16 results about "Power transform" patented technology

The invention relates to the field of line loss treatment, in particular to a dynamic treatment method and system for line loss of an electric power station area, and the method comprises the following three core steps: multi-source data cooperative processing: collecting the total meter electric quantity of the station area, branch phase data and a GIS topological relation in parallel, and generating a dynamic monitoring matrix through time sequence alignment and abnormality cleaning; time-space coupling abnormity diagnosis: fusing the line loss rate deviation degree and a hierarchical node transmission efficiency threshold value, and identifying three types of nodes of transformer abnormity, phase imbalance and electricity stealing suspicion; and reinforcement learning closed-loop optimization: outputting a primary instruction based on the pre-training rule base, driving a reinforcement learning engine to dynamically update a rule weight through feedback data, and iteratively optimizing the instruction until the line loss rate continuously reaches the standard. According to the method, the technical bottlenecks that multi-source data are asynchronous, the static threshold adaptability is poor, and the governance instruction lacks dynamic optimization are solved, and full-process dynamic control from data acquisition to governance closed loop is realized.

The invention relates to the technical field of power equipment operation and maintenance, in particular to a power transformation equipment state monitoring and fault diagnosis method, which comprises the following steps: S1, acquiring multi-dimensional operation data such as voltage, current, vibration, gas concentration and the like through a real-time monitoring module, and uploading and storing the multi-dimensional operation data based on block chain distributed nodes; s2, noise is removed through data cleaning, and time domain, frequency domain and trend features are extracted by using a CNN-LSTM model; s3, inputting the feature vector into a knowledge graph and AlexNet fused multi-modal model, and judging whether the equipment is abnormal or not; s4, if the fault is abnormal, combining electrical parameter analysis, mechanical characteristic detection and a laser radar to position the fault position; s5, fault types and causes are diagnosed through PSCAD / EMTDC simulation and a historical database; and S6, executing targeted repair schemes such as dynamic load adjustment and part replacement. According to the invention, comprehensive monitoring, accurate diagnosis and efficient repair of the power transformation equipment are realized, and the operation safety and economical efficiency of a power grid are remarkably improved.

The invention belongs to the technical field of power transformer insulation design and verification, and particularly relates to a power transformer insulation characteristic data analysis and performance prediction method and system, and the method comprises the steps: constructing a structured sample set containing multi-dimensional design parameters and lightning impulse response tags based on a three-phase differential prototype; identifying key variables in the structured sample set and extracting physical consistency constraints; and inputting the key variable and the physical consistency constraint into a preset XGBoost prediction model, and outputting a prediction value and a confidence interval. According to the method, the influence of multi-dimensional parameters on the insulation impact indexes is disassembled into clear main effects and interaction effects, and a traceable mechanism map is formed. Compared with a traditional method which depends on single-point experience judgment or post trial and error, the method has the advantages that standardized data evidences and explainable output are provided, and designers can conveniently and quickly position key constraints, formulate optimization priorities and directly backfill results to design specification and parameter boundaries.

The application discloses a kind of power transformer health state determination methods, including obtaining the attribute data of power transformer;Attribute data is normalized and corresponding grey correlation coefficient is calculated;The weight value of attribute data information is calculated using analytic hierarchy process, and grey correlation degree value is calculated;The attribute of power transformer is divided into health grade and the priority of each health grade is determined by comparison;Health grade is associated with grey correlation degree value to construct fuzzy logic control rule;The health state determination of actual power transformer is carried out using fuzzy logic control rule.The application also discloses a kind of system for realizing the power transformer health state determination method.The application obtains and processes the data of power transformer, and predicts the state of power transformer based on analytic hierarchy process and grey correlation analysis scheme, so that the application can not only realize the health state determination of power transformer, but also has high reliability and good accuracy.

The invention relates to a power transformer simulation verification method and device based on recording data, computer equipment, a medium and a product. The method comprises the steps of obtaining transformer parameters of a to-be-simulated transformer from a pre-established database, obtaining simulation parameters according to the transformer parameters, constructing a transformer physical blueprint and a simulation scene according to the simulation parameters, and constructing a transformer field-circuit coupling model according to the transformer physical blueprint, analyzing the wave recording file of the power system, obtaining short-circuit current data of the to-be-simulated transformer, loading an excitation load for the transformer field-circuit coupling model according to the short-circuit current data, performing simulation solution on the transformer field-circuit coupling model in the simulation scene, and obtaining a simulation solution result; and verifying the anti-short-circuit capability of the to-be-simulated transformer based on the simulation solution result. By adopting the method, the anti-short-circuit verification reliability can be improved.

The invention discloses a power transformer state evaluation method based on vibration sensing network characteristics, which comprises the following steps: arranging a plurality of vibration sensors on the surface of a power transformer oil tank opposite to a winding position, acquiring steady-state vibration data under different current or voltage, extracting a sample vibration phase sequence of each measuring point from the steady-state vibration data, and calculating the state of the power transformer; calculating the PLV between every two measuring points, obtaining a PLV matrix of the power transformer, and carrying out feature extraction; and establishing an adaptive threshold system, and performing transformer state diagnosis according to the characteristic value of the PLV matrix under the system. According to the method, the vibration response relationship among different channels is fully excavated and fused to realize accurate monitoring and evaluation of the state of the transformer, and vibration information of multiple measuring points can be effectively fused and is not easily influenced by the positions of the measuring points.

The application provides a power transformer measurement point optimization method and system based on quantum computing, and relates to the technical fields of power equipment monitoring and quantum computing application. The method comprises the following steps: obtaining multi-source sensor monitoring data of a power transformer at each candidate measurement point, fusing the multi-source sensor monitoring data, and constructing a multi-dimensional feature vector of each candidate measurement point; mapping the multi-dimensional feature vector of each candidate measurement point into a corresponding feature quantum state to obtain a unified quantum state representation of multi-source high-dimensional features; based on the corresponding feature quantum state of each candidate measurement point, establishing a measurement point combination superposition state for the selection state of each candidate measurement point; using a quantum approximate optimization algorithm to evolve and solve the measurement point combination superposition state, obtaining the probability distribution of the candidate measurement point combination, and outputting a candidate measurement point combination scheme according to the probability distribution. The application obtains a more optimal measurement point layout scheme, and improves the coverage, sensitivity and diagnostic accuracy of transformer state parameter monitoring.

The embodiment of the invention relates to the technical field of power systems, in particular to a power transformer health state quantitative evaluation method and device and electronic equipment. The method comprises the following steps: collecting multi-dimensional operation parameters of the power transformer; the multi-dimensional operation parameters comprise a dissolved gas parameter, an oil quality parameter, an electrical parameter and a new energy adaptation parameter; the new energy adaptation parameters are used for quantifying the influence of new energy grid connection on the operation state and the aging process of the transformer; performing feature processing on the multi-dimensional operation parameters to obtain a core feature set; inputting the core feature set into a pre-trained adaptive multi-task hybrid model, carrying out working condition adaptive feature optimization double-target collaborative prediction, and obtaining the health index and the residual life of the power transformer as prediction results; and generating an evaluation report according to the prediction result. According to the method, dynamic working conditions such as new energy load fluctuation and harmonic interference can be accurately adapted, and technical support is provided for efficient operation and maintenance of the transformer in a new energy grid-connected scene.

The invention discloses a micro-service architecture-based power transformer operation state evaluation method, system and equipment and a medium, and relates to the technical field of power equipment state monitoring and intelligent diagnosis, and the method comprises the steps: collecting multi-source operation data of a power transformer, carrying out the unified processing of the multi-source operation data, constructing a standardized feature vector, and carrying out the calculation of the multi-source operation data; based on multi-physics field coupling simulation, calculating field distribution and mechanical response of the power transformer, inputting standardized feature vectors into an intelligent classification model, classifying winding deformation faults, outputting fault types and confidence coefficients, performing interactive visual rendering on simulation results and intelligent classification results, and performing fault curve comparison display. And distributed service management is carried out by using a containerized micro-service mode. According to the invention, deep fusion and collaborative optimization are carried out under the micro-service architecture, so that full-chain intelligent improvement of transformer faults from mechanism revealing and accurate identification to visual decision support is realized.

The invention relates to the technical field of electric power, in particular to a power transformer reliability evaluation method. The method comprises the following steps: S1, data acquisition: collecting real-time operation state data, historical fault records and operation environment parameters of the power transformer; s2, data processing: carrying out cleaning and feature extraction on the collected data, and identifying key factors influencing the reliability of the transformer; s3, model construction: constructing a power transformer reliability evaluation model based on the processed data; s4, reliability evaluation: inputting real-time operation data into the evaluation model; and S5, result display and strategy making: displaying the reliability evaluation result in a visual mode, and making and executing a corresponding operation and maintenance strategy according to the result. According to the method, the reliability of the transformer is evaluated based on data analysis and mathematical modeling, the evaluation process is more objective and accurate, potential risks can be found in advance, and decision support is provided for maintenance and replacement of the transformer.

The invention discloses a standing wave ranging method and an object edge identification method and device, and the method comprises the steps: obtaining a signal wave reflected by a to-be-ranged object and a standing wave signal formed by the transmitted signal wave after a sound wave sensor transmits the signal wave to the to-be-ranged object; obtaining a standing wave signal expression at an original point where a microphone of the sonic sensor is located, and performing power transformation; expanding the standing wave signal expression after power transformation in a frequency domain to obtain an unbiased differential function expression; and performing coefficient scaling on the unbiased differential function expression at the frequency where the pulse peak is formed to obtain a distance frequency spectrum, wherein the peak value of the distance frequency spectrum is the distance from the sonic sensor to the object to be subjected to distance measurement. The acoustic method is used to realize shape measurement and identification of objects with blind spots in vision measurement, such as mirror surface objects or transparent earth surface objects, and the defects of vision measurement of the unmanned aerial vehicle are made up, so that the unmanned aerial vehicle has better robustness in measurement of the earth object.

The invention provides a power transformer state evaluation method based on loss analysis. The method comprises the following steps: (1) collecting working information of a power transformer; (2) performing preliminary judgment on the power transformer according to the working information, and giving an alarm if abnormity exists; if no abnormity exists, entering the step (3); (3) calculating the electric energy loss of the power transformer; (4) calculating an electric energy loss prediction value of the power transformer; (5) calculating an electric energy loss characteristic value of the power transformer; (6) judging whether abnormity exists or not according to the electric energy loss characteristic value, and if yes, giving an alarm; if not, entering the step (7); (7) calculating an electric energy loss accumulation characteristic value of the power transformer; and (8) judging whether abnormity exists or not according to the electric energy loss accumulated characteristic value, and if yes, giving an alarm. The invention provides a power transformer state evaluation method based on loss analysis. The accuracy of a power transformer state evaluation result can be effectively improved.

The invention discloses a power transformer health state intelligent assessment method based on a knowledge graph and a graph neural network, and the method comprises the steps: carrying out the preprocessing of multi-source state data in the operation of a transformer, converting the data into a health score value, marking a health grade label, and obtaining a training data set; constructing a health state knowledge graph by using the training data set; based on the training data set and the health state knowledge graph, calculating an edge weight by adopting a graph attention network; based on the edge weight, utilizing a node feature aggregation mechanism guided by the edge weight to iteratively update the node embedding representation, and obtaining a node representation fusing the structure information and the feature information; and introducing an incremental learning mechanism on the health state knowledge graph, and updating the health state knowledge graph based on the multi-source state data at the current moment. According to the method, multi-source state knowledge can be fused, the graph structure expression ability is achieved, dynamic updating is supported, the structure expression ability is achieved, and edge weight self-adaptive updating and sustainable evolution are supported.

The invention relates to a power transformer state evaluation method and system based on vibration sound signals. The method comprises the following steps: acquiring historical data of a power transformer, and respectively extracting characteristics of a vibration signal and an acoustic signal in each piece of historical data; fuzzifying the extracted features, and constructing and reducing a fuzzy decision table; state association rules are extracted from the reduced decision table, and a rule base is constructed; training a neural network based on historical data and a rule base, and learning a fault mode of the power transformer to obtain a power transformer state evaluation model; and finally, extracting time domain and frequency domain characteristics of the real-time vibration signal and the acoustic signal of the power transformer, inputting the extracted characteristics into the power transformer state evaluation model, and outputting a real-time transformer state grade by the model. Compared with the prior art, the method has the advantages of solving the problem of early leak detection of mechanical defects, improving the detection efficiency and accuracy and the like.

The invention relates to the technical field of power system state monitoring and prediction, in particular to a power transformer oil temperature prediction method and system based on multivariable time series data, and fuses multi-domain feature extraction, adaptive length patch division and a comparative learning mechanism based on meta learning. Firstly, multi-dimensional representation of input data in a time domain, a residual domain and a frequency domain is obtained through a multi-domain feature extraction module, and periodic and local change features of the data are fully captured; then, using an adaptive length patch generator in the backbone network to realize semantic complete patch division, and modeling a long-term time sequence dependence and short-term interaction relationship in combination with a sparse attention mechanism; and the multi-level features are integrated through a gating fusion unit, and prediction output is completed. Meanwhile, a comparative learning network based on meta learning is introduced, a high-quality enhanced sample is generated in a self-adaptive mode, and the backbone network is assisted in improving the feature representation capability and generalization performance; the method can be used for realizing high-precision and stable prediction of the oil temperature of the power transformer in a complex power grid operation environment.