CN113591792A - Transformer fault identification method based on self-organizing competitive neural network algorithm - Google Patents
Transformer fault identification method based on self-organizing competitive neural network algorithm Download PDFInfo
- Publication number
- CN113591792A CN113591792A CN202110952066.0A CN202110952066A CN113591792A CN 113591792 A CN113591792 A CN 113591792A CN 202110952066 A CN202110952066 A CN 202110952066A CN 113591792 A CN113591792 A CN 113591792A
- Authority
- CN
- China
- Prior art keywords
- transformer
- vibration
- neural network
- self
- network algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 25
- 230000002860 competitive effect Effects 0.000 title claims abstract description 19
- 238000005070 sampling Methods 0.000 claims abstract description 17
- 239000013598 vector Substances 0.000 claims abstract description 8
- 230000001133 acceleration Effects 0.000 claims abstract description 5
- 210000002569 neuron Anatomy 0.000 claims description 25
- 238000004804 winding Methods 0.000 claims description 18
- 238000013507 mapping Methods 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 abstract description 17
- 238000006243 chemical reaction Methods 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 abstract description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 15
- 238000012795 verification Methods 0.000 description 8
- 238000002474 experimental method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
A transformer fault identification method based on a self-organizing competitive neural network algorithm belongs to the technical field of transformers, and comprises the steps of carrying out time-frequency domain conversion on sampling signals on the basis of transformer vibration signal field sampling, extracting component amplitude values under a frequency domain to serve as vibration acceleration characteristic vectors, and carrying out training and identification through an SOM algorithm on the basis to achieve the purpose of transformer operation state and fault identification based on vibration signals. The method has the advantages of being scientific, reasonable, real, effective, accurate in calculation, high in practical value and the like.
Description
Technical Field
The invention belongs to the technical field of transformers, and particularly relates to a transformer fault identification method based on a self-organizing competitive neural network algorithm, which is applied to power transformer fault operation state identification and safety evaluation.
Background
The power transformer is an extremely important device in a power grid, and plays an important role in interconnection and power transmission of power grids of various grades. With the continuous construction and improvement of national power grids, the transformation capacity of the national power grid reaches 49.4 hundred million kilowatts at present, and the transformer is influenced by the operation condition and the environment, so that the transformer has faults, and the disintegration analysis of the transformer after the accident shows that the ratio of the damage of the iron core and the winding structure caused by the electromagnetic force of the transformer is high. At present, a diagnosis method based on electrical parameters is mostly adopted in a transformer fault identification method, but the method is influenced by the running state of the transformer and the external environment, the electrical parameters are difficult to effectively and comprehensively reflect the internal fault of the transformer, and a vibration signal contains more internal component change information, so that the method has important significance in researching the vibration mechanism of the transformer and combining the vibration signal to realize the running state identification of the transformer.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method comprises the steps of obtaining a frequency domain transformation result of a transformer time domain acquisition signal through fast Fourier decomposition according to a vibration acquisition parameter of a field real-time transformer, combining frequency domain characteristics on the basis to form a sample characteristic vector set, and performing sample characteristic training by adopting a self-organizing mapping neural network algorithm to finally achieve the purpose of transformer fault identification.
