CN114019365A - On-load tap-changer fault diagnosis method based on gas detection technology in oil - Google Patents
On-load tap-changer fault diagnosis method based on gas detection technology in oil Download PDFInfo
- Publication number
- CN114019365A CN114019365A CN202111308298.9A CN202111308298A CN114019365A CN 114019365 A CN114019365 A CN 114019365A CN 202111308298 A CN202111308298 A CN 202111308298A CN 114019365 A CN114019365 A CN 114019365A
- Authority
- CN
- China
- Prior art keywords
- fault
- changer
- load tap
- oil
- gas
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 238000005516 engineering process Methods 0.000 title claims abstract description 12
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 238000013499 data model Methods 0.000 claims abstract description 9
- 239000002245 particle Substances 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 4
- 239000007789 gas Substances 0.000 claims description 56
- 238000012360 testing method Methods 0.000 claims description 26
- 238000012706 support-vector machine Methods 0.000 claims description 11
- 238000004088 simulation Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 239000000725 suspension Substances 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims 2
- 238000005259 measurement Methods 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000012843 least square support vector machine Methods 0.000 description 13
- 239000013598 vector Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000007599 discharging Methods 0.000 description 6
- 238000009826 distribution Methods 0.000 description 4
- 239000003990 capacitor Substances 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000009413 insulation Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004939 coking Methods 0.000 description 2
- 238000013021 overheating Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 230000005526 G1 to G0 transition Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 239000012159 carrier gas Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000007790 solid phase Substances 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
本发明公开了一种基于油中气体检测技术的有载分接开关故障诊断方法，属于电力变压器有载分接开关局部放电后油中气体检测技术领域。包括以下步骤：S1：油中7种特征气体含量获取与特征参量计算；S2：建立故障类型关联数据模型；S3：故障分类和诊断；S4：数据库自更新，输出诊断结果。本发明通过检测有载分接开关油中特征气体含量,可以有效鉴别变压器内部故障的种类，判断变压器有载分接开关状态。本发明采用基于粒子群优化算法来诊断故障，提高了诊断的收敛速度，解决了传统方法选取的输入特征作为油中溶解气体分析特征量会陷入局部最优问题，本发明在实际应用中能快速有效的得到故障类型，提高变压器安全运行水平。
The invention discloses a fault diagnosis method for an on-load tap changer based on the gas-in-oil detection technology, and belongs to the technical field of gas-in-oil detection after partial discharge of the on-load tap changer of a power transformer. It includes the following steps: S1: acquisition of 7 kinds of characteristic gas contents in oil and calculation of characteristic parameters; S2: establishment of fault type correlation data model; S3: fault classification and diagnosis; S4: self-update of database and output of diagnosis results. By detecting the characteristic gas content in the oil of the on-load tap-changer, the invention can effectively identify the types of internal faults of the transformer and judge the state of the on-load tap-changer of the transformer. The invention adopts the particle swarm optimization algorithm to diagnose faults, improves the convergence speed of the diagnosis, and solves the problem that the input feature selected by the traditional method as the analysis feature quantity of dissolved gas in oil will fall into the local optimum. Effectively get the fault type and improve the safe operation level of the transformer.
Description
Technical Field
The invention belongs to the technical field of gas detection in oil after partial discharge of an on-load tap-changer of a power transformer, and relates to a transformer on-load tap-changer fault diagnosis method based on a characteristic gas detection technology in oil.
Background
The power transformer is a core main device of a power system and is key equipment for electric energy transmission and voltage transformation. In recent years, the capacity of newly-added transformers in China is rapidly increased at a speed of approximately 8% -10% every year, the capacity of a single transformer is increased along with the improvement of the manufacturing level, and once a fault occurs, great economic loss is inevitably caused. The on-load tap changing transformer plays an important role in connecting a power grid, adjusting active and reactive power flows and stabilizing the central voltage of a load in a power system, is widely applied to the power grid, and generally performs on-load tap changing on a high-voltage transmission transformer and a distribution transformer of an important load.
Worldwide investigation of the reliability of the transformer by global power industry organizations and statistical analysis of high-voltage switchgear accidents by combining the power system in China show that about 50% of accidents of the transformer come from a constant part of an on-load tap-changer, and the contact resistance of an internal contact of the on-load tap-changer is increased, so that the contact is overheated, coked and discharged, and even electric arcs and even burning loss are generated. Overheating and electrical discharge produce a hydrocarbon mixture that dissolves in the on-load tap changer oil. In order to improve the reliability of the on-load tap-changer action, the off-line or on-line detection of the dissolved gas in the on-load tap-changer oil is required, so that the aims of effectively preventing the occurrence of faults, finding potential faults in advance and reducing the fault rate of equipment are fulfilled. The exploration of effective methods for detecting dissolved gas in the on-load tap-changer oil of the transformer and diagnosing faults is always a key problem which is commonly concerned by domestic and foreign research institutions for many years.
Aiming at the conditions that the on-load tap-changer of the power transformer is easy to have faults under long-term and efficient operation, fault characteristic gas can be generated after the faults occur, and the like, the types and the positions of the faults can be found in time, the faults are effectively prevented from occurring, and the fault rate of equipment is reduced. Therefore, the type of the internal fault of the transformer can be effectively identified through detecting the characteristic gas in the on-load tap-changer oil of the power transformer, the state of the on-load tap-changer of the transformer can be effectively judged, and the safe operation level of the transformer is improved.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following problems: the input characteristics selected by the traditional method are used as the analysis characteristic quantity of the dissolved gas in the oil, so that the problem of local optimum can be solved, the problem of fault classification of the transformer on-load tap-changer can not be comprehensively reflected, and fault diagnosis errors are likely to be caused in practical application.
An authorization publication number of CN102680890B discloses a method for fault diagnosis of an on-load tap-changer of an oil-immersed transformer, belonging to the field of fault diagnosis of electrical equipment. The method adopts the dissolved gas in the oil to diagnose the fault of the transformer tap changer, 5 criteria are formed by the dissolved gas in the oil and the ratio of the dissolved gas in the oil, and the corresponding analysis method comprises 5 steps and is respectively used for judging the states of normal operation, large-scale operation, low-energy discharge, high-energy discharge, overheating, slight coking and severe coking of the transformer tap changer. Although the method can be used for fault diagnosis of the tap changer, the detection is not accurate enough.
Patent with publication number CN104792467B discloses a method for judging internal leakage possibility of an on-load tap-changer based on characteristic gas content in oil, which comprises the following steps: 1) measuring the content of characteristic gas in the transformer body oil; 2) measuring the characteristic gas content in the on-load tap-changer oil; 3) calculating the correlation coefficient of the characteristic gas content in the transformer body and the on-load tap-changer oil, and replacing the correlation coefficient with r; 4) and (3) judging: when r is more than or equal to 0.9 and less than or equal to 1, the on-load tap-changer has internal leakage. The method can compare the contents of characteristic gas components in the transformer body and the on-load tap-changer oil, and judge whether the on-load tap-changer has internal leakage faults or not according to the comparison result, but cannot judge the fault type.
Disclosure of Invention
In view of the above, the present invention provides a fault diagnosis method for an on-load tap-changer based on an oil-gas detection technology.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a fault diagnosis method for an on-load tap-changer based on an oil-gas detection technology comprises the following steps:
s1: acquiring characteristic gas data in oil and calculating characteristic parameters: building a fault simulation test platform of the on-load tap-changer of the transformer, obtaining sample data through a test, performing noise reduction and normalization processing on an original fault sample, and calculating characteristic parameters of characteristic gas in oil;
s2: establishing a fault type associated data model: obtaining a correlation data model of gas generated by the on-load tap-changer, the severity of a fault and the type of the fault based on a particle swarm optimization least square support vector machine method;
s3: fault classification and diagnosis: diagnosing an oil sample to be detected by using a fault type correlation data model to obtain a fault characteristic gas diagnosis result of the on-load tap-changer;
s4: the database is self-updated, and the diagnosis result is output: transmitting the failure types which cannot be diagnosed by the LS-SVM model to a background, constructing a new training set by the background according to the optimal characteristic quantity, and combining the optimal parameter combination to bring the training set into a support vector machine to establish a new failure diagnosis model; diagnosing the test set sample according to the established new fault diagnosis model, and self-updating the database to establish a new characteristic sample; and outputting a diagnosis result to obtain the fault type of the on-load tap-changer.
The step S1 specifically includes:
s11: detecting the magnitude of environmental noise and intrinsic noise of equipment; measuring the initial discharge voltage of the model and detecting the intensity of discharge; pre-pressurizing before testing to ensure that the testing voltage is in a safe range;
s12: building a transformer on-load tap-changer fault simulation test platform, wherein discharge faults comprise on-load tap-changer contact discharge, point discharge, suspension discharge and creeping discharge; building on-load tap-changer contact discharge, point discharge, suspension discharge and creeping discharge models; the method of changing the electrode gap in oil is adopted to simulate the electric box fault of the transformer on-load tap-changer under various conditions;
s13: and obtaining sample data through tests, carrying out noise reduction and normalization processing on the original fault sample, calculating characteristic parameters of characteristic gas in oil, and constructing a database.
The step S2 specifically includes:
s21: training an LS-SVM classifier based on sample data of an on-load tap-changer, performing parameter optimization calculation by adopting a Particle Swarm Optimization (PSO), and selecting an optimal LS-SVM classifier parameter combination;
s22: an LS-SVM model is built, an on-load tap-changer fault diagnosis model is built, and a classifier is built for each on-load tap-changer fault type.
The step S3 specifically includes:
and inputting the characteristic parameters of the fault to obtain a fault characteristic gas diagnosis result of the on-load tap-changer, outputting and judging the type of the fault, and transmitting the diagnosis result to a background.
The step S4 specifically includes:
s41: if the background judges that the fault is normal according to the diagnosis result, the diagnosis result is output to obtain the fault type of the on-load tap-changer;
s42: if the background judges that the fault is abnormal according to the diagnosis result, a new fault diagnosis model is established, the test set sample is diagnosed, and the database is updated automatically to establish a new characteristic sample; and outputting a diagnosis result to obtain the fault type of the on-load tap-changer.
Compared with the prior art, the invention has the following beneficial effects:
compared with the existing fault diagnosis of the on-load tap-changer of the power transformer, the input characteristics selected according to the traditional method are used as the analysis characteristic quantity of the dissolved gas in the oil, so that the problem of local optimum can be solved, the fault classification problem of the transformer can not be comprehensively reflected, and fault diagnosis errors are likely to be caused in practical application. Therefore, in order to improve the accuracy of fault diagnosis, in the invention, firstly, an input attribute set needs to be determined, and the characteristics of the input attribute set need to be optimized, so that a reasonable model is constructed. In the invention, different characteristics are selected as original attribute sets during model construction, and fault characteristic gas (including H) of the on-load tap-changer of the power transformer is established based on a least square support vector machine (LS-SVM)2、CH4、C2H2、C2H4、C2H6、CO2And CO, 7 characteristic gases) diagnosis model, and finally forming a discrimination method for fault diagnosis of the on-load tap-changer based on the gas dissolved in the oil. The invention has the advantages of short detection time, high sensitivity, small detection error and the like. Therefore, the failure rate of the equipment is greatly reduced, the on-load tap-changer can accurately and timely act, the large-amplitude fluctuation of the voltage is reduced and avoided, and the financial loss is also reduced.
Drawings
In order to make the object, technical scheme and beneficial effect of the invention more clear, the invention provides the following drawings for explanation:
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of a built fault testing platform;
FIG. 3 is a schematic diagram of the separation process of an oil sample through a chromatographic column;
fig. 4 is a program flow diagram of a fault diagnosis algorithm.
The meaning of the respective reference numerals is as follows:
1: alternating current power supply, 2: step-up transformer, 3: protection resistance, 4: coupling capacitor, 5: high-voltage bushing, 6: simulating a tap switch tank body, 7: pulse current sensor, 8: artificially simulating an insulation defect discharge device, 9: oscilloscope, 10: an oil taking port.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to fig. 1 to 4 of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention, are within the scope of the invention.
Examples
The diagnosis is carried out by collecting characteristic parameters of different discharged faults of the on-load tap-changer of the transformer, fig. 1 is a flow schematic diagram of the method of the invention, and as shown in the figure, the method comprises the following specific steps:
step 1: building a fault simulation test platform of the on-load tap-changer of the transformer, obtaining sample data through tests, performing noise reduction and normalization processing on an original fault sample, and calculating characteristic gas (H) in oil2、CH4、C2H2、C2H4、C2H6、CO2CO);
detecting the magnitude of environmental noise and intrinsic noise of equipment; measuring the initial discharge voltage of the model and detecting the intensity of discharge; pre-pressurizing before testing to ensure that the testing voltage is in a safe range;
fig. 2 is a built fault simulation test platform for a transformer on-load tap changer, which comprises a step-up transformer 2, a protection resistor 3, a coupling capacitor 4, a voltage divider, a high-voltage bushing 5, a simulation tap changer tank 6, a pulse current sensor 7, an artificial simulation insulation defect discharge device 8 and an oscilloscope 9; the test platform is powered by an alternating current power supply 1, a manual simulated insulation defect discharging device 8 is arranged inside a simulated tap switch tank body 6 and can generate characteristic gas after discharging, and an oil taking port is arranged on one side of the simulated tap switch tank body 6; the voltage divider is connected to the coupling capacitor 4. A fault simulation test platform of the transformer on-load tap-changer is built, and the electric box fault of the transformer on-load tap-changer under various conditions is simulated.
The discharge fault comprises on-load tap-changer contact discharge, point discharge, suspension discharge and creeping discharge; high-voltage equipment such as a step-up transformer, a voltage divider, a high-voltage bushing, a sensor and the like is adopted to build an on-load tap-changer contact discharging, point discharging, suspension discharging and creeping discharging model; the method of changing the type and the gap of electrodes in oil is adopted to simulate the faults of the on-load tap-changer of the transformer under various conditions; fig. 3 is a schematic diagram of the separation process of an oil sample through a chromatographic column: the detected gas concentration is collected to obtain the main gas and the secondary gas dissolved in the oil, and the main gas and the secondary gas are combined according to the relative concentration of the dissolved gas in the oil, so that the fault type of the on-load tap-changer of the transformer can be obtained, and the fault diagnosis is more reliable.
The gas to be detected is mixed with the carrier gas thoroughly and then passed through the stationary phase, so that the gas is redistributed. The physicochemical properties of different gases are different, so that the distribution coefficients K of the gases are also different, and when the gases reach dynamic equilibrium, the distribution coefficients are as follows:
the different gases flow through the solid phase at different rates, and the gases to be detected flow out of the chromatographic column in different orders, so that the gases are separated, and the gas types are detected. And installing an identifier behind the chromatographic column, converting the concentrations of various gases into electric signals by the identifier, and obtaining the concentration of the gases according to the peak value of the electric signals on the identifier.
Obtaining sample data through tests, carrying out noise reduction and normalization processing on an original fault sample, and calculating characteristic gas (H) in oil2、CH4、C2H2、C2H4、C2H6、CO2CO) and constructing a database.
Step 2: constructing a characteristic sample based on a particle swarm optimization least square support vector machine (LS-SVM) method, establishing a classifier for each on-load tap-changer fault type, and obtaining an on-load tap-changer gas and fault severity and fault type correlation data model;
least squares support vector machines (LS-SVM) are an improved and extended form of support vector machines.
The principle of Support Vector Machines (SVMs) is as follows: in sample space, the hyperplane can be described by the following equation:
wTx+b＝0 (2)
in formula (2): w ═ w (w)1：w2：......wd) The vector is a hyperplane normal vector, and the direction of the hyperplane is controlled; b is the displacement, the distance from the hyperplane to the origin is controlled, and the hyperplane is marked as (w, b), then the distance from any point x to (w, b) in the sample space can be represented as r:
the sample point closest to the hyperplane determines the validity of the classification, called support vector (support vector), and the sum of the distances from the support vectors of two different classifications to the hyperplane is γ:
as can be seen from the equation (4), in order to maximize the spacing, the||w-1The value of | | reaches the maximum, namely minimizing | | | w | | | luminance2As shown in formula (5)
In the formula: x is the number ofiFor a sample set, each sample xiThe corresponding category label is yi，yi∈{-1,+1}。
The LS-SVM uses equality constraint to replace inequality constraint of a conventional SVM, so that the problem of solving quadratic programming is avoided, and the calculation efficiency is improved. The calculation of the LS-SVM can be equivalent to solving the following optimization problem:
in the formula: e is an error vector; e.g. of the typekIs an error variable to allow a certain error rate; loss function
Is the sum of the error and the rule quantization; ω is the weight vector.
Based on Lagrange multiplier method
In the formula: alpha is alphakK is lagrange multiplier, 1, 2, …, k.
Based on the optimization conditions
In the formula: c is threshold value, alpha ═ alpha1，...，αN],1v＝[1，...，1]，Y＝[y1，...，yN](ii) a Matrix Ω ═ { Ω }ij＝yiyjK(xi，xj)|i，j＝1，...，N}；
As the kernel function, the invention adopts the RBF kernel function, as shown in formula (9):
wherein; sigma2The bandwidth is squared.
Fig. 4 is a program flow diagram of a fault diagnosis algorithm. And transmitting the test sample to a background, calculating data characteristic parameters and optimizing characteristic quantity by the background to construct a new training set, and combining the optimal parameter group (a kernel parameter sigma and a penalty parameter C) to be brought into a support vector machine to establish a new fault diagnosis model. And optimizing by a Particle Swarm Optimization (PSO), starting from a random solution, comparing the adaptive value of each fault with the best position which the fault has undergone, if the adaptive value is better, taking the fault as the current best position, and searching for the optimal solution by iterative operation. And diagnosing the test set sample according to the established new fault diagnosis model, and self-updating the database to establish a new characteristic sample. And outputting a diagnosis result to obtain the fault type of the on-load tap-changer.
And (3) performing parameter optimization on a kernel parameter sigma and a penalty parameter C, wherein the variation of the kernel parameter sigma influences the complexity of the sample data in the high-dimensional feature space distribution, thereby influencing the generalization performance of the optimal classification hyperplane obtained by the SVM in the feature space. The penalty parameter C serves to balance the complexity of the learning machine with the empirical risk in determining the minimization objective function.
And step 3: diagnosing an oil sample to be detected by using an LS-SVM fault association data model, outputting a fault diagnosis result if the support vector machine model can judge the fault of the on-load tap-changer of the transformer, and ending the program; and if the support vector machine model can not be judged, transmitting the characteristic parameters to the background.
And 4, step 4: the background has a large amount of expert knowledge and experience in the field of on-load tap-changer fault diagnosis and identification, and the problems in the field can be processed by using the professional knowledge. The background evaluates the characteristic parameters of which the diagnosis result is abnormal in the step 3, judges whether the characteristic parameters are abnormal according to the diagnosis result, if the characteristic parameters are abnormal, completes self-updating of the database, and reestablishes an on-load tap-changer fault diagnosis model; and if the fault type is normal, outputting a diagnosis result to obtain the fault type of the on-load tap-changer.
If the background judges the abnormality according to the diagnosis result, the specific steps are as follows: a background builds a new training set according to the optimized characteristic quantity, and combines the optimal parameter combination to bring the training set into a support vector machine to build a new fault diagnosis model; diagnosing the test set sample according to the established new fault diagnosis model, and self-updating the database to establish a new characteristic sample; and outputting a diagnosis result to obtain the fault type of the on-load tap-changer.
Finally, it is noted that the above-mentioned preferred embodiments illustrate rather than limit the invention, and that, although the invention has been described in detail with reference to the above-mentioned preferred embodiments, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the scope of the invention as defined by the appended claims.
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111308298.9A CN114019365B (en) | 2021-11-05 | 2021-11-05 | On-load tap-changer fault diagnosis method based on oil gas detection technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111308298.9A CN114019365B (en) | 2021-11-05 | 2021-11-05 | On-load tap-changer fault diagnosis method based on oil gas detection technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114019365A true CN114019365A (en) | 2022-02-08 |
| CN114019365B CN114019365B (en) | 2024-07-30 |
Family
ID=80062121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111308298.9A Active CN114019365B (en) | 2021-11-05 | 2021-11-05 | On-load tap-changer fault diagnosis method based on oil gas detection technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114019365B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116930746A (en) * | 2023-09-19 | 2023-10-24 | 中国电力科学研究院有限公司 | On-load tap-changer electrical switching waveform characteristic parameter extraction analysis method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102680890A (en) * | 2012-06-01 | 2012-09-19 | 南京师范大学 | Failure diagnosis method for on-load tap changer of transformer |
| WO2017128455A1 (en) * | 2016-01-25 | 2017-08-03 | 合肥工业大学 | Analogue circuit fault diagnosis method based on generalized multiple kernel learning-support vector machine |
| CN107065568A (en) * | 2017-05-26 | 2017-08-18 | 广州供电局有限公司 | A kind of Diagnosis Method of Transformer Faults based on particle swarm support vector machine |
| CN107862114A (en) * | 2017-10-25 | 2018-03-30 | 广西电网有限责任公司电力科学研究院 | Small echo PSO SVM Diagnosis Method of Transformer Faults based on three ratio feature amounts |
-
2021
- 2021-11-05 CN CN202111308298.9A patent/CN114019365B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102680890A (en) * | 2012-06-01 | 2012-09-19 | 南京师范大学 | Failure diagnosis method for on-load tap changer of transformer |
| WO2017128455A1 (en) * | 2016-01-25 | 2017-08-03 | 合肥工业大学 | Analogue circuit fault diagnosis method based on generalized multiple kernel learning-support vector machine |
| CN107065568A (en) * | 2017-05-26 | 2017-08-18 | 广州供电局有限公司 | A kind of Diagnosis Method of Transformer Faults based on particle swarm support vector machine |
| CN107862114A (en) * | 2017-10-25 | 2018-03-30 | 广西电网有限责任公司电力科学研究院 | Small echo PSO SVM Diagnosis Method of Transformer Faults based on three ratio feature amounts |
Non-Patent Citations (1)
| Title |
|---|
| 高国磊;李英娜;段效琛;李川;: "基于ACO优化LS-SVM的变压器故障诊断", 电子科技, no. 06, 15 June 2018 (2018-06-15) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116930746A (en) * | 2023-09-19 | 2023-10-24 | 中国电力科学研究院有限公司 | On-load tap-changer electrical switching waveform characteristic parameter extraction analysis method and system |
| CN116930746B (en) * | 2023-09-19 | 2023-12-01 | 中国电力科学研究院有限公司 | On-load tap-changer electrical switching waveform characteristic parameter extraction analysis method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114019365B (en) | 2024-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105512962B (en) | A kind of gas insulated combined electrical equipment state of insulation comprehensive estimation method | |
| Flores et al. | Expert system for the assessment of power transformer insulation condition based on type-2 fuzzy logic systems | |
| Li et al. | An integrated method of set pair analysis and association rule for fault diagnosis of power transformers | |
| CN104535865A (en) | Comprehensive diagnosing method for operation troubles of power transformer based on multiple parameters | |
| CN103389430B (en) | A kind of oil-filled transformer fault detection method based on Bayesian discrimination theory | |
| CN107132310B (en) | Transformer Equipment Health Status Discrimination Method Based on Gaussian Mixture Model | |
| Li et al. | Condition assessment of power transformers using a synthetic analysis method based on association rule and variable weight coefficients | |
| CN103926491A (en) | Transformer state evaluation method with influence of direct-current magnetic bias taken into account | |
| CN105911407B (en) | Associated transformer state fuzzy set can be opened up to appraisal procedure based on matter-element augmentation | |
| CN112183590A (en) | A Transformer Fault Diagnosis Method Based on OneclassSVM Algorithm | |
| CN110618340A (en) | Transformer state evaluation method | |
| CN104123468A (en) | Distribution transformer state assessment method based on kernel state quantity set | |
| CN110503305A (en) | A Transformer Performance Evaluation Method | |
| Wu et al. | Research on short-circuit fault-diagnosis strategy of lithium-ion battery in an energy-storage system based on voltage cosine similarity | |
| CN114019365A (en) | On-load tap-changer fault diagnosis method based on gas detection technology in oil | |
| CN117907839A (en) | Battery lithium deposition diagnosis method based on multidimensional feature clustering | |
| CN114814501B (en) | An online diagnosis method for capacitive breakdown fault of capacitive voltage transformer | |
| CN106644436B (en) | A kind of assessment method of breaker mechanic property | |
| CN112465010A (en) | DKPCA and KFDA-based transformer fault detection and classification method | |
| CN110110816A (en) | A kind of Power Transformer Faults deduction method | |
| CN108445385A (en) | A kind of load ratio bridging switch tap selector state evaluating method based on partial discharge monitoring and oil chromatogram analysis | |
| CN118427607A (en) | Transformer fault early warning method based on multivariate time sequence | |
| Xie et al. | Transformer fault diagnosis based on bayesian network and rough set reduction theory | |
| Zhang et al. | Research on variable weight synthesizing model for transformer condition assessment | |
| CN114462692A (en) | Power grid old and old equipment technical improvement strategy optimization and adjustment method |
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 |