Loop level state reasoning method and device based on working condition context, equipment, storage medium and program product

Abstract

The application relates to a circuit level state reasoning method and device based on working condition context, computer equipment, a readable storage medium and a program product, and relates to the technical field of online monitoring of power equipment. The application can improve the accuracy of state analysis under complex working conditions. The method comprises the following steps: based on a device level state model, a mechanism model, a circuit correlation model and a working condition model, a state evaluation benchmark under different operation scenarios is established; multi-source monitoring data of a high-voltage switchgear is collected, the multi-source monitoring data is subjected to time synchronization and standardization processing, a standardized data set under a unified time axis is constructed, the standardized data set is subjected to credibility evaluation, and a credibility evaluation result is obtained; based on unit operation data and equipment action sequences, the current operation working condition of the unit is identified, working condition context information is generated, and on the basis of the state evaluation benchmark and the credibility evaluation result, the expected operation state of the equipment and the circuit is analyzed by reasoning in combination with the working condition context information.

Description

Technical Field

[0001] This application relates to the field of online monitoring technology for power equipment, and in particular to a loop-level state reasoning method, apparatus, computer equipment, computer-readable storage medium, and computer program product based on operating condition context. Background Technology

[0002] Pumped storage power stations, as an important component of the new power system, undertake multiple key functions such as peak shaving, frequency regulation, phase regulation, emergency backup, and renewable energy consumption, and are an important regulatory resource to ensure the safe and stable operation of the power grid. With the continuous and rapid growth of the installed capacity of intermittent renewable energy sources such as wind power and photovoltaics, the demand for flexible regulation capabilities in the power system is constantly increasing, resulting in a significant increase in the start-up and shutdown frequency of pumped storage units. The operating conditions frequently switch between various modes such as pumping, power generation, drive, start-up, and commutation, and the operating mode exhibits highly dynamic, complex, and multi-state coupling characteristics.

[0003] However, traditional condition analysis still mostly uses a fixed threshold judgment mode. The physical meaning of the operating parameters of the same equipment under different operating conditions is significantly different from the normal range. It is easy to misjudge the normal parameter fluctuations caused by the switching of operating conditions as equipment abnormalities, resulting in frequent false alarms. This leads to low analysis accuracy and makes it difficult to adapt to complex dynamic operating conditions. Summary of the Invention

[0004] Therefore, it is necessary to provide a loop-level state reasoning method, apparatus, computer device, computer-readable storage medium, and computer program product based on operating condition context to address the above-mentioned technical problems.

[0005] Firstly, this application provides a loop-level state reasoning method based on operating condition context, including:

[0006] Based on the equipment structure and functional division of high-voltage switchgear in pumped storage power stations, an equipment-level state model is established. Based on the equipment-level state model and combined with relevant equipment parameters, a mechanism model that maps to the equipment-level state model is established.

[0007] Based on the primary system topology of the pumped storage power station, a loop association model between each of the high-voltage switchgear is constructed, and based on the operation process of the pumped storage unit, a working condition model corresponding to various typical operating conditions is established.

[0008] Based on the device-level state model, the mechanism model, the loop association model, and the operating condition model, state evaluation benchmarks are established for different operating scenarios.

[0009] Multi-source monitoring data of the high-voltage switchgear is collected, and the multi-source monitoring data is time-synchronized and standardized to construct a standardized dataset under a unified time axis. Based on the logical consistency relationship, historical operation pattern and equipment operation characteristics of the multi-source monitoring data, the credibility of the standardized dataset is evaluated to obtain the credibility evaluation result.

[0010] Based on unit operation data and equipment action sequences, the current operating condition of the unit is identified, and corresponding operating condition context information is generated. Based on the state evaluation benchmark and the credibility assessment results, and combined with the operating condition context information, the expected operating state of the equipment and circuits is inferred and analyzed. In one embodiment, before performing credibility assessment on the standardized dataset, the method further includes: performing consistency analysis on the standardized dataset to obtain the consistency relationship between the multi-source monitoring data; combining the logical relationship between the multi-source monitoring data to obtain the logical consistency relationship; and assigning credibility weights to each monitoring data point based on its importance.

[0011] The credibility assessment of the standardized dataset based on the logical consistency relationship, historical operating patterns, and equipment operating characteristics of the multi-source monitoring data includes: identifying abnormal data in the standardized dataset according to the logical consistency relationship, historical operating patterns, and equipment operating characteristics; and assessing the credibility of the standardized dataset based on the abnormal data and the credibility weight.

[0012] In one embodiment, the establishment of an equipment-level state model based on the equipment structure and functional division of high-voltage switchgear in a pumped storage power station includes:

[0013] Based on the equipment structure and functional division of the high-voltage switchgear, the high-voltage switchgear is divided into five functional components: operating mechanism, drive system, contact system, auxiliary circuit, and control circuit. Component-level modeling is performed on each of these functional components to obtain multiple single component models. These single component models are then fused to obtain the equipment-level state model. In one embodiment, the step of constructing a loop association model between the high-voltage switchgear based on the primary system topology of the pumped storage power station includes: based on the primary system topology, incorporating the electric braking switch, starting disconnector, generator circuit breaker, drive disconnector, phase sequence switching disconnector, main transformer, and combined high-voltage switch into a unified loop structure for description, thereby constructing the loop association model.

[0014] The step of identifying the current operating condition of the unit based on the unit operation data and equipment action sequence, and generating corresponding operating condition context information, includes: determining the current operating condition of the unit from multiple candidate operating conditions based on the unit operation data and the equipment action sequence, and performing operating context identification on the current operating condition of the unit to generate the operating condition context information; the candidate operating conditions include: start-up condition, traction condition, pumping condition, power generation condition, commutation condition, electrical braking condition, and maintenance condition.

[0015] In one embodiment, the step of reasoning and analyzing the expected operating state of the equipment and circuits based on the state evaluation benchmark and the reliability assessment result, combined with the operating condition context information, includes:

[0016] Based on the state evaluation benchmark, the reliability assessment result, and the operating condition context information, a fusion reasoning analysis is performed to obtain the expected action path, expected timing relationship, and expected location state of the equipment and circuit; the expected action path, expected timing relationship, and expected location state are summarized to generate the expected operating state. In one embodiment, the method further includes:

[0017] The actual monitored equipment status and loop status are compared and analyzed with the expected operating status to obtain the status deviation result. If the status deviation result indicates that a status deviation has been detected, the deviation cause reasoning is carried out based on the status deviation result, combined with the status evaluation benchmark, the loop association model and the operating condition context information. The deviation sources are distinguished into three categories: equipment body abnormality, loop logic abnormality and monitoring data abnormality. A comprehensive evaluation result including equipment status, loop status and risk level is output.