A transformer fault identification method based on a self-organizing competitive neural network algorithm is characterized by comprising the following steps: comprises the following steps which are sequentially carried out,
step one, collecting and preprocessing fault signals
Arranging a transformer vibration measuring point in a box corresponding to the middle of a transformer winding, collecting an original vibration signal of the transformer, performing data preprocessing on the original vibration signal through fast Fourier decomposition (FFT), and assuming that a sampling signal is a linear superposition result of multiple groups of signals in the FFT principle, the original vibration sampling signal can be expressed as
g(t)＝a0+a1*t+a2*t2+...+an-1*tn-1
In the formula a0、a1…an-1In order to be a coefficient of the decomposition,
by parity arrangement, and introduction of twiddle factors
Converting a time domain result of a transformer vibration sampling signal into a frequency domain result through FFT (fast Fourier transform), and extracting vibration acceleration amplitude values under each frequency domain component to form a vibration signal characteristic vector;
step two, establishing self-organizing competitive neural network identification
Establishing an SOM neural network structure comprising an input layer and an output layer, wherein the output layer can be represented as a two-dimensional plane array formed by a x b neurons under the condition that the number of neurons in the input layer is m, and the Euclidean distance of the jth neuron is calculated as
In the formula, wijThe weight value between the ith neuron of the input layer and the jth neuron of the mapping layer is obtained. The weight of the victory neuron is corrected in the weight learning process, and the method comprises the following steps
Δwij＝wij(t+1)-wij(t)＝η(t)(xi(t)-wij(t))
Wherein eta is a constant of 0-1, and continuously decays to 0 with time.
In the first step, the original vibration sampling signal is obtained by odd-even arrangement
In the first step, a twiddle factor is introduced
The result of the transformation in the frequency domain is
Through the design scheme, the invention can bring the following beneficial effects: a transformer fault identification method based on a self-organizing competitive neural network algorithm is characterized in that time-frequency domain conversion is carried out on sampling signals on the basis of field sampling of transformer vibration signals, component amplitude values under a frequency domain are extracted to serve as vibration acceleration characteristic vectors, training and identification are carried out through an SOM algorithm on the basis, the purpose of identifying the running state and the fault of the transformer based on the vibration signals is achieved, and the method has the advantages of being scientific, reasonable, real, effective, accurate in calculation, high in practical value and the like.
Drawings
The invention is further described with reference to the following figures and detailed description:
fig. 1 is an experimental wiring diagram of a transformer fault identification method based on a self-organizing competitive neural network algorithm.
Fig. 2 is a flowchart of a transformer fault identification method based on a self-organizing competitive neural network algorithm.
FIG. 3 is a SOM algorithm topological graph of a transformer fault identification method based on a self-organizing competitive neural network algorithm.
Fig. 4 is a graph of a current characteristic value identification result of a transformer fault identification method based on a self-organizing competitive neural network algorithm.
Fig. 5 is a diagram of a vibration characteristic value identification result of a transformer fault identification method based on a self-organizing competitive neural network algorithm.
Detailed Description
A transformer fault identification method based on a self-organizing competitive neural network algorithm comprises the following steps of 1, sampling and preprocessing of fault signals
According to the existing standard, arranging a transformer vibration measuring point in a box corresponding to the middle of a transformer winding, collecting an original vibration signal of the transformer, and performing data preprocessing on the original vibration signal through fast Fourier decomposition (FFT). In the FFT principle, the original vibration sampling signal can be expressed as a form shown in formula (1) under the assumption that the sampling signal is formed by linearly superposing a plurality of groups of signals
g(t)＝a0+a1*t+a2*t2+...+an-1*tn-1 (1)
The following formula is obtained by arranging the formula (1) according to odd-even order
g(t)＝(a0+a2*t2+…+an-2*tn-2)
+(a1+a3*t3+…+an-1*tn-1) (2)
＝g1(t)+g2(t)＝g1(t2)+tg2(t2)
Introduction of twiddle factors
Brought into the above formula to obtain
And converting a time domain result of the transformer vibration sampling signal into a frequency domain result through FFT (fast Fourier transform), and further extracting vibration acceleration amplitude values under each frequency domain component to form a vibration signal characteristic vector.
2. Building self-organizing competitive neural network identification
Self-Organizing Feature mapping (SOM) is a leaderless, Self-Organizing, Self-learning network formed from an array of fully connected neural network elements. The basic theory of SOM is that neurons at different positions in space have different division of work, when one neural network receives external input, different reaction regions react to the external input, and the response characteristics of the different reaction regions to the external input are different. Different from the traditional self-organizing network, the SOM network can learn the distribution characteristics of the training input parameters and can also learn the parameter topological structure of the training input to realize the visual cluster analysis of data.
The SOM neural network structure includes an input layer and a competition layer (output layer), and the competition layer can be represented as a two-dimensional planar array formed by a × b neurons assuming that the number of neurons in the input layer is m. Fig. 2 shows the basic flow of the SOM algorithm.
The SOM neural network structure comprises an input layer and a competition layer (output layer), wherein the number of neurons in the input layer is m, the competition layer can be represented as a two-dimensional plane array formed by a multiplied by b neurons, and the Euclidean distance of the jth neuron is calculated as follows
In the formula, wijThe weight value between the ith neuron of the input layer and the jth neuron of the mapping layer is obtained. The weight of the victory neuron is corrected in the weight learning process, and the method comprises the following steps
Δwij＝wij(t+1)-wij(t)＝η(t)(xi(t)-wij(t)) (6)
Wherein eta is a constant of 0-1, and continuously decays to 0 with time.
3. Analysis of experiments
Aiming at a customized three-phase dry-type double-winding experimental transformer (model: SG-10kVA 1.1kV/0.38kV), a moving die experimental platform of the transformer is built, and original vibration data of windings and iron cores of the transformer in different running states are collected. The transformer parameters are shown in table 1. The experimental platform is shown in figure 1.
TABLE 1 Experimental Transformer parameters
The basic steps of the vibration data acquisition experiment of the transformer are
1) Equipment connection: the experimental transformer, the current data acquisition module (oscilloscope: Lecrey WaveSurfer 4000HD), the vibration data acquisition module (magnetic vibration pickup, YD-104/10kHZ) and the voltage control module (voltage regulator) are connected, and the connected equipment respectively realizes vibration signal output, current data acquisition, vibration data acquisition and transformer load control.
2) Arranging vibration measuring points: vibration measuring points are respectively arranged for the transformer winding and the iron core, and in consideration of the accuracy of the vibration measuring points for collecting vibration signals, the winding vibration measuring points are arranged at the center positions of the front sides of the windings of the phases as shown in figure 4, and the iron core vibration measuring points are arranged at the center positions of the phases of the upper iron jaw.
3) Setting the running state: the method is characterized in that the running states of the transformer are set to be 75% load normal running, three-phase unbalanced running, direct-current magnetic biasing faults and winding/iron core loosening faults by combining the actual running condition on site and common faults of the transformer (the added excitation is power frequency excitation), wherein the running state experiment of each fault is set as follows:
a. three-phase unbalanced operation: the secondary side resistance is adjusted so that the transformer a phase is in an operating state with an unbalance rate α of 5%, 10%, 15%.
b. Direct current magnetic biasing: firstly, the no-load current of the transformer is measured, on the basis of the no-load current, the direct current injection amount is set to be beta which is 0.5, 1.0 and 2.0 times of the no-load current, and the direct current injection point is the primary neutral point of the transformer.
c. And (5) loosening the components, and respectively adjusting the upper and lower fastening bolts of the transformer winding and the iron jaw fastening bolts to realize loosening of the transformer winding and the iron core.
4) Data acquisition and processing: and respectively collecting winding current and winding and iron core vibration data in different running states, and decomposing and reconstructing the vibration signals through WPT (wavelet packet transform) to further obtain the vibration signal characteristic vector.
The method comprises the steps that original vibration signals and FFT results of a transformer are obtained, original sampling signals of the transformer have certain periodicity, but original waveforms are complex, effective identification of the running state of the transformer is difficult to conduct through the original vibration signals, the state characteristics of time domain results after FFT conversion are obvious, the vibration signals are concentrated on 100Hz and frequency multiplication and are affected by magnetic leakage, certain 50Hz frequency multiplication components are contained in FFT frequency domain results, FFT conversion results are extracted to serve as vibration characteristics, a vibration characteristic sample set is formed, and SOM training and identification are conducted.
100 groups of samples of vibration data under 5 running states (normal running, three-phase unbalance, direct-current magnetic biasing, winding loosening and iron core loosening) are selected, 500 groups of samples are selected, wherein 90 groups of samples are randomly selected to be a training sample set (450 groups in total) in the 5 running states, and the remaining 50 groups of samples in the 5 running states are verification sample sets.
In the aspect of selection of vibration characteristic parameters, the three-phase imbalance and winding looseness states select the winding vibration characteristic parameters as identification parameters; selecting an iron core vibration characteristic parameter as an identification parameter through direct current magnetic biasing and iron core loosening; and in the normal running state, the winding and iron core vibration characteristic parameters are selected as identification parameters, and a current-vibration characteristic parameter set is formed on the basis.
And extracting 16 sets of characteristic parameters from the FFT result, and setting the number of neurons in the mapping layer to be 20 in consideration of the fact that the number of neuron nodes in the mapping layer of the SOM algorithm needs to be larger than the input characteristic dimension. Considering the uniformity of the training process of the characteristic parameter sets of different running states, the training times are respectively set to be 10, 20, 30, 50, 200, 500 and 1000, and the appropriate training times are determined by taking the direct current magnetic bias state (63# sample) as a verification sample. As shown in table 2, results for different training times.
After 1000 trains, each state is divided into 5 regions, indicating that the training set is correctly divided.
The verification set samples are effectively identified, and the problem of dead nodes does not exist.
TABLE 2SOM recognition results
As can be seen from table 2, when the training times are 10, 20, 30, and 50 times, the operation state classification results overlap, which indicates that the training times are insufficient, and when the training times are 200 times, the operation state classification does not cause the overlap problem, which indicates that the training times are sufficient. When the training times are 1000 times, the neuron number of the verification vector output layer is 40 and is consistent with the neuron number of the output layer direct current magnetic bias state, so that the SOM algorithm can identify the running state of the transformer.
Further, comparing and analyzing the identification accuracy of the traditional current characteristic parameter and the identification accuracy of the vibration characteristic parameter, wherein the identification accuracy is the ratio of the number of the correct identification samples to the total verification samples, and obtaining the results shown in fig. 4 and 5
From the SOM algorithm current characteristic value identification result fig. 4, it can be seen that only 17 groups of identification errors in 50 groups of verification samples of current characteristic parameters are adopted, the identification accuracy is 66%, the identification accuracy of normal operation and three-phase unbalanced operation states is high, the identification accuracy of direct current magnetic biasing and component loosening states is low, the main reasons of the direct current magnetic biasing and component loosening states are analyzed, and port current changes are small under the direct current magnetic biasing and component loosening states, so that the internal fault problem of the transformer is difficult to effectively identify through the traditional electrical parameter identification method.
As can be seen from the SOM algorithm vibration characteristic value identification result figure 5, 2 groups of identification errors in the verification samples are verified by adopting 50 groups of global characteristic parameters, the identification accuracy is 96%, and the identification accuracy is far higher than that of the verification samples only adopting current characteristic parameters, so that the transformer fault identification method adopting the global characteristic parameters can effectively identify various faults of the transformer.
The transformer fault identification method based on the self-organizing competitive neural network algorithm shows that the method can be used for correctly identifying various running states and faults of the transformer through experimental analysis results, the purpose of the invention is achieved, and the effect is achieved.
The terms of calculation, illustration and the like in the embodiments of the present invention are used for further description, are not exhaustive, and do not limit the scope of the claims, and those skilled in the art can conceive other substantially equivalent alternatives without inventive step based on the teachings of the embodiments of the present invention, which are within the scope of the present invention.
Claims (3)
1. A transformer fault identification method based on a self-organizing competitive neural network algorithm is characterized by comprising the following steps: comprises the following steps which are sequentially carried out,
step one, collecting and preprocessing fault signals
Arranging a transformer vibration measuring point in a box corresponding to the middle of a transformer winding, collecting an original vibration signal of the transformer, performing data preprocessing on the original vibration signal through fast Fourier decomposition (FFT), and assuming that a sampling signal is a linear superposition result of multiple groups of signals in the FFT principle, the original vibration sampling signal can be expressed as
g(t)＝a0+a1*t+a2*t2+…+an-1*tn-1
In the formula a0、a1…an-1In order to be a coefficient of the decomposition,
by parity arrangement, and introduction of twiddle factors
Converting a time domain result of a transformer vibration sampling signal into a frequency domain result through FFT (fast Fourier transform), and extracting vibration acceleration amplitude values under each frequency domain component to form a vibration signal characteristic vector;
step two, establishing self-organizing competitive neural network identification
Establishing an SOM neural network structure comprising an input layer and an output layer, wherein the output layer can be represented as a two-dimensional plane array formed by a x b neurons under the condition that the number of neurons in the input layer is m, and the Euclidean distance of the jth neuron is calculated as
In the formula, wijThe weight value between the ith neuron of the input layer and the jth neuron of the mapping layer is obtained. The weight of the victory neuron is corrected in the weight learning process, and the method comprises the following steps
Δwij＝wij(t+1)-wij(t)＝η(t)(xi(t)-wij(t))
Wherein eta is a constant of 0-1, and continuously decays to 0 with time.
2. The method for identifying the transformer fault based on the self-organizing competitive neural network algorithm as claimed in claim 1, wherein: in the first step, the original vibration sampling signal is obtained by odd-even arrangement
3. The method for identifying the transformer fault based on the self-organizing competitive neural network algorithm as claimed in claim 1, wherein: in the first step, a twiddle factor is introduced
The result of the transformation in the frequency domain is
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110952066.0A CN113591792B (en) | 2021-08-19 | 2021-08-19 | Transformer fault identification method based on self-organizing competitive neural network algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110952066.0A CN113591792B (en) | 2021-08-19 | 2021-08-19 | Transformer fault identification method based on self-organizing competitive neural network algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113591792A true CN113591792A (en) | 2021-11-02 |
| CN113591792B CN113591792B (en) | 2023-11-28 |
Family
ID=78238498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110952066.0A Active CN113591792B (en) | 2021-08-19 | 2021-08-19 | Transformer fault identification method based on self-organizing competitive neural network algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113591792B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024000764A1 (en) * | 2022-06-29 | 2024-01-04 | 南方电网科学研究院有限责任公司 | Transformer health state assessment method, apparatus, and device, and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008071255A (en) * | 2006-09-15 | 2008-03-27 | Saga Univ | Pattern generating method using self-organizing map, its program and device |
| CN104330255A (en) * | 2014-11-04 | 2015-02-04 | 徐州隆安光电科技有限公司 | Gear fault diagnosing method based on multi-sensor information fusion |
| CN109829538A (en) * | 2019-02-28 | 2019-05-31 | 苏州热工研究院有限公司 | A kind of equipment health Evaluation method and apparatus based on deep neural network |
| CN110443302A (en) * | 2019-08-02 | 2019-11-12 | 天津相和电气科技有限公司 | Load discrimination method and its application based on Fusion Features and deep learning |
| CN112345252A (en) * | 2020-11-22 | 2021-02-09 | 国家电网有限公司 | Rolling bearing fault diagnosis method based on EEMD and improved GSA-SOM neural network |
| CN112734001A (en) * | 2020-12-09 | 2021-04-30 | 东南大学 | Wind power transmission chain intelligent fault diagnosis method based on order spectrum migration |
-
2021
- 2021-08-19 CN CN202110952066.0A patent/CN113591792B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008071255A (en) * | 2006-09-15 | 2008-03-27 | Saga Univ | Pattern generating method using self-organizing map, its program and device |
| CN104330255A (en) * | 2014-11-04 | 2015-02-04 | 徐州隆安光电科技有限公司 | Gear fault diagnosing method based on multi-sensor information fusion |
| CN109829538A (en) * | 2019-02-28 | 2019-05-31 | 苏州热工研究院有限公司 | A kind of equipment health Evaluation method and apparatus based on deep neural network |
| CN110443302A (en) * | 2019-08-02 | 2019-11-12 | 天津相和电气科技有限公司 | Load discrimination method and its application based on Fusion Features and deep learning |
| CN112345252A (en) * | 2020-11-22 | 2021-02-09 | 国家电网有限公司 | Rolling bearing fault diagnosis method based on EEMD and improved GSA-SOM neural network |
| CN112734001A (en) * | 2020-12-09 | 2021-04-30 | 东南大学 | Wind power transmission chain intelligent fault diagnosis method based on order spectrum migration |
Non-Patent Citations (1)
| Title |
|---|
| 赵智;任桂山;陈津刚;陈学梅;: "基于自组织特征映射网络的配电网故障类型识别", 自动化技术与应用, no. 09 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024000764A1 (en) * | 2022-06-29 | 2024-01-04 | 南方电网科学研究院有限责任公司 | Transformer health state assessment method, apparatus, and device, and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113591792B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112041693B (en) | Power distribution network fault positioning system based on mixed wave recording | |
| CN109948597B (en) | High-voltage circuit breaker mechanical fault diagnosis method | |
| CN108960339A (en) | A kind of electric car induction conductivity method for diagnosing faults based on width study | |
| CN108229544A (en) | A kind of NPC three-level photovoltaic inverters open fault diagnostic method | |
| Atthapol et al. | Internal Fault Classification in Transformer Windings using Combination of Discrete Wavelet-Transforms and Back-propagation Neural Networks | |
| CN109142851A (en) | A kind of novel power distribution network internal overvoltage recognition methods | |
| CN110703151A (en) | Transformer fault diagnosis method based on vibration blind source separation and Bayesian model | |
| CN112083328A (en) | Fault diagnosis method, system and device for high-voltage circuit breaker | |
| CN110174255A (en) | A kind of transformer vibration signal separation method based on radial base neural net | |
| CN116089857A (en) | Transformer fault identification method based on CEEMDAN-DBN | |
| CN113866684A (en) | Distribution transformer fault diagnosis method based on hybrid sampling and cost sensitivity | |
| CN113591792B (en) | Transformer fault identification method based on self-organizing competitive neural network algorithm | |
| Dey et al. | Rough-granular approach for impulse fault classification of transformers using cross-wavelet transform | |
| CN113884818B (en) | Method for accurately estimating arrival time of fault traveling wave of power distribution network based on LSTM | |
| CN111413543A (en) | Experimental device and method for identifying harmonic resistance parameters of low-voltage distribution line | |
| CN116298509A (en) | Online identification method for harmonic resonance of power system | |
| CN114091534A (en) | Winding vibration characteristic identification method based on wavelet packet scale-energy ratio | |
| CN114186590A (en) | Power distribution network single-phase earth fault identification method based on wavelet and deep learning | |
| CN114062832A (en) | Method and system for identifying short-circuit fault type of power distribution network | |
| CN114814391A (en) | Charging pile fault identification method and storage medium | |
| Yue et al. | A power system harmonic problem based on the BP neural network learning algorithm | |
| CN113341223A (en) | Method suitable for power grid harmonic analysis and harmonic source positioning | |
| CN112560888A (en) | Method and system for evaluating short-circuit resistance of transformer winding based on octave geometric transformation | |
| CN116992326A (en) | Transformer fault identification method based on wavelet packet-mapping network algorithm | |
| CN112327220B (en) | Distribution transformer health on-line diagnosis method and equipment based on multi-source data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |