940 results about "Grid fault" patented technology

The invention relates to the technical field of fault analysis, in particular to a power grid fault intelligent diagnosis and analysis system which comprises a fault signal detection module, a propagation path analysis module, a fault positioning calculation module, a fault type analysis module and a fault influence analysis module. According to the invention, by monitoring the voltage transient data of the plurality of nodes of the power grid in real time, the instantaneous offset and the time sequence difference of the voltage can be accurately calculated, so that the voltage mutation exceeding the preset threshold value can be quickly identified in the continuous time window, the early identification of the power grid fault is quicker, the risk of false alarm is reduced, and the accuracy of the early identification is improved. By analyzing the propagation path and speed of the sudden change quantity along the power grid, the fault positioning precision is improved, rapid and accurate fault source tracing is realized, and by careful analysis of the current waveform of a fault point and combination of real-time tripping current data, the fault type can be identified more accurately, the fault handling strategy can be optimized, and the fault handling efficiency is improved. And the power grid fault processing efficiency and safety are improved.

The invention relates to the technical field of smart power grids, in particular to a fine tuning method and system based on a power failure multi-modal model and a medium, and the method comprises the steps: generating a knowledge retention mask according to a pre-training weight matrix of a multi-modal large language model; generating a sparse low-rank matrix according to the space-time sparse characteristic of the structured multi-modal data set; generating a conflict mitigation regularization item according to the knowledge retention mask and the sparse low-rank matrix, constructing a power task joint loss function according to the conflict mitigation regularization item, and performing fine tuning training on the multi-modal large language model to obtain a fine tuning multi-modal large language model; and inputting the real-time operation data of the power grid into the fine-tuning multi-mode large language model for reasoning to obtain a power grid fault diagnosis result, and performing isolation control on a power grid fault section according to the power grid fault diagnosis result. According to the method, efficient fine tuning is performed on the multi-modal large language model by using the power grid data space-time sparsity modeling and the conflict mitigation regularization strategy, and rapid and accurate diagnosis of the power grid fault is realized.

The invention discloses an intelligent diagnosis system of a power distribution network fault self-judgment switch device, and relates to the technical field of power system automation and intelligent power grids, and the intelligent diagnosis system comprises an intelligent diagnosis system interconnection hub which is in communication connection with a power parameter monitoring module, an intelligent fault detection module and a visual decision support module; the electric power parameter monitoring module monitors the state of a power distribution network in real time through a mutual inductor, voltage, current, power factors and harmonic data are collected through an intelligent electric meter, the intelligent fault detection module achieves fault recognition, trend prediction and anomaly detection through an LSTM neural network, and the decision support module provides a graphical interface and automatically generates a fault response strategy. According to the method, autonomous judgment and quick response of the power distribution network fault are achieved, the accuracy and efficiency of fault detection are remarkably improved, the false alarm rate and the missing report rate are reduced, meanwhile, the decision support module of the graphical interface simplifies the fault processing flow, and the stability and safety of power grid operation are improved.

The invention provides a power transmission network equipment fault diagnosis and life prediction method and system, and relates to the technical field of fault diagnosis, and the method comprises the steps: obtaining the time sequence electrical characteristic data of a plurality of monitoring nodes, carrying out the window segmentation and statistical characteristic extraction, building a dynamic association graph structure based on a space-time association constraint model, and obtaining the time sequence electrical characteristic data; and calculating the abnormal contribution degree of each node, marking candidate abnormal nodes, determining a fault propagation path through reverse tracing and path analysis, and finally outputting a fault positioning result. According to the invention, abnormal nodes can be accurately identified, a fault propagation path can be accurately tracked, and the accuracy and timeliness of power transmission network fault diagnosis are improved.

The invention discloses a low-voltage ride-through control method of a flywheel energy storage system, which is based on a low-voltage ride-through control strategy of model predictive current control (MPCC) so as to improve the low-voltage ride-through capability of the flywheel energy storage system when a power grid fails. A future current value is predicted through system modeling and a prediction algorithm, so that effective control is realized. The MPCC-based machine side-power grid side coordination control strategy can quickly respond to the voltage sag of the power grid, provide reactive power support, stabilize the voltage of the direct current bus, and ensure the safe and reliable operation of the flywheel energy storage system during the voltage sag period of the power grid. A traditional pulse width modulation (PWM) technology is abandoned, the optimal switching state is directly selected through a limited control set, and hardware implementation of a power grid side converter is simplified. A differential control strategy aiming at a power grid symmetric fault (three-phase voltage sudden drop) and an asymmetric fault (single-phase grounding) is provided, the method is suitable for a complex power grid fault scene, and the system universality is improved.

The invention discloses a power failure and recovery logic-based power supply fault diagnosis method for a low-voltage power distribution network, which belongs to the technical field of power supply fault diagnosis and comprises the following steps of: converting a user unstructured power failure complaint into a standardized event tag by utilizing a natural language processing technology, synchronously aligning an ammeter power failure pulse and a branch switch action record, and performing power failure diagnosis; constructing a multi-dimensional space-time event sequence; a fault propagation logic network is established through power supply unit topology division, a fault diffusion path is deduced according to a power failure time sequence difference of adjacent units and a failure state of a protection device, and an initial fault point is reversely positioned. And meanwhile, the fault association probability between the units is dynamically corrected, and a weighted candidate fault chain is generated. And through multiple verification mechanisms, the fault propagation tree is reversely corrected. And finally, calculating the confidence coefficient, and screening out the fault chain with the optimal time-space consistency. The problems of multi-source information splitting, space-time correlation weakening and insufficient verification reliability in low-voltage power distribution network fault positioning are solved.

A method, system, and readable storage medium for fault line selection in distribution networks is provided. The method includes: obtaining the zero-sequence current of each feeder and the zero-sequence voltage of the busbar within a preset time window after a fault occurs; using these to process the feeder's short-time window zero-sequence instantaneous power curve cluster in the distribution network through KPCA (Kernel Principal Component Analysis) for dimensionality reduction, determining the principal component scores; and performing BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies) clustering based on these scores to identify whether a feeder is faulted. This clustering process allows for precise and rapid identification of the faulted feeder, even when the current is small, improving detection accuracy. This solves the problem of quickly identifying the faulted feeder in a small current grounding distribution network during single-phase grounding faults.

The invention discloses a coal mine power supply system multi-scene modeling method, system, device and medium, and belongs to the technical field of power system scene modeling, and the method comprises the steps: building a main circuit topology, and constructing a simulation model containing a user-defined module; configuring equipment parameters, and importing field survey data to construct a dynamic load matrix; setting a fault scene, and accurately simulating various power grid faults through a circuit breaker time sequence; parallel simulation is started, and bus and key node data are collected in the simulation process; performing multi-dimensional index analysis on the collected data, and extracting key indexes; a verification report is automatically generated, and evaluation is completed in combination with a manual checking mechanism; and visually outputting a simulation result. According to the method, real-time adaptation of load impedance characteristics is realized, historical load curves can be imported in batches, a dynamic load matrix can be generated, and time-varying characteristics of coal mine loads can be accurately reproduced. On the fault simulation level, circuit breaker opening and closing logic is adopted, superposition simulation of bilateral voltage loss and multi-source faults is supported, and the seamless switching performance of the energy storage system is verified.

The invention relates to the technical field of digital twinning, in particular to a digital twinning fused power grid fault prediction system and method, and the system comprises a state sensing module, a path deduction module, a twinning mapping module and a prediction execution module. According to the method, multi-source heterogeneous sensing data are fused, a space-time alignment algorithm is executed to construct a structural state tensor, Laplacian operation is combined with a stress wave propagation model to analyze non-rigid deformation characteristics, a load transfer path atlas is generated to reveal recessive mechanical association, Young modulus is dynamically corrected through a finite element grid to form a structural degradation coefficient matrix, and the structural degradation coefficient matrix is obtained. The time sequence difference and the long short-term memory network are combined to capture the equipment degradation trend, the Kolmogov test is used to quantify the fault space-time distribution probability, the power grid equipment jumps from single threshold early warning to multi-physics coupling prediction, the fault prediction space-time resolution and dynamic adaptability are improved, the artificial experience dependence is reduced, and the fault prediction efficiency is improved. And the robustness of the complex working condition system is enhanced.

The invention discloses a transient optimization control method based on a parallel system of a virtual synchronous machine and a grid-following converter. The method comprises the following steps: 1, constructing a topological structure of the parallel system of the virtual synchronous machine and the grid-following converter; 2, based on the topological structure, establishing a mathematical model of a parallel system, including an active loop equation and a reactive loop equation of a virtual synchronous machine and a phase-locked loop equation of a grid-following converter; 3, constructing an equivalent circuit, a network equation and a transient analysis model of the parallel system based on the mathematical model; 4, on the basis of the equivalent circuit, the network equation and the transient analysis model, determining conditions met by respective balance points of the virtual synchronous machine and the grid-following converter by using a balance point method; and 5, when the power grid has a fault, constructing a transient optimization strategy according to a condition satisfied by the balance point so as to realize transient optimization control of the parallel system. According to the method, the control modes of a virtual synchronous machine power loop and a grid-following type converter phase-locked loop can be improved, so that the transient stability of a parallel system converter is improved.

The invention discloses an intelligent power grid fault deduction method and device based on a knowledge graph and electronic equipment, and relates to the technical field of power grid fault diagnosis, and the method comprises the steps: receiving protection action alarm information and circuit breaker tripping alarm information when a target intelligent power grid breaks down; based on the protection action alarm information and the circuit breaker tripping alarm information, performing hypothesis reasoning by using a preset power grid topology knowledge graph to obtain a suspected fault equipment set; performing deductive reasoning on each suspected fault device in the suspected fault device set by using a preset protection configuration knowledge graph based on the protection action alarm information and the circuit breaker tripping alarm information to obtain observation event confidence corresponding to each suspected fault device; and evidence fusion reasoning is carried out on each suspected fault device based on each expected observation event confidence, and actual fault information of the smart power grid is obtained. The method can improve the accuracy of the fault diagnosis result of the smart power grid.

The invention relates to a power electronics and energy storage technology, and aims to provide a medium-voltage uninterruptible power supply system based on cascade super-capacitance energy storage and a control method. According to the system, a cascade super-capacitance energy storage module with a three-phase structure is connected between an isolation reactor and a load side switch through a filter reactor and is used for stabilizing the voltage of a load bus; according to the invention, operations of adaptive power reference calculation, voltage phase control and voltage amplitude stable control are carried out; according to the method, the over-capacitance wide voltage operation characteristic is fully considered, and the control on the over-capacitance charging and discharging process is adaptively adjusted according to the power grid fault state and the over-capacitance voltage deviation, so that the system can provide the required power support when the fault occurs, stable energy supplementation is performed after recovery, the risks of over-capacitance voltage out-of-limit and the like are favorably avoided, and the system reliability is improved. And the effectiveness of energy management and the stability of the system are improved. And during a power grid fault period, the load voltage is recovered to be close to a rated value in a short time, voltage drop and overshoot are reduced, and the response speed and the voltage supporting capability of the system are enhanced.

The invention discloses a multi-target cooperative fault ride-through method suitable for a network-forming converter, and the method comprises the steps: carrying out the precise amplitude limiting of a fault current through an annular current limiter, and adjusting a power angle to a lower boundary of a transient stability domain during a fault period; and multi-target collaborative optimization of transient synchronous stability, power grid reactive power support and fault current suppression in the fault ride-through process is realized. An optimal power angle set meeting fault ride-through multi-target cooperation in a multi-element fault scene is constructed by performing off-line beforehand rehearsal training on a system physical model; when the power grid breaks down, the network construction type converter carries out online table look-up search based on the trained set, an active power instruction meeting the transient stability and the optimal reactive power support in the current fault scene is calculated, and the supporting capacity of the network construction type converter to the power grid is mined to the maximum extent while the network construction type converter operates safely and stably. According to the method provided by the invention, the network construction operation characteristics of the converter can be maintained under the power grid fault, and the multi-target collaborative fault ride-through capability of equipment is enhanced.

The invention relates to the technical field of power grid fault positioning, in particular to a rapid power grid fault positioning system based on digital twinning and AI, which obtains multi-dimensional operation data of each node of a power distribution network, constructs a structured data set, reflects the state of the system, and performs joint modeling on node features and a topological structure through a graph neural network. And reasoning to generate candidate fault nodes. And further constructing a digital twinborn model containing load flow calculation and disturbance injection, performing analogue simulation on candidate nodes, extracting an electrical quantity change rate, performing fuzzy similarity matching with operation data in a fault window, and accurately positioning a fault node. Through cooperation of three stages of prediction, simulation and matching, the problems of weak complex topology perception, poor perturbation identification, positioning offset and the like of the existing method are effectively solved, and the fault positioning precision and robustness are improved.

The invention relates to a reconfigurable battery energy storage system grid-connected and off-grid seamless switching control method and device. The method comprises the following steps of: sensing a real-time power grid state, pre-judging a system operation mode, and acquiring a millisecond-level panoramic information flow of the power grid state through a high-speed sampling voltage sensor, a high-speed sampling frequency sensor, a high-speed sampling phase sensor and a high-speed sampling communication interface. And pre-judging the stability and disturbance trend of the power grid through a deep learning algorithm, executing a power distribution and voltage support algorithm in grid-connected and off-grid modes, and calculating an optimal switching opportunity point and a system reconstruction target topology scheme. Meanwhile, the harmonic distortion rate and the voltage sag depth are calculated in real time through discrete Fourier transform, so that a mode pre-judgment mechanism is automatically triggered. After switching, key parameters such as voltage, frequency and power are automatically corrected through real-time sampling and observation, and zero-sensing switching is achieved. The method can effectively improve the response speed and stability of the battery energy storage system when the power grid fails, and guarantees the safe operation of the power grid.

The invention discloses a power grid fault positioning system and method based on traveling wave distance measurement, relates to the technical field of fault analysis, and solves the technical problems that traveling wave feature analysis, temperature compensation and high-precision synchronization technologies are not effectively integrated, and rapid and accurate fault positioning of a smart power grid is difficult to meet. Through the technical combination of dynamic temperature compensation, high-precision time synchronization and intelligent fault classification, the bottlenecks of traditional traveling wave distance measurement in the aspects of precision, reliability and intelligence are systematically solved, temperature sensors are deployed at key nodes of a cable, the temperature is monitored in real time, the wave speed is dynamically corrected through a formula, the overall error is reduced, and the fault location accuracy is improved. Meanwhile, an optical fiber two-way time transmission method is combined, transmission delay errors are reduced, synchronization reliability is improved, finally, a mapping library is constructed through laboratory simulation and field data, a Euclidean distance matching algorithm is combined, fault reasons are automatically recognized, and rapid positioning of the faults and accurate recognition of the fault reasons are achieved.

The invention provides a transient current capability improvement control system and method of a wind and light power generation system. The system comprises a self-synchronizing voltage source control module, a junction temperature prediction module, a transient current improvement control module, a current instruction calculation module and a transient current precise control module. According to the invention, online observation of the junction temperature of the wind-solar converter power device can be realized, the maximum short-circuit current which can be output can be accurately predicted, the DC bus voltage, the switching frequency and the modulation strategy are adjusted when the power grid has a fault, the junction temperature of the power device is reduced, and the transient current endurance capability of the power device is improved. And the transient current is accurately controlled to limit the utilization of the transient capability of the power device.

The invention relates to the technical field of power distribution network fault processing, in particular to a power distribution network fault automatic reconstruction control method of a power system. The method comprises the following steps: collecting operation state data of the power distribution network; dividing the power distribution network operation state data into power distribution network operation fault data and power distribution network operation state candidate data to be detected; performing disturbance interference potential state simulation analysis on the to-be-detected candidate data of the operation state of the power distribution network to generate disturbance interference potential state simulation data of the power distribution network; performing disturbance fault analysis through the power distribution network disturbance potential state simulation data to generate power distribution network disturbance fault data; based on the power distribution network operation fault data and the power distribution network disturbance fault data, intelligent reconstruction control decision design is carried out, and power distribution network intelligent reconstruction control decision data is generated; and power distribution network fault automatic reconstruction control operation is executed through the power distribution network intelligent reconstruction control decision data. According to the invention, efficient automatic reconstruction control is realized when the power distribution network fails.

The invention provides a low-voltage ride-through control method for a grid-forming type grid-connected converter based on reactive power synchronization, and belongs to the technical field of converter low-voltage ride-through control. When the voltage of a power grid drops, a current amplitude limiting module in the power grid sends a control switching signal to trigger low-voltage ride-through control, and the low-voltage ride-through control is switched to a reactive power synchronization mode; a reactive power synchronous control gain KQs is calculated according to an inner loop gain coefficient Kcp, a current amplitude limiting value, a power grid voltage Vg and a grid side inductance Lgi, a virtual power angle reference value is generated by combining a set reactive power direct current component reference value QN, so that a power angle delta is stabilized in a range close to a normal working point, and a control effect is verified by comparing with a traditional method. According to the method, the system can quickly recover to a normal working state regardless of the duration of the fault and the severity of the fault, meanwhile, the system can effectively work under different power grid fault levels, and the robustness of the system is further enhanced.

The invention relates to the technical field of power systems, and discloses a power distribution network fault positioning method, device and equipment and a medium, and the method comprises the steps: synchronously collecting fault traveling wave data through a transformer area intelligent terminal and a feeder terminal disposed in a power distribution network; dynamically calculating traveling wave transmission parameters based on the topological information and the real-time operation parameters of the power distribution network; performing feature extraction and fusion processing on fault traveling wave data acquired by the transformer area intelligent terminal and the feeder terminal to generate a joint feature matrix; based on the joint feature matrix and the traveling wave transmission parameters, cooperative verification is carried out through the single-end positioning information and the double-end positioning information, and a fault section is determined; and performing fault type identification on the fault section by using the intelligent classification model, and performing consistency verification according to an obtained fault type identification result and the fault section to generate a fault diagnosis result. According to the invention, accurate positioning of the power distribution network fault can be realized, and the problems of positioning blind areas, high cost and easy misjudgment in the prior art are solved.

The invention discloses a power grid fault handling method and system based on a large model and multiple agents. Acquiring and collecting power grid multi-source data to form power grid fault information; the method comprises the following steps: performing semantic analysis on power grid fault information, generating a fault disposal strategy through a fine-tuning trained power field large model, disassembling the fault disposal strategy into an executable subtask sequence, and determining an input / output and execution sequence of each subtask; constructing a plurality of agents, and cooperatively controlling and executing a plurality of subtasks of a fault handling strategy; and after the execution of the fault processing strategy is completed, setting a multi-dimensional evaluation index, and carrying out quantitative evaluation on the fault processing effect. According to the large model and multi-agent cooperative power grid fault disposal technical scheme provided by the invention, the intelligent level and the emergency response efficiency of power grid fault disposal are improved.

The invention discloses a power grid fault intelligent diagnosis method, system and device based on big data and a medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining power grid electrical parameters, setting a first monitoring time period and a second monitoring time period, and obtaining a first monitoring parameter value sequence and a second monitoring parameter value sequence; obtaining a first increment value and a first attenuation value, obtaining a second increment value and a second attenuation value, obtaining a predicted increment value corresponding to the electrical parameters of the power grid based on the prediction model, the first increment value and the second increment value, and obtaining a predicted attenuation value corresponding to the electrical parameters of the power grid based on the prediction model, the first attenuation value and the second attenuation value; obtaining an upper fluctuation threshold value and a lower fluctuation threshold value corresponding to the electrical parameters of the power grid, and obtaining a fault index according to the upper fluctuation threshold value, the lower fluctuation threshold value, the prediction attenuation value and the prediction increment value; and obtaining a power grid fault diagnosis result according to the fault index. The method has the advantages of accurate fault diagnosis, self-adaptive threshold and full-period management.

The invention discloses a middle and low voltage power grid fault positioning system and method based on grid topology, and relates to the technical field of power grid fault positioning, and the method comprises the steps: obtaining historical electrical parameter records of equipment nodes in grid topology modeling, evaluating the node abnormality degree of the equipment nodes, and obtaining abnormal equipment nodes; obtaining coordinates of the abnormal equipment nodes in the grid topology modeling, traversing the equipment nodes in the grid topology modeling, generating candidate abnormal regions, and evaluating region anomalies of the candidate abnormal regions to obtain a target abnormal region; acquiring traveling wave signal data in the target abnormal area, and positioning a fault in the target abnormal area based on the traveling wave signal data to obtain fault position data of the target abnormal area; and acquiring fault position data in the power grid in the current period, planning a fault maintenance path in the power grid, and dispatching maintenance personnel to sequentially maintain the faults in the power grid according to the fault maintenance path.

The invention discloses a photovoltaic grid-connected flexible control method and system, and relates to the technical field of photovoltaic grid-connected control, and the method comprises the steps: carrying out the fault prediction of a power grid through a power grid fault model, and automatically controlling a photovoltaic inverter to stop outputting power to the power grid when the power grid is predicted to have a fault risk, the method comprises the following steps: switching a photovoltaic system into an island mode, independently supplying power to a local load after the photovoltaic system is switched into the island mode, cutting off power supply of a power grid to the local load while the photovoltaic system independently supplies power to the local load, and adjusting the working state of a photovoltaic panel through a maximum power point tracking algorithm in the island mode. And a cooperative control strategy for the energy storage system is generated in combination with the operation state of the photovoltaic system and the local load demand. The control system can reasonably dispatch the charging and discharging process of the energy storage system according to the real-time load requirement and the power generation condition of the photovoltaic system, so that the stability and the energy utilization efficiency of the system are improved, and the power supply reliability in the island mode is ensured.

The invention discloses a reclosing coordination control method and system based on electrical parameter measurement, particularly relates to the technical field of intelligent power grid fault processing and security defense, and is used for solving the problem that the reliability of fault judgment is reduced due to the fact that high-proportion distributed photovoltaic is connected to a power distribution network. A harmonic detection signal is injected during a reclosing waiting period, a response signal is measured, harmonic subspace energy distribution is extracted, an energy distribution matrix is constructed to calculate a nuclear norm change rate and form similarity, a system harmonic impedance stable state is judged through double verification, and finally a reclosing decision is executed according to a fault judgment parameter. The method can accurately identify the convergence characteristic of the dynamic process of the system, effectively distinguish the instantaneous fault from the permanent fault, and significantly improve the reclosing success rate and the power supply reliability of the distributed photovoltaic power distribution network.

An electrical grid fault localization system including: a plurality of current sensors (measurement devices) electrically connected to the electrical grid; a memory for storing a representation of the electrical grid as a plurality of geographical markers, and for storing a plurality of sets of expected time data, each one of the plurality of sets of expected time data associated with each one of the plurality of geographical markers, each member of the set of expected time data based on an expected signal propagation time from, at least one of the plurality of geographical markers to at least one current sensor; a processor communicative with the plurality of current sensors and the memory, the processor configured to receive measured time data of a fault event from, the plurality of sensors to generate a set of fault event time data and to match the set of fault event time data to at least one of the plurality of sets of expected time data and identify in g / outputting at least one matched geographical marker. Methods and computer-readable media directed to electrical grid fault localization are also described.

The invention provides a multi-unmanned aerial vehicle communication sensing cooperation method in a power grid fault scene, and the method combines unmanned aerial vehicle dynamic topology reconstruction and a multi-stage optimization strategy, and achieves efficient information acquisition for emergency scenes of damaged ground base stations and large-area power failure in disaster areas after a power grid fault. Power flow entropy is introduced to analyze power grid node vulnerability, communication unmanned aerial vehicle deployment is optimized, and an optimal communication coverage strategy is solved based on a multi-target grey wolf optimization algorithm; meanwhile, a graph theory method and a shortest path search algorithm Dijkstra are used for optimizing the inspection path of the unmanned aerial vehicle, so that the fault diagnosis efficiency is improved; under a two-stage optimization framework, in the first stage, important load nodes are preferentially covered and routing inspection is executed, in the second stage, supplementary optimization is carried out on an uncovered area, and finally a global optimal solution considering unmanned aerial vehicle resource efficiency, communication quality and information acquisition is obtained. The method improves the recovery efficiency of a post-disaster power grid, and is suitable for the emergency response of a power system in an extreme disaster environment.

The invention discloses a power failure event cooperative processing method, system and device based on geographic information and a medium, and relates to the technical field of power system power distribution network fault processing and informatization. The method comprises the following steps: when a power failure event occurs, acquiring multi-source heterogeneous data from an associated system; performing fault analysis on the multi-source heterogeneous data through a fault diagnosis model, and outputting fault positioning information and a fault type; obtaining associated maintenance resource state data and real-time traffic road condition data according to the fault positioning information; the maintenance resource state data comprises a rush repair team position, a skill level and a vehicle state; and based on the fault positioning information, the fault type, the user attribute, the historical work order data, the maintenance resource state data and the real-time traffic road condition data, generating an optimal maintenance scheduling scheme through a reinforcement learning scheduling model. The cross-department and cross-business cooperative processing is realized, and the first-aid repair efficiency and the resource utilization rate are remarkably improved.

The invention belongs to the crossing field of artificial intelligence and a power system, and discloses a power grid fault handling plan knowledge retrieval method and a related device. The power grid fault handling plan knowledge retrieval method comprises the following steps: on the basis of an obtained expression, generating a query by utilizing a large language model, and performing retrieval in a constructed graph database to obtain a power grid fault handling plan knowledge retrieval result; when the graph database is constructed, firstly, all themes in a free text of a selected power grid fault field are recognized, and an entity which can best represent the theme in each theme serves as a seed entity; then, entity relation triads in the free text are extracted through a large language model and serve as candidate triads, integration is carried out to obtain a fused knowledge graph, the fused knowledge graph is stored, and a constructed graph database is obtained. The problems that an existing retrieval method is low in query efficiency and poor in accuracy are solved.

The invention discloses a VR-based power distribution network maintenance virtual training system and method in the technical field of electric power. A VR-based power distribution network maintenance virtual training system comprises a modeling module, a database module, a training platform module, an operation learning module, a comprehensive training module and a training evaluation module. A three-dimensional virtual environment is created for trainees through the VR technology, so that the trainees can feel the actual operation scene and the fault condition of the power distribution network in an immersive manner; students can deeply understand the structure and the working principle of the power distribution network and various phenomena and details when faults occur from different angles; in the virtual training environment, the trainee can perform various dangerous operations and fault processing exercises without causing any actual threat to the safety of the trainee. In combination with actual cases and data in a power distribution network fault database, the system can intelligently adjust the difficulty of training contents and fault scenes, so that the training contents and the fault scenes are matched with the ability of students.