[0018] Secondly, this application also provides a loop-level state reasoning device based on operating condition context, comprising:

[0019] The model building module is used to establish an equipment-level state model based on the equipment structure and functional division of high-voltage switchgear in pumped storage power stations. Based on the equipment-level state model and combined with relevant equipment parameters, a mechanism model that maps to the equipment-level state model is established.

[0020] The operating condition establishment module is used to construct a loop association model between each of the high-voltage switchgear based on the primary system topology of the pumped storage power station, and to establish operating condition models corresponding to various typical operating conditions based on the operation process of the pumped storage unit.

[0021] The benchmark establishment module is used to establish state evaluation benchmarks for different operating scenarios based on the device-level state model, the mechanism model, the loop association model, and the operating condition model.

[0022] The credibility assessment module is used to collect multi-source monitoring data of the high-voltage switchgear, perform time synchronization and standardization processing on the multi-source monitoring data, construct a standardized dataset under a unified time axis, and perform credibility assessment on the standardized dataset based on the logical consistency relationship, historical operation pattern and equipment operation characteristics of the multi-source monitoring data to obtain the credibility assessment result.

[0023] The reasoning and analysis module is used to identify the current operating condition of the unit from the unit's operating data and equipment action sequence, generate corresponding operating condition context information, and, based on the state evaluation benchmark and the credibility assessment results, combine the operating condition context information to perform reasoning and analysis on the expected operating state of the equipment and circuits.

[0024] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0025] Based on the equipment structure and functional division of high-voltage switchgear in pumped storage power stations, an equipment-level state model is established. Based on this model and relevant equipment parameters, a mechanism model mapping the equipment-level state model is established. According to the primary system topology of the pumped storage power station, a loop association model between each high-voltage switchgear is constructed. Based on the operation process of the pumped storage units, operating condition models corresponding to various typical operating conditions are established. Based on the equipment-level state model, the mechanism model, the loop association model, and the operating condition models, state evaluation benchmarks for different operating scenarios are established. Data is collected from the pumped storage units. The multi-source monitoring data of the high-voltage switchgear is time-synchronized and standardized to construct a standardized dataset under a unified time axis. Based on the logical consistency relationship, historical operating patterns, and equipment operating characteristics of the multi-source monitoring data, the standardized dataset is evaluated for reliability, and a reliability evaluation result is obtained. Based on the unit operating data and equipment action sequence, the current operating condition of the unit is identified, and corresponding operating condition context information is generated. Based on the state evaluation benchmark and the reliability evaluation result, combined with the operating condition context information, the expected operating state of the equipment and circuit is inferred and analyzed.

[0026] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0027] Based on the equipment structure and functional division of high-voltage switchgear in pumped storage power stations, an equipment-level state model is established. Based on this model and relevant equipment parameters, a mechanism model mapping the equipment-level state model is established. According to the primary system topology of the pumped storage power station, a loop association model between each high-voltage switchgear is constructed. Based on the operation process of the pumped storage units, operating condition models corresponding to various typical operating conditions are established. Based on the equipment-level state model, the mechanism model, the loop association model, and the operating condition models, state evaluation benchmarks for different operating scenarios are established. Data is collected from the pumped storage units. The multi-source monitoring data of the high-voltage switchgear is time-synchronized and standardized to construct a standardized dataset under a unified time axis. Based on the logical consistency relationship, historical operating patterns, and equipment operating characteristics of the multi-source monitoring data, the standardized dataset is evaluated for reliability, and a reliability evaluation result is obtained. Based on the unit operating data and equipment action sequence, the current operating condition of the unit is identified, and corresponding operating condition context information is generated. Based on the state evaluation benchmark and the reliability evaluation result, combined with the operating condition context information, the expected operating state of the equipment and circuit is inferred and analyzed.

[0028] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0029] Based on the equipment structure and functional division of high-voltage switchgear in pumped storage power stations, an equipment-level state model is established. Based on this model and relevant equipment parameters, a mechanism model mapping the equipment-level state model is established. According to the primary system topology of the pumped storage power station, a loop association model between each high-voltage switchgear is constructed. Based on the operation process of the pumped storage units, operating condition models corresponding to various typical operating conditions are established. Based on the equipment-level state model, the mechanism model, the loop association model, and the operating condition models, state evaluation benchmarks for different operating scenarios are established. Data is collected from the pumped storage units. The multi-source monitoring data of the high-voltage switchgear is time-synchronized and standardized to construct a standardized dataset under a unified time axis. Based on the logical consistency relationship, historical operating patterns, and equipment operating characteristics of the multi-source monitoring data, the standardized dataset is evaluated for reliability, and a reliability evaluation result is obtained. Based on the unit operating data and equipment action sequence, the current operating condition of the unit is identified, and corresponding operating condition context information is generated. Based on the state evaluation benchmark and the reliability evaluation result, combined with the operating condition context information, the expected operating state of the equipment and circuit is inferred and analyzed.

[0030] The aforementioned loop-level state reasoning method, device, computer equipment, computer-readable storage medium, and computer program product based on operating condition context extend the state of high-voltage switchgear from the overall level to the component level by establishing a device-level modeling and component-level index analysis mechanism. This enables the decomposition and analysis of key indicators such as action time, travel characteristics, and contact actions, allowing the equipment operating state to be expressed in a more granular way, thereby improving the accuracy and interpretability of equipment state identification. Furthermore, by constructing a loop association model, multiple high-voltage switchgear devices in the primary system topology of a pumped storage power station are incorporated into a unified loop structure for analysis, achieving a unified expression of the action sequence, logical relationships, and state dependencies between devices. This overcomes the limitations of independent analysis of single devices, allowing the system to understand the equipment operating state from the perspective of the entire loop. Additionally, by introducing an operating condition context modeling method, the operating state of the equipment is correlated with the actual operating conditions of the unit, enabling the state analysis results to reflect the differences in equipment behavior under different operating conditions. This avoids the problem of semantic inconsistency of the same indicator at different operating stages, thereby improving the accuracy, adaptability, and consistency of state analysis under complex operating conditions and enabling it to adapt to complex dynamic operating conditions. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 This is an application environment diagram of a loop-level state reasoning method based on operating condition context in one embodiment;

[0033] Figure 2 This is a flowchart illustrating a loop-level state reasoning method based on operating condition context in one embodiment.

[0034] Figure 3 This is a flowchart illustrating a loop-level state reasoning method based on operating condition context in a specific embodiment.

[0035] Figure 4 This is a schematic diagram of the overall system architecture of a loop-level state reasoning method based on working condition context in an application embodiment;

[0036] Figure 5 This is an architecture diagram of a distributed modular acquisition device in an application embodiment;

[0037] Figure 6 This is a diagram of a real-time monitoring platform in one application example;

[0038] Figure 7 This is a device-level diagnostic reasoning graph in one application embodiment;

[0039] Figure 8 This is a loop-level diagnostic reasoning graph in one application example;

[0040] Figure 9 This is a working condition access diagram for an application embodiment;

[0041] Figure 10 A loop modeling diagram for one application embodiment;

[0042] Figure 11 A device modeling diagram for one application embodiment;

[0043] Figure 12 This is a structural block diagram of a loop-level state reasoning device based on operating condition context in one embodiment;

[0044] Figure 13 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0045] 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.

[0046] The online monitoring system for high-voltage switchgear in pumped-storage power stations consists of sensors, data acquisition devices, communication networks, and an analysis platform. Due to the complex on-site operating environment, the monitoring system is inevitably affected by factors such as electromagnetic interference, equipment aging, communication anomalies, time synchronization deviations, and software defects during long-term operation, leading to data distortion, drift, missing data, or abnormal fluctuations. Furthermore, the development and testing phases of online monitoring systems often struggle to construct an operating environment completely identical to that of actual power stations. Reliability verification is frequently based on limited operating conditions and samples, failing to cover the entire equipment lifecycle and all operating scenarios. Therefore, regardless of rule-based methods, statistical analysis methods, or intelligent analysis methods, there is a possibility of erroneous judgments due to incomplete data, data anomalies, or insufficient cognitive basis. In addition, the operating conditions of pumped-storage units are complex; the equipment status is not only related to its own operating parameters but also influenced by current operating conditions, equipment functional positioning, and loop operation relationships. Simply relying on local monitoring indicators for status analysis is insufficient to accurately interpret the actual operating status of the equipment and to distinguish between equipment anomalies, monitoring anomalies, and status differences caused by changes in operating conditions. Therefore, there is a need for an analytical method that can comprehensively utilize multi-source monitoring information, operating condition information, and loop correlations to improve the understanding and cognition of system status under conditions of uncertainty in monitoring data, incomplete equipment mechanism information, and complex and variable operating conditions. This method can reduce the impact of abnormal data, erroneous data, and cognitive biases on the status judgment results, and achieve accurate analysis and comprehensive evaluation of equipment operating status and loop operating status.

[0047] The loop-level state reasoning method based on operating condition context provided in this application can be applied to, for example... Figure 1 The application environment shown illustrates this. In this environment, the terminal can communicate with the server via a network. The data storage system can store the data that the server needs to process. The data storage system can be integrated onto the server or located on the cloud or other network servers. In such... Figure 1 In the application environment shown, the terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. The server can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0048] In one embodiment, such as Figure 2 As shown, a loop-level state reasoning method based on operating condition context is provided, which can be applied to... Figure 1 In the terminal, the method may include the following steps:

[0049] Step S201: Based on the equipment structure and functional division of the high-voltage switchgear in the pumped storage power station, establish an equipment-level state model. Based on the equipment-level state model and combined with relevant equipment parameters, establish a mechanism model that maps to the equipment-level state model.

[0050] Specifically, based on the equipment structure and functional division, the terminal performs equipment-level modeling of high-voltage switchgear, including operating mechanisms, drive systems, contact systems, auxiliary circuits, and control circuits, defining the functional attributes, state variables, monitoring parameters, and correlations of each component. At the same time, combined with equipment design parameters, experimental data, reverse analysis, and simulation results, a mechanism model related to equipment state changes and performance degradation is established, forming a mapping relationship between equipment structure, operating status, monitoring data, and performance indicators, providing a theoretical basis for condition assessment and degradation analysis.

[0051] Step S202: Based on the primary system topology of the pumped storage power station, construct a loop association model between each high-voltage switchgear, and establish operating condition models corresponding to various typical operating conditions based on the operation process of the pumped storage unit.

[0052] Specifically, based on the primary system structure, control logic, and equipment functional relationships of the pumped storage power station, the terminal constructs a loop association model between equipment. This loop model describes the connection relationships, action sequence relationships, logical dependencies, and state influence relationships between equipment, enabling the state of individual equipment to be expressed in relation to each other at the loop level. Furthermore, based on the operation process of the pumped storage unit, typical operating condition models are established, including startup, traction, pumping, power generation, commutation, electrical braking, shutdown, and maintenance. These operating condition models describe the participating equipment, equipment responsibilities, action objectives, and expected behaviors at different operating stages, and form corresponding state constraints. Through these operating condition models, equipment state judgment is transformed from fixed threshold judgment to state understanding based on operating scenarios.

[0053] Step S203: Based on the device-level state model, mechanism model, loop correlation model, and operating condition model, establish state evaluation benchmarks for different operating scenarios.

[0054] The status evaluation benchmark includes the expected state of the equipment, the relationship between the states of components, the timing of actions, the process of position changes, the logic constraints of the loop, and the allowable deviation range. This evaluation benchmark changes with the operating conditions and the responsibilities of the equipment, rather than being a fixed alarm threshold.

[0055] Specifically, the terminal establishes state evaluation benchmarks for different operating scenarios based on device-level state models, mechanism models, loop correlation models, and operating condition models.

[0056] Step S204: Collect multi-source monitoring data of the high-voltage switchgear, perform time synchronization and standardization processing on the multi-source monitoring data, construct a standardized dataset under a unified time axis, and conduct a credibility assessment on the standardized dataset based on the logical consistency relationship, historical operation patterns and equipment operation characteristics of the multi-source monitoring data to obtain the credibility assessment result.

[0057] The multi-source monitoring data can include current, voltage, displacement, auxiliary contacts, event sequence records, visual recognition results, and other operating status data.

[0058] Specifically, this solution adopts an overall architecture of "lightweight front-end acquisition and centralized unified analysis." The front-end acquisition device is only responsible for acquiring analog, digital, and event data, and performs basic functions such as analog-to-digital conversion, waveform recording, event sequence recording, timestamp marking, and data uploading. It does not perform status analysis, index calculation, or fault diagnosis on-site, ensuring the integrity and traceability of the raw data. Then, the terminal performs unified time synchronization and standardization processing on multi-source data from different acquisition nodes, constructing a data representation system under a unified time axis. Then, based on the logical consistency relationship, historical operating patterns, and equipment operating characteristics of the multi-source monitoring data, the terminal performs a credibility assessment on the standardized dataset, identifying abnormal data caused by factors such as sensor failure, acquisition anomalies, communication anomalies, time synchronization anomalies, and environmental interference, and obtaining a credible monitoring dataset containing the data credibility assessment results.

[0059] For example, multiple front-end data acquisition devices are deployed on-site according to the equipment, while the centralized processing platform is deployed at the power plant monitoring center. The front-end data acquisition devices are responsible for collecting full monitoring data during the operation of the corresponding equipment. Analog quantities include continuously changing signals such as opening and closing coil current, motor current, contact displacement, SF6 gas density, and equipment temperature; digital quantities include switching information such as auxiliary contact status, limit switch signals, and protection action signals. The acquisition devices also record waveforms of key actions such as opening and closing of the equipment and add high-precision timestamps to all collected data and event data. Specifically, the front-end data acquisition devices only perform signal acquisition, analog-to-digital conversion, data caching, and data encapsulation functions; they do not perform any state calculations, index analysis, or logical judgments, thus ensuring the integrity, objectivity, and traceability of the raw data from an architectural perspective. The collected data is transmitted to the centralized processing platform via industrial Ethernet.

[0060] Step S205: Based on the unit operation data and equipment action sequence, identify the current operating condition of the unit, generate the corresponding operating condition context information, and, based on the status evaluation benchmark and credibility assessment results, combine the operating condition context information to perform reasoning analysis on the expected operating state of the equipment and circuits.

[0061] Specifically, based on the unit's operating data and equipment action sequence, the terminal identifies the unit's current operating condition and generates corresponding operating condition context information. Based on the status evaluation benchmark and reliability assessment results, and combined with the operating condition context information, it further deduces the expected operating state that the equipment and circuits should achieve under the current operating condition, including the expected action path, expected position status, expected action sequence, and expected circuit status. Through comparative analysis of the actual state and the expected state, the terminal obtains the state deviation results and, in conjunction with the operating condition context, circuit relationships, and historical operating behavior, infers and analyzes the causes of the deviation.

[0062] This embodiment establishes a device-level modeling and component-level index analysis mechanism, extending the state of high-voltage switchgear from the overall level to the component level. This enables the decomposition and analysis of key indicators such as action time, travel characteristics, and contact actions, allowing for a more granular expression of equipment operating status and improving the accuracy and interpretability of equipment status identification. Furthermore, by constructing a loop association model, multiple high-voltage switchgear devices in the primary system topology of a pumped storage power station are incorporated into a unified loop structure for analysis. This achieves a unified expression of the action sequence, logical relationships, and state dependencies between devices, overcoming the limitations of independent analysis of single devices and allowing the system to understand equipment operating status from an overall loop perspective. Additionally, by introducing a condition context modeling method, the equipment operating status is correlated with the actual operating conditions of the unit, enabling the state analysis results to reflect the differences in equipment behavior under different operating conditions. This avoids semantic inconsistencies in the same indicator at different operating stages, thereby improving the accuracy, adaptability, and consistency of state analysis under complex operating conditions and enabling it to adapt to complex dynamic conditions.

[0063] In one embodiment, before performing a credibility assessment on the standardized dataset, the method of this application further includes the following steps:

[0064] Consistency analysis is performed on the standardized dataset to obtain the consistency relationship between multi-source monitoring data. Combined with the logical relationship between the multi-source monitoring data, the logical consistency relationship is obtained. Based on the importance of each monitoring data in the multi-source monitoring data, a credibility weight is assigned to each monitoring data.

[0065] In step S204 above, the credibility assessment of the standardized dataset based on the logical consistency relationship, historical operating patterns, and equipment operating characteristics of multi-source monitoring data may include the following steps:

[0066] Based on logical consistency relationships, historical operating patterns, and equipment operating characteristics, abnormal data in the standardized dataset is identified; based on the abnormal data and credibility weights, the credibility of the standardized dataset is evaluated.

[0067] Specifically, after receiving monitoring data from different acquisition nodes and sampling frequencies, the terminal first uses a unified clock across the entire station as a reference and employs an interpolation alignment algorithm to synchronize the multi-source data, constructing a standardized dataset with a unified time axis to eliminate timing deviations caused by time offsets and communication delays from different acquisition channels. Then, the terminal performs a reliability assessment of the standardized dataset based on a triple-check logic: first, single-channel self-consistency check, judging whether data exhibits sudden changes, jams, or exceeding limits based on historical statistical patterns; second, multi-channel consistency check, combining electrical logic and physical correlation to verify whether related multi-channel data conforms to logical correspondences, such as the timing correspondence between tripping commands and auxiliary contact actions; and third, historical pattern check, comparing historical operating data under the same conditions to identify slow data drift trends. Based on the triple-check results, each monitoring data point is assigned a reliability weight of 0 to 1. Data with a reliability weight below a set threshold is downweighted or removed in subsequent analysis, ultimately forming a reliable monitoring dataset.

[0068] In one embodiment, step S201 above, based on the equipment structure and functional division of the high-voltage switchgear in the pumped storage power station, establishes an equipment-level state model, which may include the following steps:

[0069] Based on the equipment structure and functional division of the high-voltage switchgear, the high-voltage switchgear is divided into five functional components: operating mechanism, drive system, contact system, auxiliary circuit, and control circuit. Component-level modeling is performed on each type of functional component to obtain multiple single component models. The multiple single component models are then fused to obtain the equipment-level state model.

[0070] Specifically, for each high-voltage switchgear, the terminal classifies it into five functional components according to their functional structure: operating mechanism, drive system, contact system, auxiliary circuit, and control circuit. Component-level modeling is performed for each type of functional component, resulting in multiple individual component models. These models are then fused to obtain an equipment-level state model, defining the functional attributes, state variables, monitoring parameters, and relationships of each component. Simultaneously, combining equipment design parameters, experimental data, reverse engineering, and simulation results, a mechanism model related to equipment state changes and performance degradation is established, forming a mapping relationship between equipment structure, operating status, monitoring data, and performance indicators, providing a theoretical basis for state assessment and degradation analysis.

[0071] In one embodiment, step S202 above, which involves constructing a loop association model between various high-voltage switchgear based on the primary system topology of the pumped storage power station, may include the following steps:

[0072] Based on the primary system topology, the electric braking switch, starting disconnector, generator circuit breaker, drive disconnector, phase sequence switching disconnector, main transformer, and combined high-voltage switch are incorporated into a unified loop structure for description, so as to construct a loop association model.

[0073] In step S205 above, based on the unit's operating data and equipment action sequence, the current operating condition of the unit is identified, and the corresponding operating condition context information is generated. This may include the following steps:

[0074] Based on the unit's operating data and equipment action sequence, the current operating condition of the unit is determined from multiple candidate operating conditions, and the operating context of the current operating condition of the unit is identified to generate operating condition context information. The candidate operating conditions include: start-up condition, traction condition, pumping condition, power generation condition, commutation condition, electrical braking condition, and maintenance condition.

[0075] Specifically, based on the electrical topology of the power plant's primary system, the terminal constructs a complete loop association model for electrical braking switches, starting disconnectors, generator circuit breakers, drive disconnectors, phase sequence switching disconnectors, main transformers, and combined high-voltage switches. The model defines the electrical connections between devices, the sequence of actions during operating condition switching, the logical dependencies of electrical interlocks, and the state transmission relationships during faults. For example, the timing constraint that "under drive conditions, the drive disconnector can only operate after the starting disconnector has been closed" is included. The loop association model realizes the associated expression of the state of a single device at the loop level, providing a structural foundation for subsequent system-level analysis. Furthermore, based on the characteristics of unit operation control signals and equipment action sequences, the terminal identifies the current operating condition of the unit, including seven typical operating conditions: start-up, drive, pumping, power generation, commutation, electrical braking, and maintenance. Each type of operating condition generates a unique operating condition context information, which clarifies the functional positioning of each device, the sequence of actions to be executed, the timing requirements, and the target state under that operating condition. For example, under the power generation condition, the generator outlet circuit breaker should be in the closed position and the electric braking switch should be in the open position. The operating condition context provides scenario-based constraint boundaries for state analysis, enabling state judgment to adapt to the differentiated requirements of different operating stages.

[0076] In one embodiment, step S205 above, based on the state evaluation benchmark and the reliability assessment results, and combined with the operating condition context information, performs reasoning analysis on the expected operating state of the equipment and circuits, which may include the following steps:

[0077] Based on the state evaluation benchmark, credibility assessment results, and operating condition context information, a fusion reasoning analysis is performed to obtain the expected action paths, expected timing relationships, and expected location states of the equipment and loops. These expected action paths, timing relationships, and location states are then summarized to generate the expected operating state. Specifically, based on the state evaluation benchmark and credibility assessment results, and combined with operating condition context information, the terminal derives the expected operating states of each device and the entire loop under the current operating condition, including expected action paths, expected timing relationships, and expected location states. Then, the expected action paths, timing relationships, and location states are summarized to generate the expected operating state.

[0078] In one embodiment, the method of this application further includes the following steps:

[0079] The actual monitored equipment status and loop status are compared and analyzed with the expected operating status to obtain the status deviation results. If the status deviation results indicate that a status deviation has been detected, the deviation cause reasoning is carried out based on the status deviation results, combined with the status evaluation benchmark, loop association model and operating condition context information. The deviation sources are distinguished into three categories: equipment body abnormality, loop logic abnormality and monitoring data abnormality. A comprehensive evaluation result including equipment status, loop status and risk level is output.

[0080] Specifically, the terminal compares the actual monitored equipment status and loop status with the expected operating status item by item, calculates the status deviation amount and duration, and forms a status deviation result. When a status deviation is detected, the platform combines the equipment-level analysis results, loop correlations, and operating context information to infer the cause of the deviation: if the indicators of the equipment components are abnormal and conform to the characteristics of equipment failure, it is determined to be an equipment-specific abnormality; if the indicators of a single equipment component are normal, but the timing of equipment actions and loop conduction logic do not conform to the operating constraints, it is determined to be a loop logic abnormality; if there are no corresponding abnormalities in the equipment components and loop logic, and the corresponding monitoring data has low reliability, it is determined to be a monitoring data abnormality. After completing the deviation tracing, the platform outputs a comprehensive evaluation result, including the equipment status level, loop operating status, deviation type, risk level, and reliability description.

[0081] In one embodiment, such as Figure 3 As shown, a loop-level state reasoning method based on operating condition context is provided in a specific embodiment, which specifically includes the following steps:

[0082] Step S301: Based on the equipment structure and functional division of the high-voltage switchgear, the high-voltage switchgear is divided into five functional components: operating mechanism, drive system, contact system, auxiliary circuit, and control circuit. Component-level modeling is performed on each type of functional component to obtain multiple single component models. The multiple single component models are then fused to obtain the equipment-level state model. Based on the equipment-level state model and combined with relevant equipment parameters, a mechanism model that maps to the equipment-level state model is established.

[0083] Step S302: Based on the primary system topology, the electric braking switch, starting disconnect switch, generator circuit breaker, drive disconnect switch, phase sequence switching disconnect switch, main transformer, and combined high-voltage switch are incorporated into a unified circuit structure for description, so as to construct a circuit association model between various high-voltage switchgear, and establish operating condition models corresponding to various typical operating conditions according to the operation process of the pumped storage unit.

