Relay protection misoperation root cause analysis method, device, equipment, medium and program product

Abstract

The application relates to a relay protection misoperation root cause analysis method, device, equipment, medium and program product. The method comprises the following steps: in response to detecting a relay protection misoperation event, acquiring a corresponding observation data set; extracting and locking an exogenous noise vector of the relay protection misoperation event by inverse operation of a mixed driving structure equation; calculating average causal effects of each environmental state variable on relay protection action behavior, and generating a root cause quantitative analysis result according to the average causal effects; receiving an intervention operation instruction input by a user for a target environmental state variable, keeping the locked exogenous noise vector unchanged, inputting the modified target environmental state variable into a structural causal model, performing forward prediction and waveform synthesis through a mixed deduction engine, generating a virtual fault waveform and corresponding relay protection logic simulation results; and comparing the time domain waveform and the action logic to generate a comparison result. The method can quickly reproduce an accident scene and quantitatively locate a misoperation root cause.

Description

Technical Field

[0001] This application relates to the field of power system automation and intelligent operation and maintenance technology, and in particular to a method, device, equipment, medium and program product for analyzing the root causes of relay protection malfunctions. Background Technology

[0002] With the development of intelligent operation of power systems and grid connection technology of new energy sources, the operating conditions of power grids are becoming increasingly complex. Complex faults such as system oscillations and external faults accompanied by current transformer saturation occur frequently, which places higher demands on the analysis of the action behavior of relay protection devices and the location of the root causes of malfunctions. As the core line of defense for the safe and stable operation of the power grid, relay protection needs to quickly complete accident review, cause verification and responsibility determination after a malfunction occurs.

[0003] In traditional relay protection malfunction analysis and handling methods, maintenance personnel mainly retrieve fault waveform data, use conventional waveform analysis software to view the characteristics of the electrical quantities that have occurred, or use electromagnetic transient simulation software to build a power grid model and manually adjust parameters repeatedly to try to reproduce the on-site fault waveform.

[0004] However, traditional methods for analyzing malfunctions in relay protection have significant technical flaws: the root causes and liability determination of malfunctions rely heavily on qualitative judgments based on expert experience, lacking quantitative causal contribution indicators; the reproduction of complex fault scenarios requires manual adjustment of a large number of parameters, making it difficult to restore the unique random noise characteristics of the fault; and the accident reproduction is time-consuming, inefficient, and lacks convincing conclusions. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, device, equipment, medium, and program product for analyzing the root causes of relay protection malfunctions that can quickly reproduce accident scenarios and quantify and locate the root causes of malfunctions, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for root cause analysis of relay protection malfunctions, the method comprising:

[0007] In response to the detection of a relay protection malfunction event, the corresponding observation dataset is acquired;

[0008] A causal operation is performed on the observation dataset to extract and lock the exogenous noise vector of the relay protection maloperation event through the inverse operation of the hybrid driving structure equation;

[0009] Using a pre-defined structural causal model, a single attribution test is performed on each environmental state variable of the relay protection maloperation event. The average causal effect of each environmental state variable on the relay protection action behavior is calculated, and root cause quantitative analysis results are generated based on the average causal effect.

[0010] Based on the root cause quantification analysis results, the target environmental state variables to be intervened are determined. The intervention operation instructions input by the user for the target environmental state variables are received. The locked exogenous noise vector remains unchanged. The modified target environmental state variables are input into the structural causal model. The hybrid inference engine performs forward prediction and waveform synthesis to generate virtual fault waveforms and corresponding relay protection logic simulation results.

[0011] The virtual fault waveform, the relay protection logic simulation result, and the original fault waveform and the original relay protection action result are compared in the time domain to generate a comparison result.

[0012] In some embodiments of the method, a causal operation is performed on the observation dataset to extract and lock the exogenous noise vector of the relay protection maloperation event through the inverse operation of the hybrid driving structure equation, including:

[0013] By combining the inverse mapping neural network inverse solver with physical stripping processing, the observation dataset is inversely mapped and solved to extract and lock the exogenous noise vector of the relay protection maloperation event.

[0014] In some embodiments of the method, the step of performing a single attribution test on each environmental state variable of the relay protection maloperation event using a preset structural causal model, calculating the average causal effect of each environmental state variable on the relay protection action behavior, and generating root cause quantification analysis results based on the average causal effect includes:

[0015] Using a pre-defined structural causal model, a single attribution test is performed on each environmental state variable of the relay protection maloperation event to calculate the marginal effect of each environmental state variable on the relay protection action behavior, and the marginal effect is used as the average causal effect.

[0016] Based on the average causal effect, the proportion of each malfunctioning factor in the cause of the relay protection malfunction is determined, and a pie chart of malfunction causes is generated and output. The pie chart of malfunction causes is used to display the results of root cause quantitative analysis.

[0017] In some embodiments of the method, receiving the intervention operation instruction input by the user regarding the target environmental state variable includes:

[0018] The system receives user intervention commands for target environmental state variables via parameter sliders, numerical input boxes, or drop-down menus for preset power grid operation scenarios.

[0019] In some embodiments of the method, the step of comparing the virtual fault waveform, the relay protection logic simulation result, and the original fault waveform and the original relay protection action result in the time domain to generate a comparison result includes:

[0020] The original fault waveform is drawn as a solid line on the same time-domain coordinate axis, and the virtual fault waveform is drawn as a dashed line. The time-domain waveform visualization comparison is performed to generate the first comparison result.

[0021] The relay protection action logic is compared with the original relay protection action result based on the relay protection logic simulation result, and a second comparison result is generated.

[0022] Based on the first comparison result and the second comparison result, a counterfactual deduction conclusion is generated. The deduction conclusion is used to characterize the correspondence between the adjustment range and direction of the target environmental state variable and whether the relay protection malfunctions.

[0023] In some embodiments of the method, the step of acquiring the observation dataset in response to detecting a relay protection maloperation event includes:

[0024] In response to the detection of a relay protection maloperation event, the fault recording data, protection setting data, and power grid topology parameters corresponding to the relay protection maloperation event are obtained from the data storage layer to form an observation dataset.

[0025] According to a second aspect of the present disclosure, a relay protection malfunction root cause analysis device is provided. The device includes:

[0026] The data acquisition module is used to acquire the corresponding observation dataset in response to the detection of a relay protection maloperation event;

[0027] The cause-finding processing module is used to perform cause-finding operations on the observation dataset, extracting and locking the exogenous noise vector of the relay protection maloperation event through the inverse operation of the hybrid driving structure equation;

[0028] The root cause analysis module is used to perform single attribution tests on each environmental state variable of the relay protection maloperation event through a preset structural causal model, calculate the average causal effect of each environmental state variable on the relay protection action behavior, and generate root cause quantitative analysis results based on the average causal effect.

[0029] The counterfactual inference module is used to determine the target environmental state variable to be intervened based on the root cause quantification analysis results, receive the intervention operation instructions input by the user for the target environmental state variable, keep the locked exogenous noise vector unchanged, input the modified target environmental state variable into the structural causal model, and perform forward prediction and waveform synthesis through the hybrid inference engine to generate virtual fault waveforms and corresponding relay protection logic simulation results.

[0030] The result comparison module is used to compare the virtual fault waveform, the relay protection logic simulation result, and the original fault waveform and the original relay protection action result in the time domain waveform and action logic, and generate comparison results.

[0031] According to a third aspect of the present disclosure, a computer device is provided. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0032] In response to the detection of a relay protection malfunction event, the corresponding observation dataset is acquired;

[0033] A causal operation is performed on the observation dataset to extract and lock the exogenous noise vector of the relay protection maloperation event through the inverse operation of the hybrid driving structure equation;

[0034] Using a pre-defined structural causal model, a single attribution test is performed on each environmental state variable of the relay protection maloperation event. The average causal effect of each environmental state variable on the relay protection action behavior is calculated, and root cause quantitative analysis results are generated based on the average causal effect.

[0035] Based on the root cause quantification analysis results, the target environmental state variables to be intervened are determined. The intervention operation instructions input by the user for the target environmental state variables are received. The locked exogenous noise vector remains unchanged. The modified target environmental state variables are input into the structural causal model. The hybrid inference engine performs forward prediction and waveform synthesis to generate virtual fault waveforms and corresponding relay protection logic simulation results.

