CN112347695B - Method and system for predicting top layer oil temperature of transformer - Google Patents
Method and system for predicting top layer oil temperature of transformer Download PDFInfo
- Publication number
- CN112347695B CN112347695B CN202011178764.1A CN202011178764A CN112347695B CN 112347695 B CN112347695 B CN 112347695B CN 202011178764 A CN202011178764 A CN 202011178764A CN 112347695 B CN112347695 B CN 112347695B
- Authority
- CN
- China
- Prior art keywords
- moment
- predicted
- transformer
- oil temperature
- time
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012706 support-vector machine Methods 0.000 claims abstract description 76
- 238000011160 research Methods 0.000 claims abstract description 27
- 238000012795 verification Methods 0.000 claims description 53
- 238000012549 training Methods 0.000 claims description 45
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 6
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 18
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Abstract
The application discloses a method and a system for predicting the top layer oil temperature of a transformer, wherein the method comprises the following steps: calculating the comprehensive correlation degree between each moment in the research sample and the moment to be predicted, and obtaining a similar moment set with the maximum comprehensive correlation degree with the moment to be predicted; determining optimal parameters of a support vector machine based on the research samples; and predicting the top-layer oil temperature of the transformer according to the size of the similar time set and the optimal parameters of the support vector machine. The method effectively improves the prediction precision of the top oil temperature of the transformer, can timely find potential hidden hazards in the transformer, ensures the service life of the transformer, and can provide a basis for judging abnormal sounds of the transformer by predicting the top oil temperature of the transformer.
Description
Technical Field
The application relates to a method and a system for predicting top layer oil temperature of a transformer, and belongs to the technical field of transformers.
Background
As core equipment of a power grid, the power transformer has wide application prospect in the power grid, and the working state of the power transformer influences the safe and stable operation of the power grid. In theory, the winding hot spot temperature of the power transformer is an important parameter for measuring the internal thermal state, but in view of the defects of difficult winding hot spot temperature measurement, high cost and the like, the top layer oil temperature is generally adopted to evaluate the thermal state of the power transformer at present. If the top oil temperature of the transformer can be predicted, the thermal state of the transformer can be estimated in advance, internal potential thermal faults can be found in time, the service life of the transformer is ensured, meanwhile, the power failure time is reduced, the power supply reliability of the whole society is ensured, and the prediction of the top oil temperature of the transformer is of practical significance.
At present, a great deal of researches are carried out at home and abroad aiming at the calculation and prediction of the hot spot temperature and the oil temperature of a transformer, and the hot spot temperature is summarized and mainly divided into three types of an empirical formula, a thermal circuit model and numerical calculation, wherein the empirical formula is to roughly estimate the hot spot temperature by utilizing the existing calculation formula and artificial experience, and the general error is larger; the thermal circuit model is a thermoelectric temperature calculation model established based on a thermal principle and a thermoelectric analogy method, and the calculation accuracy of the method is greatly influenced by model parameters; the numerical calculation is to establish internal temperature distribution of multi-physical fusion calculation through the research of the internal structure of the transformer and the heat dissipation medium, further estimate the hot spot temperature, and along with the improvement of the numerical simulation level, the calculation result of the method basically accords with the real thermal state of the transformer, but the method is more complex. In addition, as the artificial intelligence algorithm is continuously in depth in the field of transformers, part of researchers gradually apply the artificial intelligence algorithm to the prediction of the hot spot temperature and the oil temperature of the transformer, but the algorithm is difficult to realize. In order to solve the above problems, it is needed to study a method for predicting the top-layer oil temperature of a transformer with simple algorithm and high prediction accuracy.
Disclosure of Invention
The application aims to overcome the defects in the prior art and provides a method and a system for predicting the top-layer oil temperature of a transformer, which can effectively improve the prediction precision of the top-layer oil temperature of the transformer. In order to achieve the above purpose, the application is realized by adopting the following technical scheme:
in a first aspect, the present application provides a method for predicting the top-layer oil temperature of a transformer, the method comprising the steps of:
calculating the comprehensive correlation degree between each moment in the research sample and the moment to be predicted, and obtaining a similar moment set with the maximum comprehensive correlation degree with the moment to be predicted;
determining optimal parameters of a support vector machine based on the research samples;
and predicting the top-layer oil temperature of the transformer according to the size of the similar time set and the optimal parameters of the support vector machine.
With reference to the first aspect, further, the calculating the comprehensive correlation between each time in the study sample and the time to be predicted includes the following steps:
calculating the direct correlation coefficient of each influence factor of the top layer oil temperature of the transformer;
according to the calculated direct correlation coefficient, calculating weather correlation, time correlation and load correlation between each moment and the moment to be predicted in the research sample;
and carrying out linear weighting based on the weather correlation, the time correlation and the load correlation to obtain the comprehensive correlation between each moment in the research sample and the moment to be predicted.
In combination with the first aspect, further, the influencing factors of the top-layer oil temperature of the transformer comprise three factors including weather, time and load, wherein the weather factors comprise temperature, humidity, wind speed, air pressure, rainfall and illumination intensity, and the time factors comprise transverse date and longitudinal time.
In combination with the first aspect, further, the values of the influence factors are normalized to obtain values convenient for subsequent calculation:
in the formula (1), xg ij Represents the g-th influencing factor at the j-th moment of the i-th day before the moment to be predicted, C x The normalized coefficient is represented, and the value range is 0.01 to 0.45.
With reference to the first aspect, further, a direct correlation coefficient of each influence factor of the top oil temperature of the transformer is calculated, where the direct correlation coefficient is:
in the formula (2), R g Represents the direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer, RH g The transverse direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is shown:
in the formula (3), bh g Represents the lateral partial regression coefficient, M represents the number of samples, xg ij Represents the g-th influencing factor at the j-th moment of the i-th day before the moment to be predicted, Y ij The top layer oil temperature of the transformer at the j-th moment of the i-th day before the moment to be predicted is represented;
in formula (2), RZ g The longitudinal direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is shown:
in formula (4), bz g Representing longitudinal partial regression coefficients;
in the formula (2), R 7 Representing the direct correlation coefficient of the transverse date and the oil temperature of the top layer of the transformer, RH 7 A transverse direct correlation coefficient of a transverse date and the oil temperature of the top layer of the transformer is represented; r is R 8 Representing the direct correlation coefficient of the longitudinal moment and the oil temperature of the top layer of the transformer, RH 8 And the longitudinal direct correlation coefficient of the longitudinal moment and the temperature of the top layer oil of the transformer is shown.
With reference to the first aspect, further, the integrated correlation degree is:
in the formula (5), D lij Representing the comprehensive correlation degree between the moment to be predicted l and the moment (j) of the ith day before the moment to be predicted R g The direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is represented, R 9 A represents the direct correlation coefficient of the load factor and the top layer oil temperature of the transformer lij The weather correlation between the time l to be predicted and the time j of the i day before the time l to be predicted is shown:
in formula (6), MD lij Euclidean distance representing meteorological factors between time l to be predicted and time j on day i before the time l to be predicted:
in the formula (7), xg 0l Representing the g-th influencing factor corresponding to the moment to be predicted, xg ij The g-th influencing factor of the j-th moment of the i-th day before the moment to be predicted is represented;
in formula (6), MD max Maximum Euclidean distance representing meteorological factors:
in the formula (8), C x Represents normalized coefficient, the value range is 0.01-0.45, MDT g The intermediate value of the Euclidean distance corresponding to the g-th influencing factor is represented:
in the formula (5), B lij The time correlation degree between the time l to be predicted and the time j of the ith day before the time l to be predicted is shown:
in the formula (10), R 7 Representing the direct correlation coefficient of the transverse date and the oil temperature of the top layer of the transformer, R 8 X7, a direct correlation coefficient between the longitudinal time and the top layer oil temperature of the transformer 0l Represents the lateral date corresponding to the moment to be predicted i,
X7 il represents the lateral date, MDT, at the j-th day before the instant to be predicted 7 Representing lateral date correspondenceIntermediate value of Euclidean distance, X8 0l Represents the longitudinal time corresponding to the time to be predicted l, X8 il MDT representing the longitudinal time of the j-th day before the time to be predicted 8 Representing the Euclidean distance intermediate quantity corresponding to the longitudinal moment;
in the formula (5), C lij The load correlation degree between the time l to be predicted and the time j of the ith day before the time l to be predicted is represented:
in the formula (11), X9 0l Representing the load factor corresponding to the moment to be predicted, X9 ij Load factors representing the j-th moment of the i-th day before the moment to be predicted, MDT 9 And representing the Euclidean distance intermediate quantity corresponding to the load factor.
With reference to the first aspect, further, the step of obtaining the similar time set with the greatest comprehensive correlation with the time to be predicted from the study sample includes the following steps:
setting a comprehensive correlation threshold value D 0 ；
Judging the comprehensive relativity limit value D 0 And comprehensive relativity D lij Is a numerical value of (1):
when D is lij ≥D 0 The ith and jth moments before the moment to be predicted are potential similar moments of the moment to be predicted l; when D is lij <D 0 When the potential similar time of the moment l to be predicted is not the moment j of the ith day before the moment l to be predicted;
counting the number E of potential similar moments;
selecting a set of similar moments of the moments to be predicted:
when E is more than or equal to 20, selecting the comprehensive relativity D lij The maximum 20 potential similar moments are used as a similar moment set of the moment to be predicted l; when E is<When E is more than or equal to 10 and 20, selecting the comprehensive relativity D lij The maximum 10 potential similar moments are used as a similar moment set of the moment to be predicted l; e (E)<And 10, selecting all potential similar moments as a similar moment set of the moment to be predicted l.
With reference to the first aspect, further including determining a main influencing factor of the top layer oil temperature of the transformer, including:
selecting the minimum value R of the direct correlation coefficient between each influencing factor and the top oil temperature of the transformer 0 ；
Determining the direct correlation coefficient R of each influence factor g And R is R 0 Is of the size of (2):
in the formula (12), R g The direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is represented, R 0 And (3) representing.
With reference to the first aspect, further, the determining the optimal parameters of the support vector machine according to the set of similar moments includes the following steps:
determining main influencing factors of the top layer oil temperature of the transformer;
the research sample is divided into a training sample and a verification sample;
calculating similar moments of each moment of the verification sample from the training sample to obtain a verification sample similar moment set;
taking main influencing factors of all moments in the verification sample similarity moment set as training input variables of the support vector machine, and taking the top layer oil temperature of the transformer corresponding to all moments in the verification sample similarity moment set as training output variables of the support vector machine;
initializing and setting related parameters of a support vector machine, wherein the related parameters comprise a kernel function ker, kernel parameters p1 and p2, a parameter C and a Loss function Loss;
importing the constructed input training vector and output training vector into a support vector machine, and training the support vector machine to obtain a support vector machine with training completed;
taking main influencing factors at all moments in the verification sample as verification input variables, inputting the verification input variables into a support vector machine after training is completed, and obtaining verification values of the top layer oil temperature of the transformer at all moments in the verification sample;
establishing a parameter evaluation function based on error square sum:
in the formula (13), Y1 j Represents the verification value at the j-th moment obtained by the support vector machine, Y0 j Representing the actual value at the j-th moment;
when the parameter evaluation function obtains the minimum value, the relevant parameter of the support vector machine is the optimal parameter of the support vector machine, otherwise, the kernel function ker, the kernel parameters p1 and p2, the parameter C and the Loss function Loss of the support vector machine are updated, and the support vector machine is retrained until the parameter evaluation function obtains the minimum value;
and outputting optimal parameters of the support vector machine to obtain the prediction support vector machine capable of being used for predicting the top-layer oil temperature of the transformer.
Specifically, the study samples are divided into training samples and verification samples according to the time sequence, wherein the time sequence is the first training sample, and the time sequence is the later verification sample.
Specifically, the training sample includes a verification sample similar to the main influencing factors and the corresponding transformer top layer oil temperature at the corresponding moments in the training sample, and the verification sample includes a verification sample similar to the main influencing factors and the corresponding transformer top layer oil temperature at the moments in the training sample.
With reference to the first aspect, further, the predicting the top-layer oil temperature of the transformer includes:
the method for predicting the top-layer oil temperature of the transformer is selected according to the quantity of the similar moments in the similar moment set:
when the number of similar moments in the similar moment set is less than or equal to 10, adopting a linear weighting algorithm to process the top-layer oil temperature of the transformer corresponding to each moment in the similar moment set, and obtaining a predicted value of the top-layer oil temperature of the transformer;
when the number of similar moments in the similar moment set=20, predicting the top-layer oil temperature of the transformer by using a predictive support vector machine, and obtaining a predicted value of the top-layer oil temperature of the transformer.
With reference to the first aspect, further, the linear weighting algorithm is:
according to the comprehensive correlation degree of each similar time and the time to be predicted in the similar time set, different weight coefficients p are configured for each similar time x And 0 < p x ＜1；
Calculating a predicted value of the top layer oil temperature of the transformer:
in the formula (14), Y represents a predicted value of the top layer oil temperature of the transformer; y0 x And the actual value of the top layer oil temperature of the transformer at the x-th similar moment is shown.
In a second aspect, the present application provides a system for predicting a top-layer oil temperature of a transformer, including:
a first calculation module: the method comprises the steps of calculating the comprehensive correlation degree between each moment in a research sample and the moment to be predicted, and obtaining a similar moment set with the maximum comprehensive correlation degree with the moment to be predicted;
an optimal parameter determining module: the optimal parameters are used for determining the support vector machine;
the top layer oil temperature prediction module of the transformer: the method is used for predicting the top-layer oil temperature of the transformer according to the size of the similar time set and the optimal parameters of the support vector machine.
Compared with the prior art, the method and the system for predicting the top-layer oil temperature of the transformer provided by the embodiment of the application have the beneficial effects that:
according to the method, the comprehensive correlation degree between each moment in the research sample and the moment to be predicted is calculated, a similar moment set with the maximum comprehensive correlation degree with the moment to be predicted is obtained, the effectiveness of similar moment selection can be ensured, and the precision of predicting the top-layer oil temperature of the transformer can be improved;
according to the method, the direct correlation coefficient of each influence factor of the top layer oil temperature of the transformer is calculated from the two aspects of the transverse direct correlation coefficient and the longitudinal direct correlation coefficient, so that the interaction among the influence factors of the top layer oil temperature of the transformer is eliminated;
the application can accurately predict the top oil temperature of the transformer, can timely find potential hidden trouble in the transformer, ensures the service life of the transformer, and can provide basis for judging abnormal sounds of the transformer by predicting the top oil temperature of the transformer.
Drawings
Fig. 1 is a flowchart of a method for predicting the top-layer oil temperature of a transformer according to the present application.
Detailed Description
The application is further described below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present application, and are not intended to limit the scope of the present application.
Embodiment one:
as shown in fig. 1, the embodiment of the application provides a method for predicting the top layer oil temperature of a transformer, which comprises the following steps:
step 1: and calculating the direct correlation coefficient between each influencing factor and the top layer oil temperature of the transformer.
Step 1.1: selecting influencing factors of the top layer oil temperature of the transformer:
the influence factors of the top-layer oil temperature of the transformer comprise three factors including weather, humidity, wind speed, air pressure, rainfall and illumination intensity, time and load, and the time factors comprise transverse date and longitudinal time. Specifically, define X1 ij X2 is the temperature at the j-th time of the i-th day before the time to be predicted ij X3 for humidity at the j-th day before the time to be predicted ij X4 is the wind speed at the j-th moment of the i-th day before the moment to be predicted ij X5 is the air pressure at the j-th moment of the i-th day before the moment to be predicted ij For the rainfall at the j-th moment of the i-th day before the moment to be predicted, X6 ij X7 is the illumination intensity at the j-th day before the time to be predicted ij X8 for transverse date of the ith and jth moments before the moment to be predicted ij X9 is the longitudinal time of the ith day and the jth time before the time to be predicted ij For the ith and jth moments before the moment to be predicted, Y ij And the top layer oil temperature of the transformer is the jth moment of the ith day before the moment to be predicted.
Step 1.2: normalizing the values of all the influencing factors to obtain values convenient for subsequent calculation:
in the formula (1), xg ij Represents the g-th influencing factor at the j-th moment of the i-th day before the moment to be predicted, C x The normalized coefficient is represented, and the value range is 0.01 to 0.45.
Step 1.3: calculating the direct correlation coefficient of each influence factor of the top layer oil temperature of the transformer:
the direct correlation coefficient is:
in the formula (2), R g Represents the direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer, RH g The transverse direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is shown:
in the formula (3), bh g Represents the lateral partial regression coefficient, M represents the number of samples, xg ij Represents the g-th influencing factor at the j-th moment of the i-th day before the moment to be predicted, Y ij The top layer oil temperature of the transformer at the j-th moment of the i-th day before the moment to be predicted is represented;
in formula (2), RZ g The longitudinal direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is shown:
in formula (4), bz g Representing longitudinal partial regression coefficients;
in the formula (2), R 7 Representing the direct correlation coefficient of the transverse date and the oil temperature of the top layer of the transformer, RH 7 Representing transverseA transverse direct correlation coefficient of date and oil temperature of the top layer of the transformer; r is R 8 Representing the direct correlation coefficient of the longitudinal moment and the oil temperature of the top layer of the transformer, RH 8 And the longitudinal direct correlation coefficient of the longitudinal moment and the temperature of the top layer oil of the transformer is shown.
Step 2: and calculating the comprehensive correlation degree between each moment in the research sample and the moment to be predicted.
Step 2.1: calculating weather correlation A between each moment and moment to be predicted lij 。
Because the 6 meteorological factors are normalized and the direct correlation coefficients of different meteorological factors are different, the Euclidean distance method based on the weighted optimization of the direct correlation coefficients is adopted when the meteorological correlation is researched.
Calculating Euclidean distance MD between time l to be predicted and weather factor at ith and jth days before the time to be predicted lij ：
In the formula (5), xg 0l Representing the g-th influencing factor corresponding to the moment to be predicted, xg ij Represents the g-th influencing factor at the j-th moment of the i-th day before the moment to be predicted, R g The direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is represented;
defining the maximum Euclidean distance MD of meteorological factors max ：
In formula (6), MDT g The intermediate value of the Euclidean distance corresponding to the g-th influencing factor is represented:
in the formula (7), C x The normalized coefficient is represented, and the value range is 0.01 to 0.45.
Minimum Euclidean distance MD taking weather factors into consideration min If the value is 0, the weather correlation A between the time l to be predicted and the time j of the i day before the time l to be predicted can be obtained according to the Euclidean distance lij ：
Step 2.2: calculating the time correlation degree B between each moment and the moment to be predicted lij 。
According to the weather correlation calculation principle, the time correlation B between the time l to be predicted and the time j of the i day before the time to be predicted can be obtained in the same way lij ：
In the formula (9), R 7 Representing the direct correlation coefficient of the transverse date and the oil temperature of the top layer of the transformer, R 8 X7, a direct correlation coefficient between the longitudinal time and the top layer oil temperature of the transformer 0l Represents the transverse date corresponding to the time l to be predicted, X7 il Represents the lateral date, MDT, at the j-th day before the instant to be predicted 7 Represents the Euclidean distance intermediate quantity corresponding to the transverse date, X8 0l Represents the longitudinal time corresponding to the time to be predicted l, X8 il MDT representing the longitudinal time of the j-th day before the time to be predicted 8 The intermediate value of the euclidean distance corresponding to the longitudinal time is represented.
Step 2.3: calculating the comprehensive load correlation degree C of each moment and the moment to be predicted lij 。
According to the direct correlation coefficient of the load factor and the top oil temperature of the transformer, the load correlation degree C between the moment to be predicted I and the moment i and j before the moment to be predicted can be obtained lij ：
In the formula (10), X9 0l Representing the load factor corresponding to the moment to be predicted, X9 ij Load factors representing the j-th moment of the i-th day before the moment to be predicted, MDT 9 And representing the Euclidean distance intermediate quantity corresponding to the load factor.
Step 2.4: calculating the comprehensive correlation degree D between each moment and the moment to be predicted lij 。
Weighting the weather correlation, the time correlation and the load correlation based on the direct correlation coefficient to obtain the comprehensive correlation D between the time l to be predicted and the j time on the i day before the time to be predicted lij ：
In the formula (11), R 9 And the direct line pipe coefficient representing the load factor and the top layer oil temperature of the transformer.
Step 3: and obtaining a similar time set with the maximum comprehensive correlation degree with the time to be predicted from the research sample.
Step 3.1: setting a comprehensive correlation threshold value D 0 Judging the comprehensive relativity limit value D 0 And comprehensive relativity D lij Is a numerical value of (1):
when D is lij ≥D 0 The ith and jth moments before the moment to be predicted are potential similar moments of the moment to be predicted l; when D is lij <D 0 When the time to be predicted is not the potential similar time of the time to be predicted l, the i day and the j day before the time to be predicted is not the potential similar time of the time to be predicted l.
Step 3.2: and counting the number E of the potential similar moments.
Step 3.3: selecting a set of similar moments of the moments to be predicted:
when E is more than or equal to 20, selecting the comprehensive relativity D lij The maximum 20 potential similar moments are used as a similar moment set of the moment to be predicted l; when E is<When E is more than or equal to 10 and 20, selecting the comprehensive relativity D lij The maximum 10 potential similar moments are used as a similar moment set of the moment to be predicted l; e (E)<And 10, selecting all potential similar moments as a similar moment set of the moment to be predicted l.
Step 4: determining main influencing factors of the top layer oil temperature of the transformer:
selecting the minimum value R of the direct correlation coefficient between each influencing factor and the top oil temperature of the transformer 0 ；
Determining the direct correlation coefficient R of each influence factor g And R is R 0 Is of the size of (2):
in the formula (12), R g The direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is represented, R 0 And (3) representing.
Step 5: the method for determining the optimal parameters of the support vector machine according to the similar time set comprises the following steps:
step 5.1: the main influencing factors of the top layer oil temperature of the transformer are determined.
Step 5.2: from the study samples, training samples and validation samples are separated.
Step 5.3: calculating similar moments of each moment of the verification sample from the training sample to obtain a verification sample similar moment set;
step 5.4: taking main influencing factors of all moments in the verification sample similarity moment set as training input variables of the support vector machine, and taking the top layer oil temperature of the transformer corresponding to all moments in the verification sample similarity moment set as training output variables of the support vector machine;
step 5.5: initializing and setting related parameters of a support vector machine, wherein the related parameters comprise a kernel function ker, kernel parameters p1 and p2, a parameter C and a Loss function Loss;
step 5.6: importing the constructed input training vector and output training vector into a support vector machine, and training the support vector machine to obtain a support vector machine with training completed;
step 5.7: taking main influencing factors at all moments in the verification sample as verification input variables, inputting the verification input variables into a support vector machine after training is completed, and obtaining verification values of the top layer oil temperature of the transformer at all moments in the verification sample;
step 5.8: establishing a parameter evaluation function based on error square sum:
in the formula (13), Y1 j Represents the verification value at the j-th moment obtained by the support vector machine, Y0 j The actual value at the j-th time is shown.
Step 5.9: when the parameter evaluation function obtains the minimum value, the relevant parameter of the support vector machine is the optimal parameter of the support vector machine, otherwise, the kernel function ker, the kernel parameters p1 and p2, the parameter C and the Loss function Loss of the support vector machine are updated, and the support vector machine is retrained until the parameter evaluation function obtains the minimum value; and outputting optimal parameters of the support vector machine to obtain the prediction support vector machine capable of being used for predicting the top-layer oil temperature of the transformer.
The study samples are divided into training samples and verification samples according to the time sequence, wherein the training samples are the first time sequence, and the verification samples are the later time sequence. The training sample comprises main influencing factors and corresponding transformer top layer oil temperatures of the similar moment sets of the verification sample at corresponding moments in the training sample, and the verification sample comprises main influencing factors and corresponding transformer top layer oil temperatures of the corresponding moments in the verification sample.
Step 6: and predicting the top layer oil temperature of the transformer.
The method for predicting the top-layer oil temperature of the transformer is selected according to the quantity of the similar moments in the similar moment set:
when the number of similar moments in the similar moment set is less than or equal to 10, adopting a linear weighting algorithm to process the top-layer oil temperature of the transformer corresponding to each moment in the similar moment set, and obtaining a predicted value of the top-layer oil temperature of the transformer;
when the number of similar moments in the similar moment set=20, predicting the top-layer oil temperature of the transformer by using a predictive support vector machine, and obtaining a predicted value of the top-layer oil temperature of the transformer.
Specifically, a linear weighting algorithm is adopted to process the top-layer oil temperature of the transformer corresponding to each moment in the similar moment set, and a predicted value of the top-layer oil temperature of the transformer is obtained, and the method comprises the following steps:
according to the comprehensive correlation degree of each similar time and the time to be predicted in the similar time set, different weight coefficients p are configured for each similar time x And 0 < p x ＜1；
Calculating a predicted value of the top layer oil temperature of the transformer:
in the formula (14), Y represents a predicted value of the top layer oil temperature of the transformer; y0 x And the actual value of the top layer oil temperature of the transformer at the x-th similar moment is shown.
Embodiment two:
the embodiment of the application provides a prediction system for the top layer oil temperature of a transformer, which comprises the following steps:
a first calculation module: the method comprises the steps of calculating the comprehensive correlation degree between each moment in a research sample and the moment to be predicted, and obtaining a similar moment set with the maximum comprehensive correlation degree with the moment to be predicted;
an optimal parameter determining module: the optimal parameters are used for determining the support vector machine;
the top layer oil temperature prediction module of the transformer: the method is used for predicting the top-layer oil temperature of the transformer according to the size of the similar time set and the optimal parameters of the support vector machine.
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 foregoing is merely a preferred embodiment of the present application, and it should be noted that modifications and variations could be made by those skilled in the art without departing from the technical principles of the present application, and such modifications and variations should also be regarded as being within the scope of the application.
Claims (2)
1. The method for predicting the top-layer oil temperature of the transformer is characterized by comprising the following steps of:
calculating the comprehensive correlation degree between each moment in the research sample and the moment to be predicted, and obtaining a similar moment set with the maximum comprehensive correlation degree with the moment to be predicted; the method for calculating the comprehensive correlation degree between each moment in the research sample and the moment to be predicted comprises the following steps:
calculating the direct correlation coefficient of each influence factor of the top layer oil temperature of the transformer; the direct correlation coefficient is:
in the formula (1), R g Represents the direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer, RH g The transverse direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is shown:
in the formula (2), bh g Represents the lateral partial regression coefficient, M represents the number of samples, xg ij Represents the g-th influencing factor at the j-th moment of the i-th day before the moment to be predicted, Y ij The top layer oil temperature of the transformer at the j-th moment of the i-th day before the moment to be predicted is represented;
in formula (1), RZ g The longitudinal direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is shown:
in formula (3), bz g Representing longitudinal partial regression coefficients;
in the formula (1), R 7 Representing the direct correlation coefficient of the transverse date and the oil temperature of the top layer of the transformer, RH 7 A transverse direct correlation coefficient of a transverse date and the oil temperature of the top layer of the transformer is represented; r is R 8 Representing the direct correlation coefficient of the longitudinal moment and the oil temperature of the top layer of the transformer, RH 8 The longitudinal direct correlation coefficient between the longitudinal moment and the top layer oil temperature of the transformer is represented;
according to the calculated direct correlation coefficient, calculating weather correlation, time correlation and load correlation between each moment and the moment to be predicted in the research sample;
linear weighting is carried out based on the weather correlation, the time correlation and the load correlation, so that the comprehensive correlation between each moment in the research sample and the moment to be predicted is obtained; the comprehensive correlation degree is as follows:
in the formula (4), D lij Representing the comprehensive correlation degree between the moment to be predicted l and the moment (j) of the ith day before the moment to be predicted R g The direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is represented, R 9 A represents the direct correlation coefficient of the load factor and the top layer oil temperature of the transformer lij The weather correlation between the time l to be predicted and the time j of the i day before the time l to be predicted is shown:
in formula (5), MD lij Euclidean distance representing meteorological factors between time l to be predicted and time j on day i before the time l to be predicted:
in the formula (6), xg 0l Representing the g-th influencing factor corresponding to the moment to be predicted, xg ij The g-th influencing factor of the j-th moment of the i-th day before the moment to be predicted is represented;
in formula (5), MD max Maximum Euclidean distance representing meteorological factors:
in formula (7), MDT g The intermediate value of the Euclidean distance corresponding to the g-th influencing factor is represented:
in the formula (8), C x Representing the normalized coefficient, wherein the value range is 0.01-0.45;
in the formula (4), B lij The time correlation degree between the time l to be predicted and the time j of the ith day before the time l to be predicted is shown:
in the formula (9), R 7 Representing the direct correlation coefficient of the transverse date and the oil temperature of the top layer of the transformer, R 8 X7, a direct correlation coefficient between the longitudinal time and the top layer oil temperature of the transformer 0l Represents the transverse date corresponding to the time l to be predicted, X7 il Represents the lateral date, MDT, at the j-th day before the instant to be predicted 7 Represents the Euclidean distance intermediate quantity corresponding to the transverse date, X8 0l Represents the longitudinal time corresponding to the time to be predicted l, X8 il MDT representing the longitudinal time of the j-th day before the time to be predicted 8 Representing the Euclidean distance intermediate quantity corresponding to the longitudinal moment;
in the formula (4), C lij The load correlation degree between the time l to be predicted and the time j of the ith day before the time l to be predicted is represented:
in the formula (10), X9 0l Representing the load factor corresponding to the moment to be predicted, X9 il Load factors representing the j-th moment of the i-th day before the moment to be predicted, MDT 9 Representing the Euclidean distance intermediate quantity corresponding to the load factor;
the method for acquiring the similar time set with the maximum comprehensive correlation degree with the time to be predicted from the research sample comprises the following steps:
setting a comprehensive correlation threshold value D 0 ；
Judging the comprehensive relativity limit value D 0 And comprehensive relativity D lij Is a numerical value of (1):
when D is lij ≥D 0 The ith and jth moments before the moment to be predicted are potential similar moments of the moment to be predicted l; when D is lij <D 0 When the potential similar time of the moment l to be predicted is not the moment j of the ith day before the moment l to be predicted;
counting the number E of potential similar moments;
selecting a set of similar moments of the moments to be predicted:
when E is more than or equal to 20, selecting the comprehensive relativity D lij The maximum 20 potential similar moments are used as a similar moment set of the moment to be predicted l; when E is<When E is more than or equal to 10 and 20, selecting the comprehensive relativity D lij The maximum 10 potential similar moments are used as a similar moment set of the moment to be predicted l; e (E)<10, selecting all potential similar moments as a similar moment set of the moment to be predicted l;
determining optimal parameters of a support vector machine based on the research samples; also included is determining the primary influencing factors of the top layer oil temperature of the transformer, including:
selecting the minimum value R of the direct correlation coefficient between each influencing factor and the top oil temperature of the transformer 0 ；
Determining the direct correlation coefficient R of each influence factor g And R is R 0 Is of the size of (2):
in the formula (11), R g The direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is represented;
the method for determining the optimal parameters of the support vector machine based on the research samples comprises the following steps:
determining main influencing factors of the top layer oil temperature of the transformer;
separating a training sample and a verification sample from the study sample;
calculating similar moments of each moment of the verification sample from the training sample to obtain a verification sample similar moment set;
taking main influencing factors of all moments in the verification sample similarity moment set as training input variables of the support vector machine, and taking the top layer oil temperature of the transformer corresponding to all moments in the verification sample similarity moment set as training output variables of the support vector machine;
initializing and setting related parameters of a support vector machine, wherein the related parameters comprise a kernel function ker, kernel parameters p1 and p2, a parameter C and a Loss function Loss;
importing the constructed input training vector and output training vector into a support vector machine, and training the support vector machine to obtain a support vector machine with training completed;
taking main influencing factors at all moments in the verification sample as verification input variables, inputting the verification input variables into a support vector machine after training is completed, and obtaining verification values of the top layer oil temperature of the transformer at all moments in the verification sample;
establishing a parameter evaluation function based on error square sum:
in the formula (12), Y1 j Represents the verification value at the j-th moment obtained by the support vector machine, Y0 j Representing the actual value at the j-th moment;
when the parameter evaluation function obtains the minimum value, the relevant parameter of the support vector machine is the optimal parameter of the support vector machine, otherwise, the kernel function ker, the kernel parameters p1 and p2, the parameter C and the Loss function Loss of the support vector machine are updated, and the support vector machine is retrained until the parameter evaluation function obtains the minimum value;
outputting optimal parameters of the support vector machine to obtain a prediction support vector machine capable of being used for predicting the top layer oil temperature of the transformer;
predicting the top layer oil temperature of the transformer according to the size of the similar time set and the optimal parameters of the support vector machine, wherein the method comprises the following steps:
the method for predicting the top-layer oil temperature of the transformer is selected according to the quantity of the similar moments in the similar moment set:
when the number of the similar moments in the similar moment set is less than or equal to 10, adopting a linear weighting algorithm to process the similar moment setObtaining a predicted value of the top layer oil temperature of the transformer corresponding to each moment; the linear weighting algorithm is as follows: according to the comprehensive correlation degree of each similar time and the time to be predicted in the similar time set, different weight coefficients p are configured for each similar time x And 0 < p x < 1; calculating a predicted value of the top layer oil temperature of the transformer:
in the formula (13), Y represents a predicted value of the top oil temperature of the transformer; y0 x Representing the actual value of the top layer oil temperature of the transformer at the x-th similar moment;
when the number of similar moments in the similar moment set=20, predicting the top-layer oil temperature of the transformer by adopting a support vector machine, and obtaining a predicted value of the top-layer oil temperature of the transformer.
2. A prediction system for top-layer oil temperature of a transformer, comprising:
a first calculation module: the method comprises the steps of calculating the comprehensive correlation degree between each moment in a research sample and the moment to be predicted, and obtaining a similar moment set with the maximum comprehensive correlation degree with the moment to be predicted; the method for calculating the comprehensive correlation degree between each moment in the research sample and the moment to be predicted comprises the following steps:
calculating the direct correlation coefficient of each influence factor of the top layer oil temperature of the transformer; the direct correlation coefficient is:
in the formula (1), R g Represents the direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer, RH g The transverse direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is shown:
in the formula (2), bh g Represents the lateral partial regression coefficient, M represents the number of samples, xg ij Represents the g-th influencing factor at the j-th moment of the i-th day before the moment to be predicted, Y ij The top layer oil temperature of the transformer at the j-th moment of the i-th day before the moment to be predicted is represented;
in formula (1), RZ g The longitudinal direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is shown:
in formula (3), bz g Representing longitudinal partial regression coefficients;
in the formula (1), R 7 Representing the direct correlation coefficient of the transverse date and the oil temperature of the top layer of the transformer, RH 7 A transverse direct correlation coefficient of a transverse date and the oil temperature of the top layer of the transformer is represented; r is R 8 Representing the direct correlation coefficient of the longitudinal moment and the oil temperature of the top layer of the transformer, RH 8 The longitudinal direct correlation coefficient between the longitudinal moment and the top layer oil temperature of the transformer is represented;
according to the calculated direct correlation coefficient, calculating weather correlation, time correlation and load correlation between each moment and the moment to be predicted in the research sample;
linear weighting is carried out based on the weather correlation, the time correlation and the load correlation, so that the comprehensive correlation between each moment in the research sample and the moment to be predicted is obtained; the comprehensive correlation degree is as follows:
in the formula (4), D lij Representing the comprehensive correlation degree between the moment to be predicted l and the moment (j) of the ith day before the moment to be predicted R g The direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is represented, R 9 A represents the direct correlation coefficient of the load factor and the top layer oil temperature of the transformer lij Indicating the time l to be predicted and the i day and j day before the time to be predictedWeather correlation at time:
in formula (5), MD lij Euclidean distance representing meteorological factors between time l to be predicted and time j on day i before the time l to be predicted:
in the formula (6), xg 0l Representing the g-th influencing factor corresponding to the moment to be predicted, xg ij The g-th influencing factor of the j-th moment of the i-th day before the moment to be predicted is represented;
in formula (5), MD max Maximum Euclidean distance representing meteorological factors:
in the formula (8), C x Represents normalized coefficient, the value range is 0.01-0.45, MDT g The intermediate value of the Euclidean distance corresponding to the g-th influencing factor is represented:
in the formula (4), B lij The time correlation degree between the time l to be predicted and the time j of the ith day before the time l to be predicted is shown:
in the formula (9), R 7 Representing the direct correlation coefficient of the transverse date and the oil temperature of the top layer of the transformer, R 8 X7, a direct correlation coefficient between the longitudinal time and the top layer oil temperature of the transformer 0l Represents the transverse date corresponding to the time l to be predicted, X7 il Represents the lateral date, MDT, at the j-th day before the instant to be predicted 7 Represents the Euclidean distance intermediate quantity corresponding to the transverse date, X8 0l Represents the longitudinal time corresponding to the time to be predicted l, X8 il MDT representing the longitudinal time of the j-th day before the time to be predicted 8 Representing the Euclidean distance intermediate quantity corresponding to the longitudinal moment;
in the formula (4), C lij The load correlation degree between the time l to be predicted and the time j of the ith day before the time l to be predicted is represented:
in the formula (10), X9 0l Representing the load factor corresponding to the moment to be predicted, X9 il Load factors representing the j-th moment of the i-th day before the moment to be predicted, MDT 9 Representing the Euclidean distance intermediate quantity corresponding to the load factor;
the method for acquiring the similar time set with the maximum comprehensive correlation degree with the time to be predicted from the research sample comprises the following steps:
setting a comprehensive correlation threshold value D 0 ；
Judging the comprehensive relativity limit value D 0 And comprehensive relativity D lij Is a numerical value of (1):
when D is lij ≥D 0 The ith and jth moments before the moment to be predicted are potential similar moments of the moment to be predicted l; when D is lij <D 0 When the potential similar time of the moment l to be predicted is not the moment j of the ith day before the moment l to be predicted;
counting the number E of potential similar moments;
selecting a set of similar moments of the moments to be predicted:
when E is more than or equal to 20, selecting the comprehensive relativity D lij The maximum 20 potential similar moments are used as a similar moment set of the moment to be predicted l; when E is<When E is more than or equal to 10 and 20, selecting the comprehensive relativity D lij The maximum 10 potential similar moments are used as a similar moment set of the moment to be predicted l; e (E)<10, selecting all potential similar moments as to-be-predictedA set of similar moments for moment l;
an optimal parameter determining module: the optimal parameters are used for determining the support vector machine; also included is determining the primary influencing factors of the top layer oil temperature of the transformer, including:
selecting the minimum value R of the direct correlation coefficient between each influencing factor and the top oil temperature of the transformer 0 ；
Determining the direct correlation coefficient R of each influence factor g And R is R 0 Is of the size of (2):
in the formula (11), R g The direct correlation coefficient of the g-th influencing factor and the top layer oil temperature of the transformer is represented;
the method for determining the optimal parameters of the support vector machine based on the research samples comprises the following steps:
determining main influencing factors of the top layer oil temperature of the transformer;
separating a training sample and a verification sample from the study sample;
calculating similar moments of each moment of the verification sample from the training sample to obtain a verification sample similar moment set;
taking main influencing factors of all moments in the verification sample similarity moment set as training input variables of the support vector machine, and taking the top layer oil temperature of the transformer corresponding to all moments in the verification sample similarity moment set as training output variables of the support vector machine;
initializing and setting related parameters of a support vector machine, wherein the related parameters comprise a kernel function ker, kernel parameters p1 and p2, a parameter C and a Loss function Loss;
importing the constructed input training vector and output training vector into a support vector machine, and training the support vector machine to obtain a support vector machine with training completed;
taking main influencing factors at all moments in the verification sample as verification input variables, inputting the verification input variables into a support vector machine after training is completed, and obtaining verification values of the top layer oil temperature of the transformer at all moments in the verification sample;
establishing a parameter evaluation function based on error square sum:
in the formula (12), Y1 j Represents the verification value at the j-th moment obtained by the support vector machine, Y0 j Representing the actual value at the j-th moment;
when the parameter evaluation function obtains the minimum value, the relevant parameter of the support vector machine is the optimal parameter of the support vector machine, otherwise, the kernel function ker, the kernel parameters p1 and p2, the parameter C and the Loss function Loss of the support vector machine are updated, and the support vector machine is retrained until the parameter evaluation function obtains the minimum value;
outputting optimal parameters of the support vector machine to obtain a prediction support vector machine capable of being used for predicting the top layer oil temperature of the transformer;
the top layer oil temperature prediction module of the transformer: the method is used for predicting the top-layer oil temperature of the transformer according to the size of the similar time set and the optimal parameters of the support vector machine, and comprises the following steps:
the method for predicting the top-layer oil temperature of the transformer is selected according to the quantity of the similar moments in the similar moment set:
when the number of similar moments in the similar moment set is less than or equal to 10, adopting a linear weighting algorithm to process the top-layer oil temperature of the transformer corresponding to each moment in the similar moment set, and obtaining a predicted value of the top-layer oil temperature of the transformer; the linear weighting algorithm is as follows: according to the comprehensive correlation degree of each similar time and the time to be predicted in the similar time set, different weight coefficients p are configured for each similar time x And 0 < p x < 1; calculating a predicted value of the top layer oil temperature of the transformer:
in the formula (13), Y represents a predicted value of the top oil temperature of the transformer; y0 x Representing the actual value of the top layer oil temperature of the transformer at the x-th similar moment;
when the number of similar moments in the similar moment set=20, predicting the top-layer oil temperature of the transformer by adopting a support vector machine, and obtaining a predicted value of the top-layer oil temperature of the transformer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011178764.1A CN112347695B (en) | 2020-10-29 | 2020-10-29 | Method and system for predicting top layer oil temperature of transformer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011178764.1A CN112347695B (en) | 2020-10-29 | 2020-10-29 | Method and system for predicting top layer oil temperature of transformer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112347695A CN112347695A (en) | 2021-02-09 |
| CN112347695B true CN112347695B (en) | 2023-12-01 |
Family
ID=74356969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011178764.1A Active CN112347695B (en) | 2020-10-29 | 2020-10-29 | Method and system for predicting top layer oil temperature of transformer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112347695B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664682A (en) * | 2017-11-30 | 2018-10-16 | 全球能源互联网研究院有限公司 | A kind of prediction technique and its system of transformer top-oil temperature |
| CN111666711A (en) * | 2020-05-12 | 2020-09-15 | 杭州安脉盛智能技术有限公司 | Transformer top layer oil temperature abnormity monitoring method based on multi-dimensional information |
| CN111680712A (en) * | 2020-04-16 | 2020-09-18 | 国网江苏省电力有限公司检修分公司 | Transformer oil temperature prediction method, device and system based on similar moments in the day |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170206291A1 (en) * | 2016-01-20 | 2017-07-20 | Soliton Holdings Corporation, Delaware Corporation | Method for computational fluid dynamics and apparatuses for jet-effect use |
-
2020
- 2020-10-29 CN CN202011178764.1A patent/CN112347695B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108664682A (en) * | 2017-11-30 | 2018-10-16 | 全球能源互联网研究院有限公司 | A kind of prediction technique and its system of transformer top-oil temperature |
| CN111680712A (en) * | 2020-04-16 | 2020-09-18 | 国网江苏省电力有限公司检修分公司 | Transformer oil temperature prediction method, device and system based on similar moments in the day |
| CN111666711A (en) * | 2020-05-12 | 2020-09-15 | 杭州安脉盛智能技术有限公司 | Transformer top layer oil temperature abnormity monitoring method based on multi-dimensional information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112347695A (en) | 2021-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111639815B (en) | Method and system for predicting power grid defect materials through multi-model fusion | |
| CN112700027B (en) | Multi-precision index comprehensive evaluation method and system for electric power prediction model | |
| CN109976147B (en) | Intelligent learning-based large-volume concrete temperature control method | |
| CN109583585A (en) | A kind of station boiler wall temperature prediction neural network model | |
| CN111639783A (en) | Line loss prediction method and system based on LSTM neural network | |
| CN111178621A (en) | Parameter optimization method of electric heating load prediction support vector regression model | |
| Feng et al. | End temperature prediction of molten steel in LF based on CBR–BBN | |
| CN112733354B (en) | Meteorological element time sequence simulation method, system, medium and electronic equipment | |
| Sogabe et al. | Optimization of decentralized renewable energy system by weather forecasting and deep machine learning techniques | |
| CN105631550A (en) | Short-term wind power combined prediction method | |
| CN111680712B (en) | Method, device and system for predicting oil temperature of transformer based on similar time in day | |
| CN112085156B (en) | Partial pressure line loss rate prediction and loss reduction potential evaluation method and system | |
| CN115423009A (en) | Cloud edge coordination-oriented power equipment fault identification method and system | |
| CN110969306A (en) | Power distribution low-voltage distribution area load prediction method and device based on deep learning | |
| CN115167562A (en) | Method and device for controlling temperature of machine room | |
| CN113887833A (en) | Distributed energy user side time-by-time load prediction method and system | |
| Niu et al. | Application of AHP and EIE in reliability analysis of complex production lines systems | |
| CN112347695B (en) | Method and system for predicting top layer oil temperature of transformer | |
| CN116544934B (en) | Power scheduling method and system based on power load prediction | |
| CN116862077A (en) | Electric heating operation cost prediction method and medium based on multi-mode combination model | |
| CN104515591B (en) | A kind of high-precision coal pulverizer vibration detection process | |
| CN109027700B (en) | Method for evaluating leakage detection effect of leakage point | |
| CN116522752A (en) | Compressed air energy storage system simulation method based on mechanism and data fusion | |
| CN110210642A (en) | A kind of city electric energy substitution amount prediction technique and device | |
| CN111859783B (en) | Water pressure prediction method, system, storage medium, equipment and urban water supply system |
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 |