when the matching results are the same, the operation data and annual inspection data are merged into the sub-module level model corresponding to the sub-module level.

[0071] In one optional implementation, the data fusion unit 303 fuses the alarm message and the fault recording data into the functional component hierarchical model according to the association relationship, specifically for: The data variation trends of various electrical parameters in the fault recording data are analyzed to obtain the first data analysis result; The first data analysis result is matched with the fault performance data in the association relationship to determine the functional component to which the fault cause corresponding to the first data analysis result points. The fault recording data is fused into the corresponding functional component model in the functional component hierarchical model; The alarm cause in the alarm message is matched with the fault cause in the association relationship to determine the functional component corresponding to the alarm message, and the alarm message is merged into the corresponding functional component model in the functional component hierarchical model.

[0072] In one optional implementation, the model building unit 302 includes: The parameter acquisition module 3021 is used to acquire the physical topology parameters, electrical performance parameters and hierarchical division rules of the flexible DC converter valve. The hierarchical division rules are used to clarify the boundaries and nesting relationships of the valve tower level, sub-module level and functional component level. The model building module 3022 is used to construct a valve tower hierarchical model, a sub-module hierarchical model, and a functional component hierarchical model in sequence based on the geometric parameters and electrical performance parameters obtained by the parameter acquisition module 3021, and to configure independent attribute interfaces and control interfaces for each model. The attribute interface is used to mount corresponding multi-source operating data, and the control interface is used to independently drive the status display of the model. The model association module 3023 is used to perform hierarchical nesting and association of the valve tower hierarchical model, sub-module hierarchical model and functional component hierarchical model constructed by the model construction module 3022 according to the hierarchical division rules, so as to form a three-dimensional digital model of a flexible DC converter valve with a hierarchical structure.

[0073] In one optional implementation, the fault inversion unit 305 is specifically used for: According to the order of timestamps, traverse the multi-source operating data that have been integrated into the three-dimensional digital model of the flexible DC converter valve and have a temporal relationship; For each timestamp, obtain the operational status data associated with the valve tower level, sub-module level, and functional component level in the 3D digital model at the corresponding time, and form the full-level operational status data corresponding to the timestamp; Based on the full-level operational status data, render a snapshot of the state of the 3D digital model at the corresponding timestamp; All timestamp-corresponding state snapshots are organized into structured fault inversion sequence data.

[0074] In one optional implementation, the data processing unit 304 is specifically used for: If there are multiple alarm messages in the multi-source operation data, the alarm timestamp of the earliest triggered alarm message will be determined as the global reference time. Using the global reference time as the zero point, a time axis is constructed according to the preset fault inversion accuracy requirements. The time axis consists of discrete time points with a fixed time granularity. The multi-source operational data at the valve tower level, sub-module level, and functional component level are mapped to the unified time axis according to their original timestamps, and corresponding data values ​​at each discrete time point are generated by linear interpolation or nearest neighbor matching to obtain multi-source operational data with temporal relationships in the three-dimensional digital model of the flexible DC converter valve.

[0075] In one optional implementation, when the data processing unit 304 generates the corresponding data values ​​at each discrete time point through linear interpolation or nearest neighbor matching, it is specifically used for: Determine whether the time interval between the timestamps corresponding to two adjacent original data points of the discrete time point to be interpolated meets the preset fault inversion accuracy requirements. If the time interval is not greater than the time threshold corresponding to the fault inversion accuracy requirement, then the nearest neighbor matching method is adopted, and the original data value closest to the discrete time point to be interpolated is taken as the corresponding data value. If the time interval is greater than the time threshold, then linear interpolation is used to calculate the data value of the discrete time point to be interpolated based on two adjacent original data values ​​of the discrete time point to be interpolated.

[0076] Furthermore, embodiments of the present invention also provide a storage medium for storing a computer program, wherein the computer program, when running, controls the device where the storage medium is located to execute the above-described... Figure 1-2 The fault inversion method for flexible DC converter valves described in the paper.

[0077] Furthermore, embodiments of the present invention also provide a processor for running a program, wherein the program executes the above-described... Figure 1-2 The fault inversion method for flexible DC converter valves described in the paper.

[0078] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0079] It is understood that the relevant features in the above methods and apparatus can be referenced interchangeably. Furthermore, the terms "first," "second," etc., in the above embodiments are used to distinguish between embodiments and do not represent the superiority or inferiority of any particular embodiment.

[0080] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0081] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0082] In addition, the memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0083] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0085] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0086] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0087] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0088] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0089] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0090] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0091] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A fault inversion method for a flexible DC converter valve, characterized in that, The method includes: Acquire multi-source operating data of the flexible DC converter valve, which covers the valve tower level, sub-module level, and the level of each functional component within the sub-module; According to the preset model building strategy, a three-dimensional digital model of the flexible DC converter valve is constructed. The three-dimensional digital model includes a valve tower hierarchical model, a sub-module hierarchical model and a functional component hierarchical model. The valve tower hierarchical model, the sub-module hierarchical model and the functional component hierarchical model have a hierarchical nested structure. According to the preset data fusion rules, multi-source operating data are fused into the three-dimensional digital model of the flexible DC converter valve; Based on the alarm time in the multi-source operating data, the multi-source operating data fused into the three-dimensional digital model of the flexible DC converter valve is processed in a time sequence to obtain multi-source operating data with a time sequence relationship in the three-dimensional digital model of the flexible DC converter valve. The three-dimensional digital model driving the flexible DC converter valve generates fault inversion sequence data for visualization based on multi-source operating data with temporal relationships.

2. The method according to claim 1, characterized in that, According to preset data fusion rules, multi-source operational data are fused into the three-dimensional digital model of the flexible DC converter valve, including: Acquire the temperature and humidity data, operation data, annual inspection data, alarm messages, fault waveform data and fault case data included in the multi-source operation data; Based on the fault time, fault content, fault handling process, and fault waveform data in the fault case library, determine the correlation between the fault type, fault cause, and fault performance data at the functional component level of the flexible DC converter valve. Based on the data identifiers corresponding to the temperature and humidity data, operation data, and annual inspection data, as well as the data identifiers corresponding to the valve tower level and sub-module level, the temperature and humidity data, operation data, and annual inspection data are respectively integrated into the valve tower level model and sub-module level model corresponding to the valve tower level and sub-module level, respectively. The alarm messages and fault recording data are fused into the functional component hierarchical model based on the aforementioned relationship.

3. The method according to claim 2, characterized in that, Based on the data identifiers corresponding to the temperature and humidity data, operational data, and annual inspection data, as well as the data identifiers corresponding to the valve tower level and submodule level, the temperature and humidity data, operational data, and annual inspection data are respectively integrated into the valve tower level model and submodule level model corresponding to the valve tower level and submodule level, respectively, including: The data identifier corresponding to the temperature and humidity data is matched with the data identifier corresponding to the valve tower level, and when the matching results are the same, the temperature and humidity data is merged into the valve tower level model corresponding to the valve tower level. The data identifiers corresponding to the operation data and annual inspection data are matched with the data identifiers corresponding to the sub-module level, and when the matching results are the same, the operation data and annual inspection data are merged into the sub-module level model corresponding to the sub-module level.

4. The method according to claim 2, characterized in that, Based on the aforementioned correlation, the alarm messages and fault recording data are fused into the functional component hierarchical model, including: The data variation trends of each electrical parameter in the fault recording data are analyzed to obtain the first data analysis result; The first data analysis result is matched with the fault performance data in the association relationship to determine the functional component to which the fault cause corresponding to the first data analysis result points. The fault recording data is fused into the corresponding functional component model in the functional component hierarchical model; The alarm cause in the alarm message is matched with the fault cause in the association relationship to determine the functional component corresponding to the alarm message, and the alarm message is merged into the corresponding functional component model in the functional component hierarchical model.

