CN111914426A - Transformer intelligent maintenance method based on correlation analysis - Google Patents
Transformer intelligent maintenance method based on correlation analysis Download PDFInfo
- Publication number
- CN111914426A CN111914426A CN202010786664.0A CN202010786664A CN111914426A CN 111914426 A CN111914426 A CN 111914426A CN 202010786664 A CN202010786664 A CN 202010786664A CN 111914426 A CN111914426 A CN 111914426A
- Authority
- CN
- China
- Prior art keywords
- temperature rise
- load rate
- causal
- transformer
- winding
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012423 maintenance Methods 0.000 title claims abstract description 15
- 238000010219 correlation analysis Methods 0.000 title claims abstract description 11
- 238000004804 winding Methods 0.000 claims abstract description 73
- 230000001364 causal effect Effects 0.000 claims abstract description 48
- 230000000694 effects Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000013021 overheating Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000012097 association analysis method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Housings And Mounting Of Transformers (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
The invention particularly relates to an intelligent transformer maintenance method based on correlation analysis. The method is characterized in that: 1) calculating the temperature rise of the winding; 2) discretizing original data; 3) connecting all the load rate intervals and the winding temperature rise intervals pairwise to form a causal pair; 4) calculating the support degree and the confidence degree of all causal pairs in the causal pair set; 5) determining a minimum support threshold value, and outputting a causal pair set which is not less than the minimum support threshold value; 6) determining a minimum confidence threshold value, and outputting all causal pairs not smaller than the minimum confidence threshold value; 7) calculating the normal temperature rise range of the winding corresponding to each load rate interval from the result obtained in the step 6); 8): if the temperature rise of the winding of the transformer is not within the normal temperature rise range in the corresponding load rate interval at a certain moment, the system sends out an alarm signal to remind maintenance personnel to overhaul in time. The invention can quickly and accurately judge the transformer fault through the load rate and the temperature signal.
Description
Technical Field
The invention belongs to the field of transformer maintenance methods, and particularly relates to an intelligent transformer maintenance method based on correlation analysis.
Background
The transformer is a pivotal device in the whole power system, plays an important role in power transmission, power distribution and other electric energy conversion, and the normal operation of the transformer is related to the stability and safety of a power grid system.
In the actual operation process, most faults of the transformer are accompanied by heat generation, so that the internal temperature of the transformer changes. Common causes of elevated transformer temperatures include poor tap changer contact, coil turn-to-turn short circuits, cooling system failures, and the like. The overheating fault of the transformer means that the temperature of the transformer body is overhigh due to various fault factors or external factors, so that the aging rate of the insulating part is accelerated, and the running power is reduced. When the transformer temperature exceeds the limit temperature in the specification table, the fuselage temperature is already relatively high, even to the extent of causing damage to the components. Therefore, the early stage of abnormal transformer temperature can be alarmed and overhauled in time, so that damage to other parts can be avoided, negative influence caused by transformer overheating faults is reduced, and the safety and reliability of transformer operation are improved.
Considering that the larger the load connected to the transformer is, the larger the temperature rise of the transformer is, the set transformer temperature alarm value should correspond to the load rate at the same time. However, the load and temperature rise of the transformer are not simply linear, and two methods are mainly used at present for determining the normal temperature rise range of the transformer at a certain load factor level.
Firstly, the method passes through the test, but the test mode has many limitations, and the method is generally only suitable for the temperature rise test of the small transformer before leaving the factory so as to establish a temperature rise table. When the transformer is put into practical use, it is not practical to pause the transformer and then test the transformer; the second method is to apply the thermal and fluid mechanics principle to analyze the heat transfer of the transformer and to build the thermal model of the transformer according to the technical parameters of the transformer. Different physical models need to be established for transformers with different structural types, and the universality is not strong. In addition, in order to verify the established physical model, the accuracy of the model needs to be checked in combination with the method of the test. For transformers that are already in use, neither of these methods is practical.
