CN115809553A - Temperature and humidity calculation method and terminal in substation protection cell - Google Patents
Temperature and humidity calculation method and terminal in substation protection cell Download PDFInfo
- Publication number
- CN115809553A CN115809553A CN202211533444.2A CN202211533444A CN115809553A CN 115809553 A CN115809553 A CN 115809553A CN 202211533444 A CN202211533444 A CN 202211533444A CN 115809553 A CN115809553 A CN 115809553A
- Authority
- CN
- China
- Prior art keywords
- temperature
- data
- humidity
- external influence
- error correction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention discloses a temperature and humidity calculation method and a terminal in a substation protection cell, which are used for collecting external influence data of the substation protection cell and temperature and humidity data of a cell wall surface; establishing a convective heat transfer model according to the size data of the small chamber, so that the temperature and humidity data of the small chamber can be obtained through external influence data calculation, and establishing a correlation database of the external influence data and the calculated temperature and humidity data; comparing the calculated temperature and humidity data with actual temperature and humidity data measured on the wall surface, and obtaining a corresponding calculation error coefficient by combining external influence data; therefore, the corresponding temperature and humidity data and the error coefficients can be calculated according to the external influence data under the real-time working condition, and the temperature and humidity data can be obtained through prediction. With this mode, the temperature and humidity prediction can be carried out to the factor that can combine the external influence factor of cell and body, solves the not enough problem of current sensor monitoring precision, promotes the humiture calculation's of transformer substation protection cell accuracy.
Description
Technical Field
The invention relates to the technical field of transformer substation monitoring, in particular to a temperature and humidity calculation method and a terminal in a transformer substation protection cell.
Background
The temperature condition of the substation protection cubicle can directly influence the operation condition of the substation secondary equipment, and is very important for the stable operation of a power grid. However, the current real-time sensor monitoring method can only obtain the temperature condition of the position of the real-time sensor, cannot perform early warning on the abnormal change of the temperature and the humidity in the small chamber in the future abnormal weather, lacks a method for protecting the temperature and the humidity in the small chamber, and is not beneficial to the operation and maintenance work of finely protecting the secondary equipment of the small chamber. In addition, in the traditional temperature and humidity calculation method, only some weather factors such as outdoor environment temperature, humidity and the like are considered, the difference of different small chambers in aspects of building design, screen cabinet arrangement and the like is not considered, and the calculation accuracy is not sufficient.
Therefore, a method for calculating the temperature and humidity in the protection chamber is needed.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the temperature and humidity calculation method and the terminal in the substation protection cell are provided, and the calculation accuracy of the temperature and humidity of the substation protection cell can be improved.
In order to solve the technical problems, the invention adopts the technical scheme that:
a temperature and humidity calculation method in a substation protection cell comprises the following steps:
acquiring external influence data of a protection small chamber of a transformer substation and first temperature and humidity data of the wall surface of the small chamber;
according to the size data of the substation protection small chamber, a convection heat exchange model in the small chamber is established, the external influence data is input into the convection heat exchange model, second temperature and humidity data in the small chamber are obtained through calculation, and a temperature and humidity database is established by combining the external influence data and the corresponding second temperature and humidity data;
comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data to obtain temperature and humidity calculation errors, and constructing an error correction coefficient knowledge base;
receiving a real-time working condition, matching a corresponding error correction coefficient from the error correction coefficient knowledge base according to external influence data in the real-time working condition, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working condition, and correcting the second temperature and humidity data by using the error correction coefficient to obtain predicted temperature and humidity data in the cell.
In order to solve the technical problem, the invention adopts another technical scheme as follows:
the utility model provides a humiture calculation terminal in transformer substation's protection cell, includes:
the data acquisition module is used for acquiring external influence data of a substation protection small chamber and first temperature and humidity data of the wall surface of the small chamber;
the convective heat transfer calculation module is used for establishing a convective heat transfer model in a small room according to the size data of the protection small room of the transformer substation, inputting the external influence data into the convective heat transfer model, calculating to obtain second temperature and humidity data in the small room, and establishing a temperature and humidity database by combining the external influence data and the corresponding second temperature and humidity data;
the knowledge base generation module is used for obtaining temperature and humidity calculation errors by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and constructing an error correction coefficient knowledge base;
and the temperature and humidity prediction module is used for receiving real-time working conditions, matching corresponding error correction coefficients from the error correction coefficient knowledge base according to external influence data in the real-time working conditions, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working conditions, and correcting the second temperature and humidity data by using the error correction coefficients to obtain predicted temperature and humidity data in the cell.
The invention has the beneficial effects that: collecting external influence data of a substation protection small chamber and temperature and humidity data of the wall surface of the small chamber; establishing a convective heat transfer model according to the size data of the small chamber, so that the temperature and humidity data of the small chamber can be obtained through external influence data calculation, and establishing a correlation database of the external influence data and the calculated temperature and humidity data; comparing the calculated temperature and humidity data with actual temperature and humidity data measured on the wall surface, and obtaining a corresponding calculation error coefficient by combining external influence data; therefore, the corresponding temperature and humidity data and the error coefficients can be calculated according to the external influence data under the real-time working condition, and the temperature and humidity data can be obtained through prediction. With this mode, the temperature and humidity prediction can be carried out to the factor that can combine the external influence factor of cell and body, solves the not enough problem of current sensor monitoring precision, promotes the humiture calculation's of transformer substation protection cell accuracy.