[0036] The virtual fault waveform, the relay protection logic simulation result, and the original fault waveform and the original relay protection action result are compared in the time domain to generate a comparison result.

[0037] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0038] In response to the detection of a relay protection malfunction event, the corresponding observation dataset is acquired;

[0039] A causal operation is performed on the observation dataset to extract and lock the exogenous noise vector of the relay protection maloperation event through the inverse operation of the hybrid driving structure equation;

[0040] Using a pre-defined structural causal model, a single attribution test is performed on each environmental state variable of the relay protection maloperation event. The average causal effect of each environmental state variable on the relay protection action behavior is calculated, and root cause quantitative analysis results are generated based on the average causal effect.

[0041] Based on the root cause quantification analysis results, the target environmental state variables to be intervened are determined. The intervention operation instructions input by the user for the target environmental state variables are received. The locked exogenous noise vector remains unchanged. The modified target environmental state variables are input into the structural causal model. The hybrid inference engine performs forward prediction and waveform synthesis to generate virtual fault waveforms and corresponding relay protection logic simulation results.

[0042] The virtual fault waveform, the relay protection logic simulation result, and the original fault waveform and the original relay protection action result are compared in the time domain to generate a comparison result.

[0043] According to a fifth aspect of the present disclosure, a computer program product is provided. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0044] In response to the detection of a relay protection malfunction event, the corresponding observation dataset is acquired;

[0045] A causal operation is performed on the observation dataset to extract and lock the exogenous noise vector of the relay protection maloperation event through the inverse operation of the hybrid driving structure equation;

[0046] Using a pre-defined structural causal model, a single attribution test is performed on each environmental state variable of the relay protection maloperation event. The average causal effect of each environmental state variable on the relay protection action behavior is calculated, and root cause quantitative analysis results are generated based on the average causal effect.

[0047] Based on the root cause quantification analysis results, the target environmental state variables to be intervened are determined. The intervention operation instructions input by the user for the target environmental state variables are received. The locked exogenous noise vector remains unchanged. The modified target environmental state variables are input into the structural causal model. The hybrid inference engine performs forward prediction and waveform synthesis to generate virtual fault waveforms and corresponding relay protection logic simulation results.

[0048] The virtual fault waveform, the relay protection logic simulation result, and the original fault waveform and the original relay protection action result are compared in the time domain to generate a comparison result.

[0049] The relay protection maloperation root cause analysis scheme provided in this application acquires a complete observation dataset after detecting a relay protection maloperation event, completes the cause tracing and locks the exogenous noise vector, and can accurately extract the unique random disturbance characteristics of the accident. It eliminates the need for repeated manual debugging of simulation parameters to match the field waveform, and can quickly restore the real accident scenario, solving the problem that traditional methods are difficult to reproduce the random characteristics of faults. It can transform the qualitative judgment that relies on expert experience into quantitative causal analysis, accurately distinguish the influence weight of each environmental state variable on the maloperation event, and free the root cause location from the constraints of subjective experience. The analysis conclusions are more objective and supported by data. By comparing the original and virtual waveforms and action logic, it can not only quickly locate the core root cause, but also provide a direct and reliable basis for subsequent power grid operation mode adjustments.

[0050] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0051] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0052] Figure 1 This is a flowchart illustrating a method for analyzing the root causes of relay protection malfunctions according to an exemplary embodiment.

[0053] Figure 2 This is an overall architecture diagram of a system for performing a root cause analysis method for relay protection malfunction, according to an exemplary embodiment.

[0054] Figure 3 This is a schematic flowchart illustrating a root cause analysis method for relay protection malfunction according to an exemplary embodiment.

[0055] Figure 4 This is a structural block diagram of a relay protection malfunction root cause analysis device according to an exemplary embodiment;

[0056] Figure 5 This is a diagram illustrating the internal structure of a computer device according to an exemplary embodiment. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0058] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, 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 a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded. For example, the use of terms such as "first," "second," etc., to denote names does not indicate any specific order.

[0059] In some embodiments provided in this disclosure, the execution of the relay protection malfunction root cause analysis method can be controlled by a unified controller or by multiple controllers. These controllers may include controllers on local terminals or controllers on remote servers. In some embodiments, the controllers on local terminals and the controllers on servers may jointly assist in completing the control processing for relay protection malfunction root cause analysis. The local terminal mentioned in this disclosure may include, but is not limited to, various robotic devices, vehicle-mounted devices, personal computers, laptops, smartphones, tablets, wearable devices, medical devices, VR (Virtual Reality) devices, etc. The server may also be a server, server cluster, distributed subsystem, cloud processing platform, server containing blockchain nodes, or a combination thereof. The controllers described in this disclosure may include various control units capable of implementing logic processing functions, including but not limited to CPU (Central Processing Unit), PLC (Programmable Logic Controller), ECU (Electronic Control Unit), MCU (Microcontroller Unit), FPGA (Field Programmable Gate Array), and CPLD (Complex Programmable Logic Device), as well as controllers composed of one or more logic function units, chips, etc.

[0060] In some embodiments of this disclosure, a method for analyzing the root causes of relay protection malfunctions is provided, such as... Figure 1 As shown, it includes the following steps:

[0061] S20. In response to the detection of a relay protection malfunction event, obtain the corresponding observation dataset.

[0062] A relay protection maloperation event typically refers to an event in which a relay protection device erroneously triggers its operation when no corresponding fault has occurred in the power system and the protection does not need to be activated.

[0063] The observation dataset typically refers to a collection of relevant data, such as fault recordings, protection settings, and power grid topology, used for analysis after a malfunction event occurs.

[0064] S22. Perform a causal operation on the observation dataset, and extract and lock the exogenous noise vector of the relay protection maloperation event through the inverse operation of the hybrid driving structure equation.

[0065] Hybrid-driven structural equations typically refer to a system of equations that integrates electrical physics mechanisms with data-driven logic, enabling both forward deduction and reverse solution.

[0066] Exogenous noise vectors typically refer to a set of unique random perturbation features in malfunction events that cannot be fully characterized by conventional physical models.

[0067] S24. Using a preset structural causal model, perform a single attribution test on each environmental state variable of the relay protection maloperation event, calculate the average causal effect of each environmental state variable on the relay protection action behavior, and generate root cause quantitative analysis results based on the average causal effect.

[0068] Structural causal models are mathematical analysis models used to analyze causal relationships between variables and to quantify the degree of influence of each factor.

[0069] Environmental state variables typically refer to relevant parameter variables such as power grid operation and equipment status that can affect the action behavior of relay protection.

[0070] Average causal effect usually refers to the average degree of influence on the relay protection behavior when a certain environmental state variable changes.

[0071] Root cause analysis results typically refer to the quantitative conclusions of the influence weights of each error-causing factor on the erroneous event, calculated based on causal effects.

[0072] S26. Based on the root cause quantification analysis results, determine the target environmental state variables to be intervened, receive the intervention operation instructions input by the user for the target environmental state variables, keep the locked exogenous noise vector unchanged, input the modified target environmental state variables into the structural causal model, and perform forward prediction and waveform synthesis through the hybrid inference engine to generate virtual fault waveforms and corresponding relay protection logic simulation results.

[0073] Intervention commands typically refer to user commands that adjust or modify the state variables of the target environment.

[0074] Virtual fault waveforms typically refer to electrical quantity waveforms generated through model deduction and after simulation parameter adjustment under fault conditions.

[0075] The simulation results of relay protection logic usually refer to the simulation conclusions of the relay protection device's operating logic obtained based on virtual fault waveforms.

[0076] S28. Compare the virtual fault waveform, the relay protection logic simulation result, and the original fault waveform and the original relay protection action result in the time domain to generate a comparison result.

[0077] The comparison results usually refer to the final conclusions obtained after comparing and analyzing the original and virtual waveforms and action logic.

[0078] In some embodiments of this disclosure, after detecting a relay protection maloperation event, a complete observation dataset is acquired, the cause is traced, and the exogenous noise vector is locked. This enables the accurate extraction of the unique random disturbance characteristics of the accident, eliminating the need for repeated manual adjustments to simulation parameters to match the on-site waveform. It can quickly recreate the real accident scenario, solving the problem that traditional methods struggle to reproduce the random characteristics of faults. It can transform the traditional qualitative judgment relying on expert experience into quantitative causal analysis, accurately distinguishing the influence weight of each environmental state variable on the maloperation event, allowing root cause localization to break free from the constraints of subjective experience, and making the analysis conclusions more objective and data-supported. By comparing the original and virtual waveforms and action logic, it can quickly locate the core root cause and provide a direct and reliable basis for subsequent adjustments to the power grid operation mode.

[0079] The following is in conjunction with the appendix Figure 2 and attached Figure 3 Further explanation is needed.

[0080] In some embodiments of this disclosure, S20 includes:

[0081] In response to the detection of a relay protection maloperation event, the fault recording data, protection setting data, and power grid topology parameters corresponding to the relay protection maloperation event are obtained from the data storage layer to form an observation dataset.

[0082] In some implementations, the data storage layer can store fault recording data, protection setting data, and power grid topology parameters, which together form an observation dataset. When a user imports a fault recording file, the observation data... It can automatically perform causal analysis on the observed dataset.

[0083] In some embodiments of this disclosure, fault recording data, protection setting data, and power grid topology parameters corresponding to relay protection maloperation events can be directly obtained from the data storage layer to form an observation dataset, ensuring that the data source is complete and authentic, eliminating the need for manual data sorting and screening, shortening the preparation time in the early stages of analysis, and further improving the efficiency and convenience of implementation.

[0084] In some embodiments of this disclosure, S22 includes:

[0085] By combining the inverse mapping neural network inverse solver with physical stripping processing, the observation dataset is inversely mapped and solved to extract and lock the exogenous noise vector of the relay protection maloperation event.

[0086] In some implementations, the inverse function of the hybrid driving structure equation can be utilized. The exogenous noise vector that caused the waveform distortion in this fault was calculated in reverse. . This study captures unique and irregular details in relay protection maloperation events, such as the random phase angle at the moment of lightning strikes and the random arc characteristics of tree-to-ground discharges. It can also extract and lock the exogenous noise vector of relay protection maloperation events. At this point, the system is capable of perfectly reproducing the accident without the need for manual adjustment of simulation parameters.

[0087] In some embodiments of this disclosure, exogenous noise vectors are extracted by combining a reverse solver with physical stripping processing, which can accurately capture the unique random disturbance characteristics of accidents, solve the problem that conventional simulations cannot reproduce real random working conditions, and make accident scene reproduction more in line with the actual situation on site.

[0088] In some embodiments of this disclosure, S24 includes:

[0089] Using a pre-defined structural causal model, a single attribution test is performed on each environmental state variable of the relay protection maloperation event to calculate the marginal effect of each environmental state variable on the relay protection action behavior, and the marginal effect is used as the average causal effect.

[0090] Based on the average causal effect, the proportion of each malfunctioning factor in the cause of the relay protection malfunction is determined, and a pie chart of malfunction causes is generated and output. The pie chart of malfunction causes is used to display the results of root cause quantitative analysis.

[0091] In some implementations, for relay protection malfunction events, the average causal effect (ACE) of each environmental state variable can be automatically calculated using a preset structural causal model. For example, it can be calculated for each environmental state variable. (e.g., weak feedback) Perform a single attribution test to calculate its impact on protection actions. The marginal effect is shown in the following formula (1):

[0092] (1)

[0093] In equation (1), ACE stands for average causal effect, and Y represents the protective action. For environmental state variables.

[0094] In some examples, the output can be visualized to generate a pie chart showing the causes of the malfunction, such as: 60% of the malfunction is attributed to CT saturation, 30% to improper setting, and 10% to random interference.

[0095] In some embodiments of this disclosure, the average causal effect is calculated through a single attribution test and a visualization chart is generated, transforming traditional qualitative analysis into quantitative analysis. This clearly presents the degree of influence of each error-causing factor and provides intuitive and objective data support for determining liability for erroneous actions.

[0096] In some embodiments of this disclosure, S26 includes:

[0097] The system receives user intervention commands for target environmental state variables via parameter sliders, numerical input boxes, or drop-down menus for preset power grid operation scenarios.

[0098] In some implementations, when receiving user intervention commands, the user's adjustment commands for target environmental state variables can be received through parameter sliding adjustment components, numerical input boxes, or selection menus for preset power grid operation scenarios, adapting to different operating habits and improving the convenience of interaction.

[0099] In some embodiments of this disclosure, user intervention commands are received through multiple interactive methods, adapting to the operating habits of different users, simplifying the parameter adjustment process, reducing the operational threshold of counterfactual inference, and enabling various types of operation and maintenance personnel to quickly complete parameter settings.

[0100] In some embodiments of this disclosure, S28 includes:

[0101] The original fault waveform is drawn as a solid line on the same time-domain coordinate axis, and the virtual fault waveform is drawn as a dashed line. The time-domain waveform visualization comparison is performed to generate the first comparison result.

[0102] The relay protection action logic is compared with the original relay protection action result based on the relay protection logic simulation result, and a second comparison result is generated.

[0103] Based on the first comparison result and the second comparison result, a counterfactual deduction conclusion is generated. The deduction conclusion is used to characterize the correspondence between the adjustment range and direction of the target environmental state variable and whether the relay protection malfunctions.

[0104] In some implementations, users can perform hypothetical analyses through an interactive control interface. In some examples, users can drag parameter sliders through the interactive control interface to move them from... (Original value) modified to (Assuming values, for example, changing a weak grid to a strong grid). Then, perform positive predictions from the model, maintaining the previously locked noise. Unchanged, will Input structural causal model, at this time , At this point, entirely new fault voltage / current waveforms can be quickly generated, and the operating logic of the protection device under the new waveforms can be simulated.

[0105] The time-domain comparison displays the original waveform as a solid line and the counterfactual waveform as a dashed line on the same coordinate axis. Logical comparison also provides a comparison; for example, if the original result is "Distance II segment moves (false move)," the deduced result is "Distance II segment does not move (correct)."

[0106] Finally, a pop-up message appeared on the interactive control interface: "Deductive conclusion: If the system impedance had increased by 20% at that time, the protection would not have tripped erroneously. This proves that the excessively low system impedance was the main cause of this erroneous trip."

[0107] In some embodiments of this disclosure, the differences between the original scene and the virtual scene are intuitively displayed by comparing time-domain waveforms and action logic. The generated counterfactual inference conclusions can accurately clarify the relationship between variable adjustment and erroneous action, providing a basis for subsequent accident rectification and protection optimization.

[0108] The methods for root cause analysis of relay protection maloperation disclosed herein acquire a complete observation dataset after detecting a relay protection maloperation event, complete the cause tracing and lock the exogenous noise vector, and can accurately extract the unique random disturbance characteristics of the accident. They eliminate the need for repeated manual adjustments to simulation parameters to match the field waveform, and can quickly recreate the real accident scenario, solving the problem that traditional methods struggle to reproduce the random characteristics of faults. Furthermore, they transform traditional qualitative judgments relying on expert experience into quantitative causal analysis, accurately distinguishing the influence weight of various environmental state variables on the maloperation event, freeing root cause localization from subjective experience constraints, and making the analysis conclusions more objective and data-supported. By comparing the original and virtual waveforms and action logic, they can quickly locate the core root cause and provide a direct and reliable basis for subsequent adjustments to the power grid operation mode.

[0109] It is understood that the various embodiments of the methods described in this specification are presented in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. Related details can be found in the descriptions of other method embodiments.

[0110] It should be understood that although the steps in the flowcharts shown in the accompanying drawings are displayed sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the accompanying drawings may include multiple steps or stages, which are not necessarily completed at the same time, but may be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but may be performed alternately or in turn with other steps or at least a portion of the steps or stages of other steps.

[0111] Based on the description of the relay protection malfunction root cause analysis method embodiments described above, this disclosure also provides a relay protection malfunction root cause analysis device for implementing the aforementioned relay protection malfunction root cause analysis method. The device may include a system (including a distributed system), software (application), module, component, controller, server, terminal, etc., using the method described in the embodiments of this specification, combined with necessary implementation hardware. Based on the same innovative concept, the devices in one or more embodiments provided in this disclosure are as described in the following embodiments. Since the implementation schemes and methods for solving the problem by the devices are similar, the implementation of specific devices in the embodiments of this specification can refer to the implementation of the aforementioned method, and repeated details will not be repeated. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0112] Figure 4 This is a schematic block diagram of a relay protection malfunction root cause analysis device according to an exemplary embodiment. The device can be the aforementioned terminal, a server, or a module, component, device, control unit, etc., integrated into the terminal. For details, please refer to... Figure 4 The device 100 may include: a data acquisition module 120, a causal processing module 140, a root cause analysis module 160, a counterfactual deduction module 180, and a result comparison module 190. Specifically, the data acquisition module 120 is used to acquire the corresponding observation dataset in response to the detection of a relay protection maloperation event; the causal processing module 140 is used to perform causal operations on the observation dataset, extracting and locking the exogenous noise vector of the relay protection maloperation event through the inverse operation of the hybrid driving structural equation; the root cause analysis module 160 is used to perform single attribution tests on each environmental state variable of the relay protection maloperation event using a preset structural causal model, calculate the average causal effect of each environmental state variable on the relay protection action behavior, and generate root cause quantitative analysis results based on the average causal effect; the counterfactual deduction module 180... 80 is used to determine the target environmental state variable to be intervened based on the root cause quantification analysis results, receive the intervention operation command input by the user for the target environmental state variable, keep the locked exogenous noise vector unchanged, input the modified target environmental state variable into the structural causal model, and perform forward prediction and waveform synthesis through the hybrid inference engine to generate a virtual fault waveform and the corresponding relay protection logic simulation result; the result comparison module 190 is used to compare the virtual fault waveform, the relay protection logic simulation result with the original fault waveform and the original relay protection action result in the time domain waveform and action logic, and generate a comparison result.

[0113] Each module in the aforementioned relay protection malfunction root cause analysis device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0114] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for analyzing the root causes of relay protection malfunctions.

[0115] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0116] Based on the foregoing description of the relevant methods and apparatus embodiments, this disclosure also provides a computer device, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, implements the relay protection malfunction root cause analysis method described in any embodiment of this specification.

[0117] Based on the foregoing description of the relevant methods and apparatus embodiments, this disclosure also provides a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by the processor of a computer device, enables the computer device to implement the relay protection malfunction root cause analysis method as described in any embodiment of this disclosure.

[0118] Based on the foregoing description of the relevant methods and apparatus embodiments, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the relay protection malfunction root cause analysis method described in any embodiment of this specification.

[0119] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0120] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0121] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0122] It should be noted that the apparatus, computer equipment, storage medium, and computer program products described above may also include other implementation methods according to the description of the method embodiments. Specific implementation methods can be found in the description of the relevant method embodiments. Furthermore, new embodiments formed by combinations of features from various methods, apparatuses, devices, and server embodiments still fall within the scope of this disclosure and will not be elaborated upon here.

[0123] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, when implementing one or more of these specifications, the functions of each module can be implemented in the same or different software and / or hardware, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling and communication connections between the devices or units shown or described can be implemented through direct and / or indirect coupling / connection, through standard or custom interfaces or protocols, and can be implemented electrically, mechanically, or in other forms.

[0124] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0125] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for analyzing the root causes of relay protection malfunctions, characterized in that, The method includes: In response to the detection of a relay protection malfunction event, the corresponding observation dataset is acquired; A causal operation is performed on the observation dataset to extract and lock the exogenous noise vector of the relay protection maloperation event through the inverse operation of the hybrid driving structure equation; Using a pre-defined structural causal model, a single attribution test is performed on each environmental state variable of the relay protection maloperation event. The average causal effect of each environmental state variable on the relay protection action behavior is calculated, and root cause quantitative analysis results are generated based on the average causal effect. Based on the root cause quantification analysis results, the target environmental state variables to be intervened are determined. The intervention operation instructions input by the user for the target environmental state variables are received. The locked exogenous noise vector remains unchanged. The modified target environmental state variables are input into the structural causal model. The hybrid inference engine performs forward prediction and waveform synthesis to generate virtual fault waveforms and corresponding relay protection logic simulation results. The virtual fault waveform, the relay protection logic simulation result, and the original fault waveform and the original relay protection action result are compared in the time domain to generate a comparison result.

2. The method according to claim 1, characterized in that, Perform a causal operation on the observation dataset, extracting and locking the exogenous noise vector of the relay protection maloperation event through the inverse operation of the hybrid driving structure equation, including: By combining the inverse mapping neural network inverse solver with physical stripping processing, the observation dataset is inversely mapped and solved to extract and lock the exogenous noise vector of the relay protection maloperation event.

3. The method according to claim 1, characterized in that, The process involves performing a single attribution test on each environmental state variable of the relay protection maloperation event using a pre-defined structural causal model, calculating the average causal effect of each environmental state variable on the relay protection's action behavior, and generating root cause quantification analysis results based on the average causal effect, including: Using a pre-defined structural causal model, a single attribution test is performed on each environmental state variable of the relay protection maloperation event to calculate the marginal effect of each environmental state variable on the relay protection action behavior, and the marginal effect is used as the average causal effect. Based on the average causal effect, the proportion of each malfunctioning factor in the cause of the relay protection malfunction is determined, and a pie chart of malfunction causes is generated and output. The pie chart of malfunction causes is used to display the results of root cause quantitative analysis.

4. The method according to claim 1, characterized in that, The step of receiving intervention operation instructions input by the user regarding the target environment state variables includes: The system receives user intervention commands for target environmental state variables via parameter sliders, numerical input boxes, or drop-down menus for preset power grid operation scenarios.

5. The method according to claim 1, characterized in that, The step of comparing the virtual fault waveform, the relay protection logic simulation result, and the original fault waveform and original relay protection action result in the time domain to generate a comparison result includes: The original fault waveform is drawn as a solid line on the same time-domain coordinate axis, and the virtual fault waveform is drawn as a dashed line. The time-domain waveform visualization comparison is performed to generate the first comparison result. The relay protection action logic is compared with the original relay protection action result based on the relay protection logic simulation result, and a second comparison result is generated. Based on the first comparison result and the second comparison result, a counterfactual deduction conclusion is generated. The deduction conclusion is used to characterize the correspondence between the adjustment range and direction of the target environmental state variable and whether the relay protection malfunctions.

6. The method according to claim 1, characterized in that, The step of acquiring an observation dataset in response to detecting a relay protection maloperation event includes: In response to the detection of a relay protection maloperation event, the fault recording data, protection setting data, and power grid topology parameters corresponding to the relay protection maloperation event are obtained from the data storage layer to form an observation dataset.

7. A relay protection malfunction root cause analysis device, characterized in that, The device includes: The data acquisition module is used to acquire the corresponding observation dataset in response to the detection of a relay protection maloperation event; The cause-finding processing module is used to perform cause-finding operations on the observation dataset, extracting and locking the exogenous noise vector of the relay protection maloperation event through the inverse operation of the hybrid driving structure equation; The root cause analysis module is used to perform single attribution tests on each environmental state variable of the relay protection maloperation event through a preset structural causal model, calculate the average causal effect of each environmental state variable on the relay protection action behavior, and generate root cause quantitative analysis results based on the average causal effect. The counterfactual inference module is used to determine the target environmental state variable to be intervened based on the root cause quantification analysis results, receive the intervention operation instructions input by the user for the target environmental state variable, keep the locked exogenous noise vector unchanged, input the modified target environmental state variable into the structural causal model, and perform forward prediction and waveform synthesis through the hybrid inference engine to generate virtual fault waveforms and corresponding relay protection logic simulation results. The result comparison module is used to compare the virtual fault waveform, the relay protection logic simulation result, and the original fault waveform and the original relay protection action result in the time domain waveform and action logic, and generate comparison results.

8. A computer device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program thereon, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Images