Disclosure of Invention
The invention aims to provide an intelligent transformer maintenance method based on correlation analysis, which does not need a traditional test method, utilizes a large amount of data accumulated in the historical operation process of a transformer, and determines the relation between the load rate of the transformer and the temperature rise of a winding through a correlation analysis technology, thereby judging the fault of the transformer only through a temperature signal and providing a universal intelligent maintenance method for the transformer which is already put into use.
The invention is realized by the following technical scheme:
namely, the transformer intelligent maintenance method based on correlation analysis is characterized by comprising the following steps:
the method comprises the following steps: calculating the winding temperature rise through the transformer winding temperature and the environment temperature, wherein the transformer winding temperature rise is the difference between the winding temperature and the environment temperature;
step two: because the load rate and the winding temperature rise of the transformer are continuous data, and the correlation analysis must be classified attribute data, the original data needs to be discretized, the load rate and the winding temperature rise need to be discretized respectively, and are included in the divided intervals, and the intervals are represented by symbols as follows:
[L1,L2,…,Ln]、[T1,T2,…,Tn]
wherein n is the number of divided intervals;
step three: connecting all the load rate intervals and the winding temperature rise intervals pairwise to form causal pairs, considering that the temperature change of the winding is caused by the change of the load rate, the default load rate is the cause, the winding temperature rise is the effect, and the set of the causal pairs can be expressed as follows:
{[L1,T1],[L1,T2],…,[L2,T1],[L2,T2],…,[Ln,Tn]}；
step four: calculating the support degree and the confidence degree of all causal pairs in the causal pair set,
the calculation formula of the support degree is as follows:
the confidence coefficient is calculated by the formula:
in the formula, LiRefers to the ith load factor interval, TjRefers to the j winding temperature rise interval, count (L)i∩Tj) The number of causal pairs belonging to an ith load rate interval and a jth winding temperature rise interval at the same time is indicated, and N is the number of all causal pairs in a causal pair set;
step five: setting a minimum support degree, which is expressed as SUP by symbolsminFinding out all SUP not less than the minimum support degreeminCause and effect pairs of, moving downwards from high valueState adjustment minimum support SUPminSo as not to be less than the minimum support SUPminThe causal pair set comprises all load rate intervals, the minimum support threshold at the moment is determined, and the causal pair set not smaller than the minimum support threshold is output;
step six: setting minimum confidence, symbolically expressed as CONFminFinding out all CONFs not less than the minimum confidence coefficient from the results obtained in the step fiveminDynamically adjust the minimum confidence CONF from high value downminSo as not to be less than the minimum confidence CONFminThe causal pair set comprises all load rate intervals, the minimum confidence coefficient threshold value at the moment is determined, and all causal pairs not smaller than the minimum confidence coefficient threshold value are output;
step seven: calculating the normal temperature rise range of the winding corresponding to each load rate interval from the result obtained in the step six;
step eight: if the temperature of the winding of the transformer is not within the normal temperature rise range in the corresponding load rate interval at a certain moment, the transformer is possibly in fault, and the system sends out an alarm signal to remind maintenance personnel to overhaul in time.
The invention aims at the transformer which is already put into use, and the relation between the temperature rise of the transformer winding and the load factor is researched by adopting an association analysis method on the basis of a large database.
Drawings
FIG. 1 is a maintenance flow diagram of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby. It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
The technical scheme adopted by the invention is as follows:
the method comprises the following steps: the winding temperature rise is calculated through the transformer winding temperature and the environment temperature, taking the A-phase winding as an example, the calculation formula of the winding temperature rise is as follows:
in the formula (I), the compound is shown in the specification,
represents the A-phase winding temperature, TenvRepresenting the ambient temperature.
Step two: dividing the load rate of the transformer and the A, B, C three-phase winding temperature rise data into n intervals with equal distance in the respective maximum value and minimum value, and respectively classifying the original load rate and A, B, C three-phase winding temperature rise data into the divided intervals.
Taking the load rate as an example, the formula for dividing the regions is as follows:
then, the n divided load rate intervals are respectively:
[Lmin,Lmin+LΔ],[Lmin+LΔ,Lmin+2LΔ],…,[Lmin+(n-1)LΔ,Lmin+nLΔ]
the load rate interval { [ L ]min,Lmin+LΔ],[Lmin+LΔ,Lmin+2LΔ],…,[Lmin+(n-1)LΔ,Lmin+nLΔ]Symbolically denoted by { L }1,L2,…,Ln}。
Taking the temperature rise of the A-phase winding as an example, the formula for dividing the intervals is as follows:
then, the divided n a-phase winding temperature rise intervals are respectively:
and performing similar operation on the winding temperature rises of the B phase and the C phase, and dividing winding temperature rise intervals.
Temperature rise interval of A-phase winding
May be symbolized as T1 A,T2 A,…,Tn A}。
Temperature rise interval of B-phase winding
May be symbolized as T1 B,T2 B,…,Tn B}。
Temperature rise interval of C-phase winding
May be symbolized as T1 C,T2 C,…,Tn C}。
Step three: and connecting all the load rate intervals and the winding temperature rise intervals pairwise to form a causal pair, and considering that the temperature change of the winding is caused by the change of the load rate, the default load rate is the cause, and the winding temperature rise is the effect.
The causal pair set of A-phase windings may be representedIs { [ L ]1,T1 A],[L1,T2 A],…,[L2,T1 A],[L2,T2 A],…,[Ln,Tn A]}。
The causal pair set of the B-phase windings may be represented as { [ L ]1,T1 B],[L1,T2 B],…,[L2,T1 B],[L2,T2 B],…,[Ln,Tn B]}。
The causal pair set of C-phase windings may be represented as { [ L ]1,T1 C],[L1,T2 C],…,[L2,T1 C],[L2,T2 C],…,[Ln,Tn C]}。
Step four: and calculating the support degree and the confidence degree of each causal pair, taking the A-phase winding as an example, and calculating the support degree and the confidence degree according to the following formula:
in the formula, LiRefers to the ith load rate interval,
refers to the temperature rise interval of the jth A-phase winding,
the number of causal pairs which belong to the ith load rate interval and the jth A-phase winding temperature rise interval at the same time is indicated, and N is the number of all causal pairs in a causal pair set.
The support measure is the probability of the event A and the event B occurring simultaneously in all the events, and the confidence measure is that the event A occurs beforeAnd on the premise of the probability of occurrence of the event B, the two judgment criteria are both unavailable. If the confidence of a causal pair is high but the support degree is low, the causal pair is less established in the records of all events. For example, cause and effect pairs
The confidence of (1) is 75%, but if events a and B occur only 10 times simultaneously in a total number of 10000 event records, i.e. the support is 0.001, the amount of data is too small to support the causal pair to be true.
Step five: set the minimum support, denoted SUPminAnd finding out all causal pairs not less than the minimum support degree in all causal pair sets. Dynamically adjusting the minimum support degree, firstly, the minimum support degree SUPminAnd setting the number to be 1, reducing the number by 1% each time until the causal pair set not less than the minimum support degree comprises all load rate intervals, determining the threshold value of the minimum support degree at the moment, and outputting the causal pair set not less than the threshold value of the minimum support degree.
Step six: set the minimum confidence, represent it as CONFminAnd finding all causal pairs not less than the minimum confidence level in the causal pair set obtained in the step five. Dynamically adjusting the minimum confidence, firstly, the minimum confidence CONFminSetting the value to be 1, reducing the value by 1% each time until the causal pair set not less than the minimum confidence coefficient comprises all load rate intervals, determining the minimum confidence coefficient threshold value at the moment, and outputting the causal pair set not less than the minimum confidence coefficient threshold value to obtain the results shown in the following table:
| serial number | Reason for | Results | Confidence level | Degree of support |
| 1 | L2 | T2 A | CONF1 | SUP1 |
| 2 | L3 | T3 A | CONF2 | SUP2 |
| 3 | L1 | T1 A | CONF3 | SUP3 |
| 4 | L2 | T3 A | CONF4 | SUP4 |
TABLE 1 Transformer maintenance correlation analysis results
Each causal pair in table 1 is not less than the minimum support threshold and the minimum confidence threshold at the same time, and one causal pair represents that the temperature rise interval belongs to the normal range of the temperature rise of the phase a winding in the load factor interval.
Step seven: for each load rate interval, finding the corresponding normal temperature rise interval and establishing the result in the form of the following table:
TABLE 2A phase winding Normal temperature rise Range
Step eight: repeating the steps from one step to the seventh step for the B, C phase, researching the relationship between the load rate and the temperature rise of the phase winding, calculating the normal range of the temperature rise of the phase winding under a certain load rate interval, and establishing a table in the form of the following table:
TABLE 3 Normal temperature rise Range of winding
Step nine: in actual operation, as long as the temperature rise of any phase of winding is not within the normal temperature rise range in the corresponding load rate interval, the transformer is very likely to have a fault, and the system sends out an alarm signal to remind maintenance personnel to overhaul in time.
Example simulation:
the data adopted by the example simulation is the July month data of a certain transformer, and the load factor and the three-phase winding temperature rise are firstly divided into 6 intervals with equal distance in the respective maximum value and minimum value.
The maximum value and the minimum value of the load rate are 0.7568 and 0 respectively, and the divided 6 load rate intervals are as follows: [0,0.1261], [0.1261,0.2522], [0.2522,0.3784], [0.3784,0.5045], [0.5045,0.6307], [0.6307,0.7568 ].
The maximum value and the minimum value of the A-phase winding temperature rise are respectively 62.40 ℃ and 16.50 ℃, and the divided 6A-phase winding temperature rise intervals are as follows: [16.40,24.15], [24.15,31.80], [31.80,39.45], [39.45,47.10], [47.10,54.75], [54.75,62.40 ].
The maximum value and the minimum value of the temperature rise of the phase B winding are 67.90 ℃ and 22.50 ℃ respectively, and the divided 6 phase B winding temperature rise intervals are as follows: [22.50,30.07], [30.07,37.63], [37.63,45.20], [45.20,52.77], [52.77,60.33], [60.33,67.90 ].
The maximum value and the minimum value of the temperature rise of the C-phase winding are 57.30 ℃ and 15.70 ℃ respectively, and the divided 6 temperature rise intervals of the C-phase winding are as follows: [15.70,22.63], [22.63,29.57], [29.57,36.50], [36.50,43.43], [43.43,50.37], [50.37,57.30 ].
The normal range of the temperature rise of the transformer in a certain load factor interval is deduced according to the method of the invention, and the result is shown in table 4. The monitoring system monitors the load rate of the transformer in real time, finds out the corresponding transformer winding temperature belonged section according to the table 4, simultaneously monitors the A-phase winding temperature rise, the B-phase winding temperature rise and the C-phase winding temperature rise in real time, and when the monitoring winding temperature rise is not in the belonged section, the monitoring system shows that the inside of the transformer has a fault, and sends an alarm signal.
TABLE 4 simulation results
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; these modifications and substitutions do not cause the essence of the corresponding technical solution to depart from the scope of the technical solution of the embodiments of the present invention, and are intended to be covered by the claims and the specification of the present invention.
Claims (1)
1. An intelligent transformer maintenance method based on correlation analysis is characterized by comprising the following steps:
the method comprises the following steps: calculating the winding temperature rise through the transformer winding temperature and the environment temperature, wherein the transformer winding temperature rise is the difference between the winding temperature and the environment temperature;
step two: because the load rate and the winding temperature rise of the transformer are continuous data, and the correlation analysis must be classified attribute data, the original data needs to be discretized, the load rate and the winding temperature rise need to be discretized respectively, and are included in the divided intervals, and the intervals are represented by symbols as follows:
[L1,L2,…,Ln]、[T1,T2,…,Tn]
wherein n is the number of divided intervals;
step three: connecting all the load rate intervals and the winding temperature rise intervals pairwise to form causal pairs, considering that the temperature change of the winding is caused by the change of the load rate, the default load rate is the cause, the winding temperature rise is the effect, and the set of the causal pairs can be expressed as follows:
{[L1,T1],[L1,T2],…,[L2,T1],[L2,T2],…,[Ln,Tn]}；
step four: calculating the support degree and the confidence degree of all causal pairs in the causal pair set,
the calculation formula of the support degree is as follows:
the confidence coefficient is calculated by the formula:
in the formula, LiRefers to the ith load factor interval, TjRefers to the j winding temperature rise interval, count (L)i∩Tj) The number of causal pairs belonging to an ith load rate interval and a jth winding temperature rise interval at the same time is indicated, and N is the number of all causal pairs in a causal pair set;
step five: setting a minimum support degree, which is expressed as SUP by symbolsminFinding out all SUP not less than the minimum support degreeminCause and effect pair of (1), dynamically adjusted from high value downWhole minimum support SUPminSo as not to be less than the minimum support SUPminThe causal pair set comprises all load rate intervals, the minimum support threshold at the moment is determined, and the causal pair set not smaller than the minimum support threshold is output;
step six: setting minimum confidence, symbolically expressed as CONFminFinding out all CONFs not less than the minimum confidence coefficient from the results obtained in the step fiveminDynamically adjust the minimum confidence CONF from high value downminSo as not to be less than the minimum confidence CONFminThe causal pair set comprises all load rate intervals, the minimum confidence coefficient threshold value at the moment is determined, and all causal pairs not smaller than the minimum confidence coefficient threshold value are output;
step seven: calculating the normal temperature rise range of the winding corresponding to each load rate interval from the result obtained in the step six;
step eight: if the temperature of the winding of the transformer is not within the normal temperature rise range in the corresponding load rate interval at a certain moment, the transformer is possibly in fault, and the system sends out an alarm signal to remind maintenance personnel to overhaul in time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010786664.0A CN111914426A (en) | 2020-08-07 | 2020-08-07 | Transformer intelligent maintenance method based on correlation analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010786664.0A CN111914426A (en) | 2020-08-07 | 2020-08-07 | Transformer intelligent maintenance method based on correlation analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111914426A true CN111914426A (en) | 2020-11-10 |
Family
ID=73288252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010786664.0A Pending CN111914426A (en) | 2020-08-07 | 2020-08-07 | Transformer intelligent maintenance method based on correlation analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111914426A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966867A (en) * | 2021-03-11 | 2021-06-15 | 山东德佑电气股份有限公司 | Transformer early warning method based on PSO-BP neural network and quartile method |
| CN114019298A (en) * | 2021-09-28 | 2022-02-08 | 中电华创(苏州)电力技术研究有限公司 | PCC-SVM-based generator rotor turn-to-turn short circuit online monitoring method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103592545A (en) * | 2013-11-22 | 2014-02-19 | 国家电网公司 | Transformer temperature rise abnormity monitoring and diagnosis method based on probability statistics |
| US20150094983A1 (en) * | 2013-09-30 | 2015-04-02 | Nec (China) Co., Ltd. | Feature extraction method and apparatus for use in casual effect analysis |
| CN110007182A (en) * | 2019-03-22 | 2019-07-12 | 中国电力科学研究院有限公司 | A kind of the health status method for early warning and device of distribution transformer |
| CN110518550A (en) * | 2019-08-30 | 2019-11-29 | 珠海格力电器股份有限公司 | Power module overheating protection method, computer device and computer readable storage medium |
-
2020
- 2020-08-07 CN CN202010786664.0A patent/CN111914426A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150094983A1 (en) * | 2013-09-30 | 2015-04-02 | Nec (China) Co., Ltd. | Feature extraction method and apparatus for use in casual effect analysis |
| CN103592545A (en) * | 2013-11-22 | 2014-02-19 | 国家电网公司 | Transformer temperature rise abnormity monitoring and diagnosis method based on probability statistics |
| CN110007182A (en) * | 2019-03-22 | 2019-07-12 | 中国电力科学研究院有限公司 | A kind of the health status method for early warning and device of distribution transformer |
| CN110518550A (en) * | 2019-08-30 | 2019-11-29 | 珠海格力电器股份有限公司 | Power module overheating protection method, computer device and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 葛东旭: "《数据挖掘原理与应用》", 30 April 2020 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966867A (en) * | 2021-03-11 | 2021-06-15 | 山东德佑电气股份有限公司 | Transformer early warning method based on PSO-BP neural network and quartile method |
| CN114019298A (en) * | 2021-09-28 | 2022-02-08 | 中电华创(苏州)电力技术研究有限公司 | PCC-SVM-based generator rotor turn-to-turn short circuit online monitoring method |
| CN114019298B (en) * | 2021-09-28 | 2023-12-05 | 中电华创(苏州)电力技术研究有限公司 | On-line monitoring method for turn-to-turn short circuit of generator rotor based on PCC-SVM |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111914426A (en) | Transformer intelligent maintenance method based on correlation analysis | |
| CN101666841B (en) | Fault diagnosis method of digitalizing transformer substation electronic transducer | |
| CN102288842B (en) | Based on the primary frequency modulation on-line evaluation method that WAMS filtering AGC affects | |
| CN111537839B (en) | Transient voltage safety evaluation method and system suitable for high-proportion new energy transmission end power grid | |
| CN108629520B (en) | Method for evaluating running state of high-voltage transmission line in microclimate environment | |
| CN115356592B (en) | Novel fault monitoring method and system for low-voltage distribution equipment | |
| CN110061521B (en) | Maximum wind power permeability rapid evaluation method considering frequency accumulation effect | |
| CN114994441A (en) | Intelligent electric power efficiency monitoring device | |
| CN112711832B (en) | Method and system for early warning of temperature and fault identification of stator winding of synchronous generator | |
| CN107015140A (en) | A kind of analysis of vibration signal method for failure that load ratio bridging switch spring kinetic energy is not enough | |
| CN113588123A (en) | Stator winding temperature early warning method | |
| CN107122506B (en) | top layer oil temperature thermal model construction method considering transformer oil nonlinear time constant | |
| CN109617091B (en) | Dynamic reactive power compensation device control strategy verification system | |
| CN105160445A (en) | Evaluation system and method for power supply reliability for important user | |
| CN115859092A (en) | Generator winding temperature early warning method and device based on principal component decomposition | |
| CN114199505B (en) | Generator stator bar flow performance evaluation method based on correlation analysis | |
| CN112084661B (en) | Wind turbine converter water cooling system cooling state assessment early warning method | |
| CN116071036A (en) | Transformer temperature state evaluation method, equipment and medium | |
| Zeng et al. | Fault Diagnosis Analysis of Distribution Network Based on Compound Statistics of Residual and Score | |
| Peng et al. | Wind Farm Clustering Optimization Method Using Gap Statistic | |
| US20220317646A1 (en) | Self-adaptive test method for intelligent prediction algorithm of analog measured values | |
| Hongda et al. | Research on Remote Diagnosis Model of Metering Point Anomaly of 10kV Distribution Line Based on AMI Data | |
| Cunxiang et al. | The fault diagnosis of transformer Based on the SOM neural network current | |
| CN117278425B (en) | Information technology operation and maintenance management method and system | |
| CN105548750A (en) | Substation current secondary loop state evaluation method based on multi-data processing |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201110 |
|
| RJ01 | Rejection of invention patent application after publication |