5. The method according to claim 1, characterized in that, Based on the pre-defined model building strategy, a three-dimensional digital model of the flexible DC converter valve is constructed, including: The physical topology parameters, electrical performance parameters, and hierarchical division rules of the flexible DC converter valve are obtained. The hierarchical division rules are used to clarify the boundaries and nesting relationships of the valve tower level, sub-module level, and functional component level. Based on the geometric and electrical performance parameters, a valve tower hierarchical model, a sub-module hierarchical model, and a functional component hierarchical model are constructed sequentially. Each model is configured with an independent attribute interface and a control interface. The attribute interface is used to load corresponding multi-source operating data, and the control interface is used to independently drive the state display of the model. Based on the hierarchical division rules, the valve tower hierarchical model, submodule hierarchical model, and functional component hierarchical model are nested and associated hierarchically to form a three-dimensional digital model of a flexible DC converter valve with a hierarchical structure.

6. The method according to claim 1, characterized in that, Based on the alarm times in the multi-source operating data, time-series processing is performed on the multi-source operating data fused into the three-dimensional digital model of the flexible DC converter valve to obtain multi-source operating data with time-series relationships in the three-dimensional digital model of the flexible DC converter valve, including: If there are multiple alarm messages in the multi-source operation data, the alarm timestamp of the earliest triggered alarm message will be determined as the global reference time. Using the global reference time as the zero point, a time axis is constructed according to the preset fault inversion accuracy requirements. The time axis consists of discrete time points with a fixed time granularity. The multi-source operational data at the valve tower level, sub-module level, and functional component level are mapped to the unified time axis according to their original timestamps, and corresponding data values ​​at each discrete time point are generated by linear interpolation or nearest neighbor matching to obtain multi-source operational data with temporal relationships in the three-dimensional digital model of the flexible DC converter valve.

7. The method according to claim 6, characterized in that, Data values ​​at each discrete time point are generated using linear interpolation or nearest neighbor matching, including: Determine whether the time interval between the timestamps corresponding to two adjacent original data points of the discrete time point to be interpolated meets the preset fault inversion accuracy requirements. If the time interval is not greater than the time threshold corresponding to the fault inversion accuracy requirement, then the nearest neighbor matching method is adopted, and the original data value closest to the discrete time point to be interpolated is taken as the corresponding data value. If the time interval is greater than the time threshold, then linear interpolation is used to calculate the data value of the discrete time point to be interpolated based on two adjacent original data values ​​of the discrete time point to be interpolated.

8. A fault inversion device for a flexible DC converter valve, characterized in that, The device includes: The data acquisition unit is used to acquire multi-source operating data of the flexible DC converter valve. The multi-source operating data covers the valve tower level, the sub-module level, and the level of each functional component within the sub-module. The model building unit is used to build a three-dimensional digital model of the flexible DC converter valve according to a preset model building strategy. The three-dimensional digital model includes a valve tower hierarchical model, a sub-module hierarchical model and a functional component hierarchical model. The valve tower hierarchical model, the sub-module hierarchical model and the functional component hierarchical model have a hierarchical nested structure. The data fusion unit is used to fuse the multi-source operating data acquired by the data acquisition unit into the three-dimensional digital model of the flexible DC converter valve constructed by the model building unit according to the preset data fusion rules. The data processing unit is used to perform time-series processing on the multi-source operating data fused into the three-dimensional digital model of the flexible DC converter valve by the data fusion unit according to the alarm time in the multi-source operating data, so as to obtain multi-source operating data with time-series relationship in the three-dimensional digital model of the flexible DC converter valve. The fault inversion unit, used to drive the three-dimensional digital model of the flexible DC converter valve, generates fault inversion sequence data for visualization based on the multi-source operating data with temporal relationships processed by the data processing unit.

9. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, the device containing the storage medium is controlled to perform the fault inversion method for the flexible DC converter valve as described in any one of claims 1 to 7.

10. A processor, characterized in that, The processor is used to run a program, wherein the program executes the fault inversion method for the flexible DC converter valve as described in any one of claims 1 to 7.

Images