96 results about "Transform fault" patented technology

The invention discloses a time series data cleaning method based on correlation analysis and principal component analysis, comprising the following steps: finding out hidden correlation between transformer faults and other power data by using a Pearson's correlation coefficient (PCC); reducing the dimension and noise of all relevant time series through principal component analysis (PCA); and inputting part of cleaned data as a training set into a BP neural network (BPNN) for training and learning, and taking the remaining data as a test set to verify a model. Compared with the traditional technology, the accuracy of transformer fault diagnosis is significantly improved, the accuracy of classification is improved, and the operation time is shorter for high-dimensional data.

The invention relates to a power transformer fault diagnosis method which combines the extension theory and the rough set theory, belonging to the electric power main equipment fault diagnosis technical field. The invention completes primary reduction classification of the attribute condition needed by various fault types according to a rough set attribute reduction method and then establishes a matter element model of transformer fault diagnosis; DGA testing data is taken as a transformer fault diagnosis attribute set; a transformer standard fault mode is taken as a transformer fault diagnosis decision-making set; various fault degrees are calculated by means of an extension correlation function; moreover, fault inclusion-exclusion rule is defined to determine a transformer fault. The power transformer fault diagnosis method carries out analysis through taking a certain transformer as an example with the diagnosis result according with the practical situation; seventy six pieces of transformer DGA information are collected and fault diagnosis is carried out by means of the method, thereby obtaining higher diagnosis correct rate as compared with IEC three-ratio method.

The invention discloses a power transformer fault diagnosis method. The power transformer fault diagnosis method comprises the following steps of determining N fault types of a transformer, and determining corresponding fault characteristic quantities for diagnosing the N fault types; taking the fault characteristic quantities corresponding to the N fault types as a testing sample, and performing normalizing processing of testing sample data; combining any two of the N fault types, establishing X (described in the specification) SVM ( Support Vector Machine) secondary classifiers, and training the X SVM secondary classifiers, and optimizing a SVM kernel function using a method based on combination of K-fold cross validation and an artificial bee colony algorithm; calculating generalization errors of each SVM classifier according to the K-fold cross validation method; and diagnosing the N fault types using an improved reordering adaptive directed acyclic graph support vector machine method. The invention has a capability of well diagnosing the fault type of a transformer, can greatly improve the accuracy of transformer fault diagnosis, and provides a reliable basis for transformer maintenance.

The invention provides a method of carrying out transformer fault identification based on a BP neural network algorithm. The method comprises the following steps of step S1, through a partial discharge test system, collecting discharge pulse graphs of different transformer faults; step S2, carrying out power graph analysis on discharge pulses acquired through the step S1; step S3, extracting a training sample and a test sample from characteristic quantities acquired through the power graph analysis obtained from the step S2; step S4, constructing a BP network nerve; step S5, carrying out BP network nerve training; step S6, carrying out BP network nerve testing. By using the method of carrying out transformer fault identification based on the BP neural network algorithm, a fault type of a transformer can be accurately identified. And the method plays an important role in transformer fault diagnosis and a state assessment and the method is convenient.

The invention discloses a transformer fault diagnosis analysis method based on a bayesian network. The method includes the specific steps: step 1, determining transformer oil chromatography property variables Y = { Y1, Y2, Y3... Yn } and fault type variables D = { D1, D2, D3... Dm }, wherein yi is a value of Y1, dm is a value of Dm, using characteristic gas of a transformer oil chromatography as the transformer oil chromatography property variables, and using transformer fault types as the fault type variables; step 2, determining classification models, structural parameters and probability parameters of the bayesian network according to the transformer oil chromatography property variables and the fault type variables; and step 3, determining the transformer fault types by utilization of a connection tree algorithm.

The invention discloses a transformer fault diagnosis method based on case-based reasoning. The implementation steps includes: (1), establishing a fault case base; (2), retrieving fault cases; (3), maintaining a transformer; (4), judging whether a fault case concentrated repair scheme can solve transformer faults, if not, turning to a step (5), and otherwise, turning to a step (9); (5), revising the fault cases; (6), maintaining the transformer by maintenance personnel through using a revised maintenance scheme; (7), judging whether the revised maintenance scheme can solve the transformer faults, if can, turning to a step (8), and otherwise, the step (5) is actuated; (8), updating the fault case base; and (9), learning the fault cases. According to the transformer fault diagnosis method based on the case-based reasoning, a fault case reversing and learning strategy idea is applied to the transformer fault diagnosis method, and compared with a prior transformer fault diagnosis method, the transformer fault diagnosis method has more strong adaptability and higher case retrieval efficiency.

The invention discloses a transformer fault diagnosis method based on an added momentum item BP (back propagation) neural network. On the basis of the added momentum item BP neural network, the invention structures a full sense of intelligent method, namely a transformer fault diagnosis method based on gas data dissolved in oil, so as to improve the speed and accuracy rate of fault diagnosis. The method comprises the following steps of 1) determining neural elements of an input layer and an output layer; 2) determining activation function, the number of hidden layers of the neural network and the neural element number of the hidden layers, thereby establishing a neural network; 3) utilizing a BP algorithm of the added momentum item to adjust the network parameter, and training the established neural network; and 4) utilizing an MATLAB (matrix laboratory) software to simulate the tested neural network, thereby performing test diagnosis for the transformer fault.

The invention discloses a transformer fault diagnosis method based on an improved cuckoo search optimal neural network. According to the method, first, the concentrations of DGA characteristic gases are collected and subjected to normalization processing; the number of neurons in an implicit layer of a BP neural network, a training function and a transfer function from an input layer to an outputlayer are determined, and a fault diagnosis model based on the BP neural network is established; an improved cuckoo search algorithm is adopted to optimize parameters of the BP neural network, an optimal weight threshold parameter is obtained, and an optimal BP neural network model is obtained; training samples are utilized to train the optimal BP neural network model, and an improved cuckoo search neural network diagnosis model is obtained; and the improved cuckoo search neural network diagnosis model is adopted to predict test samples, and the output of the model is a transformer fault diagnosis result. Through the method, the problems that the existing BP neural network is slow in overfitting and convergence speed and a solution in a CS algorithm is poor in quality and low in diagnosisprecision are solved.

The invention discloses a transformer fault diagnosis method based on feature information quantization and weighted KNN, comprising the following steps: S1, dividing sample data into a training set and a test set; S2, inputting the training set, and performing preprocessing on the sample data; S3, based on principal component analysis (PCA) and grey relational analysis (GRA), performing quantization on fault feature information; S4, introducing a particle swarm optimization algorithm for optimizing a weighted KNN categorization algorithm, according to a true fault category, training a sample in a standardized fault feature matrix, and obtaining a power transformer fault diagnosis model, thus categorization on a power transformer fault is realized; and S5, inputting the test set into the power transformer fault diagnosis model, and obtaining a diagnosis result, thus diagnosis on the power transformer fault is realized. The transformer fault diagnosis method disclosed by the invention solves the problems that processing efficiency is low, model training is difficult and limitation exists in the prior art.

The invention discloses a transformer fault detection method based on an SOM (Self Organizing Map) neural network. The method comprises the following steps: S100: selecting a transformer as a testing object, and acquiring vibration signals of the transformer in different states as sample data; S200: decomposing and extracting a characteristic vector by utilizing ensemble empirical mode decomposition in Hilbert-Huang transform; S300: inputting the characteristic vector into the SOM neural network; S400: calculating a distance between a weight of a mapping layer and an input vector; S500: adjusting weights of an efferent neuron and an adjacent neuron; S600: judging whether pre-set conditions are met or not, and finishing SOM neural network training to obtain a testing sample; and S700: inputting the testing sample, and outputting the transformer fault type corresponding to the testing sample according to the network, thereby realizing the technical effect of online detection of the transformer.

The invention discloses a transformer fault diagnosis method based on improved principal component analysis, which belongs to the technical field of transformer fault diagnosis. The method adopts the sum of absolute values of sample indexes to carry out standardized treatment on sample index values, and thus, the difference of each sample index value in magnitude can be eliminated, and the information difference features between samples can also be kept; and sample principal components are selected according to cumulative contribution rates of the principal components, Euclidean distances among the sample principal components are clustered, and a transformer fault type is judged. The method of the invention can effectively improve the accuracy for diagnosing inner hidden fault of the transformer.

The invention relates to a transformer fault diagnosis method based on a fuzzy Petri net. The method comprises the steps of firstly, constructing a transformer fault diagnosis model by using the fuzzy Petri net; performing separation by using a gas chromatography to obtain a concentration value of gas in transformer oil; acquiring the increase speed of the gas in the transformer oil through a gas generation rate formula; an obtaining initial identification of a model through combination of the concentration value and the gas generation rate of the gas in the comprehensive transformer oil; and performing rational analysis of transformer fault diagnosis by using the transformer fault diagnosis model to obtain a diagnosis result. According to the transformer fault diagnosis method based on the fuzzy Petri net, weighted sum of values of values on input arcs of the processed transitional range of input places serve as the fault possibility, so that the problems such as missing determination, false determination and incapability of determination of transformer faults are solved, the possibility of each of faults is given quantitatively, and the diagnosis accuracy is improved.

The invention discloses a transformer fault diagnosis method based on a coupled hidden Markov model, which belongs to the technical field of electrical equipment state monitoring and fault diagnosis. The method adopts left and right hidden Markov chains, measured values of five gases in oil chromatography are input as observed values of one chain, corresponding ratio values of the five gases are input as observed values of the other chain, and then transformer fault diagnosis is carried out. The method provided by the invention retains the advantages of the hidden Markov model, is applicable to analysis of non-stationary signals with poor repeatability and can carry out fault diagnosis based on multichannel information.

The invention discloses a transformer fault diagnosis method based on vibration noise and a BP neural network. The invention relates to the technical field of transformer fault treatment, the method comprising the following steps: S1, acquiring the vibration noise sound pressure signals of each area of the transformer through a noise source identification module, and obtaining the area where the maximum noise source is located according to the vibration noise sound pressure signals; S2, acquiring a vibration signal through a vibration signal measuring module to the area where the maximum noisesource is located; S3, adopting BP neural network algorithm to carry out transformer fault diagnosis on the vibration signal. The invention collects the noise sound pressure signal of the transformerthrough S1 and S2, and combines the vibration signal with the fault diagnosis of the transformer through the BP neural network algorithm, thereby greatly improving the accuracy of the fault diagnosisand solving the defect that the fault diagnosis of the transformer is difficult through the vibration signal of the state information of the transformer.

The invention discloses a transformer fault diagnosis method based on Bi-LSTM and analysis of dissolved gas in oil. The method comprises: collecting fault DGA monitoring data of each substation, carrying out normalization, sequence expansion, noise superimposing and the like on the data, and extracting fault feature information based on a non-coding ratio method; carrying out length ranking on a DGA sequence, carrying out grouping and filling, and classifying groups into a training set and a verification set; constructing a deep learning frame based on Bi-LSTM, inputting data, and carrying outtraining; and then carrying out diagnosis and network updating by combining actual test data to obtain a fault diagnosis model with the high diagnosis accuracy and portability. According to the invention, the influence of the noise and error on the diagnosis during the DGA data monitoring process is reduced effectively; and the Bi-LSTM-based transformer fault diagnosis model is constructed by considering the complex correlation between different sequences. With introduction of links of sequence sorting, grouping, filling and the like, a problem of different sampling lengths of different transformers in the actual engineering is solved by using the batch training strategy.

The invention discloses a transformer fault diagnosis method based on a radial basis function neural network. According to the method, the content of characteristic gas in insulating oil can be used as input for the radial basis function neural network, transformer faults are output accurately, and accordingly accuracy in transformer fault diagnosis is improved greatly and safe and reliable transformer operation is ensured.

The invention provides a spare automatic adaptive switching method for a transformer substation based on automatic reclosing information. A 110kV spare automatic switching logic matched with a superior safe automatic device is formed by combining a main 110kV transformer substation connection mode of unit connection, comprehensively analyzing various constraint conditions for 10kV spare automatic switching, adopting in-place information and using the reclosing process of a 110kV line and trip of a step-down switch as criteria, so that the switching rate of 10kV spare automatic switching equipment can be improved, and the method plays an important role in improving the power supply reliability of a power grid. Switching of a sectional spare automatic switching adaptive superior safe device is realized by considering the conditions such as the main connection mode, line fault electrical features, transformer faults and the like.

The invention discloses a vibration data fusion and image recognition-based transformer fault diagnosis method. A plurality of vibration measuring points are arranged on the outer surface of a transformer oil tank to measure vibration data so as to obtain vibration data under various typical fault states of the transformer. Characteristic value extraction is performed on the pieces of vibration data respectively to form characteristic value matrixes which completely describe the process change rule of the various typical faults, i.e., a sample matrix database of the various typical faults. On the basis, the image recognition technology is applied to the field of transformer fault diagnosis; through matching calculation of the characteristic value matrixes, the defects of the electric parameter measuring method and the artificial fault recognition in the field of the conventional transformer fault diagnosis are overcome, the faults and the states of transformer windings and cores can be sensitively reflected, and the potential faults in the transformer are earlier discovered.

The invention discloses a transformer fault dynamic early warning method based on a Markov model. The method comprises steps of (1) training the hidden Markov model by using gas dissolved in oil concentration data from the normal state to the fault state of a fault transformer and gas dissolved in oil concentration data of a normal transformer, to obtain a transformer fault model Mm and a transformer normal model M fitting each type of fault; and (2) using the transformer fault model Mm and the transformer normal model M to find a model M' which matches the gas dissolved in oil concentration data of a to-be-tested transformer after the linear interpolation process, and according to the model M', the current health state and data of the to-be-tested transformer, predicting the health state of the next moment of the to-be-tested transformer. The method can predict the future operation condition of the transformer by extracting the dynamic characteristics, and realize the dynamic early warning function of the transformer equipment. The method has a wide application prospect in the equipment maintenance.

The invention provides a fault diagnosis method and system for a transformer. The method comprises the steps of selecting a transformer fault case comprising dissolved characteristic gas in the transformer oil, building a fault case library of transformers; determining a training sample set and a test sample set based on the fault case library of the transformers; establishing a fault judgment decision-making tree on the basis of the training sample set and the test sample set, and pruning and optimizing the decision-making tree to obtain a transformer fault diagnosis analysis model; wherein the transformer fault case comprises the type of the dissolved characteristic gas in the transformer oil, the value of the dissolved characteristic gas and the equipment state type of the transformer.The decision-making tree is pruned and optimized on the basis of the sample set, and a fault diagnosis analysis model can be obtained to find out a latent fault inside a transformer in time. The problems that a traditional oil chromatography three-ratio method is incapable of diagnosing certain faults some and is low in judgment correct rate due to incomplete failure coding and lack of coding areeffectively solved.

The disclosure provides a transformer fault comprehensive diagnosis system based on a fuzzy association rule. The system includes a transformer fault type diagnosis module, a transformer fault location diagnosis module, and a transformer fault comprehensive diagnosis module based on case-based reasoning. The disclosure also provides a transformer fault comprehensive diagnosis method based on a fuzzy association rule. The diagnosis system diagnoses the fault type, the fault location and the fault cause of a transformer, can help the field staff to complete discrimination, and is suitable for the diagnosis of a variety of transformer faults.

The invention discloses a transformer fault diagnosis method based on an entropy weight method and grey correlation analysis, belonging to the technical field of transformer fault diagnosis. The transformer fault diagnosis method comprises the steps of: carrying out standardization processing on transformer fault sample data; adopting the entropy weight method to determine weight of a transformer fault diagnosis index; and determining a fault type of a transformer through calculating Grey Euclid weighted correlation degree. The transformer fault diagnosis method makes full use of all information of gas in oil data, exerts the advantage that the grey correlation is applicable to a small sample and poor information system, avoids defects of partial correlation and information loss, and can effectively increase accuracy rate of transformer fault diagnosis as shown by results of example analysis.

The invention discloses a transformer fault diagnosis method based on a random forest. The method comprises the following steps of collecting fault gas concentration data in insulating oil in a transformer and a corresponding fault type as a training sample; according to the training sample, based on the generation steps of a decision tree, establishing a fault decision tree; according to the fault decision tree, establishing a random forest model; and collecting the fault gas concentration data of a unknown fault type, inputting into the random forest model so as to acquire the fault type through the random forest model. The fault gas concentration data in the insulating oil in the transformer is taken as the training sample so as to establish the random forest model, a whole transformerfault can be accurately diagnosed, stability is high, and the method can be applied to the transformer diagnosis technology field.

The invention discloses a distribution transformer health assessment method, and the method comprises the steps: building a distribution transformer health assessment index hierarchical structure model according to an assessment index of a distribution transformer; Calculating subjective weights and objective weights of the evaluation indexes; Calculating a comprehensive weight according to the subjective weight and the objective weight; Calculating the weighted sum of the evaluation indexes according to the comprehensive weight to obtain a comprehensive score of the health state of the distribution transformer; And sorting the distribution transformers according to the comprehensive scores of the health states of the distribution transformers. According to the distribution transformer health assessment method, the problem that the assessment result is easily distorted because the weight setting is too subjective only depending on an analytic hierarchy process is avoided; Through calculating the subjective weight and the objective weight, more accurate distribution transformer health assessment is realized, maintenance personnel are helped to comprehensively and timely master the health condition of the distribution transformer, so that enterprises can timely arrange the maintenance work of the distribution transformer, and the distribution transformer faults are reduced.

The invention discloses a transformer fault diagnostic method based on gray fuzzy firefly algorithm optimization. The method comprises the following steps: effective data sequences of the contents of five characteristic gases of a transformer are selected through a characteristic gas content prediction module, and the characteristic gas predictive values at a time under the independent variable sequences of the five characteristic gases are obtained through a univariate time sequence gray model; pretreatment is performed on data; characteristic gas coding sequences are used as inputs of training samples, and transformer fault types corresponding to the inputs are used as outputs to built an IGSO-LM network, and the weight value and the threshold value of the LM network are optimized through an IGSO algorithm; the network is trained by using pretreated data of the characteristic gases of the transformer, so as to obtain an optimal nerve net weight value and the threshold value to built a transformer fault diagnostic model and judge the transformer fault types. The transformer fault diagnostic method provided by the invention solves the problems of data source shortage of transformer fault gases and low result accuracy in a conventional analysis method.

The invention provides a transformer fault prediction method and device, a terminal and a readable storage medium. The transformer fault prediction method comprises the steps of building a concentration prediction model of a characteristic gas according to collected historical concentration and historical electrical parameters of the characteristic gas dissolved in the transformer oil; processingthe collected current concentration and current electrical parameters of the characteristic gas by using the concentration prediction model to obtain the concentration of the characteristic gas at thenext moment; and performing fault prediction according to the concentration of the characteristic gas at the next moment to obtain the predicted fault type. According to the fault prediction method,the association relations between oil-soluble gases and between an oil-soluble gas and other electrical parameters are firstly analyzed, then the concentration prediction model of each oil-soluble gasbased on the other gases and the electrical parameters is built, the oil-soluble gas concentration of a transformer at any moment in the future is predicted according to the concentration predictionmodel, fault prediction is performed according to the oil-soluble gas concentration, and the accuracy of transformer fault prediction is improved.

The invention discloses a CNN-based transformer fault diagnosis method. The method comprises the following steps of 1, obtaining a monitoring image of a transformer; 2, inputting the monitoring imageinto a CNN judgment model, and obtaining a probability value of the monitoring image being a transformer in a normal state; And step 3, judging whether the probability value is lower than a set probability threshold value or not, and if yes, judging that the transformer is in a fault state. According to the invention, the deep neural network is used to determine and diagnose the fault state of themonitoring image of the transformer; According to the method, the calculation complexity of traditional fault diagnosis is reduced, the efficiency of transformer fault identification and diagnosis inthe transformer substation and the accuracy of a diagnosis result can be effectively improved, the robustness is high, and monitoring images of different transformer substation backgrounds can be processed.

The invention discloses a transformer fault diagnosis method based on a conditional generative adversarial network. The method includes the following steps: (1) collecting transformer state historicalmonitoring data, forming a transformer fault diagnosis data set, and dividing the transformer fault diagnosis data set into a training set and a test set; (2) constructing a conditional generative adversarial network into a multi-layer sensor structure, wherein the conditional generative adversarial network has a generator and a discriminator and N outputs of the discriminator comprise: N-1 faulttypes and a judgment result about whether the data comes from analog fault data of the generator; (3) training and testing the generator and discriminator; and (4) inputting collected real-time monitoring data of the state of a transformer into the discriminator, and obtaining a fault diagnosis result of the transformer from the output of the discriminator. In addition, the invention discloses asystem based on a conditional generative adversarial network. The transformer fault diagnosis method can realize automatic identification of defects of transformer equipment.

The invention discloses a transformer fault diagnosis method based on gauss transform and global optimization SVM (support vector machine) and belongs to the field of fault diagnosis of a transformer.The method comprises the following steps of S10, calculating a three-ratio characteristic quantity according to DGA data of a transformer fault characteristic gas; S20, performing normalization preprocessing on the three-ratio characteristic quantity to obtain a preprocessed sample which is divided into a training sample and a test sample; S30, constructing an SVM fault diagnosis model, and establishing the SVM fault diagnosis model based on GA (Genetic Algorithm) optimization in combination with a cross validation principle and a genetic algorithm; and S40, diagnosing the test sample according to the SVM fault diagnosis model based on GA optimization to obtain a fault diagnosis result. Compared with a transformer fault diagnosis accurate rate performed by use of a conventional standard support vector machine method, an IEC three-ratio method and a neural network algorithm, the accurate rate of a transformer fault diagnosis result obtained by the invention is higher.

The invention belongs to the technical field of transformer fault type detection, and discloses a transformer state evaluation and fault detection method based on multi-source data fusion. Transformercurrent data are detected by using a current sensor corrected in a cyclic mode based on least square method. A voltmeter improving accuracy based on a remainder splitting algorithm is utilized to detect transformer voltage data. Transformer temperature data are detected by using a temperature sensor. A gas sensor performing temperature compensation based on a standard artificial bee colony algorithm is used for detecting concentration data of transformer fault characteristic gas. A data processing software is utilized to build a transformer fault model, and the transformer fault state is evaluated according to the detected data. An alarm or notification is given in time according to the evaluation results by using an alarm apparatus. The transformer state evaluation and fault detection method adopts a theory of a probability fuzzy set to process and analyze; the fault state of a transformer can be evaluated, the uncertainty of the characteristic value of the fault state of the transformer is reflected, and theoretical guidance is provided for the evaluation of the fault state of the transformer.