Drawings
Fig. 1 is a flowchart of a temperature and humidity calculation method in a substation protection cell according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a temperature and humidity calculation terminal in a substation protection cell according to an embodiment of the present invention.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
Referring to fig. 1, an embodiment of the present invention provides a method for calculating a temperature and humidity in a substation protection cell, including:
acquiring external influence data of a substation protection small chamber and first temperature and humidity data of a small chamber wall surface;
according to the size data of the substation protection small chamber, a convection heat exchange model in the small chamber is established, the external influence data is input into the convection heat exchange model, second temperature and humidity data in the small chamber are obtained through calculation, and a temperature and humidity database is established by combining the external influence data and the corresponding second temperature and humidity data;
obtaining temperature and humidity calculation errors by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and constructing an error correction coefficient knowledge base;
receiving a real-time working condition, matching a corresponding error correction coefficient from the error correction coefficient knowledge base according to external influence data in the real-time working condition, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working condition, and correcting the second temperature and humidity data by using the error correction coefficient to obtain predicted temperature and humidity data in the small room.
As can be seen from the above description, the beneficial effects of the present invention are: acquiring external influence data of a substation protection chamber and temperature and humidity data of a chamber wall surface; establishing a convective heat transfer model according to the size data of the small chamber, so that the temperature and humidity data of the small chamber can be obtained through external influence data calculation, and establishing a correlation database of the external influence data and the calculated temperature and humidity data; comparing the calculated temperature and humidity data with actual temperature and humidity data measured on the wall surface, and obtaining a corresponding calculation error coefficient by combining external influence data; therefore, the corresponding temperature and humidity data and the error coefficients can be calculated according to the external influence data under the real-time working condition, and the temperature and humidity data can be obtained through prediction. With this mode, the temperature and humidity prediction can be carried out to the factor that can combine the external influence factor of cell and body, solves the not enough problem of current sensor monitoring precision, promotes the humiture calculation's of transformer substation protection cell accuracy.
Further, inputting the external influence data into the convection heat exchange model, calculating to obtain second temperature and humidity data in the small room, and constructing a temperature and humidity database by combining the external influence data and the corresponding second temperature and humidity data comprises:
performing cluster analysis on the external influence data, and exhaustively combining the external influence data of the cluster center sample to form input data;
inputting the input data into the convective heat transfer model, calculating to obtain second temperature data and second humidity data in the small room, and establishing a second temperature data matrix and a second humidity data matrix;
constructing a temperature and humidity database according to the second temperature data matrix and the second humidity data matrix:
D＝[T,H] T ，T＝[T 1 ,T 2 ,…,T n ]，H＝[H 1 ,H 2 ,…,H n ]；
where T represents the second temperature data matrix, H represents the second humidity data matrix, and n represents the number of exhaustive combinations.
According to the description, through cluster analysis and exhaustive combination of the external influence data, the combination of various external influence data can be obtained, and the working condition coverage of the temperature and humidity database is improved.
Further, performing cluster analysis on the external influence data, and exhaustively combining the external influence data of the cluster center samples to form input data includes:
establishing a sample set Z = [ Z ] of the external influence data 1 ,Z 2 ,…,Z p ]P represents the number of the collected first temperature and humidity data, and the ith sample Z in the sample set i ＝[S i1 ,S i2 ,…,S iM ]M represents the kind of the external influence data;
selecting a preset number of samples from the sample set as clustering center samples to form a first clustering center set;
iteratively updating the clustering center samples of the first clustering center set to obtain a second clustering center set;
and exhaustively combining the external influence data of each clustering center sample in the second clustering center set, sequencing the exhaustively combined samples at least from multiple samples according to the occurrence frequency, and taking the preset number of combinations before sequencing as input data.
According to the description, exhaustive combination is performed according to different external influence data of different clustering center samples, and a final combination is selected as input data according to the occurrence frequency, so that less combinations are filtered, and the efficiency and the precision of subsequent temperature and humidity calculation can be improved.
Further, the step of obtaining temperature and humidity calculation errors by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and the step of constructing an error correction coefficient knowledge base includes:
calculating second temperature and humidity data corresponding to a clustering center closest to the temperature and humidity database by using the Euclidean distance;
calculating temperature and humidity calculation errors of the first temperature and humidity data and the second temperature and humidity data, and constructing a change curve according to the external influence data of the nearest clustering center and the temperature and humidity calculation errors;
and obtaining an error correction coefficient according to the change curve, and constructing an error correction coefficient knowledge base by combining the clustering center and the corresponding external influence data and the error correction coefficient.
According to the description, the change curve of the influence factors and the errors is constructed according to the external influence factors and the calculation errors of the temperature and the humidity, so that the error correction coefficient can be rapidly and accurately determined, and the subsequent error correction of the temperature and the humidity data is facilitated.
Further, matching a corresponding error correction coefficient from the error correction coefficient knowledge base according to the external influence data in the real-time working condition, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working condition, and correcting the second temperature and humidity data by using the error correction coefficient to obtain predicted temperature and humidity data in the cell comprises:
according to real-time conditionsExtracting a corresponding error correction coefficient matrix P, P = [ P ] in the error correction coefficient knowledge base 1 、P 2 ……P m ]，P 1 ＝[P t1 ，P h1 ] T ，P t1 For temperature error correction coefficient, P, corresponding to parameter 1 h1 The humidity error correction coefficient corresponding to the 1 st parameter is m, and the m is the parameter type;
according to external influence data in real-time working conditions, second temperature and humidity data with the shortest Euclidean distance are matched in the temperature and humidity database to obtain initial temperature and humidity data [ T [ [ T ] f ，H f ]；
Calculating predicted temperature and humidity data [ T ] in the cell s ，H s ]：
[T s ，H s ]＝[T f ，H f ]+P△s；
Wherein Δ s = [ s ] 1 ,s 2 ,…,s m ] T Representing the difference of each external influence data from the cluster center.
According to the description, the initial temperature and humidity data are corrected through the error correction coefficient matrix, and the calculation accuracy of the temperature and humidity of the protection cubicle of the transformer substation can be improved.
Referring to fig. 2, another embodiment of the present invention provides a temperature and humidity calculating terminal in a substation protection cell, including:
the data acquisition module is used for acquiring external influence data of a substation protection small chamber and first temperature and humidity data of the wall surface of the small chamber;
the convective heat transfer calculation module is used for establishing a convective heat transfer model in the small room according to the size data of the substation protection small room, inputting the external influence data into the convective heat transfer model, calculating to obtain second temperature and humidity data in the small room, and establishing a temperature and humidity database by combining the external influence data and the corresponding second temperature and humidity data;
the knowledge base generation module is used for obtaining temperature and humidity calculation errors by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and constructing an error correction coefficient knowledge base;
and the temperature and humidity prediction module is used for receiving real-time working conditions, matching corresponding error correction coefficients from the error correction coefficient knowledge base according to external influence data in the real-time working conditions, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working conditions, and correcting the second temperature and humidity data by using the error correction coefficients to obtain predicted temperature and humidity data in the cell.
According to the description, external influence data of the substation protection chamber and temperature and humidity data of the wall surface of the chamber are collected; establishing a convective heat transfer model according to the size data of the small chamber, so that the temperature and humidity data of the small chamber can be obtained through calculation of external influence data, and establishing a correlation database of the external influence data and the calculated temperature and humidity data; comparing the calculated temperature and humidity data with actual temperature and humidity data measured on the wall surface, and obtaining a corresponding calculation error coefficient by combining external influence data; therefore, the corresponding temperature and humidity data and the error coefficient can be calculated according to the external influence data under the real-time working condition, and the temperature and humidity data can be obtained through prediction. In this way, the humiture prediction can be carried out to the factor that can combine the external influence factor of cell and body, solves the not enough problem of current sensor monitoring precision, promotes the humiture calculation's of transformer substation protection cell accuracy.
Further, inputting the external influence data into the convection heat exchange model, calculating to obtain second temperature and humidity data in the small room, and constructing a temperature and humidity database by combining the external influence data and the corresponding second temperature and humidity data, wherein the temperature and humidity database comprises:
performing cluster analysis on the external influence data, and exhaustively combining the external influence data of the cluster center sample to form input data;
inputting the input data into the convective heat transfer model, calculating to obtain second temperature data and second humidity data in the small room, and establishing a second temperature data matrix and a second humidity data matrix;
constructing a temperature and humidity database according to the second temperature data matrix and the second humidity data matrix:
D＝[T,H] T ，T＝[T 1 ,T 2 ,…,T n ]，H＝[H 1 ,H 2 ,…,H n ]；
where T represents the second temperature data matrix, H represents the second humidity data matrix, and n represents the number of exhaustive combinations.
According to the description, through cluster analysis and exhaustive combination of the external influence data, the combination of various external influence data can be obtained, and the working condition coverage of the temperature and humidity database is improved.
Further, performing cluster analysis on the external influence data, and exhaustively combining the external influence data of the cluster center samples to form input data includes:
establishing a sample set Z = [ Z ] of the external influence data 1 ,Z 2 ,…,Z p ]P represents the number of the collected first temperature and humidity data, and the ith sample Z in the sample set i ＝[S i1 ,S i2 ,…,S iM ]M represents the kind of the external influence data;
selecting a preset number of samples from the sample set as clustering center samples to form a first clustering center set;
iteratively updating the clustering center samples of the first clustering center set to obtain a second clustering center set;
and exhaustively combining the external influence data of each clustering center sample in the second clustering center set, sequencing the exhaustively combined samples at least from multiple samples according to the occurrence frequency, and taking the preset number of combinations before sequencing as input data.
According to the description, exhaustive combination is performed according to different external influence data of different clustering center samples, and a final combination is selected as input data according to the occurrence frequency, so that less combinations are filtered, and the efficiency and the precision of subsequent temperature and humidity calculation can be improved.
Further, the step of obtaining temperature and humidity calculation errors by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and the step of constructing an error correction coefficient knowledge base includes:
calculating second temperature and humidity data corresponding to a clustering center closest to the temperature and humidity database by using the Euclidean distance;
calculating temperature and humidity calculation errors of the first temperature and humidity data and the second temperature and humidity data, and constructing a change curve according to the external influence data of the nearest clustering center and the temperature and humidity calculation errors;
and obtaining an error correction coefficient according to the change curve, and constructing an error correction coefficient knowledge base by combining the clustering center and the corresponding external influence data and the error correction coefficient.
According to the above description, the change curve of the influence factor-error is constructed according to the external influence factor and the calculation error of the temperature and humidity, so that the error correction coefficient can be determined quickly and accurately, and the subsequent error correction of the temperature and humidity data is facilitated.
Further, matching a corresponding error correction coefficient from the error correction coefficient knowledge base according to the external influence data in the real-time working condition, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working condition, and correcting the second temperature and humidity data by using the error correction coefficient to obtain predicted temperature and humidity data in the cell comprises:
extracting a corresponding error correction coefficient matrix P, P = [ P ] from the error correction coefficient knowledge base according to external influence data in real-time working conditions 1 、P 2 ……P m ]，P 1 ＝[P t1 ，P h1 ] T ，P t1 For temperature error correction coefficient, P, corresponding to parameter 1 h1 The humidity error correction coefficient corresponding to the 1 st parameter is m, and the m is the parameter type;
according to external influence data in real-time working conditions, second temperature and humidity data with the shortest Euclidean distance are matched in the temperature and humidity database to obtain initial temperature and humidity data [ T [ [ T ] f ，H f ]；
Calculating predicted temperature and humidity data [ T ] in the cell s ，H s ]：
[T s ，H s ]＝[T f ，H f ]+P△s；
Wherein Δ s = [ s ] 1 ,s 2 ,…,s m ] T The difference of each of the extrinsic impact data from the cluster center is represented.
According to the description, the initial temperature and humidity data are corrected through the error correction coefficient matrix, and the calculation accuracy of the temperature and humidity of the protection cubicle of the transformer substation can be improved.
The temperature and humidity calculation method and the terminal in the substation protection cell are suitable for calculating the temperature and humidity in the substation protection cell based on multi-dimensional influence quantities, and are described in the following through specific embodiments:
example one
Referring to fig. 1, a method for calculating temperature and humidity in a substation protection cell includes the steps of:
s1, collecting external influence data of a substation protection small chamber and first temperature and humidity data of a small chamber wall surface.
Specifically, in this embodiment, the external influence data includes environmental data outside the small room and air conditioning condition data inside the small room. Wherein the environmental data comprises temperature, relative humidity, total solar radiation value, scattered solar radiation value, wind direction and wind speed per hour; the air-conditioning condition data includes a daily air-conditioning set temperature, the number of the air-conditioners to be put in and taken out, an operation mode, and a wind direction.
S2, according to size data of the substation protection cell, a convection heat exchange model in the cell is established, the external influence data are input into the convection heat exchange model, second temperature and humidity data in the cell are obtained through calculation, and a temperature and humidity database is built by combining the external influence data and the corresponding second temperature and humidity data.
And S21, establishing a convective heat transfer model in the small chamber by adopting finite element simulation software according to the size data of the substation protection small chamber.
In this embodiment, the size data of the protection cubicle of the transformer substation includes a cubicle building size parameter, a cubicle parameter and a temperature regulation parameter. Wherein the cell building size parameters comprise wall size, roof slope and indoor area; the screen cabinet parameters comprise screen cabinet types, the number of chargers and heating power; the temperature regulation and control parameters comprise air conditioner layout, refrigeration power and air conditioner quantity.
And S22, calculating the temperature and the humidity of the small chamber according to the typical data of the external influence quantity parameters, and constructing a typical parameter temperature and humidity database.
S221, carrying out clustering analysis on the external influence data, and exhaustively combining the external influence data of the clustering center sample to form input data.
S2211, establishing a sample set Z = [ Z ] of the external influence data 1 ,Z 2 ,…,Z p ]P represents the number of the collected first temperature and humidity data, and the ith sample Z in the sample set i ＝[S i1 ,S i2 ,…,S iM ]And M represents the kind of the external influence data.
And S2212, selecting a preset number of samples in the sample set as clustering center samples to form a first clustering center set.
Specifically, K samples are selected from the sample set Z as clustering center samples to form a first clustering center set A of K categories 0 ＝[a 1 ,a 2 ,…,a k ,…a K ]，a k For cluster-centered samples of class K, K =1,2, \ 8230;, K.
And S2213, performing iterative updating on the clustering center samples of the first clustering center set to obtain a second clustering center set.
Specifically, in this embodiment, iteration is performed up to L times, and for the L-th iteration, L =1,2, \8230, L, each sample Z in the calculation samples Z i Distance D to K cluster center samples i ，D i ＝[D il1 ,D il2 ,…,D ilK ]，D ilk Represents a sample Z i Distance to the kth cluster center sample, sample Z i Classifying to a class having the smallest distance from the cluster centerThe preparation method comprises the following steps of (1) performing;
recalculating clustering centers a of different classes lj ：
Wherein j =1,2, \8230;, K, c lj Represents the number of samples in the sample set Z that belong to the class j at the l-th iteration, I (Z) i J) represents an indicator function, when Z i When belonging to category j, I (Z) i J) =1, otherwise, I (Z) i ,j)＝0；
Obtaining the first clustering center set A l ＝[a l1 ,a l2 ,…,a lK ]。
S2214, exhaustive combination is carried out on each external influence data of each cluster center sample in the second cluster center set, at least the exhaustive combination is sorted according to the occurrence frequency, and the combination with the preset number before sorting is used as input data.
Specifically, for clustering center set A l ＝[a l1 ,a l2 ,…,a lK ]The k-th clustering center a lk Is [ S ] as the external influence quantity parameter data set k1 ,S k2 ,…,S kM ]The method takes the parameter data of the external influence quantity of the clustering center as typical values, then the M-th class of external parameter data, M =1,2 \8230, M, the typical value set of which is [ S [ ] 1m ,S 2m ,…,S Km ]The typical values of the external parameters of the M classes are combined exhaustively and form K in total M The typical value combinations are selected as input data by selecting several combinations which occur frequently in the sample.
S222, inputting the input data into the convective heat exchange model, calculating to obtain second temperature data and second humidity data in the small room, and establishing a second temperature data matrix T and a second humidity data matrix H;
constructing a temperature and humidity database according to the second temperature data matrix and the second humidity data matrix:
D＝[T,H] T ，T＝[T 1 ,T2,…,T n ]，H＝[H 1 ,H 2 ,…,H n ]；
in the formula, n represents an exhaustive number of combinations.
And S3, comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data to obtain temperature and humidity calculation errors, and constructing an error correction coefficient knowledge base.
And S31, calculating second temperature and humidity data corresponding to the nearest clustering center in the temperature and humidity database by using the Euclidean distance.
And S32, calculating temperature and humidity calculation errors delta T and delta H of the first temperature and humidity data and second temperature and humidity data of the nearest clustering center, and constructing a change curve according to external influence data of the nearest clustering center and the temperature and humidity calculation error influence quantity-error.
And S33, obtaining an error correction coefficient according to the change curve, and constructing an error correction coefficient knowledge base by combining the clustering center, external influence data corresponding to the clustering center and the error correction coefficient.
S4, receiving a real-time working condition, matching a corresponding error correction coefficient from the error correction coefficient knowledge base according to external influence data in the real-time working condition, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working condition, and correcting the second temperature and humidity data by using the error correction coefficient to obtain predicted temperature and humidity data in the cell.
Extracting a corresponding error correction coefficient matrix P = [ P ] from the error correction coefficient knowledge base according to external influence data in real-time working conditions 1 ,P 2 ,…,P m ]，P1＝[P t1 ，P h1 ] T ，P t1 For temperature error correction factor, P, corresponding to parameter 1 h1 The humidity error correction coefficient corresponding to the 1 st parameter is m, which is a parameter type.
According to external influence data in real-time working conditions, second temperature and humidity data with the shortest Euclidean distance are matched in the temperature and humidity database to obtain initial temperature and humidity data [ T [ [ T ] f ，H f ]；
Calculating predicted temperature and humidity data [ T ] in the cell s ，H s ]：
[T s ，H s ]＝[T f ，H f ]+P△s；
Wherein Δ s = [ s ] 1 ,s 2 ,…,s m ] T The difference of each of the extrinsic impact data from the cluster center is represented.
Example two
Referring to fig. 2, a temperature and humidity calculation terminal in a substation protection cell is characterized by comprising:
the data acquisition module is used for acquiring external influence data of the substation protection chamber and first temperature and humidity data of the wall surface of the chamber.
And the convective heat transfer calculation module is used for establishing a convective heat transfer model in the small room according to the size data of the protection small room of the transformer substation, inputting the external influence data into the convective heat transfer model, calculating to obtain second temperature and humidity data in the small room, and establishing a temperature and humidity database by combining the external influence data and the corresponding second temperature and humidity data.
Wherein, the heat convection computing module is used for including:
carrying out cluster analysis on the external influence data, and exhaustively combining the external influence data of the cluster center sample to form input data:
establishing a sample set Z = [ Z ] of the external influence data 1 ,Z 2 ,…,Z p ]P represents the number of the collected first temperature and humidity data, and the ith sample Z in the sample set i ＝[S i1 ,S i2 ,…,S iM ]M represents the kind of the external influence data;
selecting a preset number of samples from the sample set as clustering center samples to form a first clustering center set;
iteratively updating the clustering center samples of the first clustering center set to obtain a second clustering center set;
and exhaustively combining the external influence data of each clustering center sample in the second clustering center set, sequencing the exhaustively combined samples at least from multiple samples according to the occurrence frequency, and taking the preset number of combinations before sequencing as input data.
And inputting the input data into the convective heat transfer model, calculating to obtain second temperature data and second humidity data in the small room, and establishing a second temperature data matrix and a second humidity data matrix.
Constructing a temperature and humidity database according to the second temperature data matrix and the second humidity data matrix:
D＝[T,H] T ，T＝[T 1 ,T 2 ,…,T n ]，H＝[H 1 ,H 2 ,…,H n ]；
where T represents the second temperature data matrix, H represents the second humidity data matrix, and n represents the number of exhaustive combinations.
And the knowledge base generation module is used for obtaining temperature and humidity calculation errors by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and constructing an error correction coefficient knowledge base.
Wherein, the knowledge base generation module comprises a module for:
calculating second temperature and humidity data corresponding to a clustering center closest to the temperature and humidity database by using the Euclidean distance;
calculating temperature and humidity calculation errors of the first temperature and humidity data and the second temperature and humidity data, and constructing a change curve according to the external influence data of the nearest clustering center and the temperature and humidity calculation errors;
and obtaining an error correction coefficient according to the change curve, and constructing an error correction coefficient knowledge base by combining the clustering center and the corresponding external influence data and the error correction coefficient.
And the temperature and humidity prediction module is used for receiving real-time working conditions, matching corresponding error correction coefficients from the error correction coefficient knowledge base according to external influence data in the real-time working conditions, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working conditions, and correcting the second temperature and humidity data by using the error correction coefficients to obtain predicted temperature and humidity data in the cell.
Wherein, humiture prediction module is including being used for:
extracting a corresponding error correction coefficient matrix P, P = [ P ] from the error correction coefficient knowledge base according to external influence data in real-time working conditions 1 、P 2 ……P m ]，P 1 ＝[P t1 ，P h1 ] T ，P t1 For temperature error correction coefficient, P, corresponding to parameter 1 h1 The humidity error correction coefficient corresponding to the 1 st parameter is m, and the m is the parameter type;
according to external influence data in real-time working conditions, second temperature and humidity data with the shortest Euclidean distance are matched in the temperature and humidity database to obtain initial temperature and humidity data [ T f ，H f ]；
Calculating predicted temperature and humidity data [ T ] in the cell s ，H s ]：
[T s ，H s ]＝[T f ，H f ]+P△s；
Wherein Δ s = [ s ] 1 、s 2 ……s m ] T Representing the difference of each external influence data from the cluster center.
In summary, according to the temperature and humidity calculation method and terminal in the substation protection cell provided by the invention, external influence data of the substation protection cell and temperature and humidity data of the cell wall surface are collected; establishing a convective heat transfer model according to the size data of the small chamber, so that the temperature and humidity data of the small chamber can be obtained through external influence data calculation, and establishing a correlation database of the external influence data and the calculated temperature and humidity data; comparing the calculated temperature and humidity data with actual temperature and humidity data measured on the wall surface, and combining external influence data to obtain a corresponding calculation error coefficient; therefore, the corresponding temperature and humidity data and the error coefficients can be calculated according to the external influence data under the real-time working condition, and the temperature and humidity data can be obtained through prediction. With this mode, the temperature and humidity prediction can be carried out to the factor that can combine the external influence factor of cell and body, solves the not enough problem of current sensor monitoring precision, promotes the humiture calculation's of transformer substation protection cell accuracy.
The above description is only an embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent modifications made by the present invention and the contents of the accompanying drawings, which are directly or indirectly applied to the related technical fields, are included in the scope of the present invention.
Claims (10)
1. A temperature and humidity calculation method in a substation protection cell is characterized by comprising the following steps:
acquiring external influence data of a protection small chamber of a transformer substation and first temperature and humidity data of the wall surface of the small chamber;
according to the size data of the substation protection small chamber, a convection heat exchange model in the small chamber is established, the external influence data are input into the convection heat exchange model, second temperature and humidity data in the small chamber are obtained through calculation, and a temperature and humidity database is built by combining the external influence data and the corresponding second temperature and humidity data;
obtaining temperature and humidity calculation errors by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and constructing an error correction coefficient knowledge base;
receiving a real-time working condition, matching a corresponding error correction coefficient from the error correction coefficient knowledge base according to external influence data in the real-time working condition, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working condition, and correcting the second temperature and humidity data by using the error correction coefficient to obtain predicted temperature and humidity data in the small room.
2. The method for calculating the temperature and humidity in the substation protection cell according to claim 1, wherein the step of inputting the external influence data into the convection heat exchange model, calculating second temperature and humidity data in the cell, and constructing a temperature and humidity database by combining the external influence data and the corresponding second temperature and humidity data comprises the steps of:
performing cluster analysis on the external influence data, and exhaustively combining the external influence data of the cluster center sample to form input data;
inputting the input data into the convective heat transfer model, calculating to obtain second temperature data and second humidity data in the small room, and establishing a second temperature data matrix and a second humidity data matrix;
a temperature and humidity database is built according to the second temperature data matrix and the second humidity data matrix:
D＝[T,H] T ，T＝[T 1 ,T 2 ,…,T n ]，H＝[H 1 ,H 2 ,…,H n ]；
where T represents the second temperature data matrix, H represents the second humidity data matrix, and n represents the number of exhaustive combinations.
3. The method of claim 2, wherein the step of performing cluster analysis on the external influence data and exhaustively combining the external influence data of the cluster center samples to form input data comprises the steps of:
establishing a sample set Z = [ Z ] of the external influence data 1 ,Z 2 ,…,Z p ]P represents the number of the collected first temperature and humidity data, and the ith sample Z in the sample set i ＝[S i1 ,S i2 ,…,S iM ]M represents the kind of the external influence data;
selecting a preset number of samples from the sample set as clustering center samples to form a first clustering center set;
iteratively updating the clustering center samples of the first clustering center set to obtain a second clustering center set;
and exhaustively combining the external influence data of each cluster center sample in the second cluster center set, sequencing at least the exhaustively combined samples according to the occurrence frequency, and taking the preset number of combinations before sequencing as input data.
4. The temperature and humidity calculation method in the substation protection cell according to claim 2, wherein the temperature and humidity calculation error is obtained by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and the establishing of the error correction coefficient knowledge base includes:
calculating second temperature and humidity data corresponding to a clustering center closest to the temperature and humidity database by using the Euclidean distance;
calculating temperature and humidity calculation errors of the first temperature and humidity data and the second temperature and humidity data, and constructing a change curve according to the external influence data of the nearest clustering center and the temperature and humidity calculation errors;
and obtaining an error correction coefficient according to the change curve, and constructing an error correction coefficient knowledge base by combining the clustering center and the corresponding external influence data and the error correction coefficient.
5. The method according to claim 2, wherein the step of matching corresponding error correction coefficients from the error correction coefficient knowledge base according to the external influence data in the real-time working conditions, the step of matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working conditions, and the step of correcting the second temperature and humidity data by using the error correction coefficients to obtain predicted temperature and humidity data in the small room comprises the steps of:
extracting a corresponding error correction coefficient matrix P, P = [ P ] from the error correction coefficient knowledge base according to external influence data in real-time working conditions 1 、P 2 ……P m ]，P 1 ＝[P t1 ，P h1 ] T ，P t1 For temperature error correction coefficient, P, corresponding to parameter 1 h1 The humidity error correction coefficient corresponding to the 1 st parameter is m, and the m is the parameter type;
according to external influence data in real-time working conditions, matching in the temperature and humidity databaseObtaining initial temperature and humidity data [ T ] from second temperature and humidity data with the Euclidean distance being nearest f ，H f ]；
Calculating predicted temperature and humidity data [ T ] in the cell s ，H s ]：
[T s ，H s ]＝[T f ，H f ]+P△s；
Wherein Δ s = [ s ] 1 ,s 2 ,…,s m ] T The difference of each of the extrinsic impact data from the cluster center is represented.
6. The utility model provides a humiture calculation terminal in transformer substation's protection cell which characterized in that includes:
the data acquisition module is used for acquiring external influence data of a substation protection small chamber and first temperature and humidity data of the wall surface of the small chamber;
the convective heat transfer calculation module is used for establishing a convective heat transfer model in a small room according to the size data of the protection small room of the transformer substation, inputting the external influence data into the convective heat transfer model, calculating to obtain second temperature and humidity data in the small room, and establishing a temperature and humidity database by combining the external influence data and the corresponding second temperature and humidity data;
the knowledge base generation module is used for obtaining temperature and humidity calculation errors by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and constructing an error correction coefficient knowledge base;
and the temperature and humidity prediction module is used for receiving real-time working conditions, matching corresponding error correction coefficients from the error correction coefficient knowledge base according to external influence data in the real-time working conditions, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working conditions, and correcting the second temperature and humidity data by using the error correction coefficients to obtain predicted temperature and humidity data in the cell.
7. The temperature and humidity calculation terminal in a substation protection cell according to claim 6, wherein the external influence data is input into the convection heat exchange model, second temperature and humidity data in the cell is obtained through calculation, and a temperature and humidity database is constructed by combining the external influence data and the second temperature and humidity data corresponding to the external influence data comprises:
performing cluster analysis on the external influence data, and exhaustively combining the external influence data of the cluster center sample to form input data;
inputting the input data into the convective heat transfer model, calculating to obtain second temperature data and second humidity data in the small room, and establishing a second temperature data matrix and a second humidity data matrix;
a temperature and humidity database is built according to the second temperature data matrix and the second humidity data matrix:
D＝[T,H] T ，T＝[T 1 ,T 2 ,…,T n ]，H＝[H 1 ,H 2 ,…,H n ]；
where T represents the second temperature data matrix, H represents the second humidity data matrix, and n represents the number of exhaustive combinations.
8. The temperature and humidity calculation terminal in a substation protection cell according to claim 7, wherein the clustering analysis is performed on the external influence data, and exhaustive combination is performed on the external influence data of the clustering center sample to form input data comprises:
establishing a sample set Z = [ Z ] of the external influence data 1 ,Z 2 ,…,Z p ]P represents the number of the collected first temperature and humidity data, and the ith sample Z in the sample set i ＝[S i1 ,S i2 ,…,S iM ]M represents the kind of the external influence data;
selecting a preset number of samples from the sample set as clustering center samples to form a first clustering center set;
iteratively updating the clustering center samples of the first clustering center set to obtain a second clustering center set;
and exhaustively combining the external influence data of each clustering center sample in the second clustering center set, sequencing the exhaustively combined samples at least from multiple samples according to the occurrence frequency, and taking the preset number of combinations before sequencing as input data.
9. The temperature and humidity calculation terminal in a substation protection cell according to claim 7, wherein the temperature and humidity calculation error is obtained by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and the establishing of the error correction coefficient knowledge base includes:
calculating second temperature and humidity data corresponding to a clustering center closest to the temperature and humidity database by using Euclidean distance;
calculating temperature and humidity calculation errors of the first temperature and humidity data and the second temperature and humidity data, and constructing a change curve according to the external influence data of the nearest clustering center and the temperature and humidity calculation errors;
and obtaining an error correction coefficient according to the change curve, and constructing an error correction coefficient knowledge base by combining the clustering center and the corresponding external influence data and the error correction coefficient.
10. The temperature and humidity calculation terminal in a substation protection cell according to claim 7, wherein the step of matching a corresponding error correction coefficient from the error correction coefficient knowledge base according to the external influence data in the real-time working condition, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time working condition, and using the error correction coefficient to correct the second temperature and humidity data to obtain predicted temperature and humidity data in the cell comprises:
extracting a corresponding error correction coefficient matrix P, P = [ P ] from the error correction coefficient knowledge base according to external influence data in real-time working conditions 1 、P 2 ……P m ]，P 1 ＝[P t1 ，P h1 ] T ，P t1 For temperature error correction coefficient, P, corresponding to parameter 1 h1 Is as follows1 humidity error correction coefficient corresponding to parameters, wherein m is a parameter type;
according to external influence data in real-time working conditions, second temperature and humidity data with the shortest Euclidean distance are matched in the temperature and humidity database to obtain initial temperature and humidity data [ T f ，H f ]；
Calculating predicted temperature and humidity data [ T ] in the cell s ，H s ]：
[T s ，H s ]＝[T f ，H f ]+P△s；
Wherein Δ s = [ s ] 1 ,s 2 ,…,s m ] T Representing the difference of each external influence data from the cluster center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211533444.2A CN115809553A (en) | 2022-12-01 | 2022-12-01 | Temperature and humidity calculation method and terminal in substation protection cell |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211533444.2A CN115809553A (en) | 2022-12-01 | 2022-12-01 | Temperature and humidity calculation method and terminal in substation protection cell |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115809553A true CN115809553A (en) | 2023-03-17 |
Family
ID=85484745
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211533444.2A Pending CN115809553A (en) | 2022-12-01 | 2022-12-01 | Temperature and humidity calculation method and terminal in substation protection cell |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115809553A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116451513A (en) * | 2023-06-19 | 2023-07-18 | 广东电网有限责任公司佛山供电局 | Method and system for adjusting and optimizing high-voltage room temperature of transformer substation |
| CN117236084A (en) * | 2023-11-16 | 2023-12-15 | 青岛永强木工机械有限公司 | Intelligent management method and system for woodworking machining production |
-
2022
- 2022-12-01 CN CN202211533444.2A patent/CN115809553A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116451513A (en) * | 2023-06-19 | 2023-07-18 | 广东电网有限责任公司佛山供电局 | Method and system for adjusting and optimizing high-voltage room temperature of transformer substation |
| CN116451513B (en) * | 2023-06-19 | 2023-11-24 | 广东电网有限责任公司佛山供电局 | Method and system for adjusting and optimizing high-voltage room temperature of transformer substation |
| CN117236084A (en) * | 2023-11-16 | 2023-12-15 | 青岛永强木工机械有限公司 | Intelligent management method and system for woodworking machining production |
| CN117236084B (en) * | 2023-11-16 | 2024-02-06 | 青岛永强木工机械有限公司 | Intelligent management method and system for woodworking machining production |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115809553A (en) | Temperature and humidity calculation method and terminal in substation protection cell | |
| CN112699913B (en) | Method and device for diagnosing abnormal relationship of household transformer in transformer area | |
| CN112926144B (en) | Multi-stress accelerated life test coupling effect analysis and life prediction method | |
| CN110503153B (en) | Photovoltaic system fault diagnosis method based on differential evolution algorithm and support vector machine | |
| CN106875037A (en) | Wind-force Forecasting Methodology and device | |
| CN111488896A (en) | Distribution line time-varying fault probability calculation method based on multi-source data mining | |
| CN111695736A (en) | Photovoltaic power generation short-term power prediction method based on multi-model fusion | |
| CN113991711B (en) | Capacity configuration method for energy storage system of photovoltaic power station | |
| CN113392497B (en) | Method for measuring field performance degradation of photovoltaic module according to geographical region | |
| CN114091317A (en) | Photovoltaic power station power prediction method based on NWP irradiance correction and error prediction | |
| CN114839538A (en) | Method for extracting degradation characteristics of lithium ion battery for estimating residual life | |
| CN111753259A (en) | Method for checking distribution room topology files based on distribution room energy balance | |
| Li et al. | Validation of virtual sensor-assisted Bayesian inference-based in-situ sensor calibration strategy for building HVAC systems | |
| CN115169659A (en) | Ultra-short-term roof photovoltaic power prediction method and system based on multiple classifiers | |
| CN116448161A (en) | Artificial intelligence-based environment monitoring equipment fault diagnosis method | |
| CN114970157A (en) | Method for predicting test life of small sample of electronic product under voltage stress | |
| CN116365508A (en) | Photovoltaic power station generating capacity prediction method and system based on climate mode | |
| CN101446828A (en) | Nonlinear process quality prediction method | |
| CN112736904B (en) | Power load model online analysis method based on small disturbance data | |
| CN117273195A (en) | Steam heating system demand load prediction method | |
| CN109193639B (en) | Robust estimation method for power system | |
| CN110796292A (en) | Photovoltaic power short-term prediction method considering haze influence | |
| CN111242266A (en) | Operation data management system | |
| CN116068303A (en) | Private capacity-increasing on-line monitoring method for special transformer based on data driving | |
| US11923803B2 (en) | Anomaly factor diagnosis apparatus and method, and anomaly factor diagnosis 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 |