CN111461922A - Transformer hot spot temperature real-time prediction method based on extreme learning machine - Google Patents
Transformer hot spot temperature real-time prediction method based on extreme learning machine Download PDFInfo
- Publication number
- CN111461922A CN111461922A CN202010253526.6A CN202010253526A CN111461922A CN 111461922 A CN111461922 A CN 111461922A CN 202010253526 A CN202010253526 A CN 202010253526A CN 111461922 A CN111461922 A CN 111461922A
- Authority
- CN
- China
- Prior art keywords
- temperature
- hot spot
- transformer
- extreme learning
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000004364 calculation method Methods 0.000 claims abstract description 30
- 238000012549 training Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000011160 research Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000001932 seasonal effect Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims 1
- 238000013528 artificial neural network Methods 0.000 description 12
- 210000002569 neuron Anatomy 0.000 description 11
- 238000010586 diagram Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000004804 winding Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- 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
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
The invention relates to a transformer hot spot temperature real-time prediction method based on an extreme learning machine, belonging to the technical field of transformers.A hot spot temperature calculation model is fitted by using a extreme learning machine (E L M) according to historical operating data by taking a transformer load rate, an environment temperature and a top layer oil temperature as characteristic values, and then a power load prediction model based on Support Vector Regression (SVR) is established to realize accurate prediction of the load rate, so that the power load prediction model is used as a preposed input of the hot spot temperature calculation model to construct the hot spot temperature prediction model.
Description
Technical Field
The invention relates to a transformer hot spot temperature real-time prediction method based on an extreme learning machine, and belongs to the technical field of transformers.
Background
The power transformer is used as important electrical equipment in power transmission and distribution of a power system, and the safe, reliable and economic operation of the power transformer is an important guarantee for production and life of people. The hot spot temperature of the transformer more directly affects the operation safety and the service life of the equipment of the transformer. Therefore, researches on the calculation and prediction of the hot spot temperature of the transformer are carried out at home and abroad.
At present, methods for acquiring the hot spot temperature of a transformer can be mainly classified into the following categories: direct measurement method, guiding rule calculation method, hot-circuit model calculation method, numerical value calculation method and intelligent learning method.
The direct measurement method mainly directly extracts the hot spot temperature in a way of embedding a temperature sensor on a transformer winding, and the method has requirements on the positioning accuracy of a measuring point and has a large error. The guiding rule calculation method mainly adopts a hot spot temperature calculation formula recommended by IEEEC57.91-1995 and the national standard GB/T1094.7-2008 at present, the method is similar to an empirical formula, and the obtained result has a large difference with the actually measured data. The thermal circuit model calculation method is based on a heat transfer theory and a thermoelectric analogy method, and establishes a thermal circuit model of the transformer according to heat transfer parameters and operation parameters of the transformer so as to research the thermal characteristics of the transformer. However, the method usually obtains the node temperature of the hot circuit model instead of the hot spot temperature, and certain errors exist in calculation. The numerical calculation method is mainly based on the finite element theory, a three-dimensional model of the transformer is established, and then the overall temperature field of the transformer is solved to obtain the hot spot temperature. The method is more accurate in solution, but accurate design data and electromagnetic parameters of the transformer are needed, and the method is difficult to realize. The intelligent learning method adopts historical data or factory experimental data of transformer operation to construct a relation model of each variable and the hot spot temperature, and then prediction of the hot spot temperature is achieved. The commonly adopted methods at present mainly comprise a neural network, a support vector machine, Kalman filtering and the like. The intelligent learning method has strong fault-tolerant capability and self-adaptive capability, and is increasingly applied to engineering.
An Extreme learning Machine (Extreme L earning Machine, E L M) is a typical single hidden layer feedforward neural network algorithm, weights between an input layer and a hidden layer of the algorithm and a threshold of the hidden layer are randomly generated, the training process does not need to be adjusted, only the number of neurons of the hidden layer is needed to be set to obtain a unique optimal solution, and the method has the advantages of high learning speed and good generalization performance.
Disclosure of Invention
The invention aims to provide a transformer hot spot temperature real-time prediction method based on an extreme learning machine, which comprises the steps of taking three characteristic quantities (load rate, environment temperature and top layer oil temperature) of a transformer during operation as input variables, taking winding hot spot temperature as an output variable, constructing an E L M hot spot temperature calculation model, establishing a power load prediction model based on support vector regression as a preposed input of an E L M model to realize the real-time prediction of the hot spot temperature, randomly generating weights between an input layer and a hidden layer of the extreme learning machine and a threshold value of the hidden layer, obtaining a unique optimal solution by setting the number of neurons of the hidden layer without adjustment in a training process, having the advantages of high learning speed and good generalization performance, having strong applicability, low cost, strong real-time performance, high precision, simple and convenient calculation method and high stability, bringing great convenience to the overhaul of transformer equipment, and effectively solving the problems existing in the background technology.
The technical scheme of the invention is as follows: a transformer hot spot temperature real-time prediction method based on an extreme learning machine comprises the following steps:
a. determining the number of nodes of an input layer and an output layer by taking the load rate of the transformer, the ambient temperature and the top oil temperature as input data and taking the hot spot temperature as output data, and constructing an extreme learning model;
b. carrying out normalization processing on input and output data samples of the extreme learning machine;
c. optimizing the weight and the threshold of the extreme learning algorithm, and training an E L M hot spot temperature calculation model;
d. establishing a power load prediction model based on support vector regression as the pre-input of an E L M hot spot temperature calculation model, and constructing a hot spot temperature prediction model;
e. and inputting the operation data of the transformer at the current moment to obtain the prediction result of the hot spot temperature of the transformer at the next moment.
Constructing an extreme learning model in the step a, as shown in the formula (1) and the formula (2), establishing that the number of nodes of an input layer is 3, the number of nodes of an output layer is 1,
x＝[K,θa,θtop](1)
y＝[θh](2)
wherein theta ishFor the hot spot temperature, K is the load factor (load current I/rated current I)N)、θaIs the ambient temperature, thetatopIs a roofThe layer oil temperature.
In the step b, the historical data of the load current, the ambient temperature, the top layer oil temperature and the hot spot temperature of the transformer collected in the monitoring system are normalized according to the formula (3), each group of data is processed into the range of [ -1,1],
wherein x is data to be processed, xmaxAnd xminIs the maximum and minimum values of the set of data and y is the normalized result.
In the step c, the operation data of the oil-immersed transformer is taken as a research object, and the environment temperature theta is taken asaTop layer oil temperature θtopAnd the load coefficient K is a model input value, the hot spot temperature is a model output value, and the weight value and the threshold value of the model are optimized by using an extreme learning machine model, so that a transformer hot spot temperature E L M calculation model is constructed.
In the step d, the electric load prediction model based on support vector regression is specifically a short-term load prediction model in which the temperature, humidity, weather type, seasonal type, holiday at the previous time, the load value at the same time in the previous day are used as input quantities, and the load value at the next time is used as an output quantity.
In the step e, the hot spot temperature of the transformer at the current moment, the top layer oil temperature, the environment temperature and the load value at the next moment are used as input quantities, and the hot spot temperature at the next moment is used as a hot spot temperature prediction model of the output quantity.
The method has the advantages that three characteristic quantities (load rate, environment temperature and top layer oil temperature) of the transformer during operation are used as input variables, winding hot spot temperature is used as output variables, an E L M hot spot temperature calculation model is constructed, a power load prediction model based on support vector regression is established and used as preposed input of an E L M model, real-time prediction of the hot spot temperature is achieved, weight values between an input layer and a hidden layer of an extreme learning machine and a threshold value of the hidden layer are generated randomly, adjustment is not needed in a training process, only the number of neurons of the hidden layer is needed to be set, a unique optimal solution can be obtained, the method has the advantages of high learning speed and good generalization performance, the applicability is high, the cost is low, the real-time performance is high, the accuracy is high, the calculation method is simple and convenient, and the stability is high, and great convenience is brought to.
Drawings
FIG. 1 is a flow chart of the calculation of the hot spot temperature E L M model of the transformer according to the present invention;
FIG. 2 is a diagram of a single hidden layer feedforward neural network of the present invention;
FIG. 3 is a diagram of the result of the calculation of the hot spot temperature of the Elman neural network of the present invention;
FIG. 4 is a graph of absolute error for three methods of the present invention;
FIG. 5 is a diagram of a real-time prediction model of hot spot temperature E L M according to the present invention;
FIG. 6 is a diagram showing the result of the hot spot temperature E L M real-time prediction model of the present invention.
Detailed Description
The technical solution of the present invention will be further described in detail with reference to the accompanying drawings and embodiments, which are preferred embodiments of the present invention. It is to be understood that the described embodiments are merely a subset of the embodiments of the invention, and not all embodiments; it should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A transformer hot spot temperature real-time prediction method based on an extreme learning machine comprises the following steps:
a. determining the number of nodes of an input layer and an output layer by taking the load rate of the transformer, the ambient temperature and the top oil temperature as input data and taking the hot spot temperature as output data, and constructing an extreme learning model;
b. carrying out normalization processing on input and output data samples of the extreme learning machine;
c. optimizing the weight and the threshold of the extreme learning algorithm, and training an E L M hot spot temperature calculation model;
d. establishing a power load prediction model based on support vector regression as the pre-input of an E L M hot spot temperature calculation model, and constructing a hot spot temperature prediction model;
e. and inputting the operation data of the transformer at the current moment to obtain the prediction result of the hot spot temperature of the transformer at the next moment.
Constructing an extreme learning model in the step a, as shown in the formula (1) and the formula (2), establishing that the number of nodes of an input layer is 3, the number of nodes of an output layer is 1,
x＝[K,θa,θtop](1)
y＝[θh](2)
wherein theta ishFor the hot spot temperature, K is the load factor (load current I/rated current I)N)、θaIs the ambient temperature, thetatopThe top oil temperature.
In the step b, the historical data of the load current, the ambient temperature, the top layer oil temperature and the hot spot temperature of the transformer collected in the monitoring system are normalized according to the formula (3), each group of data is processed into the range of [ -1,1],
wherein x is data to be processed, xmaxAnd xminIs the maximum and minimum values of the set of data and y is the normalized result.
In the step c, the operation data of the oil-immersed transformer is taken as a research object, and the environment temperature theta is taken asaTop layer oil temperature θtopAnd the load coefficient K is a model input value, the hot spot temperature is a model output value, and the weight value and the threshold value of the model are optimized by using an extreme learning machine model, so that a transformer hot spot temperature E L M calculation model is constructed.
In the step d, the electric load prediction model based on support vector regression is specifically a short-term load prediction model in which the temperature, humidity, weather type, seasonal type, holiday at the previous time, the load value at the same time in the previous day are used as input quantities, and the load value at the next time is used as an output quantity.
In the step e, the hot spot temperature of the transformer at the current moment, the top layer oil temperature, the environment temperature and the load value at the next moment are used as input quantities, and the hot spot temperature at the next moment is used as a hot spot temperature prediction model of the output quantity.
In practical application, as shown in fig. 1, a transformer hot spot temperature prediction method based on an extreme learning machine includes the following steps:
(1) based on the load factor K and the ambient temperature theta of the transformeraAnd top layer oil temperature θtopTo input data, the hotspot temperature θ is takenhFor output data, the input layer and the output layer of the E L M model are:
x＝[K,θa,θtop](1)
y＝[θh](2)
wherein theta ishFor the hot spot temperature, K is the load factor (load current I/rated current I)N)、θaIs the ambient temperature, thetatopThe top oil temperature. The number n of input layer neurons is 3, and the number m of output layer neurons is 1.
(2) And (3) carrying out normalization processing on input and output data samples of the extreme learning machine according to a formula (3), processing each group of input and output data within an interval of [ -1,1], and then randomly generating a training set and a test set from the data samples.
Wherein x is data to be processed, xmaxAnd xminIs the maximum and minimum values of the set of data and y is the normalized result.
(301) As shown in FIG. 2, the neural network comprises an input layer, a hidden layer and an output layer, which are respectively composed of n, l and m neurons αijThe connection weight between the ith neuron of the input layer and the jth neuron of the hidden layer, βkjThe connection weight between the jth neuron of the hidden layer and the kth neuron of the output layer. Determining the hidden layer using Kolmogorov theorem, using SiThe gmoid function acts as an activation function.
The connection weights α between the input layer and the hidden layer are:
the connection weights β between the hidden layer and the input layer are:
let threshold η for hidden layer neurons be:
η＝[η1η2…ηl]T(6)
if the training set has P samples, the input matrix E and the output matrix O are respectively:
setting a hidden side activation function G (x), the output T of the neural network is:
T＝[t1t2…tP](9)
wherein j is 1, 2, …, Q, αi＝[αi1，αi2，…，αin]；ej＝[e1j，e2j，…，enj]T。
Formula (9) can be represented as:
Hβ＝TT(11)
in the formula, H is an output matrix of the hidden layer.
(302) Training and testing the divided sample data, optimizing the weight and the threshold of a limit learning algorithm, and constructing a transformer hot spot temperature E L M calculation model, forming a prediction sample set by 350 groups of temperature rise test data and operation data, randomly selecting 320 groups of samples from the prediction sample set as the training set, and using the rest 30 groups of samples as the test set, according to the training simulation method, obtaining a hot spot temperature prediction result diagram of the model E L M shown in figure 3, wherein the difference between the calculated value and the real value is within +/-4 ℃, the calculation value has better fitting degree, the selection of the limit learning machine prediction model is reasonable, and the established prediction model is effective.
(401) And comparing the prediction accuracy of the E L M model with that of a BP neural network and an Elman neural network.
(402) The waveforms of FIG. 4 are obtained through comparison, and FIG. 4 shows the accuracy of comparing three hot-spot temperature calculation models, and it can be seen more intuitively from FIG. 4 that the calculation error of the E L M model is obviously smaller and the accuracy is higher than that of the BP neural network and the Elman neural network.
(403) The prediction performance of the model is evaluated by using various error analysis indexes such as fitting degree, Sum of Square Error (SSE), Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Square Percentage Error (MSPE) and the like of a true value and a predicted value, and table 1 shows that the indexes of the three methods are compared, so that the indexes of the three methods, such as algorithm calculation time, fitting degree, calculation error and the like, have great advantages, and the prediction method of the extreme learning machine is higher than the prediction precision of a BP neural network and an Elman neural network.
TABLE 1 comparison of evaluation indexes of three methods
| Index (I) | ELM | BP | Elman |
| Run time/s | 0.02 | 2.25 | 0.66 |
| Degree of fitting | 0.998 | 0.985 | 0.978 |
| SSE | 59.22 | 327.85 | 474.47 |
| MSE | 1.97 | 10.93 | 15.82 |
| RMSE | 5.44 | 12.80 | 15.40 |
| MAPE | 0.013 | 0.022 | 0.032 |
| MSPE | 0.048 | 0.118 | 0.141 |
(501) And establishing a hot spot temperature E L M real-time prediction model shown in FIG. 5.
(502) The hot spot temperature of a certain SFPSZ-180000/220 type 220kV oil-immersed transformer is selected as a research object from 7, 25, 18:00 and 26 days to 6:00 in 2019, the sampling interval is 5min, 4h from 7, 25, 18:00 and 22:00 is taken as a training sample, hot spot temperature data of 1h is predicted, the training sample is updated in real time, and a predicted value of the hot spot temperature is finally obtained.
Claims (6)
1. A transformer hot spot temperature real-time prediction method based on an extreme learning machine is characterized by comprising the following steps:
a. determining the number of nodes of an input layer and an output layer by taking the load rate of the transformer, the ambient temperature and the top oil temperature as input data and taking the hot spot temperature as output data, and constructing an extreme learning model;
b. carrying out normalization processing on input and output data samples of the extreme learning machine;
c. optimizing the weight and the threshold of the extreme learning algorithm, and training an E L M hot spot temperature calculation model;
d. establishing a power load prediction model based on support vector regression as the pre-input of an E L M hot spot temperature calculation model, and constructing a hot spot temperature prediction model;
e. and inputting the operation data of the transformer at the current moment to obtain the prediction result of the hot spot temperature of the transformer at the next moment.
2. The method for predicting the temperature of the hot spot of the transformer in real time based on the extreme learning machine according to claim 1, wherein the method comprises the following steps: constructing an extreme learning model in the step a, as shown in the formula (1) and the formula (2), establishing that the number of nodes of an input layer is 3, the number of nodes of an output layer is 1,
whereinθ h Is the temperature of the hot spot or hot spots,Kis the load factor (load current)IRated currentI N ）、θ a Is at ambient temperature,θ top The top oil temperature.
3. The method for predicting the temperature of the hot spot of the transformer in real time based on the extreme learning machine according to claim 1, wherein the method comprises the following steps: in the step b, the historical data of the load current, the ambient temperature, the top layer oil temperature and the hot spot temperature of the transformer collected in the monitoring system are normalized according to the formula (3), each group of data is processed into the range of [ -1,1],
wherein the content of the first and second substances,xin order to be able to process the data,x maxandx minfor the maximum and minimum values of the set of data,yis the result after normalization.
4. The method for predicting the temperature of the hot spot of the transformer in real time based on the extreme learning machine according to claim 1, wherein the method comprises the following steps: in the step c, the operation data of the oil-immersed transformer is taken as a research object, and the environment temperature is takenθ a Top layer oil temperatureθ top Load factor ofKAnd (4) optimizing the weight and the threshold value of the model input value and the hotspot temperature of the transformer by using an extreme learning machine model to construct a transformer hotspot temperature E L M calculation model.
5. The method for predicting the temperature of the hot spot of the transformer in real time based on the extreme learning machine according to claim 1, wherein the method comprises the following steps: in the step d, the electric load prediction model based on support vector regression is specifically a short-term load prediction model in which the temperature, humidity, weather type, seasonal type, holiday at the previous time, the load value at the same time in the previous day are used as input quantities, and the load value at the next time is used as an output quantity.
6. The method for predicting the temperature of the hot spot of the transformer in real time based on the extreme learning machine according to claim 1, wherein the method comprises the following steps: in the step e, the hot spot temperature of the transformer at the current moment, the top layer oil temperature, the environment temperature and the load value at the next moment are used as input quantities, and the hot spot temperature at the next moment is used as a hot spot temperature prediction model of the output quantity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010253526.6A CN111461922B (en) | 2020-04-02 | 2020-04-02 | Real-time prediction method for hot spot temperature of transformer based on extreme learning machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010253526.6A CN111461922B (en) | 2020-04-02 | 2020-04-02 | Real-time prediction method for hot spot temperature of transformer based on extreme learning machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111461922A true CN111461922A (en) | 2020-07-28 |
| CN111461922B CN111461922B (en) | 2023-04-21 |
Family
ID=71678672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010253526.6A Active CN111461922B (en) | 2020-04-02 | 2020-04-02 | Real-time prediction method for hot spot temperature of transformer based on extreme learning machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461922B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111947795A (en) * | 2020-08-18 | 2020-11-17 | 广东电网有限责任公司广州供电局 | Transformer overheating early warning method |
| CN112115648A (en) * | 2020-09-23 | 2020-12-22 | 贵州电网有限责任公司 | Transformer top layer oil temperature prediction method based on improved deep learning method |
| CN112163377A (en) * | 2020-10-13 | 2021-01-01 | 北京智芯微电子科技有限公司 | Method and device for acquiring transformer temperature early warning model and temperature prediction method |
| CN112308169A (en) * | 2020-11-10 | 2021-02-02 | 浙江大学 | Effluent quality prediction method based on improved online sequence extreme learning machine |
| 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 |
| CN115238754A (en) * | 2022-09-21 | 2022-10-25 | 国网江西省电力有限公司电力科学研究院 | Power transformer short-term operation temperature prediction method based on multivariate perception |
| CN116108760A (en) * | 2023-04-12 | 2023-05-12 | 广东电网有限责任公司佛山供电局 | Main heating characteristic monitoring method and system |
| CN116413541A (en) * | 2023-03-28 | 2023-07-11 | 国网山东省电力公司德州供电公司 | Transformer state sensing method based on digital twin and closed loop optimization |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106055888A (en) * | 2016-05-27 | 2016-10-26 | 国网上海市电力公司 | Predication method and device for top-oil temperature of transformer based on error predicting amendment |
| CN106126944A (en) * | 2016-06-28 | 2016-11-16 | 山东大学 | A kind of power transformer top-oil temperature interval prediction method and system |
| CN110598289A (en) * | 2019-08-30 | 2019-12-20 | 西安电子科技大学 | Antenna temperature field measurement method under incomplete information |
| US20210161394A1 (en) * | 2018-08-12 | 2021-06-03 | The Trustees Of Columbia University In The City Of New York | System, method, and computer-accessible medium for non-invasive temperature estimation |
-
2020
- 2020-04-02 CN CN202010253526.6A patent/CN111461922B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106055888A (en) * | 2016-05-27 | 2016-10-26 | 国网上海市电力公司 | Predication method and device for top-oil temperature of transformer based on error predicting amendment |
| CN106126944A (en) * | 2016-06-28 | 2016-11-16 | 山东大学 | A kind of power transformer top-oil temperature interval prediction method and system |
| US20210161394A1 (en) * | 2018-08-12 | 2021-06-03 | The Trustees Of Columbia University In The City Of New York | System, method, and computer-accessible medium for non-invasive temperature estimation |
| CN110598289A (en) * | 2019-08-30 | 2019-12-20 | 西安电子科技大学 | Antenna temperature field measurement method under incomplete information |
Non-Patent Citations (1)
| Title |
|---|
| 王丰华，周翔，高 沛，郗晓光 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111947795A (en) * | 2020-08-18 | 2020-11-17 | 广东电网有限责任公司广州供电局 | Transformer overheating early warning method |
| CN112115648A (en) * | 2020-09-23 | 2020-12-22 | 贵州电网有限责任公司 | Transformer top layer oil temperature prediction method based on improved deep learning method |
| CN112115648B (en) * | 2020-09-23 | 2023-12-01 | 贵州电网有限责任公司 | Transformer top layer oil temperature prediction method based on improved deep learning method |
| CN112163377A (en) * | 2020-10-13 | 2021-01-01 | 北京智芯微电子科技有限公司 | Method and device for acquiring transformer temperature early warning model and temperature prediction method |
| CN112308169A (en) * | 2020-11-10 | 2021-02-02 | 浙江大学 | Effluent quality prediction method based on improved online sequence extreme learning machine |
| CN112308169B (en) * | 2020-11-10 | 2022-05-03 | 浙江大学 | Effluent quality prediction method based on improved online sequence extreme learning machine |
| 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 |
| CN115238754A (en) * | 2022-09-21 | 2022-10-25 | 国网江西省电力有限公司电力科学研究院 | Power transformer short-term operation temperature prediction method based on multivariate perception |
| CN115238754B (en) * | 2022-09-21 | 2023-02-14 | 国网江西省电力有限公司电力科学研究院 | Power transformer short-term operation temperature prediction method based on multivariate perception |
| CN116413541A (en) * | 2023-03-28 | 2023-07-11 | 国网山东省电力公司德州供电公司 | Transformer state sensing method based on digital twin and closed loop optimization |
| CN116108760A (en) * | 2023-04-12 | 2023-05-12 | 广东电网有限责任公司佛山供电局 | Main heating characteristic monitoring method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111461922B (en) | 2023-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111461922B (en) | Real-time prediction method for hot spot temperature of transformer based on extreme learning machine | |
| Nichiforov et al. | Energy consumption forecasting using ARIMA and neural network models | |
| CN110991786B (en) | 10kV static load model parameter identification method based on similar daily load curve | |
| CN107591844B (en) | Active power distribution network robust reconstruction method considering node injection power uncertainty | |
| CN108280552B (en) | Power load prediction method and system based on deep learning and storage medium | |
| CN111401657B (en) | Transformer hot spot temperature time sequence prediction method based on support vector regression algorithm | |
| CN111537938B (en) | Error short-time prediction method for electronic transformer based on intelligent algorithm | |
| CN109002781B (en) | Fault prediction method for energy storage converter | |
| CN108957304A (en) | Breaker current-carrying failure prediction method | |
| CN112163371A (en) | Transformer bushing state evaluation method | |
| CN109298225A (en) | A kind of voltage metric data abnormality automatic identification model and method | |
| CN111461921A (en) | Load modeling typical user database updating method based on machine learning | |
| CN106408016A (en) | Distribution network power outage time automatic identification model construction method | |
| CN111091223A (en) | Distribution transformer short-term load prediction method based on Internet of things intelligent sensing technology | |
| CN112307675B (en) | Neural network-based temperature-sensitive load separation identification method and system | |
| CN113887833A (en) | Distributed energy user side time-by-time load prediction method and system | |
| CN106228033B (en) | Three-core cable conductor temperature real-time computing technique based on RBF neural | |
| CN112541634A (en) | Top layer oil temperature prediction and false fire alarm discrimination method, device and storage medium | |
| CN111612227A (en) | Load prediction method based on K-means clustering and bat optimization neural network | |
| Tai et al. | Power prediction of photovoltaic power generation based on LSTM model with additive Attention mechanism | |
| CN115118015A (en) | Platform district power supply stability monitoring system based on fuse terminal | |
| CN110852628B (en) | Rural medium-long term load prediction method considering development mode influence | |
| Gong et al. | Distribution Network Load Forecasting Based on Improved BP Neural Network | |
| Lan et al. | A Short-term Load Forecasting Method of Distribution Network Based on Improved AlexNet-GRU Deep Learning Network | |
| CN112461390A (en) | Distributed comparison type temperature measurement module and method suitable for oil-immersed transformer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |