CN105372528A - Power transformer internal fault condition maintenance method - Google Patents
Power transformer internal fault condition maintenance method Download PDFInfo
- Publication number
- CN105372528A CN105372528A CN201510821187.6A CN201510821187A CN105372528A CN 105372528 A CN105372528 A CN 105372528A CN 201510821187 A CN201510821187 A CN 201510821187A CN 105372528 A CN105372528 A CN 105372528A
- Authority
- CN
- China
- Prior art keywords
- transformer
- signal
- state
- power transformer
- symbol
- 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
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power transformer internal fault condition maintenance method. According to the method of the invention, an internal fault model of a transformer is simulated; a symbolic dynamics-based evaluation model of power transformer operation conditions is established; and the internal fault current of the transformer is adopted as the main research object, a novel power transformer condition maintenance model is researched. According to the model, monitored transformer internal current is adopted as input; obtained real-time data and historical data are compared with each other; transformer factory data and historical test data are both considered; the current operation state of the transformer is evaluated; and whether the transformer is in a fault early-stage state and the type and degree of a fault are judged. The transformer condition maintenance model can be applied to an actual condition maintenance process, so that cost can be saved, or the condition maintenance model can be applied to an integrated system, so that final results can be optimized.
Description
Technical field
The invention belongs to computer software technical field, the software application technology of particularly a kind of electric system nucleus equipment internal fault identification, specifically refers to a kind of state maintenance method of Power Transformer Internal Faults and New Transformer.
Background technology
Transformer send as the change of electric system and distributes the nucleus equipment of electric energy, and its safety and stability is most important.Therefore, carry out maintenance to transformer to be absolutely necessary.Traditional maintenance mode is prophylactic repair, as the usual way of Repair of Transformer, preventive trial and prophylactic repair bear the character of much blindness and mandatory, and cause series of problems such as " cross repair, owe to repair, blindly maintenance, the wasting of resources ", this also just highlights the necessity of repair based on condition of component.Repair based on condition of component carries out real-time assessment to the ruuning situation of transformer to draw state index, and according to a kind of maintenance mode that state index overhauls transformer; In prior art, state index refers to the operational factor detecting transformer by various method, such as: transformer temperature, oil dissolved gas ratio, degree of discharge etc.The foundation of Power Transformer Internal Faults and New Transformer model is by the research to inside transformer magnetic linkage relation, utilizes MATLA software to build the realistic model of power transformer, substantially realizes at present.
Summary of the invention
The object of the invention is to, the method for distinguishing sequence signal carries out studying judging whether signal fault exists and the degree of fault, in order to overcome the deficiencies in the prior art.
The present invention is achieved through the following technical solutions, by the Power Transformer Internal Faults and New Transformer model set up, to emulate internal current for main study subject, symbolic dynamics is used to contrast electric current and running current, set up signal difference mechanism, online transformer monitored and diagnose out transformer running status now, being specifically divided into health status, error condition, malfunction; Thus study a kind of novel Power Transformer Condition based on state maintenance model.
Comprise and set up Power Transformer Internal Faults and New Transformer model, then obtain the curtage data run under fault.This Transformer Model unconventional equivalent operation circuit model, but the fault model of transient state will be set up for the abnormal operating state of transformer, this model can emulate for malfunction in various degree, so that obtain the efficiency of higher realistic model.
Symbolic dynamics method is applied to signal transacting; be applied in the description to signal by the thought of the state of the sequence description nonlinear system after symbolism; symbolic dynamics is as a kind of description to power system coarse; phase space division is carried out to continuous time signal, the limited symbol of phase space is represented.
Described signal phase space divides, and the phase space of research signal waveform divides and makes the serializing signal obtained possess the maximum quantity of information of original data signal with reference to maximum entropy partitioning.
The described principle based on symbolic dynamics, utilize the advantage of symbolic dynamics in signal transacting, further sequence is analyzed, and set up corresponding Markov state transition matrix by symbol sebolic addressing, then matrix Euclidean distance characterization signal difference is used, thus the existence of fast and effeciently failure judgement.
The state maintenance method of this Power Transformer Internal Faults and New Transformer provided by the invention, the existence of power transformer interior fault can be identified fast and effectively, so that maintainer can find out fault weak element more rapidly and accurately, decrease the extra cost of the maintenance such as equipment installation and maintenance of introducing related sensor simultaneously.
Accompanying drawing explanation
Fig. 1 is principle flow chart.
Fig. 2 is maximum entropy partitioning schematic diagram.
Fig. 3 is for improving maximum entropy algorithm process flow diagram.
Fig. 4 is Markov process schematic diagram.
Fig. 5 is Markov matrix schematic diagram.
Embodiment
Below in conjunction with accompanying drawing 1 to 5, embodiments of the present invention is further illustrated, and the foundation of Power Transformer Internal Faults and New Transformer model is by the research to inside transformer magnetic linkage relation, utilizes MATLA software to build the realistic model of power transformer.Repair based on condition of component in realistic model carries out real-time assessment to the ruuning situation of transformer to draw state index, the matrix distance size obtained after referring to current signal process; Carry out a series of l-G simulation test to the Power Transformer Faults model set up, obtain the fault test index relevant to transformer and data, this index and data refer to fault degree size and current data; Play an assessment models by these Index Establishments again, assessment models refers to the present invention's method used and value range, and then judges the operation conditions of transformer online.
The present inventor's created symbol dynamic method, the target component of monitoring can be only internal operating current or the voltage of transformer, does not need extra to arrange sensor, also has abundant historical data availability test and use simultaneously.Symbolization dynamic method effectively can judge the existence of power transformer interior fault fast, therefore can explore a kind of than existing methods Condition Maintenance Method of Transformer that more accurate efficiency is higher mechanism.
The Power Transformer Internal Faults and New Transformer model that the present invention includes setting up carries out repair based on condition of component, repair based on condition of component in described fault model carries out real-time assessment to the ruuning situation of transformer to draw state index, described state index refer to current signal process after the matrix distance size obtained;
Carry out l-G simulation test to the Power Transformer Internal Faults and New Transformer model set up, obtain the fault test index relevant to transformer and data, described index and data refer to fault degree size and current data;
Assessment models is set up again by index and data, described assessment models refers to model internal current as main study subject, signal is formed by the maximum entropy algorithm improved, and symbolic dynamics is applied to signal transacting, corresponding Markov state transition matrix is set up by symbol sebolic addressing, then use matrix Euclidean distance characterization signal difference, compared by signal difference, and carry out in conjunction with the assessment models of power transformer operation conditions the value range that state drafts; And then judge online the operation conditions of transformer, thus the existence of fast and effeciently failure judgement.
The present invention includes following steps:
Step 1, according to Power Transformer Internal Faults and New Transformer model, simulates the internal fault current of transformer in transient state situation, gets the current data signal under fault in various degree;
Step 2, with model internal current for main study subject, forms signal by the maximum entropy algorithm improved,
The maximum entropy algorithm of described improvement comprises maximum entropy partitioning and first order difference partitioning;
Step 3, is applied to signal transacting by symbolic dynamics, and the sequence obtained by the maximum entropy algorithm improved realizes electric current and contrasts with the electric current normally worked;
Step 4, corresponding Markov state transition matrix is set up by symbol sebolic addressing, then matrix Euclidean distance characterization signal difference is used, compared by signal difference, and carry out in conjunction with the assessment models of power transformer operation conditions the value range that state drafts, and then judge online the operation conditions of transformer, thus the existence of fast and effeciently failure judgement.
The maximum entropy algorithm of described step 2 is, if by alphabetic(al) size be | A|, and signal length is N, then the algorithmic procedure based on the partitioning of maximum entropy is as follows,
I. initiation parameter, if K=2, and choose a threshold parameter ε, 0< ε≤1, threshold parameter determines the termination condition of algorithm;
II. be the signal of N by ascending order spread length;
III. by each continuous length in signal
individual signal forms an alphabetical element of independence of this division.Wherein
representative is not more than the maximum integer of X;
IV. according to the division obtained in III step and alphabet preliminary symbol original signal, according to the interval that the value of signal falls in the third step, or equal the minimum value in this interval, and by the interval corresponding letter representative of the value of signal;
V. the Probability p that compute sign occurs
i, i=1,2 ... K;
VI. calculate now corresponding H (k) and h (k)=H (k)-H (k-1);
VII. if the h (k) calculated is less than the thresholding ε of setting, then terminate algorithm, otherwise increases progressively 1 for K, and jumps to III step.
From seeing describing of maximum entropy division principle above, divided by maximum entropy, the region of the change fierceness of signal employs more symbolic formulation, but does not still reflect the relation changed before and after signal.Therefore, herein on this basis, in conjunction with first difference method, utilize method of difference can the advantage of variation relation before and after reaction signal, further improve this partitioning.
The maximum entropy algorithm of the improvement of described step 2, the division rule namely comprising maximum entropy partitioning and first order difference partitioning is as follows:
By the combination of above-mentioned two groups of formula, utilize maximum entropy to divide and division is made to roughly interval, divide according to signal context further at the interval inner first difference method that uses again, so just can obtain the signal code method based on maximum entropy and first order difference that symbol is 0 to 7.
Describedly set up corresponding Markov state transition matrix by symbol sebolic addressing and comprise:
If symbol sebolic addressing { S
t; symbols alphabet size is k; moving window is long is D; from first the symbol letter of symbol sebolic addressing one by one; with every window length for D is to right translation; often slip over a symbol letter, retain rear (D-1) individual symbol letter of preceding state according to this and add a new symbol letter and produce a new state;
I. establish symbol sebolic addressing, the next symbol occurred to D moment symbol is relevant before, then claims this process to be D rank Markov process;
That is: P (S
i| S
i-1...S
i-D...)=P (S
i| S
i-1...S
i-D),
Arranging alphabet is A, and its size is | A|, then and the number of states that the Markov process that this sequence obtains likely occurs should be: | A|
d;
II. definition p
iand p
jbe respectively the equivalent state in system, i-th state in state set Q is transferred to a jth shape probability of state and is:
π
ij＝P(S∈A|q
j∈Q,(q
i,S)→q
j)，
Matrix π is the transition probability between all states.
Obtaining between all states transition probability by this sequence can with a matrix description, i.e. Markov matrix.If the alphabet A of symbol only comprises two letters, { 0,1}, in Markov process, next state is only relevant with the symbol of two before, and the simplest Markov process can be expressed as shown in Figure 5
And Markov matrix should have:
∑
jp(i,j)＝1
Namely matrix meets all elements sum of any a line is 1.
Described signal difference compares,
Describedly to be compared by signal difference, and carry out in conjunction with the assessment models of power transformer operation conditions the value range that state drafts, and then judge that the operation conditions of transformer comprises online:
It is Nmin and Nmax that the assessment models of setting carries out the value range that state drafts,
Matrix Euclidean distance:
D<Nmin, then indication transformer is in health status;
Nmax>d>Nmin, then indication transformer is in error condition;
D>Nmax, then indication transformer is in malfunction.
Between matrix, Euclidean distance refers to: set matrix being regarded as n vector, and what obtain is Euclidean distance between n vector.Then
The assessment models of described power transformer operation conditions is carried out state and is drafted, and takes to judge based on symbolic dynamics the result that obtains, carries out the classification of different conditions in conjunction with actual transformer duty and historical data to result; Comprise the mode that the serializing divided based on phase space obtains different symbolism sequences.Described signal phase space divides, and the phase space of research signal waveform divides and makes the serializing signal obtained possess the maximum quantity of information of original data signal with reference to maximum entropy partitioning.
In the experiment of emulation, find the increase of the fault of transformer along with decay, exponentially increases by the difference of fault-signal and original signal, and then tend towards stability, this illustrates that the change procedure of fault has the narrower speed in interval mutation process faster, namely drafting of state by finding this interval, will can be drafted before, during and after interval as different states is to take different maintenance policies respectively.Being expressed as of specific embodiment:
1) if Markov state transition matrix Euclidean distance is less than 1.5, then indication transformer is in health status, without the need to overhauling transformer.
2) if Markov state transition matrix Euclidean distance is greater than 1.5 and is less than 2.5, then indication transformer is in error condition, need overhaul according to plan.
3) if Markov state transition matrix Euclidean distance is greater than 2.5, then indication transformer is in malfunction, need overhaul at once.
The above embodiment only have expressed one embodiment of the present invention, and it describes comparatively concrete and detailed, but therefore can not be interpreted as the restriction to the scope of the claims of the present invention.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (6)
1. a state maintenance method for Power Transformer Internal Faults and New Transformer,
The Power Transformer Internal Faults and New Transformer model comprised setting up carries out repair based on condition of component, it is characterized in that being,
Repair based on condition of component in described fault model carries out real-time assessment to the ruuning situation of transformer to draw state index, described state index refer to current signal process after the matrix distance size obtained;
Carry out l-G simulation test to the Power Transformer Internal Faults and New Transformer model set up, obtain the fault test index relevant to transformer and data, described index and data refer to fault degree size and current data;
Assessment models is set up again by index and data, described assessment models refers to model internal current as main study subject, signal is formed by the maximum entropy algorithm improved, and symbolic dynamics is applied to signal transacting, corresponding Markov state transition matrix is set up by symbol sebolic addressing, then use matrix Euclidean distance characterization signal difference, compared by signal difference, and carry out in conjunction with the assessment models of power transformer operation conditions the value range that state drafts; And then judge online the operation conditions of transformer, thus the existence of fast and effeciently failure judgement.
2. the state maintenance method of a kind of Power Transformer Internal Faults and New Transformer according to claim 1, is characterized in that comprising the following steps:
Step 1, according to Power Transformer Internal Faults and New Transformer model, simulates the internal fault current of transformer in transient state situation, gets the current data signal under fault in various degree;
Step 2, with model internal current for main study subject, forms signal by the maximum entropy algorithm improved,
The maximum entropy algorithm of described improvement comprises maximum entropy partitioning and first order difference partitioning;
Step 3, is applied to signal transacting by symbolic dynamics, and the sequence obtained by the maximum entropy algorithm improved realizes electric current and contrasts with the electric current normally worked;
Step 4, corresponding Markov state transition matrix is set up by symbol sebolic addressing, then matrix Euclidean distance characterization signal difference is used, compared by signal difference, and carry out in conjunction with the assessment models of power transformer operation conditions the value range that state drafts, and then judge online the operation conditions of transformer, thus the existence of fast and effeciently failure judgement.
3. the state maintenance method of a kind of Power Transformer Internal Faults and New Transformer according to claim 2, is characterized in that,
The maximum entropy algorithm of described step 2 is, if by alphabetic(al) size be | A|, and signal length is N, then the algorithmic procedure based on the partitioning of maximum entropy is as follows,
I. initiation parameter, if K=2, and choose a threshold parameter ε, 0< ε≤1, threshold parameter determines the termination condition of algorithm;
II. be the signal of N by ascending order spread length;
III. by each continuous length in signal
individual signal forms an alphabetical element of independence of this division, wherein
representative is not more than the maximum integer of X;
IV. according to the division obtained in III step and alphabet preliminary symbol original signal, according to the interval that the value of signal falls in the third step, or equal the minimum value in this interval, and by the interval corresponding letter representative of the value of signal;
V. the Probability p that compute sign occurs
i, i=1,2 ... K;
VI. calculate now corresponding H (k) and h (k)=H (k)-H (k-1);
VII. if the h (k) calculated is less than the thresholding ε of setting, then terminate algorithm, otherwise increases progressively 1 for K, and jumps to III step;
The maximum entropy algorithm of the improvement of described step 2, the division rule namely comprising maximum entropy partitioning and first order difference partitioning is as follows:
By the combination of above-mentioned two groups of formula, utilize maximum entropy to divide and division is made to roughly interval, divide according to signal context further at the interval inner first difference method that uses again, so just can obtain the signal code method based on maximum entropy and first order difference that symbol is 0 to 7.
4. the state maintenance method of a kind of Power Transformer Internal Faults and New Transformer according to claim 2, is characterized in that, describedly sets up corresponding Markov state transition matrix by symbol sebolic addressing and comprises:
If symbol sebolic addressing { S
t; symbols alphabet size is k; moving window is long is D; from first the symbol letter of symbol sebolic addressing one by one; with every window length for D is to right translation; often slip over a symbol letter, retain rear (D-1) individual symbol letter of preceding state according to this and add a new symbol letter and produce a new state;
I. establish symbol sebolic addressing, the next symbol occurred to D moment symbol is relevant before, then claims this process to be D rank Markov process;
That is: P (S
i| S
i-1...S
i-D...)=P (S
i| S
i-1...S
i-D),
Arranging alphabet is A, and its size is | A|, then and the number of states that the Markov process that this sequence obtains likely occurs should be: | A|
d;
II. definition p
iand p
jbe respectively the equivalent state in system, i-th state in state set Q is transferred to a jth shape probability of state and is:
π
ij＝P(S∈A|q
j∈Q,(q
i,S)→q
j)，
Matrix π is the transition probability between all states.
5. the state maintenance method of a kind of Power Transformer Internal Faults and New Transformer according to claim 2, is characterized in that,
Describedly to be compared by signal difference, and carry out in conjunction with the assessment models of power transformer operation conditions the value range that state drafts, and then judge that the operation conditions of transformer comprises online:
It is Nmin and Nmax that the assessment models of setting carries out the value range that state drafts,
According to matrix Euclidean distance:
Then d<Nmin, then indication transformer is in health status;
Then Nmax>d>Nmin, then indication transformer is in error condition;
Then d>Nmax, then indication transformer is in malfunction.
6. the state maintenance method of a kind of Power Transformer Internal Faults and New Transformer according to claim 1, it is characterized in that, the assessment models of described power transformer operation conditions is carried out state and is drafted, take to judge based on symbolic dynamics the result that obtains, in conjunction with actual transformer duty and historical data, the classification of different conditions is carried out to result; Comprise the mode that the serializing divided based on phase space obtains different symbolism sequences.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510821187.6A CN105372528B (en) | 2015-11-24 | 2015-11-24 | A kind of state maintenance method of Power Transformer Internal Faults and New Transformer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510821187.6A CN105372528B (en) | 2015-11-24 | 2015-11-24 | A kind of state maintenance method of Power Transformer Internal Faults and New Transformer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105372528A true CN105372528A (en) | 2016-03-02 |
| CN105372528B CN105372528B (en) | 2018-10-09 |
Family
ID=55374890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510821187.6A Expired - Fee Related CN105372528B (en) | 2015-11-24 | 2015-11-24 | A kind of state maintenance method of Power Transformer Internal Faults and New Transformer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105372528B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106569052A (en) * | 2016-10-11 | 2017-04-19 | 国网湖北省电力公司 | Real-time health status-considered method for evaluating reliability of power transformer |
| CN107063331A (en) * | 2016-11-09 | 2017-08-18 | 贵州电网有限责任公司凯里供电局 | A kind of power transformer interior fault detecting system based on microrobot |
| CN107292512A (en) * | 2017-06-20 | 2017-10-24 | 中国电力科学研究院 | A kind of power equipment space-time multidimensional safety evaluation method based on symbolic dynamics and HMM |
| CN107991097A (en) * | 2017-11-16 | 2018-05-04 | 西北工业大学 | A kind of Method for Bearing Fault Diagnosis based on multiple dimensioned symbolic dynamics entropy |
| CN108037378A (en) * | 2017-10-26 | 2018-05-15 | 上海交通大学 | Running state of transformer Forecasting Methodology and system based on long memory network in short-term |
| CN111308336A (en) * | 2020-03-24 | 2020-06-19 | 广西电网有限责任公司电力科学研究院 | High-voltage circuit breaker fast overhaul method and device based on big data |
| CN111738286A (en) * | 2020-03-17 | 2020-10-02 | 北京京东乾石科技有限公司 | Fault determination and model training method, device, equipment and storage medium thereof |
| CN112327084A (en) * | 2020-11-03 | 2021-02-05 | 华北电力大学 | Method and system for detecting vibration and sound of running state of transformer by utilizing equidistant transformation |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100029338A (en) * | 2008-09-08 | 2010-03-17 | 하주영 | System for diagnostication of transformer using ultrasonic wave |
| CN102779230A (en) * | 2012-06-14 | 2012-11-14 | 华南理工大学 | State analysis and maintenance decision judging method of power transformer system |
| CN103091603A (en) * | 2013-01-14 | 2013-05-08 | 华北电力大学 | Breakdown intelligent classification and positioning method of electric transmission line |
| CN103245911A (en) * | 2013-05-03 | 2013-08-14 | 云南电力试验研究院（集团）有限公司电力研究院 | Breaker fault diagnosis method based on Bayesian network |
| WO2014072444A1 (en) * | 2012-11-09 | 2014-05-15 | Bombardier Transportation Gmbh | Method and device for monitoring a transformer state |
| CN104007343A (en) * | 2014-05-23 | 2014-08-27 | 清华大学 | Dynamic comprehensive transformer fault diagnosis method based on Bayesian network |
| CN104036131A (en) * | 2014-06-06 | 2014-09-10 | 清华大学 | Transformer aging fault rate estimation method |
| CN104077231A (en) * | 2014-07-16 | 2014-10-01 | 国家电网公司 | Transformer maintenance optimization method based on symbol dynamics and LS-SVM |
| CN104101795A (en) * | 2014-02-19 | 2014-10-15 | 江苏倍尔科技发展有限公司 | Transformer fault control method |
-
2015
- 2015-11-24 CN CN201510821187.6A patent/CN105372528B/en not_active Expired - Fee Related
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100029338A (en) * | 2008-09-08 | 2010-03-17 | 하주영 | System for diagnostication of transformer using ultrasonic wave |
| CN102779230A (en) * | 2012-06-14 | 2012-11-14 | 华南理工大学 | State analysis and maintenance decision judging method of power transformer system |
| WO2014072444A1 (en) * | 2012-11-09 | 2014-05-15 | Bombardier Transportation Gmbh | Method and device for monitoring a transformer state |
| CN103091603A (en) * | 2013-01-14 | 2013-05-08 | 华北电力大学 | Breakdown intelligent classification and positioning method of electric transmission line |
| CN103245911A (en) * | 2013-05-03 | 2013-08-14 | 云南电力试验研究院（集团）有限公司电力研究院 | Breaker fault diagnosis method based on Bayesian network |
| CN104101795A (en) * | 2014-02-19 | 2014-10-15 | 江苏倍尔科技发展有限公司 | Transformer fault control method |
| CN104007343A (en) * | 2014-05-23 | 2014-08-27 | 清华大学 | Dynamic comprehensive transformer fault diagnosis method based on Bayesian network |
| CN104036131A (en) * | 2014-06-06 | 2014-09-10 | 清华大学 | Transformer aging fault rate estimation method |
| CN104077231A (en) * | 2014-07-16 | 2014-10-01 | 国家电网公司 | Transformer maintenance optimization method based on symbol dynamics and LS-SVM |
Non-Patent Citations (3)
| Title |
|---|
| 王松岭 等: "基于符号动力学信息熵与改进神经网络的风机故障诊断研究", 《华北电力大学学报》 * |
| 蔡红梅 等: "基于灰云模型的电力变压器故障诊断", 《电力***保护与控制》 * |
| 谭喜堂 等: "单相双绕组变压器匝间短路故障诊断", 《电力***及其自动化》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106569052A (en) * | 2016-10-11 | 2017-04-19 | 国网湖北省电力公司 | Real-time health status-considered method for evaluating reliability of power transformer |
| CN107063331A (en) * | 2016-11-09 | 2017-08-18 | 贵州电网有限责任公司凯里供电局 | A kind of power transformer interior fault detecting system based on microrobot |
| CN107292512A (en) * | 2017-06-20 | 2017-10-24 | 中国电力科学研究院 | A kind of power equipment space-time multidimensional safety evaluation method based on symbolic dynamics and HMM |
| CN107292512B (en) * | 2017-06-20 | 2020-09-15 | 中国电力科学研究院 | Power equipment space-time multi-dimensional safety assessment method based on symbolic dynamics and hidden Markov model |
| CN108037378A (en) * | 2017-10-26 | 2018-05-15 | 上海交通大学 | Running state of transformer Forecasting Methodology and system based on long memory network in short-term |
| CN108037378B (en) * | 2017-10-26 | 2020-08-07 | 上海交通大学 | Transformer operation state prediction method and system based on long-time and short-time memory network |
| CN107991097A (en) * | 2017-11-16 | 2018-05-04 | 西北工业大学 | A kind of Method for Bearing Fault Diagnosis based on multiple dimensioned symbolic dynamics entropy |
| CN111738286A (en) * | 2020-03-17 | 2020-10-02 | 北京京东乾石科技有限公司 | Fault determination and model training method, device, equipment and storage medium thereof |
| CN111308336A (en) * | 2020-03-24 | 2020-06-19 | 广西电网有限责任公司电力科学研究院 | High-voltage circuit breaker fast overhaul method and device based on big data |
| CN112327084A (en) * | 2020-11-03 | 2021-02-05 | 华北电力大学 | Method and system for detecting vibration and sound of running state of transformer by utilizing equidistant transformation |
| CN112327084B (en) * | 2020-11-03 | 2022-01-21 | 华北电力大学 | Method and system for detecting vibration and sound of running state of transformer by utilizing equidistant transformation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105372528B (en) | 2018-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105372528A (en) | Power transformer internal fault condition maintenance method | |
| CN106682303B (en) | A kind of three-level inverter method for diagnosing faults based on empirical mode decomposition and decision tree RVM | |
| CN105466693B (en) | The pre- diagnostic method of Fault of Diesel Fuel System based on gray model | |
| CN112910695B (en) | Network fault prediction method based on global attention time domain convolution network | |
| US20200200813A1 (en) | Online diagnosis method for deformation position on trasnformation winding | |
| CN102944416B (en) | Multi-sensor signal fusion technology-based fault diagnosis method for wind turbine blades | |
| CN102779230B (en) | State analysis and maintenance decision judging method of power transformer system | |
| CN107632258A (en) | A kind of fan converter method for diagnosing faults based on wavelet transformation and DBN | |
| CN104504607A (en) | Method for diagnosing photovoltaic power station faults on the basis of fuzzy clustering algorithm | |
| CN105004498A (en) | Vibration fault diagnosis method of hydroelectric generating set | |
| CN105868770A (en) | High-voltage circuit breaker fault diagnosis method based on unsupervised learning model | |
| CN104914775B (en) | Multi-modal procedure failure testing method and system based on the description of vine copula correlations | |
| CN102778355A (en) | Rolling bearing state identification method based on empirical mode decomposition (EMD) and principal component analysis (PCA) | |
| CN105114348A (en) | Device and method for induced draft fan fault early warning based on power station operation data | |
| CN107202027A (en) | A kind of large fan operation trend analysis and failure prediction method | |
| CN106526479A (en) | Grid-harmonic-characteristic-based fault diagnosis method for electric system of electric shovel | |
| CN105954616B (en) | Photovoltaic module method for diagnosing faults based on external characteristics electric parameter | |
| CN107102223A (en) | NPC photovoltaic DC-to-AC converter method for diagnosing faults based on improved hidden Markov model GHMM | |
| CN103389701A (en) | Plant-level process fault detection and diagnosis method based on distributed data model | |
| Yau et al. | Chaotic eye‐based fault forecasting method for wind power systems | |
| CN104635146B (en) | Analog circuit fault diagnosis method based on random sinusoidal signal test and HMM (Hidden Markov Model) | |
| Yan et al. | Deep learning technology for chiller faults diagnosis | |
| CN107037278A (en) | A kind of substandard intelligent substation method for diagnosing faults of IEC61850 | |
| CN103675357B (en) | The method of anemoscope fault pre-alarming and system | |
| CN113610119B (en) | Method for identifying power transmission line development faults based on convolutional neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181009 Termination date: 20211124 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |