CN106094694B - A kind of hot monitoring method based on underground substation - Google Patents
A kind of hot monitoring method based on underground substation Download PDFInfo
- Publication number
- CN106094694B CN106094694B CN201610677609.1A CN201610677609A CN106094694B CN 106094694 B CN106094694 B CN 106094694B CN 201610677609 A CN201610677609 A CN 201610677609A CN 106094694 B CN106094694 B CN 106094694B
- Authority
- CN
- China
- Prior art keywords
- transformer
- hot
- load
- air
- neural network
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/048—Monitoring; Safety
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Automation & Control Theory (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The hot monitoring method based on underground substation that the invention discloses a kind of, this method comprises: the environment around transformer and the transformer to underground substation detects, detection obtains the partial discharge amount Q of the transformerPD, humidity H, load current IloadWith air-conditioning power Pair‑con；Using BP neural network to the load current Iload, humidity H and air-conditioning power Pair‑conIt is analyzed, obtains the environment temperature T of the transformera；Using BP neural network to the load current Iload, partial discharge amount QPDWith environment temperature TaIt is analyzed, obtains the hot(test)-spot temperature T of the transformerhs.This method realizes the safety and reliability for improving underground substation.
Description
Technical field
The present invention relates to monitoring technical fields, more particularly to a kind of hot monitoring method based on underground substation.
Background technique
Currently, having used underground substation more and more due to the anxiety of land used.But heat dissipation is underground substation
The hot(test)-spot temperature of the problem of most serious, especially transformer affects its service life and working condition.Dry-type transformer is applied to
This kind of electric substation, for avoiding kindling and environmental pollution.Need to study heat dissipation and ventilation to prevent electrical equipment fault.Become
The failure of depressor can damage other equipment not only to itself causing irreversible damage.Therefore, the temperature of transformer is analyzed
Degree and the ambient conditions around it to ensure underground substation safety and reliably it is particularly significant.Transformer some
Electromagnetic energy is converted into thermal energy, these thermal energy a part increase the temperature of transformer, and another part is dissipated in environment
, for the safety and reliability of underground substation, need to carry out underground substation hot monitoring, heat monitoring becomes underground
Electricity power equipment temperature and underground substation environment temperature monitoring.But now for the research of transformer, do not have also
There is the comprehensive hot monitoring method for being directed to underground substation, under hot, moist and high salinity environment, underground substation
Safety and reliability it is very low.
Summary of the invention
The hot monitoring method based on underground substation that the object of the present invention is to provide a kind of, to realize raising underground substation
Safety and reliability.
In order to solve the above technical problems, the present invention provides a kind of hot monitoring method based on underground substation, comprising:
The environment around transformer and the transformer to underground substation detects, and detection obtains the transformer
Partial discharge amount QPD, humidity H, load current IloadWith air-conditioning power Pair-con；
Using BP neural network to the load current Iload, humidity H and air-conditioning power Pair-conIt is analyzed, obtains institute
State the environment temperature T of transformera；
Using BP neural network to the load current Iload, partial discharge amount QPDWith environment temperature TaIt is analyzed, obtains institute
State the hot(test)-spot temperature T of transformerhs。
Preferably, the method also includes:
Calculate hot(test)-spot temperature ThsMore line probability and environment temperature TaMore line probability.
Preferably, the method also includes:
If hot(test)-spot temperature ThsMore line probability be greater than 60% or environment temperature TaMore line probability be greater than 60%, carry out early
Phase early warning.
Preferably, the method also includes:
The remaining life of the transformer is estimated.
Preferably, the BP neural network that the BP neural network is three layers.
Preferably, the neuron number of the hidden layer of the BP neural network is l, whereinN is defeated
Enter the number of the neuron of layer, m is the number of the neuron of output layer, and α is constant value.
Preferably, the environment around the transformer and the transformer to underground substation detects, and detects
To the partial discharge amount Q of the transformerPD, humidity H, load current IloadWith air-conditioning power Pair-con, comprising:
Utilize TEV sensor measurement partial discharge amount QPD；
Humidity H is measured using wireless sensor；
Load current I is measured using current transformerload；
Utilize power meter measures air-conditioning power Pair-con。
Preferably, environment temperature TaError meet normal distribution, hot(test)-spot temperature ThsError meet normal distribution.
A kind of hot monitoring method based on underground substation provided by the present invention, transformer and institute to underground substation
The environment stated around transformer is detected, and detection obtains the partial discharge amount Q of the transformerPD, humidity H, load current IloadWith
Air-conditioning power Pair-con；Using BP neural network to the load current Iload, humidity H and air-conditioning power Pair-conIt is analyzed,
Obtain the environment temperature T of the transformera；Using BP neural network to the load current Iload, partial discharge amount QPDWith environment temperature
Spend TaIt is analyzed, obtains the hot(test)-spot temperature T of the transformerhs.As it can be seen that this method gets the environment temperature and heat of transformer
Point temperature realizes and the heat of underground substation is monitored that under hot, moist and high salinity environment, what can be integrated is directed to
Underground substation carries out hot monitoring, improves the safety and reliability of underground substation.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of flow chart of the hot monitoring method based on underground substation provided by the present invention；
Fig. 2 is hot monitoring process schematic diagram；
Fig. 3 is the schematic diagram for obtaining hot(test)-spot temperature；
Fig. 4 is the schematic diagram for obtaining environment temperature；
Fig. 5 is the equivalent circuit loaded for the variable speed drives of frequency analysis；
Fig. 6 is the equivalent circuit of the electric substation loaded with variable speed drives；
Fig. 7 is the schematic diagram that hot(test)-spot temperature is obtained when considering harmonic load.
Specific embodiment
Core of the invention is to provide a kind of hot monitoring method based on underground substation, to realize raising underground substation
Safety and reliability.
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Referring to FIG. 1, Fig. 1 is a kind of flow chart of the hot monitoring method based on underground substation provided by the present invention,
This method comprises:
S11: detecting the environment around the transformer and transformer of underground substation, and detection obtains the office of transformer
High-volume QPD, humidity H, load current IloadWith air-conditioning power Pair-con；
S12: using BP neural network to load current Iload, humidity H and air-conditioning power Pair-conIt is analyzed, is become
The environment temperature T of depressora；
S13: using BP neural network to load current Iload, partial discharge amount QPDWith environment temperature TaIt is analyzed, is become
The hot(test)-spot temperature T of depressorhs。
As it can be seen that this method gets the environment temperature and hot(test)-spot temperature of transformer, realizes and the heat of underground substation is supervised
It surveys, under hot, moist and high salinity environment, the underground substation that is directed to that can be integrated carries out hot monitoring, improves underground and becomes
Electricity safety and reliability.
It is further, further comprising the steps of based on the above method:
S21: hot(test)-spot temperature T is calculatedhsMore line probability and environment temperature TaMore line probability.
The calculating of out-of-limit probability is carried out on the basis of meeting normal distribution based on prediction error.Calculation formula is as follows:
Pij(Xa')=Pij(xi' > xi,lim-Δxi,j-1)=1-F (xi,lim-Δxi,j-1)
Formula X above 'aFor the predicted value of autocorrelation parameter, the importation of neural network, x ' are referred toiIt is cross-correlation coefficient
Predicted value refers to the output valve of neural network.△xi,j-1It was the prediction error at a upper moment.xi,limIt is more limit value.From phase
Closing parameter can be predicted by autoregression model.Calculate hot(test)-spot temperature ThsMore line probability, then the formula inside
Parameter X 'aIt is substituted for hot(test)-spot temperature ThsIt is calculated.Calculate environment temperature TaMore line probability when, then the formula inside
X 'aIt is substituted for environment temperature TaIt is calculated.
Further, if hot(test)-spot temperature ThsMore line probability be greater than 60% or environment temperature TaMore line probability be greater than
60%, carry out early warning.
Wherein, environment temperature TaError meet normal distribution, hot(test)-spot temperature ThsError meet normal distribution.
Further, the above method is further comprising the steps of:
S31: the remaining life of transformer is estimated.
The calculating of Facility Remainder Life, that is, remaining life is related with hot(test)-spot temperature.Here aging rate K is introduced:
Wherein, a and b is constant value, LnFor the life cycle of equipment.ThsIt is historical record value.In above formula absolutely for F grades
The dry-type transformer of edge, value a=9.6 X 10-17, b=20475.A, value of the b under the class B insulations such as other is as shown in table 1.
Table 1
LnFor the life cycle of equipment.ThsIt is historical record value, it can be fitted to the function T about the timehs(t)。
From initial time to 0 to current time t1, the service life of equipment loss is Lloss, the remaining service life is Lres.Calculation formula is as follows:
Lres(t1)=Ln-Lloss(t1)
Specifically, the BP neural network that the BP neural network is three layers.
Wherein, the neuron number of the hidden layer of BP neural network is l, whereinN is input layer
The number of neuron, m are the numbers of the neuron of output layer, and α is constant value.α is 1 to 10 constant.It is obtained most to compare
Good hidden layer neuron number, the neural network under every kind of number will input 10 test datas, and overall error is the smallest for most
It is good.
Specifically, the process of step S11 the following steps are included:
S1: TEV sensor measurement partial discharge amount Q is utilizedPD；
S2: humidity H is measured using wireless sensor；
S3: load current I is measured using current transformerload；
S4: power meter measures air-conditioning power P is utilizedair-con。
Specifically, obtaining the environment temperature T of transformer in S12aIt is the following hot(test)-spot temperature, that is, the hot(test)-spot temperature predicted is
One predicted value.The hot(test)-spot temperature T of transformer is obtained in step S13hsFor FUTURE ENVIRONMENT temperature, that is, the environment temperature predicted is
One predicted value.
Detailed, step S11 is the process of temperature prediction to step S13, and step 21 and step S31 are to carry out reliability point
The process of analysis.This method needs the parameter monitored to have: partial discharge amount QPD, hot(test)-spot temperature Ths, environment temperature Tambient, humidity H, load
Electric current IloadWith air-conditioning power Pair-con.Herein, TaIt is environment temperature TambientAbbreviation, environment temperature TambientRefer to
Ta.It include to the electric substation's environment temperature and wherein prediction technique of power equipment temperature in method, for the two parameters
Out-of-limit method for calculating probability, the estimation method of Facility Remainder Life.With reference to Fig. 2, Fig. 2 is hot monitoring process schematic diagram.
Wherein, the prediction of temperature has used 3 layers of BP neural network.Predict ThsBP neural network (HTBPNN) input have
Iload、QPDAnd Ta, in addition delay unit shares 6 inputs, predict TaNeural network (ETBPNN) input have Iload、Pair-
Con and H, in addition delay unit shares 6 inputs.Predict ThsBP neural network be referred to as HTBPNN, predict TaNerve net
Network is referred to as ETBPNN, belongs to BP neural network, with reference to Fig. 3 and Fig. 4.
Wherein, input/output argument is limited between 0.1 to 0.9, keeps the training of neural network more efficient.Parameter
Standardisation process is realized by following formula:
Wherein xiFor true value, xmaxAnd xminFor the maximal and minmal value in all data.
Specifically, having used the i.e. multiple samples of multi-group data in the training process of neural network.Each group of data have
Partial discharge amount QPD, humidity H, load current IloadWith air-conditioning power Pair-conWith the hot(test)-spot temperature T of subsequent timehs, subsequent time
Environment temperature Tambient.First 4 are inputs as neural network, the desired output of both rear HTBPNN and ETBPNN respectively,
Error desired output (measured value) is constituted with output layer output quantity (predicted value).A portion is used to training mind in these samples
The link weight coefficients of each neuron are constantly corrected through network, another part is used to test, by obtained predicted value and practical survey
Magnitude is compared, it can be deduced that the rule of prediction error distribution, calculating to probability of malfunction is temperature beyond limit probability calculation.This
The ratio of two parts data is 3: 1.
Wherein, when considering that load harmonic influences, the input of HTBPNN will consider the excess loss that harmonic current generates more.
Specifically, temperature prediction is prediction hot(test)-spot temperature and environment temperature, BP neural network is used.The measurement side of parameter
Formula: TEV sensor measurement partial discharge amount, PT100 temperature sensor measurement hot(test)-spot temperature, wireless sensor measure environment temperature and wet
Degree, load current have current transformer measurement, and air-conditioning is active to use power meter measures.Fail-safe analysis includes life estimation and out-of-limit
Probability calculation.When the probability that the predicted value of environment temperature or hot(test)-spot temperature is more than limits value is greater than 60%, it is pre- to carry out early stage
It is alert.
When parameter be unsatisfactory for following three states for the moment, sound an alarm and take further step.
(1) no more than 40 degrees Celsius, the average temperature of air of daily ambient enviroment not surpass the temperature of cooling gas
Cross 30 degrees Celsius；
(2) the per day relative humidity, that is, RHD of air is lower than 60%；
(3) hot(test)-spot temperature of transformer does not exceed 155 degrees Celsius, and maximum temperature rise, that is, knots modification does not exceed 100 is Celsius
Degree.
Referring to Fig. 3, for predicting hot(test)-spot temperature ThsNeural network HTBPNN, input quantity Iload、QPDAnd Ta, Z-1It is to prolong
Shi Danyuan.Thus the system of this entire hot monitoring process shares 6 inputs and 1 output.In the training process of neural network,
The data of input are the value of these three parameters of the value and previous moment j-1 of this 3 parameters of a certain moment j, and desired output is the j moment
Ths.After the completion of training, then with neural network carry out temperature prediction.I is inputted at this timeload、QPDAnd TaThe prediction of future time instance j
The monitor value of value and current time j-1, obtains the hot(test)-spot temperature T of future time instancehs.For first closing parameter such as I certainlyload、Pair-con、
H etc., can be by autoregressive model prediction, can be first with ETBPNN to environment temperature TaHot(test)-spot temperature is predicted after being predicted again
Ths.The structure and HTBPNN of ETBPNN is the same.
The air-conditioning equipment and water pump of underground substation are typical harmonic sources.Referring to Fig. 5, for the speed change for frequency analysis
Drive the equivalent circuit of (ASD) load.Power grid alternating current forms the direct current of pulsation in the other side through over commutation, but exchanges side meeting
Generate harmonic wave.The electric current of exchange side can be expressed as follows:
Formula I aboveChIndicate harmonic current vector, UkIndicate that voltage harmonic vector, * indicate conjugation, YC +And YC -Indicate coupling
Harmonic admittance matrix.
Referring to Fig. 6, for the equivalent circuit of the electric substation loaded with variable speed drives, variable speed drives load is water pump of air conditioner.
Electric current is made of harmonic load electric current and other load currents,
Above formula YLIt is the admittance matrix of normal load.Voltage can be expressed as:
Load terminal voltage can be calculated by harmonic power trend iterative algorithm according to above formula, so as to obtain
Flow through the harmonic current of transformer.The summation of harmonic load electric current and other load currents is load current Iload。
When transformer flows through harmonic current, it will generate additional energy loss.Referring to Fig. 7, to consider harmonic load
When obtain the schematic diagram of hot(test)-spot temperature, it is seen that consider HTBPNN structure when harmonic load, therefore the input of HTBPNN will be added
One △ P parameter, indicates the active consumption of harmonic current.△ P is consisted of three parts
Three component parts in above formula are respectively copper loss, eddy-current loss and the stray loss that harmonic wave generates.RdcFor transformation
The DC losses resistance of device, h are overtone order.PECLAnd PSLThe respectively eddy-current loss and stray loss of rated condition.FECLWith
FSLFor harmonic losses factor.
It is one with the temperature value that neural network prediction goes out for the probability distribution of environment temperature and hot(test)-spot temperature predicted value
Fixed value, but according to the comparison of historical forecast and historical record data, it can be deduced that predict the probability distribution of error.Use nerve net
The output of network is plus the probability distribution that can obtain predicted value after prediction error.There is hot(test)-spot temperature predicted value ratio when harmonic wave to have humorous
Hot(test)-spot temperature predicted value when wave is higher.
A kind of hot monitoring method based on underground substation provided by the present invention is described in detail above.Herein
In apply that a specific example illustrates the principle and implementation of the invention, the explanation of above example is only intended to sides
Assistant solves method and its core concept of the invention.It should be pointed out that for those skilled in the art, not
, can be with several improvements and modifications are made to the present invention under the premise of being detached from the principle of the invention, these improvement and modification are also fallen into
In the protection scope of the claims in the present invention.
Claims (8)
1. a kind of hot monitoring method based on underground substation characterized by comprising
The environment around transformer and the transformer to underground substation detects, and detection obtains the office of the transformer
High-volume QPD, humidity H, load current IloadWith air-conditioning power Pair-con；
Using BP neural network to the load current Iload, humidity H and air-conditioning power Pair-conIt is analyzed, obtains the change
The environment temperature T of depressora；
Using BP neural network to the load current Iload, partial discharge amount QPDWith environment temperature TaIt is analyzed, obtains the transformation
The hot(test)-spot temperature T of devicehs。
2. the method as described in claim 1, which is characterized in that further include:
Calculate hot(test)-spot temperature ThsMore line probability and environment temperature TaMore line probability；
Wherein, the calculating of out-of-limit probability is carried out on the basis of meeting normal distribution based on prediction error；Calculation formula is as follows:
Pij(X′a)=Pij(x′i> xi,lim-Δxi,j-1)=1-F (xi,lim-Δxi,j-1)；
Formula X above 'aFor the predicted value of autocorrelation parameter, the importation of neural network, x ' are referred toiIt is the prediction of cross-correlation coefficient
Value, refers to the output valve of neural network, △ xi,j-1It was the prediction error at a upper moment, xi,limIt is that more limit value, auto-correlation are joined
Number can be predicted by autoregression model, as calculating hot(test)-spot temperature ThsMore line probability, then the parameter inside the formula
X’aIt is substituted for hot(test)-spot temperature ThsIt is calculated, as calculating environment temperature TaMore line probability when, then the X ' inside the formulaaReplacement
At environment temperature TaIt is calculated.
3. method according to claim 2, which is characterized in that further include:
If hot(test)-spot temperature ThsMore line probability be greater than 60% or environment temperature TaMore line probability be greater than 60%, carry out early stage it is pre-
It is alert.
4. the method as described in claim 1, which is characterized in that further include:
Estimated using remaining life of the life formula to the transformer；
Wherein, the life formula are as follows:
In formula, LnFor the life cycle of equipment, ThsIt (t) is historical record value ThsThe function about the time being fitted to, LlossFor
From initial time to 0 to current time t1The service life of equipment loss, LresFor from initial time to 0 to current time t1The remaining longevity
Life.
5. method as claimed in claim 4, which is characterized in that the BP neural network that the BP neural network is three layers.
6. method as claimed in claim 5, which is characterized in that the neuron number of the hidden layer of the BP neural network is l,
Wherein,N is the number of the neuron of input layer, and m is the number of the neuron of output layer, and α is constant value.
7. the method as described in claim 1, which is characterized in that described all to the transformer of underground substation and the transformer
The environment enclosed is detected, and detection obtains the partial discharge amount Q of the transformerPD, humidity H, load current IloadWith air-conditioning power
Pair-con, comprising:
Utilize TEV sensor measurement partial discharge amount QPD；
Humidity H is measured using wireless sensor；
Load current I is measured using current transformerload；
Utilize power meter measures air-conditioning power Pair-con。
8. method as claimed in any of claims 1 to 7 in one of claims, which is characterized in that environment temperature TaError meet normal state point
Cloth, hot(test)-spot temperature ThsError meet normal distribution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610677609.1A CN106094694B (en) | 2016-08-16 | 2016-08-16 | A kind of hot monitoring method based on underground substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610677609.1A CN106094694B (en) | 2016-08-16 | 2016-08-16 | A kind of hot monitoring method based on underground substation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106094694A CN106094694A (en) | 2016-11-09 |
| CN106094694B true CN106094694B (en) | 2019-04-19 |
Family
ID=58069342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610677609.1A Active CN106094694B (en) | 2016-08-16 | 2016-08-16 | A kind of hot monitoring method based on underground substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106094694B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560345B (en) * | 2020-12-16 | 2022-12-06 | 中国电建集团河北省电力勘测设计研究院有限公司 | Design method of underground electric power space ventilation system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006135995A1 (en) * | 2005-06-21 | 2006-12-28 | Siemens Ltda. | System and method for centralized monitoring of distributed power transformer |
| CN201984124U (en) * | 2011-01-28 | 2011-09-21 | 保定天威集团有限公司 | Intelligent online monitoring device for dry type transformer |
| CN102427218A (en) * | 2011-10-28 | 2012-04-25 | 武汉供电公司变电检修中心 | Transformer short period overload capability assessment system based on artificial intelligence technology |
| CN103443834A (en) * | 2010-09-30 | 2013-12-11 | 甘特尔地产有限公司 | System and method for fire prevention in electrical installations |
| CN103578042A (en) * | 2013-10-14 | 2014-02-12 | 国家电网公司 | Hieratical assessment method for degree of reliability of power transformer |
| 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 |
| CN105404780A (en) * | 2015-11-25 | 2016-03-16 | 国网山东省电力公司电力科学研究院 | Multi-parameter integrated analysis transformer overload capability evaluating method |
| CN105550472A (en) * | 2016-01-20 | 2016-05-04 | 国网上海市电力公司 | Prediction method of transformer winding hot-spot temperature based on neural network |
| CN105631578A (en) * | 2015-12-10 | 2016-06-01 | 浙江大学 | Risk assessment-orientated modeling method of power transmission and transformation equipment failure probability model |
-
2016
- 2016-08-16 CN CN201610677609.1A patent/CN106094694B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006135995A1 (en) * | 2005-06-21 | 2006-12-28 | Siemens Ltda. | System and method for centralized monitoring of distributed power transformer |
| CN103443834A (en) * | 2010-09-30 | 2013-12-11 | 甘特尔地产有限公司 | System and method for fire prevention in electrical installations |
| CN201984124U (en) * | 2011-01-28 | 2011-09-21 | 保定天威集团有限公司 | Intelligent online monitoring device for dry type transformer |
| CN102427218A (en) * | 2011-10-28 | 2012-04-25 | 武汉供电公司变电检修中心 | Transformer short period overload capability assessment system based on artificial intelligence technology |
| CN103578042A (en) * | 2013-10-14 | 2014-02-12 | 国家电网公司 | Hieratical assessment method for degree of reliability of power transformer |
| 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 |
| CN105404780A (en) * | 2015-11-25 | 2016-03-16 | 国网山东省电力公司电力科学研究院 | Multi-parameter integrated analysis transformer overload capability evaluating method |
| CN105631578A (en) * | 2015-12-10 | 2016-06-01 | 浙江大学 | Risk assessment-orientated modeling method of power transmission and transformation equipment failure probability model |
| CN105550472A (en) * | 2016-01-20 | 2016-05-04 | 国网上海市电力公司 | Prediction method of transformer winding hot-spot temperature based on neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106094694A (en) | 2016-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Teh et al. | Prospects of using the dynamic thermal rating system for reliable electrical networks: A review | |
| EP1296147B1 (en) | System and method for estimating power consumption of electric apparatus, and abnormality alarm system utilizing the same | |
| US8694291B2 (en) | System and method of waveform analysis to identify and characterize power-consuming devices on electrical circuits | |
| CN106896267B (en) | A kind of Distribution Network Harmonics resonance improvement modal analysis method | |
| Khoshkhoo et al. | On-line dynamic voltage instability prediction based on decision tree supported by a wide-area measurement system | |
| CN103399241A (en) | Distribution transformer fault diagnosis system and method based on relation between temperature rise and load | |
| US20190324070A1 (en) | State estimation apparatus, state estimation method, and non-transitory medium | |
| Jiang et al. | Stochastic subspace identification‐based approach for tracking inter‐area oscillatory modes in bulk power system utilising synchrophasor measurements | |
| CN108647447A (en) | MMC converter valves analysis method for reliability and device | |
| CN104036111A (en) | Methods and systems for evaluating and diagnosing energy efficiency of energy consuming equipment | |
| CA2743580A1 (en) | Method and system for estimation of source impedence on electrical distribution lines | |
| CN107359612A (en) | A kind of comprehensive estimation method of quality of power supply to power distribution network energy consumption | |
| CN106094694B (en) | A kind of hot monitoring method based on underground substation | |
| CN106771801B (en) | Online monitoring device for capacitor bank and application method of online monitoring device | |
| CN114417574B (en) | Method and device for calculating severity of turn-to-turn short circuit | |
| Rajpoot et al. | A dynamic-SUGPDS model for faults detection and isolation of underground power cable based on detection and isolation algorithm and smart sensors | |
| CN107341736B (en) | Power load decomposition method and system based on current waveform characteristics | |
| Manimuthu et al. | Framework for Load Power Consumption in HANs Using Machine Learning and IoT Assistance | |
| CN104483570B (en) | A kind of Distribution Network Harmonics improvement method for loss reduction effect reality testing | |
| Santoso et al. | Power quality data analytics: Tracking, interpreting, and predicting performance | |
| CN116500391A (en) | Fault arc detection method, system and storage medium based on frequency domain characteristics | |
| CN111025098B (en) | Cable insulation aging degree judging method based on leakage current time domain variation factor | |
| CN110277834B (en) | Power grid response building internal load monitoring method and system and storage medium | |
| Pan et al. | Adaptive threshold event detection method based on standard deviation | |
| Ferdowsi et al. | A data-driven real-time stability metric for SST-based microgrids |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 311199 No. 165, Star Bridge Road, Star Bridge Street, Yuhang District, Hangzhou, Zhejiang Applicant after: ZHEJIANG TRULY ELECTRIC Co.,Ltd. Applicant after: STATE GRID ZHEJIANG HANGZHOU YUHANG POWER SUPPLY Co. Address before: 311199 No. 165, Star Bridge Road, Star Bridge Street, Yuhang District, Hangzhou, Zhejiang Applicant before: ZHEJIANG TRULY ELECTRIC Co.,Ltd. Applicant before: STATE GRID ZHEJIANG HANGZHOU YUHANG POWER SUPPLY Co. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180523 Address after: 310018 No. 11 street, Hangzhou economic and Technological Development Zone, Zhejiang 91 Applicant after: HANGZHOU ELECTRIC EQUIPMENT MANUFACTURING Co.,Ltd. Applicant after: STATE GRID ZHEJIANG HANGZHOU YUHANG POWER SUPPLY Co. Address before: 311199 No. 165, Star Bridge Road, Star Bridge Street, Yuhang District, Hangzhou, Zhejiang Applicant before: ZHEJIANG TRULY ELECTRIC Co.,Ltd. Applicant before: STATE GRID ZHEJIANG HANGZHOU YUHANG POWER SUPPLY Co. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |