CN111680712B - Method, device and system for predicting oil temperature of transformer based on similar time in day - Google Patents
Method, device and system for predicting oil temperature of transformer based on similar time in day Download PDFInfo
- Publication number
- CN111680712B CN111680712B CN202010298787.XA CN202010298787A CN111680712B CN 111680712 B CN111680712 B CN 111680712B CN 202010298787 A CN202010298787 A CN 202010298787A CN 111680712 B CN111680712 B CN 111680712B
- Authority
- CN
- China
- Prior art keywords
- moment
- similar
- day
- oil temperature
- nth
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N3/045—Combinations of 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
-
- 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
Abstract
The invention discloses a transformer oil temperature prediction method, device and system based on similar time in day, wherein the method comprises the steps of calculating similar days corresponding to the day to be predicted; calculating a similar time based on the calculated similar day; and based on the oil temperature data of the transformer in the similar moment, completing the oil temperature prediction of the transformer. According to the method, the similar time corresponding to each time of the day to be predicted is further selected in the similar day, and then the oil temperature of the transformer is predicted by utilizing the similar time, so that the prediction precision of the top oil temperature of the transformer can be effectively improved, a theoretical basis is provided for the insulation state evaluation of the transformer, potential internal hidden hazards can be found in time, the service life of the transformer is ensured, and the power supply reliability of a power grid is improved.
Description
Technical Field
The invention belongs to the technical field of transformers, and particularly relates to a transformer oil temperature prediction method, device and system based on similar moments in the day.
Background
In recent years, with the gradual construction of an ultra-high voltage power grid, the power grid scale is continuously enlarged, and a transformer is used as core equipment of a power system and has wide application in the field of power transmission and transformation of the power grid. According to the statistics of the related data, about 220kV and above transformers are available in 2.6 tens of thousands of places nationwide. The power transformer can not be judged by electric information such as voltage, current and the like because of occurrence of internal insulation faults when the power transformer runs under a high-voltage condition for a long time, and can only be judged by using physical information, such as dissolved gas components in oil or oil temperature, but the reliability of measuring the dissolved gas components in oil by the existing oil chromatography on-line monitoring device is not high, false alarms often occur, actual application is less on site, and the transformer station is mainly used for judging the internal faults of the transformer by on-line monitoring of oil temperature change by a background monitoring system at present. In fact, the insulation fault inside the transformer cannot be judged by a real-time oil temperature method in a short period, the judgment is often needed by means of future oil temperature change trend, if the fault can be found in advance at the initial stage of the fault, namely, the fault does not influence the operation of the transformer, and relevant measures are taken in time, so that the service life of the transformer can be prolonged, the unplanned power failure time can be shortened, the stability of a power system and the reliability of social power supply are ensured, and the prediction of the transformer oil temperature in advance becomes very significant.
The oil temperature of the power transformer is influenced by various factors such as weather conditions, social economy, tide load and the like, and has certain volatility and randomness, so that the oil temperature prediction accuracy is difficult to guarantee, analysis of the oil temperature change trend is not facilitated, and the real-time monitoring of the running state of the transformer is seriously influenced. In order to ensure safe and stable operation of the power system, accurate prediction of the oil temperature of the transformer becomes particularly important. In order to solve the problems, a transformer oil temperature prediction method with simple algorithm and high prediction accuracy is needed to be researched.
Disclosure of Invention
Aiming at the problems, the invention provides a transformer oil temperature prediction method, device and system based on similar time in the day, which further selects similar time corresponding to each time in the day to be predicted in the similar day, further predicts the transformer oil temperature by using the similar time, can effectively improve the prediction precision of the top oil temperature of the transformer, provides a theoretical basis for the insulation state evaluation of the transformer, can timely find potential hidden trouble in the transformer, ensures the service life of the transformer and improves the power supply reliability of the power grid.
The technical aim is achieved, and the technical effects are achieved by the following technical scheme:
in a first aspect, the invention provides a method for predicting the temperature of transformer oil based on similar moments in the day, which comprises the following steps:
calculating the similar days corresponding to the days to be predicted;
calculating a similar time based on the calculated similar day;
and based on the oil temperature data of the transformer in the similar moment, completing the oil temperature prediction of the transformer.
Optionally, the method for calculating the similar days includes:
determining a historical sample range;
classifying the historical samples based on meteorological factors;
and calculating the similar day corresponding to the day to be predicted based on the two classification results and the time factors.
Optionally, when determining that the range of the history sample is the history data of the first N days, the two classification is performed on the history sample, and specifically includes the following steps:
respectively taking the N day before the day to be predicted and the day to be predicted as an initial classification center CT ijk Wherein i represents a classification number, j represents a iteration number, and k represents a weather influencing factor;
according to the Euclidean distance, calculating the distance between each history sample and the initial classification center;
wherein T is nk Represents the kth weather influencing factor, k, on the nth day before the day to be predicted max Representing the number of weather influencing factors;
distributing the N historical samples to two initial classification centers according to the minimum Euclidean distance to form two new classifications and calculating the classification centers, wherein the expression of the new classification centers is as follows:
wherein N is ij Representing the number of sample days included after the ith classification has undergone the jth iteration;
iterating continuously to form new classifications until the square error sum function value is the minimum value, wherein the corresponding classification is the optimal classification, the classification of the day to be predicted is called a similar class, and the other classification is called a non-similar class; the expression of the error square sum function is as follows:
optionally, the calculating the similar day corresponding to the day to be predicted based on the two classification results and the time factor includes:
when the number of sample days in the similarity class is more than or equal to X days, selecting X sample days closest to the day to be predicted as similarity days;
when the number of sample days in the similar class is less than X days, all sample days in the similar class are taken as similar days.
Optionally, the method for calculating the similar time comprises the following steps:
determining weather factors related to the oil temperature of the transformer;
calculating the correlation degree between the meteorological factors at each moment and the transformer oil temperature;
and calculating the similar moment based on the calculated correlation degree and the set similar moment discrimination conditions.
Optionally, a calculation formula of the correlation degree between the meteorological factors and the transformer oil temperature at each moment is as follows:
R nm ＝RRW nm ×RRS nm ×RRF nm ×RRQ nm (4)
in RRW nm Showing the correlation between the transformer oil temperature at the nth moment and the temperature factor at the mth momentAn intermediate variable; RRS nm A related intermediate variable representing the transformer oil temperature at the nth moment and the humidity factor at the mth moment; RRF nm A related intermediate variable representing the transformer oil temperature at the nth moment and the wind speed factor at the mth moment; RRQ nm And the intermediate variable of the correlation degree between the transformer oil temperature at the nth moment and the air pressure factor at the mth moment is expressed.
Optionally, the similarity moment distinguishing condition is:
R nm ≥R nn (5)
wherein R is nm Representing the correlation degree between the transformer oil temperature at the nth moment and the meteorological factors at the mth moment, R nn The correlation degree between the transformer oil temperature at the nth moment and the meteorological factors at the nth moment is shown;
when the correlation degree of the transformer oil temperature at the nth moment and the weather factor at the mth moment is greater than or equal to the correlation degree of the transformer oil temperature at the nth moment and the weather factor at the nth moment, the mth moment is considered to be the similar moment at the nth moment.
Optionally, when the similar time of the nth time of the day to be predicted is the mth time, the number of similar times is B n When the oil temperature prediction method of the transformer comprises the following steps:
selecting a weather factor with the temperature correlation degree of transformer oil at the nth moment being greater than or equal to a set threshold value as a main weather factor variable;
taking main meteorological factor variables corresponding to the mth moment of each similar day as an input set of the neural network, taking the transformer oil temperature of the nth moment of each similar day as an output set, and training the neural network after reasonably setting the number of neuron layers, the number of single-layer neurons, a single-layer neuron transmission function, training parameters and a training function of the neural network;
inputting main meteorological factor variables corresponding to the mth moment of the day to be predicted into a trained neural network, wherein the output value of the neural network is a predicted value P of the transformer oil temperature at the mth moment of the day to be predicted based on the similar moment m nm ；
Number of similar moments B when the nth moment n When=1, the predicted value P of the transformer oil temperature at the nth time of the day to be predicted n ＝P nm The method comprises the steps of carrying out a first treatment on the surface of the Number of similar moments B when the nth moment n When the temperature of the transformer oil at the nth time of the day to be predicted is more than 1, the predicted value of the transformer oil temperature at the nth time of the day to be predicted is a predicted value P based on each similar time m nm The expression of which is as follows:
wherein R is nm And the correlation degree of the transformer oil temperature at the nth moment and the meteorological factors at the mth moment is shown.
In a second aspect, the present invention provides a transformer oil temperature prediction apparatus based on similar moments in the day, including:
the first calculation unit is used for calculating the similar day corresponding to the day to be predicted;
the second calculation unit is used for screening out similar moments based on the calculated similar days;
and the prediction unit is used for completing the oil temperature prediction of the transformer based on the oil temperature data of the transformer in the similar moment.
In a third aspect, the present invention provides a transformer oil temperature prediction system based on similar moments in the day, including: a storage medium and a processor;
the storage medium is used for storing instructions;
the processor is operative according to the instructions to perform the steps of the method according to any one of the first aspects.
The invention has the beneficial effects that:
according to the invention, on the basis of fully considering meteorological and time factors, the similar time is further selected in the similar day, so that the oil temperature of the transformer is predicted by using the similar time, the prediction precision is improved, and a theoretical basis is provided for the evaluation of the insulation state of the transformer and the maximum utilization of the capacity of the transformer. Meanwhile, whether the oil temperature of the transformer exceeds the limit temperature can be judged in time, a basis is provided for the development of related work of dispatching operation, and the power supply reliability of the system is ensured.
Furthermore, the method and the device select similar days based on the classification on the basis of fully considering meteorological and time factors, and ensure the effectiveness of similar day selection.
Furthermore, the method selects similar time based on the correlation between the meteorological factors and the transformer oil temperature, and ensures the effectiveness of the selection of the similar time.
Drawings
FIG. 1 is an overall flow chart of an algorithm of the transformer oil temperature prediction method of the invention;
FIG. 2 is a similar day selection flow chart of the method for predicting the oil temperature of the transformer of the invention;
FIG. 3 is a flow chart of similar time selection for the method of predicting the oil temperature of the transformer of the present invention;
fig. 4 is a flow chart of oil temperature prediction in the method for predicting the oil temperature of transformer oil according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The principle of application of the invention is described in detail below with reference to the accompanying drawings.
According to the invention, on the basis of fully considering meteorological and time factors, the similar time is further selected in the similar day, so that the oil temperature of the transformer is predicted by using the similar time, the prediction precision is improved, and a theoretical basis is provided for the evaluation of the insulation state of the transformer and the maximum utilization of the capacity of the transformer. Meanwhile, whether the oil temperature of the transformer exceeds the limit temperature can be judged in time, a basis is provided for the development of related work of dispatching operation, and the power supply reliability of the system is ensured.
Example 1
Fig. 1 is a flowchart of an overall transformer oil temperature prediction method based on similar time in day in an embodiment of the invention. The transformer oil temperature prediction method based on similar time in the day, provided by the embodiment of the invention, comprises the following steps of:
(1) Calculating the similar days corresponding to the days to be predicted;
in a specific implementation manner of the embodiment of the present invention, as shown in fig. 2, the step (1) specifically includes the following steps:
step 1.1: a historical sample range is determined.
Considering that when the selection range of the historical samples is large, weather factors are similar but the time correlation is low, and the effectiveness of similar day selection is affected; when the selection range of the historical samples is smaller, it is difficult to select the historical samples with higher correlation of the meteorological factors. In a specific application process, the day 30 before the day to be predicted can be selected as a history sample by combining the time change trend.
Step 1.2: the historical samples are classified into two categories based on meteorological factors.
The historical samples are classified into two classes based on meteorological factors, wherein 10 classes of meteorological factors such as daily maximum temperature, daily average temperature, daily minimum temperature, daily maximum humidity, daily average humidity, daily minimum humidity, daily average wind speed, daily average air pressure, daily rainfall and sunlight intensity are selected as classification factors, the historical samples are classified into two classes, the class of the day to be predicted is called a similar class, and the other class is called a non-similar class.
The following is a detailed description of a specific implementation, as shown in fig. 2:
(1) And according to the range of the historical sample selected by the day to be predicted, carrying out normalization processing on 10 weather factors such as the corresponding day maximum temperature, the day average temperature and the like, setting the classification number as 2, and setting the iteration number as R.
(2) Selecting day 30 before and day 30 as initial classification center CT ijk Where i represents the number of classifications, j represents the number of iterations, and k represents the weather-influencing factor.
(3) According to Euclidean distance, calculating the distance between each history sample and the initial classification center:
wherein T is nk Representing the kth influencing factor on the nth day before the day to be predicted.
(4) The 30 historical samples are distributed to two initial classification centers according to the minimum Euclidean distance to form two new classifications and calculate the classification centers, and the expression of the new classification centers is:
wherein N is ij Representing the number of sample days included after the jth iteration of the ith class.
(5) Iterating continuously to form new classifications until the square error sum function value is the minimum value, wherein the corresponding classification is the optimal classification, the classification of the day to be predicted is called a similar class, and the other classification is called a non-similar class; the expression of the error square sum function is as follows:
step 1.3: and calculating the similar day corresponding to the day to be predicted based on the two classification results and the time factors.
Considering weather factors only in the two classification, considering time factors, selecting similar days from the similar classes, and selecting X sample days closest to the day to be predicted as similar days when the number of the sample days in the similar classes is more than or equal to X (X can be 10 days); when the number of sample days in the similar class is less than X days, all sample days in the similar class are taken as similar days.
(2) Calculating a similar time based on the calculated similar day;
in a specific implementation manner of the embodiment of the present invention, as shown in fig. 3, the step (2) specifically includes the following steps:
step 2.1: determining weather factors related to the oil temperature of the transformer;
according to the correlation principle, when the correlation degree is more than or equal to 0.4, the correlation degree is more than medium; when the correlation is less than 0.4, weak correlation is indicated, so that only transformer oil is studied when analyzing the similar timeWeather factors with a correlation of temperature of 0.4 or more. Definition of RW nm Showing the correlation degree of transformer oil temperature at the nth moment and temperature factors at the mth moment, and RRW nm Intermediate variable representing the correlation between transformer oil temperature at the nth moment and temperature factor at the mth moment, when RW nm When not less than 0.4, RRW nm ＝RW nm When RW nm <0.4, RRW nm ＝1；RS nm Represents the correlation degree of transformer oil temperature at the nth moment and humidity factor at the mth moment, RRS nm Intermediate variable representing the correlation degree between transformer oil temperature at nth moment and humidity factor at mth moment, when RS nm RRS when not less than 0.4 nm ＝RS nm When RS nm <0.4, RRS nm ＝1；RF nm Represents the correlation degree of transformer oil temperature at the nth moment and wind speed factor at the mth moment, RRF nm Intermediate variable representing the correlation between transformer oil temperature at nth moment and wind speed factor at mth moment, when RF nm RRF when not less than 0.4 nm ＝RF nm When RF nm <0.4, RRF nm ＝1；RQ nm Represents the correlation degree of transformer oil temperature at the nth moment and air pressure factor at the mth moment, RRQ nm Intermediate variable representing the correlation between transformer oil temperature at nth moment and barometric factor at mth moment, when RQ nm RRQ when not less than 0.4 nm ＝RQ nm When RQ nm <0.4, RRQ nm ＝1。
Step 2.2: and calculating the correlation degree between the meteorological factors and the transformer oil temperature at each moment.
According to the selected meteorological factors, the correlation degree between the meteorological factors at a certain moment and the transformer oil temperature can be obtained:
R nm ＝RRW nm ×RRS nm ×RRF nm ×RRQ nm (4)
wherein R is nm And the correlation degree of the transformer oil temperature at the nth moment and the meteorological factors at the mth moment is shown.
Step 2.3: and calculating the similar moment based on the calculated correlation degree and the set similar moment discrimination conditions.
Defining the similar moment when the nth moment is considered to be the nth moment when the correlation degree of the transformer oil temperature at the nth moment and the meteorological factors at the mth moment is more than or equal to the correlation degree of the transformer oil temperature at the nth moment and the meteorological factors at the nth moment, wherein the specific discrimination conditions are as follows:
R nm ≥R nn (5)
wherein R is nm Representing the correlation degree between the transformer oil temperature at the nth moment and the meteorological factors at the mth moment, R nn And the correlation degree between the transformer oil temperature at the nth moment and the meteorological factors at the nth moment is shown.
(3) Based on the oil temperature data of the transformer in the similar moment, completing the oil temperature prediction of the transformer;
in a specific implementation manner of the embodiment of the present invention, the step (3) specifically includes:
because the day to be predicted generally has a plurality of similar days, and each time of the day to be predicted corresponds to a plurality of similar times, the BP neural network is adopted to predict the oil temperature of the transformer, the number of similar days of the day to be predicted is firstly determined as A, the number of similar times at the nth time is determined as the mth time, and the number of similar times is determined as B n As shown in fig. 4, the specific implementation process is as follows:
(1) And selecting factors with the temperature correlation degree of transformer oil at the nth moment being more than or equal to 0.4 from meteorological factors such as temperature, humidity, wind speed, air pressure and the like as main meteorological factor variables.
(2) Taking main meteorological factor variables corresponding to the mth moment of each similar day as an input set of the BP neural network, taking the transformer oil temperature of the nth moment of each similar day as an output set, and training the BP neural network after reasonably setting the neuron layer number, the single-layer neuron conveying function, the training parameters and the training function of the BP neural network.
(3) Inputting main meteorological factor variables corresponding to the mth moment of the day to be predicted into a trained BP neural network, wherein the output value of the neural network is a predicted value P of the transformer oil temperature at the mth moment of the day to be predicted based on the similar moment m nm 。
(4) Number of similar moments B when the nth moment n When=1, the predicted value P of the transformer oil temperature at the nth time of the day to be predicted n ＝P nm The method comprises the steps of carrying out a first treatment on the surface of the Number of similar moments B when the nth moment n >1, the predicted value of the transformer oil temperature at the nth time of the day to be predicted is a predicted value P based on each similar time m nm The expression of which is as follows:
wherein R is nm And the correlation degree of the transformer oil temperature at the nth moment and the meteorological factors at the mth moment is shown.
Example 2
Based on the same inventive concept as in embodiment 1, in the embodiment of the present invention, a transformer oil temperature prediction device based on similar time in day is provided, including:
the first calculation unit is used for calculating the similar day corresponding to the day to be predicted;
the second calculation unit is used for screening out similar moments based on the calculated similar days;
and the prediction unit is used for completing the oil temperature prediction of the transformer based on the oil temperature data of the transformer in the similar moment.
In a specific implementation manner of the embodiment of the present invention, when determining that the range of the history sample is the history data of the first N days, the two classification is performed on the history sample, and specifically includes the following steps:
respectively taking the N day before the day to be predicted and the day to be predicted as an initial classification center CT ijk Wherein i represents a classification number, j represents a iteration number, and k represents a weather influencing factor;
according to the Euclidean distance, calculating the distance between each history sample and the initial classification center;
wherein T is nk Represents the kth weather influencing factor, k, on the nth day before the day to be predicted max Representing the number of weather influencing factors;
distributing the N historical samples to two initial classification centers according to the minimum Euclidean distance to form two new classifications and calculating the classification centers, wherein the expression of the new classification centers is as follows:
wherein N is ij Representing the number of sample days included after the ith classification has undergone the jth iteration;
iterating continuously to form new classifications until the square error sum function value is the minimum value, wherein the corresponding classification is the optimal classification, the classification of the day to be predicted is called a similar class, and the other classification is called a non-similar class; the expression of the error square sum function is as follows:
in a specific implementation manner of the embodiment of the present invention, the calculating the similar day corresponding to the day to be predicted based on the two classification results and the time factor includes:
when the number of sample days in the similarity class is more than or equal to X days, selecting X sample days closest to the day to be predicted as similarity days;
when the number of sample days in the similar class is less than X days, all sample days in the similar class are taken as similar days.
In a specific implementation manner of the embodiment of the present invention, the method for calculating the similar time includes:
determining weather factors related to the oil temperature of the transformer;
calculating the correlation degree between the meteorological factors at each moment and the transformer oil temperature;
and calculating the similar moment based on the calculated correlation degree and the set similar moment discrimination conditions.
In a specific implementation manner of the embodiment of the invention, a calculation formula of the correlation degree between the meteorological factors and the transformer oil temperature at each moment is as follows:
R nm ＝RRW nm ×RRS nm ×RRF nm ×RRQ nm (4)
in RRW nm A related intermediate variable representing the temperature factor between the transformer oil temperature at the nth moment and the temperature factor at the mth moment; RRS nm A related intermediate variable representing the transformer oil temperature at the nth moment and the humidity factor at the mth moment; RRF nm A related intermediate variable representing the transformer oil temperature at the nth moment and the wind speed factor at the mth moment; RRQ nm And the intermediate variable of the correlation degree between the transformer oil temperature at the nth moment and the air pressure factor at the mth moment is expressed.
In a specific implementation manner of the embodiment of the present invention, the similar moment discrimination conditions are:
R nm ≥R nn (5)
wherein R is nm Representing the correlation degree between the transformer oil temperature at the nth moment and the meteorological factors at the mth moment, R nn The correlation degree between the transformer oil temperature at the nth moment and the meteorological factors at the nth moment is shown;
when the correlation degree of the transformer oil temperature at the nth moment and the weather factor at the mth moment is greater than or equal to the correlation degree of the transformer oil temperature at the nth moment and the weather factor at the nth moment, the mth moment is considered to be the similar moment at the nth moment.
In a specific implementation manner of the embodiment of the present invention, the similar time of the nth time of the day to be predicted is the mth time, and the number of similar times is B n When the oil temperature prediction method of the transformer comprises the following steps:
selecting a weather factor with the temperature correlation degree of transformer oil at the nth moment being greater than or equal to a set threshold value as a main weather factor variable;
taking main meteorological factor variables corresponding to the mth moment of each similar day as an input set of the neural network, taking the transformer oil temperature of the nth moment of each similar day as an output set, and training the neural network after reasonably setting the number of neuron layers, the number of single-layer neurons, a single-layer neuron transmission function, training parameters and a training function of the neural network;
corresponding the mth moment of the day to be predictedThe main meteorological factor variable of (2) is input into a trained neural network, and the output value of the neural network is the predicted value P of the transformer oil temperature at the nth time of the day to be predicted based on the similar time m nm ；
Number of similar moments B when the nth moment n When=1, the predicted value P of the transformer oil temperature at the nth time of the day to be predicted n ＝P nm The method comprises the steps of carrying out a first treatment on the surface of the Number of similar moments B when the nth moment n >1, the predicted value of the transformer oil temperature at the nth time of the day to be predicted is a predicted value P based on each similar time m nm The expression of which is as follows:
and the correlation degree of the transformer oil temperature at the nth moment and the weather factor at the mth moment is shown.
Example 3
Based on the same inventive concept as in embodiment 1, in the embodiment of the present invention, a transformer oil temperature prediction system based on similar time in day is provided, including: a storage medium and a processor;
the storage medium is used for storing instructions;
the processor is operative according to the instructions to perform the steps of the method of any one of embodiment 1.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the claims, which are all within the protection of the present invention.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (4)
1. The method for predicting the oil temperature of the transformer based on the similar time in the day is characterized by comprising the following steps of:
calculating the similar days corresponding to the days to be predicted;
calculating a similar time based on the calculated similar day;
based on the oil temperature data of the transformer in the similar moment, completing the oil temperature prediction of the transformer;
the method for calculating the similar days comprises the following steps:
determining a historical sample range;
classifying the historical samples based on meteorological factors;
calculating a similar day corresponding to the day to be predicted based on the two classification results and the time factors;
when the range of the history sample is determined to be the history data of the previous N days, the history sample is classified into two categories, which specifically comprises the following steps:
respectively taking the N day before the day to be predicted and the day to be predicted as an initial classification center CT ijk Wherein i represents a classification number, j represents a iteration number, and k represents a weather influencing factor;
according to the Euclidean distance, calculating the distance between each history sample and the initial classification center;
wherein T is nk Represents the kth weather influencing factor, k, on the nth day before the day to be predicted max Representing the number of weather influencing factors; distributing the N historical samples to two initial classification centers according to the minimum Euclidean distance to form two new classifications and calculating the classification centers, wherein the expression of the new classification centers is as follows:
wherein N is ij Representing the number of sample days included after the ith classification has undergone the jth iteration;
iterating continuously to form new classifications until the square error sum function value is the minimum value, wherein the corresponding classification is the optimal classification, the classification of the day to be predicted is called a similar class, and the other classification is called a non-similar class; the expression of the error square sum function is as follows:
the method for calculating the similar time comprises the following steps:
determining weather factors related to the oil temperature of the transformer;
calculating the correlation degree between the meteorological factors at each moment and the transformer oil temperature;
calculating a similar moment based on the calculated correlation degree and a set similar moment discrimination condition;
the calculation formula of the correlation degree between the meteorological factors and the transformer oil temperature at each moment is as follows:
R nm ＝RRW nm ×RRS nm ×RRF nm ×RRQ nm (4)
in RRW nm A related intermediate variable representing the temperature factor between the transformer oil temperature at the nth moment and the temperature factor at the mth moment; RRS nm A related intermediate variable representing the transformer oil temperature at the nth moment and the humidity factor at the mth moment; RRF nm A related intermediate variable representing the transformer oil temperature at the nth moment and the wind speed factor at the mth moment; RRQ nm A related intermediate variable representing the transformer oil temperature at the nth moment and the air pressure factor at the mth moment;
the similar moment discrimination conditions are as follows:
R nm ≥R nn (5)
wherein R is nm Representing the correlation degree between the transformer oil temperature at the nth moment and the meteorological factors at the mth moment, R nn The correlation degree between the transformer oil temperature at the nth moment and the meteorological factors at the nth moment is shown;
when the correlation degree of the transformer oil temperature at the nth moment and the weather factor at the mth moment is greater than or equal to the correlation degree of the transformer oil temperature at the nth moment and the weather factor at the nth moment, the mth moment is considered to be the similar moment at the nth moment;
when the similar time of the nth time of the day to be predicted is the mth time, the number of the similar times is B n When the oil temperature prediction method of the transformer comprises the following steps:
selecting a weather factor with the temperature correlation degree of transformer oil at the nth moment being greater than or equal to a set threshold value as a main weather factor variable;
taking main meteorological factor variables corresponding to the mth moment of each similar day as an input set of the neural network, taking the transformer oil temperature of the nth moment of each similar day as an output set, and training the neural network after reasonably setting the number of neuron layers, the number of single-layer neurons, a single-layer neuron transmission function, training parameters and a training function of the neural network;
inputting main meteorological factor variables corresponding to the mth moment of the day to be predicted into a trained neural network, wherein the output value of the neural network is a predicted value P of the transformer oil temperature at the mth moment of the day to be predicted based on the similar moment m nm ；
Number of similar moments B when the nth moment n When=1, the predicted value P of the transformer oil temperature at the nth time of the day to be predicted n ＝P nm ；
Number of similar moments B when the nth moment n When the temperature of the transformer oil at the nth time of the day to be predicted is more than 1, the predicted value of the transformer oil temperature at the nth time of the day to be predicted is a predicted value P based on each similar time m nm The expression of which is as follows:
wherein R is nm And the correlation degree of the transformer oil temperature at the nth moment and the meteorological factors at the mth moment is shown.
2. The method for predicting the oil temperature of transformer based on similar time in day according to claim 1, wherein,
the calculating the similar day corresponding to the day to be predicted based on the two classification results and the time factor comprises the following steps:
when the number of sample days in the similarity class is more than or equal to X days, selecting X sample days closest to the day to be predicted as similarity days;
when the number of sample days in the similar class is less than X days, all sample days in the similar class are taken as similar days.
3. Transformer oil temperature prediction device based on similar moment in day, characterized by comprising:
the first calculation unit is used for calculating the similar day corresponding to the day to be predicted;
the second calculation unit is used for screening out similar moments based on the calculated similar days;
the prediction unit is used for completing the prediction of the oil temperature of the transformer based on the oil temperature data of the transformer in the similar moment;
the method for calculating the similar days comprises the following steps:
determining a historical sample range;
classifying the historical samples based on meteorological factors;
calculating a similar day corresponding to the day to be predicted based on the two classification results and the time factors;
when the range of the history sample is determined to be the history data of the previous N days, the history sample is classified into two categories, which specifically comprises the following steps:
respectively taking the N day before the day to be predicted and the day to be predicted as an initial classification center CT ijk Wherein i represents a classification number, j represents a iteration number, and k represents a weather influencing factor;
according to the Euclidean distance, calculating the distance between each history sample and the initial classification center;
wherein T is nk Represents the kth weather influencing factor, k, on the nth day before the day to be predicted max Representing the number of weather influencing factors; distributing the N historical samples to two initial classification centers according to the minimum Euclidean distance to form two new classifications and calculating the classification centers, wherein the expression of the new classification centers is as follows:
wherein N is ij Representing the number of sample days included after the ith classification has undergone the jth iteration;
iterating continuously to form new classifications until the square error sum function value is the minimum value, wherein the corresponding classification is the optimal classification, the classification of the day to be predicted is called a similar class, and the other classification is called a non-similar class; the expression of the error square sum function is as follows:
the method for calculating the similar time comprises the following steps:
determining weather factors related to the oil temperature of the transformer;
calculating the correlation degree between the meteorological factors at each moment and the transformer oil temperature;
calculating a similar moment based on the calculated correlation degree and a set similar moment discrimination condition;
the calculation formula of the correlation degree between the meteorological factors and the transformer oil temperature at each moment is as follows:
R nm ＝RRW nm ×RRS nm ×RRF nm ×RRQ nm (4)
in RRW nm A related intermediate variable representing the temperature factor between the transformer oil temperature at the nth moment and the temperature factor at the mth moment; RRS nm A related intermediate variable representing the transformer oil temperature at the nth moment and the humidity factor at the mth moment; RRF nm A related intermediate variable representing the transformer oil temperature at the nth moment and the wind speed factor at the mth moment; RRQ nm A related intermediate variable representing the transformer oil temperature at the nth moment and the air pressure factor at the mth moment;
the similar moment discrimination conditions are as follows:
R nm ≥R nn (5)
wherein R is nm Representing the correlation degree between the transformer oil temperature at the nth moment and the meteorological factors at the mth moment, R nn The correlation degree between the transformer oil temperature at the nth moment and the meteorological factors at the nth moment is shown;
when the correlation degree of the transformer oil temperature at the nth moment and the weather factor at the mth moment is greater than or equal to the correlation degree of the transformer oil temperature at the nth moment and the weather factor at the nth moment, the mth moment is considered to be the similar moment at the nth moment;
when the similar time of the nth time of the day to be predicted is the mth time, the number of the similar times is B n When the oil temperature prediction method of the transformer comprises the following steps:
selecting a weather factor with the temperature correlation degree of transformer oil at the nth moment being greater than or equal to a set threshold value as a main weather factor variable;
taking main meteorological factor variables corresponding to the mth moment of each similar day as an input set of the neural network, taking the transformer oil temperature of the nth moment of each similar day as an output set, and training the neural network after reasonably setting the number of neuron layers, the number of single-layer neurons, a single-layer neuron transmission function, training parameters and a training function of the neural network;
inputting main meteorological factor variables corresponding to the mth moment of the day to be predicted into a trained neural network, wherein the output value of the neural network is a predicted value P of the transformer oil temperature at the mth moment of the day to be predicted based on the similar moment m nm ；
Number of similar moments B when the nth moment n When=1, the transformer is at the nth time of day to be predictedPredicted value P of oil temperature n ＝P nm The method comprises the steps of carrying out a first treatment on the surface of the Number of similar moments B when the nth moment n When the temperature of the transformer oil at the nth time of the day to be predicted is more than 1, the predicted value of the transformer oil temperature at the nth time of the day to be predicted is a predicted value P based on each similar time m nm The expression of which is as follows:
wherein R is nm And the correlation degree of the transformer oil temperature at the nth moment and the meteorological factors at the mth moment is shown.
4. Transformer oil temperature prediction system based on similar moment in day, characterized by comprising: a storage medium and a processor;
the storage medium is used for storing instructions;
the processor being operative according to the instructions to perform the steps of the method according to any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010298787.XA CN111680712B (en) | 2020-04-16 | 2020-04-16 | Method, device and system for predicting oil temperature of transformer based on similar time in day |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010298787.XA CN111680712B (en) | 2020-04-16 | 2020-04-16 | Method, device and system for predicting oil temperature of transformer based on similar time in day |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111680712A CN111680712A (en) | 2020-09-18 |
| CN111680712B true CN111680712B (en) | 2023-06-06 |
Family
ID=72433318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010298787.XA Active CN111680712B (en) | 2020-04-16 | 2020-04-16 | Method, device and system for predicting oil temperature of transformer based on similar time in day |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111680712B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112347695B (en) * | 2020-10-29 | 2023-12-01 | 国网江苏省电力有限公司检修分公司 | Method and system for predicting top layer oil temperature of transformer |
| CN112529306B (en) * | 2020-12-16 | 2023-12-01 | 国网江苏省电力有限公司检修分公司 | Camera latent defect diagnosis method and device based on oil temperature estimation of oil system |
| CN112541634B (en) * | 2020-12-16 | 2024-03-15 | 国网江苏省电力有限公司检修分公司 | Method and device for predicting top-layer oil temperature and discriminating false alarm and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015172560A1 (en) * | 2014-05-16 | 2015-11-19 | 华南理工大学 | Central air conditioner cooling load prediction method based on bp neural network |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299057B (en) * | 2014-10-17 | 2018-02-13 | 国家电网公司 | Based on multifactor oil-filled transformer top-oil temperature Forecasting Methodology |
| CN108564192B (en) * | 2017-12-29 | 2021-06-08 | 河海大学 | Short-term photovoltaic power prediction method based on meteorological factor weight similarity day |
| CN110148068A (en) * | 2019-05-23 | 2019-08-20 | 福州大学 | One kind being based on meteorological data similarity analysis and LSTM neural fusion photovoltaic plant ultra-short term power forecasting method |
| CN110852492A (en) * | 2019-10-25 | 2020-02-28 | 东北电力大学 | Photovoltaic power ultra-short-term prediction method for finding similarity based on Mahalanobis distance |
-
2020
- 2020-04-16 CN CN202010298787.XA patent/CN111680712B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015172560A1 (en) * | 2014-05-16 | 2015-11-19 | 华南理工大学 | Central air conditioner cooling load prediction method based on bp neural network |
Non-Patent Citations (1)
| Title |
|---|
| L. Raeisian et al..Prediction of Oil Hotspot Temperature in a Distribution Transformer by CFD Method .《VDE》.2018,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111680712A (en) | 2020-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111680712B (en) | Method, device and system for predicting oil temperature of transformer based on similar time in day | |
| CN105117602B (en) | A kind of metering device running status method for early warning | |
| CN109583520B (en) | State evaluation method of cloud model and genetic algorithm optimization support vector machine | |
| CN108694470B (en) | Data prediction method and device based on artificial intelligence | |
| CN107274067B (en) | Distribution transformer overload risk assessment method | |
| CN111080072A (en) | Distribution transformer health index evaluation method, device and system | |
| US20230213895A1 (en) | Method for Predicting Benchmark Value of Unit Equipment Based on XGBoost Algorithm and System thereof | |
| CN111525587B (en) | Reactive load situation-based power grid reactive voltage control method and system | |
| CN112884008B (en) | Prediction evaluation method and device for running state of power information acquisition system | |
| CN113570200B (en) | Power grid running state monitoring method and system based on multidimensional information | |
| CN106896219A (en) | The identification of transformer sub-health state and average remaining lifetime method of estimation based on Gases Dissolved in Transformer Oil data | |
| CN115760484A (en) | Method, device and system for improving potential danger identification capability of power distribution station area and storage medium | |
| CN116737510B (en) | Data analysis-based intelligent keyboard monitoring method and system | |
| CN115796434A (en) | Management and control method and device for power distribution network, electronic equipment and storage medium | |
| CN115526258A (en) | Power system transient stability evaluation method based on Spearman correlation coefficient feature extraction | |
| CN111815039A (en) | Weekly scale wind power probability prediction method and system based on weather classification | |
| CN113689072B (en) | Marine wind turbine running state evaluation method based on Markov chain | |
| CN115358437A (en) | Power supply load prediction method based on convolutional neural network | |
| CN104866679A (en) | Mechanical characteristic prediction method of switching device | |
| CN112580254B (en) | Multi-dimensional analysis and early warning method for converter transformer based on multi-level decision fusion | |
| CN113033898A (en) | Electrical load prediction method and system based on K-means clustering and BI-LSTM neural network | |
| CN111585277A (en) | Power system dynamic security assessment method based on hybrid integration model | |
| CN114912854B (en) | Subway train operation adjusting method and device, electronic equipment and storage medium | |
| CN110781206A (en) | Method for predicting whether electric energy meter in operation fails or not by learning meter-dismantling and returning failure characteristic rule | |
| CN116151799A (en) | BP neural network-based distribution line multi-working-condition fault rate rapid assessment method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |