19348results about "Information technology support system" patented technology

The invention discloses a power plant operation and maintenance knowledge intelligent query method based on a large language model and an RAG technology. The method comprises the following steps: constructing a power plant operation and maintenance knowledge vector library covering structured, semi-structured and unstructured data; receiving a natural language question of a user, inputting an improved instruction to align a preprocessor, and generating a question semantic vector and an intention tag; relevant knowledge fragments are retrieved and sorted through a semantic matching retriever in combination with the intention labels; constructing a large language model cue word structure based on the retrieval result and the original question, generating candidate answers and recording a reference path; and finally, performing term specification and consistency verification according to the expert rule base, and outputting a structured and traceable final answer. According to the invention, the improved RAG technology is fused to realize intelligent query of the operation and maintenance knowledge of the power plant.

The invention discloses a power grid equipment intelligent operation and maintenance method based on a large language model and a knowledge graph, and relates to the technical field of intelligent power grid operation and maintenance, and the method comprises the steps: carrying out the operation and maintenance of power grid equipment through a power grid operation and maintenance knowledge graph constructed through a large language model and a knowledge federation technology, the power grid equipment operation and maintenance comprises one or more of health state evaluation, fault risk prediction and early warning, intelligent operation and maintenance strategy generation and health degree dialogue query of the power grid equipment. According to the invention, a power grid operation and maintenance mode can be effectively promoted to be transformed and upgraded from a traditional manual experience type and a passive maintenance type to a data-driven, intelligent and active preventive maintenance mode. Key intelligent operation and maintenance technical support is provided for building a novel electric power system with new energy as a main body, the novel electric power system is assisted to achieve the development goals of being safer, more efficient, cleaner and lower in carbon, and important industry strategic significance and social contribution are achieved.

The invention relates to the technical field of intelligent operation and maintenance and artificial intelligence crossing of a power system, in particular to an intelligent power work order processing method of an RPA fused multi-modal large model, which analyzes multi-modal work order data such as texts, voices, images and the like through a domain adaptation large language model, and realizes fault key information extraction and conflict resolution in combination with a dynamic knowledge graph; performing work order priority scoring and resource allocation by using space-time constraint reinforcement learning; an analysis result is converted into an automatic execution script through an RPA engine, and a whole-process closed loop of order sending, processing and feedback is achieved; meanwhile, a feedback optimization and conflict resolution cooperation mechanism is constructed, and the knowledge graph and the model precision are continuously iterated. The method improves work order processing efficiency and analysis precision, enhances decision scientificity, and is suitable for an intelligent operation and maintenance scene of a power system.

The invention discloses a power distribution network line fault positioning detection system, and relates to the technical field of power distribution network fault detection. The system comprises a mixed information acquisition layer, a fault feature extraction layer, an intelligent diagnosis layer and a fault positioning layer. The mixed signal acquisition layer comprises a high-frequency transient wave recording unit, a power frequency measurement unit, a wireless pulse sensor and a distributed optical fiber temperature measurement unit; the fault feature extraction layer comprises a time-frequency analysis module, a preprocessing module and a three-dimensional feature vector module; the intelligent diagnosis layer comprises a convolutional attention network, a space-time diagram neural network and a transfer learning module; the fault positioning layer comprises a particle swarm module and a fuzzy reasoning module. According to the invention, data information of the cable is acquired through the mixed information acquisition layer, a video analysis window function is dynamically matched with signal characteristics, a time domain graph scale, a frequency domain resonance component and a space field intensity gradient are constructed, fault diagnosis and positioning are carried out by using the intelligent diagnosis layer, and the fault positioning detection efficiency of the power distribution network is improved.

The invention discloses an intelligent operation and maintenance system and method for a high-voltage switch cabinet based on digital twinning, relates to the technical field of intelligent power grids, and solves the problems of nonlinear effect modeling distortion, cross-spatio-temporal scale coupling deviation accumulation, time sequence real-time contradiction and insufficient extreme working condition adaptation in the prior art. Hysteresis parameters of the ferromagnetic material are dynamically calibrated through a quantum annealing optimization algorithm, and electromagnetic-thermal field strong coupling synchronous calculation is realized by combining multi-scale mesh generation and an implicit thermal field iterative algorithm; constructing an incremental transfer learning framework to fuse aging features and real-time data, and correcting boundary conditions of the model by adopting four-dimensional variational assimilation; establishing a hybrid verification platform to dynamically feed back extreme working condition parameters, and generating a credible operation and maintenance instruction in combination with a block chain; according to the method, the contact temperature rise prediction precision, the residual life evaluation reliability and the circuit breaker transient response real-time performance are remarkably improved, and active immune type intelligent operation and maintenance of the high-voltage switch cabinet under the extreme working condition are achieved.

A method for locating a high-impedance ground fault of a smart distribution network with topology change adaptation includes: acquiring a fault traveling wave sample within a specified time window after a fault occurs, and performing continuous wavelet transform on the fault traveling wave sample to obtain traveling wave full waveform feature information; establishing a graph structure of a power distribution network, obtaining a corresponding adjacency matrix, and obtaining node position and structure encoding information in the graph structure through graph random walk and graph Laplace transform; concatenating the node position, the structure encoding information and the traveling wave full waveform feature information to obtain a node feature, and inputting the node feature and an edge feature into the graph structure to establish a graph sample data set; constructing and training a Graph Transformer model; and calling the trained Graph Transformer model to locate a fault in to-be-detected sample data.

The invention relates to the field of frequency converter fault detection, and discloses a frequency converter fault prediction method and system based on machine learning, and the method comprises the steps: obtaining multi-dimensional real-time data in the operation process of a frequency converter; constructing a dynamic mapping relation to obtain a basic feature set; generating a time sequence feature vector capable of reflecting the state change of the equipment based on the basic feature set; comparing, analyzing and judging whether the equipment state deviates from a normal operation interval or not based on the historical operation data and the time sequence feature vector, and outputting a state deviation index; performing abnormal fluctuation judgment on the time sequence feature vector; extracting fluctuation amplitude and frequency characteristics of the key indexes to obtain quantitative description data of abnormal fluctuation; inputting the quantitative description data of the abnormal fluctuation into an abnormal prediction model; and generating a coping strategy and a triggering condition of the coping strategy based on the risk prediction result. The method has the advantages that the abnormal state of the frequency converter is recognized in time, and potential risks are predicted.

The invention relates to the technical field of fault positioning, and discloses a power distribution network grounding fault positioning method and system. The method comprises the following steps: acquiring a fault initial transient section signal, an arcing continuous section signal and an arc quenching recovery section signal of the power distribution network, and executing spectral analysis to obtain a fault feature matrix; performing zero-sequence transient frequency spectrum reconstruction on the fault feature matrix to obtain reconstructed frequency spectrum features and time-varying frequency spectrum features; calculating a transient characteristic index and a fault type based on the reconstructed spectrum characteristic and the time-varying spectrum characteristic; performing fault positioning calculation on the power distribution network according to the transient characteristic index and the fault type to obtain an initial fault point position; and performing transient fingerprint matching and probability density accumulation compensation on the initial fault point position to obtain a target fault point position. According to the method, high-precision characterization of the rapid change signal in the short time window is realized, interference of the compensation state on fault positioning is eliminated, and the grounding fault positioning accuracy of the power distribution network is improved.

The invention discloses an integrated power distribution cabinet energy efficiency dynamic optimization method based on multi-modal data fusion, and relates to the technical field of intelligent power grids. The problems of failure of an energy efficiency optimization model and poor long-term operation stability caused by data time sequence misalignment and error accumulation of a multi-source sensor in the prior art are solved. According to the scheme, the time offset is dynamically corrected through the adaptive time sequence deviation prediction model; compensating missing data by adopting a non-uniform time step reconstruction algorithm and Kalman filtering; detecting an error drift trend through an exponentially weighted moving average model, updating a feature weight, and inhibiting long-term error accumulation; constructing a self-adaptive time sequence attention fusion network model, and fusing physical constraints and a data driving mechanism to generate an optimization decision; bayesian optimization is utilized to quantify parameter uncertainty, closed-loop feedback execution data is carried out, and model parameters are dynamically updated; according to the invention, the precision, long-term stability and equipment safety of energy efficiency optimization of the power distribution cabinet are remarkably improved, and efficient and reliable operation under multi-physics field coupling constraint is ensured.

The invention relates to the technical field of data processing, and discloses a comprehensive evaluation method and system for the health degree of a distribution network cable. The method comprises the following steps: collecting cable joint multi-source monitoring signals, normalizing the monitoring signals to obtain a degradation degree feature vector, correcting multi-physics field coupling model parameters, obtaining a recessive degradation index through finite element calculation to obtain an enhanced feature vector, and performing time-frequency domain decomposition to extract multi-scale feature parameters to obtain a comprehensive feature matrix; a double attention mechanism calculates a feature weight and a time sequence correlation degree to obtain a deterioration trend prediction value, and fuzzy integral is fused with a multi-classifier output probability to obtain a health degree evaluation grade and an early warning result. According to the invention, the early defect identification accuracy and the degradation trend prediction precision are improved.

The invention discloses a power system source network interaction data security encryption verification method, system, device and medium, and belongs to the technical field of power system communication encryption, and the method comprises the following steps: a source side device and a network side device complete identity authentication through a bidirectional digital certificate verification mechanism; and an identity binding label is generated in combination with the device identifier, the timestamp and the position information. And after the authentication is passed, the two parties perform key negotiation based on an elliptic curve algorithm, and generate a temporary encryption key in combination with an authentication result. A source side device carries out structural packaging on original interaction data, adds a random number, a timestamp and a hash abstract, then encrypts the original interaction data in an AES-GCM mode, and carries out signature binding on key fields through digital signatures to form a complete data packet. And a receiving end performs compliance judgment on the timestamp and the random number in the data packet, and after the timestamp and the random number are confirmed to be in an effective time window and are not replayed, signature verification, decryption processing and Hash consistency verification are sequentially completed, so that closed-loop processing of a data flow is ensured.

The invention discloses a cross-regional virtual power plant cooperative scheduling method and device, a medium and a product, and relates to the field of data processing. The method comprises the following steps: acquiring real-time characteristic data such as space-time positions, output / demand prediction and the like of distributed energy resources and loads, and determining dynamic weights of characteristic dimensions based on a global optimization target and data of a current scheduling period; generating a dynamic resource cluster division instruction containing a member list and a coordination constraint condition according to the dynamic weight and the real-time data, and sending an initial cross-regional coordination scheduling instruction containing a net exchange power target value and the like and a compensation price signal to each dynamic resource cluster local agent; after aggregation response boundary information returned by the local agent is received, an instruction and a signal are updated, a target collaborative scheduling instruction is obtained and finally sent to each dynamic resource cluster for execution, and effective control over cross-regional virtual power plant resources is achieved. According to the method, the problem that the adaptability of the cross-regional virtual power plant collaborative scheduling instruction and the actual resource capacity is insufficient can be relieved.

The invention relates to the technical field of management and control systems, in particular to a digital intelligence system applied to collaborative management and control of water-power engineering construction participating units, which comprises a project data management module covering water-power engineering construction full life cycle management, extracting multi-source information data from various subsystems, and constructing a project view and a project management information base; the project risk analysis module is used for constructing an intelligent risk analysis model for risk analysis and generating a dynamic evaluation result, a graded early warning notification and an auxiliary decision scheme; the project collaborative management module is used for processing graded early warning notification and auxiliary decision-making schemes by using a multi-layer perceptron model, and generating finalizing service achievements and management process records; and the project document management module is used for performing compliance automatic checking and processing on the electronic documents needing to be archived, and dynamically updating and optimizing the project management information base. Through the closed-loop management and control system, the cooperative management and control efficiency of water-power engineering construction participation units is improved.

The invention discloses a power grid load prediction and scheduling optimization system based on artificial intelligence, particularly relates to the technical field of power system automation, and solves the technical problems of low power grid load prediction precision, poor scheduling strategy robustness and insufficient source grid load storage coordination in the prior art. Multi-source heterogeneous data space-time alignment is realized by constructing a data acquisition layer based on edge calculation, a load prediction result is generated by adopting an AI prediction module fused by a graph convolutional network and an attention mechanism, and a source-network-load-storage collaborative scheduling scheme is generated through a multi-target risk hedging optimization algorithm. And closed-loop optimization is realized by using digital twinborn pre-check and incremental learning. And finally, the load prediction accuracy, the scheduling decision reliability and the system adaptive capability in the new energy access environment are improved.

The invention relates to the technical field of image data processing, and discloses a power grid drawing intelligent review method and system based on a knowledge graph, and the method comprises the steps: driving a multi-mode large language model based on a domain specific prompt project, extracting a power grid domain knowledge triple from structured text data, and then carrying out the quality evaluation and conflict detection, performing automatic resolution on the conflict knowledge to obtain a candidate knowledge set; checking and confirming the candidate knowledge set through a man-machine cooperation verification mechanism, and constructing a power grid design specification knowledge graph; and identifying to-be-reviewed elements in the to-be-reviewed power grid drawing through the multi-modal large language model, querying the power grid design specification knowledge graph according to the generated structured query statement, performing compliance judgment on the to-be-reviewed power grid drawing based on the obtained query data packet, and generating a review report. According to the method and the device, the efficiency and the reliability of automatic drawing review can be improved, and meanwhile, the interpretability and the traceability of review results are ensured.

The invention discloses an insulator defect detecting and positioning method and system based on cross-scale feature fusion, and belongs to the field of intelligent routing inspection of power distribution network lines, and the method comprises the following steps: S1, obtaining image data containing a plurality of insulator defects of the power distribution network lines in real time, and carrying out the preprocessing of the image data; s2, image enhancement; s3, fusing the enhancement results under multiple scales obtained in the step S2 by adopting a pyramid fusion strategy to obtain a fused image; s4, inputting the fused image into a pre-trained cross-scale feature fused defect detection model, and outputting defect features; and S5, based on the detection time and the real-time speed of the defect features, considering the delay time, and predicting the position coordinates of the defect features. By the adoption of the insulator defect detection positioning method and system based on cross-scale feature fusion, high precision, high robustness and self-adaptive processing of insulator defect detection are achieved, and the method and system have important significance on intelligent detection and maintenance of insulator defects of a power distribution network line.

The invention belongs to the technical field of power system safety, and discloses a high-voltage transmission line safety assessment method based on an intelligent algorithm. A database is constructed through multi-source data acquisition and fusion processing, a deep learning model is utilized to analyze relevance between meteorological conditions and an icing formation mechanism, an evolution law of the meteorological conditions and the icing formation mechanism is mined, multi-scene simulation and sensitivity analysis are performed in combination with physical characteristics and landform information of a power transmission line, and a line icing risk partition assessment system is established. According to the method, a critical value of line mechanical strength and icing thickness is calculated based on a mechanical model, a grading early warning threshold standard is formulated, a time sequence prediction algorithm and a risk propagation model are constructed to realize intelligent early warning, and a prevention and control strategy is formed through optimal configuration of anti-icing resources and self-adaptive generation of a deicing scheme. According to the invention, the capability of resisting icing disasters of the high-voltage transmission line is effectively improved, and the safe and stable operation level of a power grid is enhanced.

The invention discloses an intelligent cable fault accurate positioning and early warning method and system, and the method comprises the steps: collecting the temperature gradient, strain distribution and partial discharge signals of the whole length of a cable in real time through a distributed optical fiber sensing network, and generating a multi-dimensional feature matrix of the operation state of the cable; based on the multi-dimensional feature matrix, outputting a preliminary fault positioning coordinate; generating corrected fault coordinates according to the topological structure data of the cable laying environment and the electromagnetic interference distribution diagram; historical fault data, real-time operation parameters and the corrected fault coordinates are fused, and a fault risk thermodynamic diagram in a future preset duration is output; and based on the fault risk thermodynamic diagram and real-time monitoring data, generating fault first-aid repair information by using a dynamic priority algorithm, synchronously triggering an early warning signal, and visually displaying a fault positioning result and a risk area in a three-dimensional geographic information system. According to the embodiment of the invention, rapid positioning, accurate early warning and intelligent disposal of the cable fault can be realized.

The invention discloses a power grid real-time optimization scheduling system and method based on digital twinning, and relates to the technical field of power grid scheduling. A sensor is deployed to collect environmental parameters of key nodes in real time, a dynamic environmental condition coefficient is constructed, a power grid state is analyzed in combination with frequency stability and a relative strength index, and a multi-model fusion prediction mechanism is established, so that space-time two-dimensional accurate prediction of load and power generation is realized. A multi-objective optimization model is adopted to take'maximization of new energy consumption + minimization of scheduling cost 'as a core objective, a genetic algorithm is introduced to solve an optimal scheduling scheme, and a feasible solution is screened in combination with forward simulation of a digital twin model. Through abnormal early warning triggering, environment correlation analysis and model iterative optimization, a scheduling strategy is dynamically adjusted, and the power supply efficiency and the emergency response capability in an extreme scene are improved. According to the method, multi-source heterogeneous data are effectively fused, and real-time sensing of a power grid operation state, collaborative optimization of multiple energy resources and adaptive iteration of a scheduling model are realized.

The invention provides a thermal power plant thermal instrument fault diagnosis method and system based on vibration analysis, and relates to the technical field of fault diagnosis, and the method comprises the steps: collecting and processing a vibration signal of a thermal instrument, extracting an optimized vibration feature vector, constructing a hybrid neural network model, and training the hybrid neural network model to obtain an optimized fault diagnosis model; performing fault diagnosis on the vibration feature vector, and generating a fault type, possibility and confidence; and performing fault risk assessment and case reasoning, and generating a fault reason analysis report and a maintenance suggestion.

The invention discloses a distributed power supply access-oriented power distribution network fault distance measurement method and system, and relates to the technical field of power systems, and the method comprises the steps: collecting the electrical parameters and operation states of distributed power supply access nodes in a power distribution network in real time, building a dynamic manifold model based on an ecological niche theory, and carrying out the calculation of the dynamic manifold model; adaptively adjusting manifold learning neighborhood parameters according to power fluctuation data included in the electrical parameters, and updating node ecological niches to reconstruct a dynamic manifold model; based on the reconstructed dynamic manifold model, fault features are extracted from three scales of a current harmonic component, a feed line inter-harmonic propagation path and whole network voltage influence, and a three-dimensional feature vector is generated through fusion of a graph correlation algorithm; based on the expanded fault sample library and the power fluctuation data, constructing a fault transfer relation model to predict a ground fault and a short circuit risk area; a fault source is modeled by adopting a topological neural network, and a fault point distance measurement value is output through state prediction and strategy deduction.

The invention relates to the field of image processing, and discloses an intelligent drawing checking method and system based on a multi-modal large language model, and the method comprises the steps: obtaining a to-be-checked target engineering design drawing and a to-be-checked task description; generating a global overview drawing based on the target engineering design drawing; performing global semantic analysis according to the global overview map and the review task description through a multi-modal large language model, and generating a global semantic analysis result and to-be-reviewed local area proposal information; cutting a local image from the design drawing; performing element identification analysis on the local image through a multi-modal large language model to obtain local structured information; and performing information fusion processing on the local structured information and the global semantic analysis result, generating complete drawing information, performing compliance verification and defect positioning on the complete drawing information and the structured specification knowledge base, and generating a review report. According to the method, intelligent review of the power grid engineering design drawing can be realized, the review efficiency and accuracy are improved, and meanwhile, the resource consumption is reduced.

The invention provides an intelligent optimization method and system for a revenue mode of a commercial energy storage power station, and relates to the technical field of energy storage power stations. Establishing a multi-dimensional life loss coefficient matrix by analyzing the health state data of the energy storage equipment; a candidate charging and discharging scheduling strategy is generated based on a deep reinforcement learning model, and a double-constraint optimization charging and discharging strategy with predicted income and life loss as a reward function is adopted; and finally generating a control instruction to realize optimized operation of the energy storage power station. According to the method, equipment life loss and economic benefits are comprehensively considered, and long-term benefit maximization of the energy storage power station is realized.

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 is suitable for the technical field of data analysis, and provides a transformer substation fault handling method combining causal reasoning knowledge graph modeling, comprising: acquiring multi-source heterogeneous data and performing data cleaning processing to obtain a space-time alignment data set, the space-time alignment data set comprising one or more quaternary data sets, the quaternary data set comprises a device identifier, a timestamp, a feature vector and an event tag; causal modeling processing is carried out on the time-space alignment data set to obtain a causal graph, and the causal graph comprises node information of nodes and relation information between the nodes; constructing a space-time diagram neural network model according to the causal diagram and the equipment connection relation diagram, wherein the space-time diagram neural network model realizes dynamic evolution of the graph based on an incremental updating strategy; and outputting fault root cause positioning information according to the time-space diagram neural network model.

The invention discloses a transformer substation scene three-dimensional semantic segmentation method based on point cloud enhancement and attention guidance, and the method specifically comprises the steps: carrying out the region division and category labeling of three-dimensional point cloud data in a transformer substation scene, setting a semantic tag based on an equipment type, and constructing a semantic segmentation point cloud data set adaptive to a power scene; a three-dimensional semantic segmentation model is constructed, and collaborative modeling of local details and global context is realized through a point cloud enhancement module and an attention guidance coding module; a weighted loss function and a parameter optimizer training model are adopted to solve the problem of unbalanced equipment category distribution in a substation scene; and performing semantic segmentation on the substation scene point cloud data based on the trained model, and outputting a high-precision equipment classification result. According to the method provided by the invention, through collaborative design of point cloud enhancement and attention guidance, the accuracy and robustness of three-dimensional semantic segmentation in a complex scene are effectively improved, and the method is particularly suitable for a scene with dense substation equipment and a fine structure.

The invention relates to the technical field of power system scheduling, and discloses a power distribution network simulation scheduling optimization method and system based on artificial intelligence, and the system comprises a data fusion module, a digital twin modeling module, an intelligent prediction module, a strategy optimization module, and a visual scheduling module. The whole scene of the power distribution network is simulated through the digital twin model, the operation state and fault influence of equipment are accurately simulated, a scientific basis is provided for making a maintenance plan, blind maintenance is avoided, and the maintenance and repair cost of the equipment is reduced; meanwhile, by optimizing a load transfer path and distributed power supply output, the network loss rate is reduced, and the utilization efficiency of electric power resources is improved; in addition, the knowledge graph and the LSTM deep learning algorithm are fused, the distribution network topology entity relation network is constructed, and multi-source data are trained, so that the fault prediction accuracy is improved, the power failure risk can be early warned in advance, the conversion from passive first-aid repair to active prevention is realized, and the power failure frequency outside a plan is reduced.

The invention relates to the technical field of industrial component detection, in particular to a transformer iron core detection method based on computer vision, which comprises the following steps of: acquiring an iron core image, extracting key pixel characteristics, screening a directional scattering abnormal region to generate an interference map, extracting a consistent gradient region correction image to generate a reconstruction map, and positioning a symmetric disturbance generation structure map by integral gray difference. And analyzing an overlapping relation by a superposition structure graph to generate an abnormal component graph, and evaluating a risk level by matching a reference index to generate an early warning graph layer. Interference reflection and structural features can be distinguished through linkage analysis of the pixel direction vector and the brightness change frequency, correction of a distorted area in an image is realized based on a gray statistical stable value, and the distortion of the image is corrected by constructing a symmetric point map and analyzing the change trend of a gradient difference value sequence. And the structural overlapping relation is quantitatively judged by combining a component mapping profile diagram, so that the relevance between an abnormal region and a key component is clearly expressed, and the grading evaluation capability of various fault risks in the iron core is improved.

The invention relates to a low-rank fine-tuning transformer fault diagnosis method based on adaptive attention guidance, and belongs to the technical field of artificial intelligence. An attention scoring mechanism, an adaptive attention scoring mechanism, a dynamic rank allocation strategy and a hierarchical learning rate adjustment mechanism are introduced, and a context-aware dynamic updating strategy is further fused, so that the low-rank fine-tuning transformer fault diagnosis method based on adaptive attention guidance is realized. According to updating of real-time performance, loss and gradient dynamic intelligent triggering key parameters in the model training process, a large-model lightweight adaptation frame suitable for a transformer fault diagnosis task is constructed, and on the premise that diagnosis accuracy is ensured, model fine adjustment and deployment cost is remarkably reduced.

The invention relates to the technical field of power equipment fault diagnosis, in particular to a power equipment fault intelligent diagnosis method and system based on deep learning. The method comprises the following steps: automatically learning high-dimensional space-time correlation features in original time series data through a deep feature extraction network, and generating feature vectors representing potential abnormal modes of equipment; performing adaptive weight distribution on the high-dimensional space-time correlation features by using an attention enhancement mechanism, and marking a fault sensitive area to form enhanced fault features; inputting the enhanced fault features into a multi-level classifier for joint fault mode recognition and severity evaluation, and outputting a diagnosis result tensor containing a fault type and confidence; and an equipment maintenance decision signal is triggered based on the diagnosis result tensor, and the feature extraction network and classifier parameters are iteratively optimized according to feedback data, so that the intelligent level of operation and maintenance of the power equipment can be comprehensively improved.