[0084] Step S303: Based on the equipment-level state model, mechanism model, loop correlation model, and operating condition model, establish state evaluation benchmarks for different operating scenarios; collect multi-source monitoring data of the high-voltage switchgear, perform time synchronization and standardization processing on the multi-source monitoring data, construct a standardized dataset under a unified time axis, and identify abnormal data in the standardized dataset according to the logical consistency relationship, historical operating patterns, and equipment operating characteristics of the multi-source monitoring data; based on the abnormal data and the credibility weight, evaluate the credibility of the standardized dataset to obtain the credibility evaluation result.

[0085] Step S304: Based on the unit operation data and equipment action sequence, determine the current operating condition of the unit from multiple candidate operating conditions, and perform operating context identification on the current operating condition of the unit to generate corresponding operating condition context information. Based on the status evaluation benchmark, credibility assessment results and operating condition context information, perform fusion reasoning analysis to obtain the expected action path, expected timing relationship and expected position status of the equipment and circuits. Summarize the expected action path, expected timing relationship and expected position status to generate the expected operating status.

[0086] Step S305: Compare and analyze the actual monitored equipment status and loop status with the expected operating status to obtain the status deviation result; if the status deviation result indicates that a status deviation has been detected, then based on the status deviation result, combine the status evaluation benchmark, loop association model and operating context information to carry out deviation cause reasoning, distinguish three types of deviation sources: equipment body abnormality, loop logic abnormality and monitoring data abnormality, and output a comprehensive evaluation result including equipment status, loop status and risk level.

[0087] The beneficial effects of the above embodiments are as follows:

[0088] This application does not rely on a complete equipment mechanism model from a specific manufacturer. Instead, it utilizes reliable monitoring datasets, operating context information, and loop correlations to construct a cognitive process of equipment operating status, realizing the transformation from "data monitoring" to "state understanding" and improving the accuracy, reliability, and engineering applicability of equipment status analysis results under complex operating conditions.

[0089] To more clearly illustrate the loop-level state reasoning method based on operating condition context provided in this application, the following specific description uses an application embodiment to illustrate this loop-level state reasoning method based on operating condition context. In one embodiment, such as Figure 4-11 As shown, this application also provides a loop-level state reasoning method based on operating condition context, specifically including the following steps:

[0090] Step 1: Device-level state model construction:

[0091] Based on the equipment structure and functional division, equipment-level modeling is performed on the switchgear, including operating mechanisms, drive systems, contact systems, auxiliary circuits, and control circuits. The functional attributes, state variables, monitoring parameters, and relationships of each component are defined. Simultaneously, combining equipment design parameters, experimental data, reverse analysis, and simulation results, a mechanism model related to equipment state changes and performance degradation is established, forming a mapping relationship between equipment structure, operating status, monitoring data, and performance indicators, providing a theoretical basis for condition assessment and degradation analysis.

[0092] Step 2, Loop Model Construction:

[0093] Based on the primary system structure, control logic, and equipment functional relationships of a pumped storage power station, a loop association model is constructed between the equipment. For example, the following equipment association relationships are established: electric braking switch → starting disconnect switch → generator circuit breaker → drive disconnect switch → phase sequence switching disconnect switch → main transformer → combined high-voltage switch. The loop model describes the connection relationships, action sequence relationships, logical dependencies, and state influence relationships between the equipment, enabling the state of individual equipment to be expressed in relation to each other at the loop level.

[0094] Step 3: Construction of the working condition model:

[0095] Based on the operation process of pumped storage units, typical operating condition models are established, including startup, traction, pumping, power generation, commutation, electrical braking, shutdown, and maintenance. The operating condition models are used to describe the participating equipment, equipment responsibilities, action objectives, and expected behaviors in different operating stages, and form corresponding state constraints. Through the operating condition models, the equipment state judgment is transformed from fixed threshold judgment to state understanding based on the operating scenario.

[0096] Step 4: State baseline construction:

[0097] Based on equipment-level state models, loop models, and operating condition models, state evaluation benchmarks are established for different operating scenarios. These benchmarks include the desired equipment state, component state relationships, action sequence, position change process, loop logic constraints, and allowable deviation ranges. These benchmarks vary with operating conditions and equipment responsibilities, rather than being fixed alarm thresholds.

[0098] Step 5: Multi-source data collection and credibility assessment:

[0099] The system acquires current, voltage, displacement, auxiliary contact data, event sequence records, visual recognition results, temperature, and other status data during equipment operation through on-site acquisition devices. The front-end acquisition device is responsible for data acquisition, conversion, waveform recording, event logging, and time stamping; it does not perform status judgment or business reasoning. Data from different sources is synchronized in time, and the system assesses data reliability by combining multi-source data consistency, historical operating patterns, and equipment behavior characteristics, identifying abnormal data and generating a reliability evaluation result.

[0100] Step 6: Run Context Recognition

[0101] Based on the unit's operating status, control commands, equipment action information, and loop status, the current operating condition is identified. Combined with the operating condition model, the currently participating equipment, equipment responsibilities, and corresponding status evaluation benchmarks are determined to form the current operating context.

[0102] Step 7, State Mapping and Loop-Level Reasoning:

[0103] Real-time monitoring data is mapped to equipment models and state models to form the actual state of the equipment. Combining the mechanistic relationships in the equipment model, the correlation relationships in the loop model, and the state constraints in the operating condition model, the equipment state is comprehensively inferred. By analyzing the deviation between the actual state and the expected state, it is determined whether the equipment, components, and loops meet the current operating requirements.

[0104] Step 8: Anomaly Analysis and State Prediction

[0105] When the actual state deviates from the expected state, the source of the anomaly is analyzed by combining data reliability, equipment state model, mechanistic relationships, and loop correlations, distinguishing between data anomalies, equipment anomalies, and loop anomalies. Based on the current state, historical trends, and mechanistic degradation patterns, future changes in the equipment state are predicted. Finally, the system outputs equipment state, loop state, causes of anomalies, trends, and diagnostic criteria, providing support for operation monitoring and maintenance decisions. The beneficial effects of the above embodiments are as follows:

[0106] (1) Improve the reliability and availability of monitoring data: By introducing a data credibility assessment mechanism, consistency analysis and anomaly identification are performed on multi-source monitoring data from sensors and acquisition devices, effectively reducing the impact of data distortion caused by factors such as sensor drift, acquisition anomalies, communication interference and time synchronization deviation, so that subsequent status analysis is based on credible data and the overall reliability of monitoring results is improved.

[0107] (2) Improve the precision of equipment status expression: By establishing equipment-level modeling and component-level index analysis mechanism, the status of high-voltage switchgear is extended from the overall level to the component level, realizing the decomposition and analysis of key indicators such as action time, stroke characteristics and contact action, so that the equipment operating status can be expressed in a more granular way, thereby improving the accuracy and interpretability of equipment status identification.

[0108] (3) Enhance the overall ability to express the collaborative operation status of multiple devices: By constructing a loop-level correlation model, multiple high-voltage switchgear in the primary system of the pumped storage power station are included in a unified loop structure for analysis, so as to realize the unified expression of the action sequence, logical relationship and state dependency relationship between devices, thereby breaking through the limitation of independent analysis of single devices and enabling the system to understand the operating status of devices from the perspective of the overall loop.

[0109] (4) Improve the consistency and adaptability of state analysis under complex operating conditions: By introducing the operating condition context modeling method, the operating state of the equipment is associated with the actual operating conditions of the unit, so that the state analysis results can reflect the differences in equipment behavior under different operating conditions, avoid the problem of semantic inconsistency of the same index in different operating stages, and thus improve the adaptability and consistency of state analysis under complex operating conditions.

[0110] (5) Enhance system status understanding and anomaly identification capabilities: By introducing a reasoning mechanism of “comparing actual status with expected status”, the system can not only identify the current operating status of the equipment, but also determine whether it conforms to the expected behavior under the current working conditions and loop conditions, thereby effectively distinguishing between equipment anomalies, loop anomalies and data anomalies, and improving the accuracy and interpretability of anomaly identification.

[0111] (6) Enhance the overall cognitive ability and engineering applicability of the system: By constructing a hierarchical and progressive analysis system of “data credibility - equipment-level analysis - loop-level correlation - operating condition context - state reasoning”, the system is upgraded from the traditional single-point data monitoring mode to a state cognition and reasoning mode for complex power systems, thereby significantly improving the overall accuracy, stability and engineering applicability of the operation status analysis of high-voltage switchgear in pumped storage power stations.

[0112] It should be understood that although the steps in the flowcharts of the embodiments described above are shown 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 steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0113] Based on the same inventive concept, this application also provides a circuit-level state reasoning device for implementing the circuit-level state reasoning method based on operating condition context as described above. The solution provided by this device is similar to the implementation described in the above method. Therefore, the specific limitations in one or more circuit-level state reasoning device embodiments provided below can be found in the limitations of the circuit-level state reasoning method based on operating condition context described above, and will not be repeated here.

[0114] In one exemplary embodiment, such as Figure 12 As shown, a loop-level state reasoning device based on operating condition context is provided, which may include:

[0115] The model building module 1201 is used to establish an equipment-level state model based on the equipment structure and functional division of high-voltage switchgear in pumped storage power stations. Based on the equipment-level state model and combined with relevant equipment parameters, a mechanism model that maps to the equipment-level state model is established.

[0116] The operating condition establishment module 1202 is used to construct a loop association model between various high-voltage switchgear based on the primary system topology of the pumped storage power station, and to establish operating condition models corresponding to various typical operating conditions based on the operation process of the pumped storage unit.

[0117] The benchmark establishment module 1203 is used to establish state evaluation benchmarks under different operating scenarios based on equipment-level state models, mechanism models, loop correlation models and operating condition models.

[0118] The credibility assessment module 1204 is used to collect multi-source monitoring data of the high-voltage switchgear, perform time synchronization and standardization processing on the multi-source monitoring data, construct a standardized dataset under a unified time axis, and conduct credibility assessment on the standardized dataset based on the logical consistency relationship, historical operation patterns and equipment operation characteristics of the multi-source monitoring data to obtain the credibility assessment result.

[0119] The reasoning and analysis module 1205 is used to identify the current operating condition of the unit based on the unit's operating data and equipment action sequences, generate corresponding operating condition context information, and, based on the state evaluation benchmark and credibility assessment results, combine the operating condition context information to perform reasoning and analysis on the expected operating state of the equipment and circuits. In one embodiment, the device may further include: a data analysis module, used to perform consistency analysis on the standardized dataset to obtain the consistency relationship between multi-source monitoring data, and to obtain the logical consistency relationship by combining the logical relationship between the multi-source monitoring data; and to assign credibility weights to each monitoring data according to the importance of each monitoring data in the multi-source monitoring data; and a credibility assessment module 1204, used to identify abnormal data in the standardized dataset based on the logical consistency relationship, historical operating patterns, and equipment operating characteristics; and to perform credibility assessment on the standardized dataset based on the abnormal data and the credibility weights.

[0120] In one embodiment, the model building module 1201 is further configured to divide the high-voltage switchgear into five functional components—operating mechanism, drive system, contact system, auxiliary circuit, and control circuit—based on the equipment structure and functional division of the high-voltage switchgear; perform component-level modeling on each type of functional component to obtain multiple single component models; and fuse the multiple single component models to obtain an equipment-level state model.

[0121] In one embodiment, the operating condition establishment module 1202 is further configured to incorporate the electric braking switch, starting disconnector, generator circuit breaker, drive disconnector, phase sequence switching disconnector, main transformer, and combined high-voltage switch into a unified loop structure for description based on the primary system topology, in order to construct a loop association model; the reasoning and analysis module 1205 is further configured to determine the current operating condition of the unit from multiple candidate operating conditions based on the unit operating data and equipment action sequence, and to perform operating context identification on the current operating condition of the unit to generate operating condition context information; the candidate operating conditions include: starting condition, drive condition, pumping condition, power generation condition, commutation condition, electric braking condition, and maintenance condition.

[0122] In one embodiment, the reasoning analysis module 1205 is further configured to perform fusion reasoning analysis based on the state evaluation benchmark, the credibility assessment result and the working condition context information to obtain the expected action path, expected timing relationship and expected position status of the equipment and circuit; and to summarize the expected action path, expected timing relationship and expected position status to generate the expected operating status.

[0123] In one embodiment, the device may further include: a deviation analysis module, used to compare and analyze the actual monitored equipment status and loop status with the expected operating status to obtain a status deviation result; if the status deviation result indicates that a status deviation has been detected, then based on the status deviation result, combined with the status evaluation benchmark, loop association model and operating context information, deviation cause reasoning is carried out, distinguishing three types of deviation sources: equipment body abnormality, loop logic abnormality and monitoring data abnormality, and outputting a comprehensive evaluation result including equipment status, loop status and risk level.

[0124] Each module in the aforementioned loop-level state reasoning device based on operating condition context can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0125] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 13As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational 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 stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a loop-level state reasoning method based on operational context. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0126] Those skilled in the art will understand that Figure 13 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.

[0127] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0128] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0129] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0130] 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, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0131] Those skilled in the art will understand that all or part of the processes in the methods of 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 of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory 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, artificial intelligence (AI) processors, etc., and are not limited to these.

[0132] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0133] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A loop-level state reasoning method based on operating condition context, characterized in that, The method includes: Based on the equipment structure and functional division of high-voltage switchgear in pumped storage power stations, an equipment-level state model is established. Based on the equipment-level state model and combined with relevant equipment parameters, a mechanism model that maps to the equipment-level state model is established. Based on the primary system topology of the pumped storage power station, a loop association model between each of the high-voltage switchgear is constructed, and based on the operation process of the pumped storage unit, a working condition model corresponding to various typical operating conditions is established. Based on the device-level state model, the mechanism model, the loop association model, and the operating condition model, state evaluation benchmarks are established for different operating scenarios. Multi-source monitoring data of the high-voltage switchgear is collected, and the multi-source monitoring data is time-synchronized and standardized to construct a standardized dataset under a unified time axis. Based on the logical consistency relationship, historical operation pattern and equipment operation characteristics of the multi-source monitoring data, the credibility of the standardized dataset is evaluated to obtain the credibility evaluation result. Based on the unit's operating data and equipment action sequence, the current operating condition of the unit is identified, and corresponding operating condition context information is generated. Based on the state evaluation benchmark and the credibility assessment results, and combined with the operating condition context information, the expected operating state of the equipment and circuits is inferred and analyzed.

2. The method according to claim 1, characterized in that, Before performing a credibility assessment on the standardized dataset, the method further includes: A consistency analysis is performed on the standardized dataset to obtain the consistency relationship between the multi-source monitoring data. Combined with the logical relationship between the multi-source monitoring data, the logical consistency relationship is obtained. Based on the importance of each monitoring data point in the multi-source monitoring data, a credibility weight is assigned to each monitoring data point. The credibility assessment of the standardized dataset based on the logical consistency relationship, historical operating patterns, and equipment operating characteristics of the multi-source monitoring data includes: Based on the logical consistency relationship, the historical operating patterns, and the equipment operating characteristics, abnormal data in the standardized dataset is identified; based on the abnormal data and the credibility weight, the credibility of the standardized dataset is evaluated.

3. The method according to claim 2, characterized in that, The equipment-level state model is established based on the equipment structure and functional division of high-voltage switchgear in pumped storage power stations, including: Based on the equipment structure and function of the high-voltage switchgear, the high-voltage switchgear is divided into five functional components: operating mechanism, drive system, contact system, auxiliary circuit, and control circuit. Component-level modeling is performed on all the aforementioned functional components to obtain multiple individual component models. These multiple individual component models are then fused to obtain the device-level state model.

4. The method according to claim 1, characterized in that, The step of constructing a loop association model between the high-voltage switchgear based on the primary system topology of the pumped storage power station includes: Based on the primary system topology, the electric braking switch, starting disconnect switch, generator circuit breaker, drive disconnect switch, phase sequence switching disconnect switch, main transformer, and combined high-voltage switch are incorporated into a unified loop structure for description, so as to construct the loop association model. The process of identifying the current operating condition of the unit based on unit operation data and equipment action sequences, and generating corresponding operating condition context information, includes: Based on the unit's operating data and the equipment's action sequence, the current operating condition of the unit is determined from multiple candidate operating conditions, and the operating context of the current operating condition of the unit is identified to generate the operating condition context information; the candidate operating conditions include: start-up condition, traction condition, pumping condition, power generation condition, commutation condition, electrical braking condition, and maintenance condition.

5. The method according to claim 1, characterized in that, Based on the state evaluation benchmark and the credibility assessment results, and in conjunction with the operating condition context information, the expected operating state of the equipment and circuits is inferred and analyzed, including: Based on the state evaluation benchmark, the credibility assessment result, and the working condition context information, a fusion reasoning analysis is performed to obtain the expected action path, expected timing relationship, and expected position status of the equipment and circuit. The expected action path, the expected timing relationship, and the expected position state are summarized to generate the expected running state.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: The actual monitored equipment status and circuit status are compared and analyzed with the expected operating status to obtain the status deviation results; If the status deviation result indicates that a status deviation has been detected, then based on the status deviation result, combined with the status evaluation benchmark, the loop association model and the operating condition context information, the deviation cause reasoning is carried out, and three types of deviation sources are distinguished: equipment body abnormality, loop logic abnormality and monitoring data abnormality. A comprehensive evaluation result including equipment status, loop status and risk level is output.

7. A loop-level state reasoning device based on operating condition context, characterized in that, The device includes: The model building module is used to establish an equipment-level state model based on the equipment structure and functional division of high-voltage switchgear in pumped storage power stations. Based on the equipment-level state model and combined with relevant equipment parameters, a mechanism model that maps to the equipment-level state model is established. The operating condition establishment module is used to construct a loop association model between each of the high-voltage switchgear based on the primary system topology of the pumped storage power station, and to establish operating condition models corresponding to various typical operating conditions based on the operation process of the pumped storage unit. The benchmark establishment module is used to establish state evaluation benchmarks for different operating scenarios based on the device-level state model, the mechanism model, the loop association model, and the operating condition model. The credibility assessment module is used to collect multi-source monitoring data of the high-voltage switchgear, perform time synchronization and standardization processing on the multi-source monitoring data, construct a standardized dataset under a unified time axis, and perform credibility assessment on the standardized dataset based on the logical consistency relationship, historical operation pattern and equipment operation characteristics of the multi-source monitoring data to obtain the credibility assessment result. The reasoning and analysis module is used to identify the current operating condition of the unit from the unit's operating data and equipment action sequence, generate corresponding operating condition context information, and, based on the state evaluation benchmark and the credibility assessment results, combine the operating condition context information to perform reasoning and analysis on the expected operating state of the equipment and circuits.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

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

Images