A temperature and humidity calculation method and terminal in a transformer substation protection room

Abstract

The present invention discloses a method and terminal for calculating temperature and humidity in a transformer substation protection chamber. The method collects external influence data of the transformer substation protection chamber and temperature and humidity data of the chamber wall surface; establishes a convection heat transfer model based on the chamber's own dimension data, thereby being able to calculate the chamber's temperature and humidity data through the external influence data, and establishes a database associating the external influence data with the calculated temperature and humidity data; compares the calculated temperature and humidity data with the actual temperature and humidity data measured on the wall surface, and obtains a corresponding calculation error coefficient based on the external influence data; thus, the corresponding temperature and humidity data and error coefficient can be calculated based on the external influence data under real-time working conditions, thereby predicting the temperature and humidity data. In this way, the temperature and humidity can be predicted by combining the external influence factors of the chamber with the factors of the chamber itself, solving the problem of insufficient monitoring accuracy of existing sensors and improving the accuracy of temperature and humidity calculation in the transformer substation protection chamber.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer substation monitoring, and in particular to a temperature and humidity calculation method and terminal in a transformer substation protection room. Background Art

[0002] The temperature in a substation's protection chamber directly affects the operating conditions of its secondary equipment and is crucial for the stable operation of the power grid. However, current real-time sensor monitoring methods only capture the temperature at the sensor's location and cannot provide early warning of abnormal temperature and humidity fluctuations within the chamber during future weather conditions. The lack of a method for calculating the temperature and humidity within the chamber hinders the precise operation and maintenance of the chamber's secondary equipment. Furthermore, traditional temperature and humidity calculation methods only consider certain weather factors, such as outdoor ambient temperature and humidity, and fail to account for variations in architectural design and cabinet layout between different chambers, resulting in insufficient accuracy.

[0003] Therefore, there is an urgent need for a method to calculate the temperature and humidity in the protection chamber. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and terminal for calculating the temperature and humidity in a transformer substation protection room, which can improve the calculation accuracy of the temperature and humidity in the transformer substation protection room.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A method for calculating temperature and humidity in a transformer substation protection chamber comprises the following steps:

[0007] Collect external impact data of the substation protection room and the first temperature and humidity data of the room wall;

[0008] Based on the dimension data of the substation protection chamber, a convection heat transfer model is established in the chamber, the external influence data is input into the convection heat transfer model, the second temperature and humidity data in the chamber is calculated, and a temperature and humidity database is constructed by combining the external influence data and the corresponding second temperature and humidity data;

[0009] By comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, a temperature and humidity calculation error is obtained, and an error correction coefficient knowledge base is constructed;

[0010] Receive real-time working conditions, match corresponding error correction coefficients from the error correction coefficient knowledge base according to external influence data in the real-time working conditions, match 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 use the error correction coefficient to correct the second temperature and humidity data to obtain predicted temperature and humidity data in the small room.

[0011] In order to solve the above technical problems, another technical solution adopted by the present invention is:

[0012] A temperature and humidity calculation terminal in a transformer substation protection room, comprising:

[0013] A data acquisition module is used to collect external impact data of the substation protection chamber and first temperature and humidity data of the chamber wall;

[0014] a convection heat transfer calculation module, configured to establish a convection heat transfer model within the substation protection chamber based on the dimension data of the chamber, input the external influence data into the convection heat transfer model, calculate the second temperature and humidity data within the chamber, and construct a temperature and humidity database by combining the external influence data and the corresponding second temperature and humidity data;

[0015] a knowledge base generation module, configured to obtain a temperature and humidity calculation error by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and to construct an error correction coefficient knowledge base;

[0016] The temperature and humidity prediction module is used to receive real-time working conditions, match corresponding error correction coefficients from the error correction coefficient knowledge base according to external influence data in the real-time working conditions, match 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 use the error correction coefficient to correct the second temperature and humidity data to obtain predicted temperature and humidity data in the small room.

[0017] The beneficial effects of the present invention are as follows: collecting external influence data of the substation protection chamber and temperature and humidity data of the chamber wall; establishing a convection heat transfer model based on the chamber's own dimensional data, so that the chamber's temperature and humidity data can be calculated using the external influence data, and establishing a database associating the external influence data with the calculated temperature and humidity data; comparing the calculated temperature and humidity data with the actual temperature and humidity data measured on the wall, and combining the external influence data to obtain a corresponding calculation error coefficient; thus, the corresponding temperature and humidity data and error coefficient can be calculated based on the external influence data under real-time working conditions, thereby predicting the temperature and humidity data. In this way, the temperature and humidity can be predicted by combining the external influence factors of the chamber with the factors of the chamber itself, solving the problem of insufficient monitoring accuracy of existing sensors and improving the accuracy of temperature and humidity calculation of the substation protection chamber. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of a method for calculating temperature and humidity in a substation protection chamber according to an embodiment of the present invention;

[0019] Figure 2The figure is a schematic diagram of a temperature and humidity calculation terminal in a transformer substation protection room according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] To illustrate the technical content, achieved objectives and effects of the present invention in detail, the following description is given in conjunction with the embodiments and accompanying drawings.

[0021] Please refer to Figure 1 The embodiment of the present invention provides a method for calculating temperature and humidity in a transformer substation protection room, comprising the steps of:

[0022] Collect external impact data of the substation protection room and the first temperature and humidity data of the room wall;

[0023] Based on the dimension data of the substation protection chamber, a convection heat transfer model is established in the chamber, the external influence data is input into the convection heat transfer model, the second temperature and humidity data in the chamber is calculated, and a temperature and humidity database is constructed by combining the external influence data and the corresponding second temperature and humidity data;

[0024] By comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, a temperature and humidity calculation error is obtained, and an error correction coefficient knowledge base is constructed;

[0025] Receive real-time working conditions, match corresponding error correction coefficients from the error correction coefficient knowledge base according to external influence data in the real-time working conditions, match 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 use the error correction coefficient to correct the second temperature and humidity data to obtain predicted temperature and humidity data in the small room.

[0026] From the above description, it can be seen that the beneficial effects of the present invention are: collecting the external influence data of the substation protection chamber and the temperature and humidity data of the chamber wall; establishing a convection heat transfer model based on the size data of the chamber itself, so that the temperature and humidity data of the chamber can be calculated through the external influence data, and establishing a database related to the external influence data and the calculated temperature and humidity data; comparing the calculated temperature and humidity data with the actual temperature and humidity data measured on the wall, and combining its external influence data to obtain the corresponding calculation error coefficient; therefore, the corresponding temperature and humidity data and error coefficient can be calculated based on the external influence data under real-time working conditions, thereby predicting the temperature and humidity data. In this way, the temperature and humidity can be predicted by combining the external influence factors of the chamber and the factors of the body, solving the problem of insufficient monitoring accuracy of existing sensors and improving the accuracy of temperature and humidity calculation of the substation protection chamber.

[0027] Furthermore, inputting the external influence data into the convection heat transfer model, calculating the 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 includes:

[0028] Performing cluster analysis on the external influence data, exhaustively combining the external influence data of cluster center samples to form input data;

[0029] Inputting the input data into the convection heat transfer model, calculating and obtaining second temperature data and second humidity data in the chamber, and establishing a second temperature data matrix and a second humidity data matrix;

[0030] Construct a temperature and humidity database according to the second temperature data matrix and the second humidity data matrix:

[0031] D=[T,H] T , T=[T1,T2,…,T n ],H=[H1,H2,…,H n ];

[0032] Where T represents the second temperature data matrix, H represents the second humidity data matrix, and n represents the number of exhaustive combinations.

[0033] From the above description, it can be seen that by performing cluster analysis and exhaustive combination on the external influence data, a variety of external influence data combinations can be obtained, thereby improving the working condition coverage of the temperature and humidity database.

[0034] Furthermore, cluster analysis is performed on the external influence data, and the external influence data of the cluster center samples are exhaustively combined to form input data including:

[0035] Establish the sample set Z of the external influence data = [Z1, Z2, ..., Z p ], p represents the number of the first temperature and humidity data collected, the i-th sample Z in the sample set i =[S i1 ,S i2 ,…,S iM ], M represents the type of the external impact data;

[0036] Selecting a preset number of samples from the sample set as cluster center samples to form a first cluster center set;

[0037] Iteratively updating the cluster center samples of the first cluster center set to obtain a second cluster center set;

[0038] Exhaustively combine the external influence data of each cluster center sample in the second cluster center set, sort the exhaustive combinations from most to least according to the frequency of occurrence, and use a preset number of combinations before sorting as input data.

[0039] From the above description, it can be seen that exhaustive combinations are performed based on the different external influence data of different cluster center samples, and the final combination is selected as the input data based on the frequency of occurrence. Therefore, filtering out less common combinations can improve the efficiency and accuracy of subsequent temperature and humidity calculations.

[0040] Furthermore, obtaining a temperature and humidity calculation error 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 includes:

[0041] Calculate the second temperature and humidity data corresponding to the nearest cluster center in the temperature and humidity database using Euclidean distance;

[0042] Calculating a temperature and humidity calculation error between the first temperature and humidity data and the second temperature and humidity data, and constructing a change curve based on the external influence data of the nearest cluster center and the temperature and humidity calculation error;

[0043] An error correction coefficient is obtained according to the change curve, and an error correction coefficient knowledge base is constructed by combining the cluster center and its corresponding external influence data and the error correction coefficient.

[0044] From the above description, it can be seen that by constructing an influencing factor-error change curve based on external influencing factors and the calculation error of temperature and humidity, the error correction coefficient can be determined quickly and accurately, which facilitates the subsequent error correction of temperature and humidity data.

[0045] 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 using the error correction coefficient to correct the second temperature and humidity data to obtain predicted temperature and humidity data in the small room includes:

[0046] According to the external influence data in the real-time working condition, the corresponding error correction coefficient matrix P is extracted from the error correction coefficient knowledge base, P = [P1, P2 ... P m ],P1=[P t1 , P h1 ] T , P t1 is the temperature error correction coefficient corresponding to the first parameter, P h1 is the humidity error correction coefficient corresponding to the first parameter, and m is the parameter type;

[0047] According to the external influence data in the real-time working condition, the second temperature and humidity data with the closest Euclidean distance is matched in the temperature and humidity database to obtain the initial temperature and humidity data [T f , H f ];

[0048] Calculate the predicted temperature and humidity data in the small room [T s , H s ]:

[0049] [T s , H s ]=[T f , H f ]+P△s;

[0050] Where, △s=[s1,s2,…,s m ] T Represents the difference between each external impact data and the cluster center.

[0051] From the above description, it can be seen that correcting the initial temperature and humidity data through the error correction coefficient matrix can improve the calculation accuracy of the temperature and humidity of the substation protection room.

[0052] Please refer to Figure 2 Another embodiment of the present invention provides a temperature and humidity calculation terminal in a transformer substation protection room, comprising:

[0053] A data acquisition module is used to collect external impact data of the substation protection chamber and first temperature and humidity data of the chamber wall;

[0054] a convection heat transfer calculation module, configured to establish a convection heat transfer model within the substation protection chamber based on the dimension data of the chamber, input the external influence data into the convection heat transfer model, calculate the second temperature and humidity data within the chamber, and construct a temperature and humidity database by combining the external influence data and the corresponding second temperature and humidity data;

[0055] a knowledge base generation module, configured to obtain a temperature and humidity calculation error by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and to construct an error correction coefficient knowledge base;

[0056] The temperature and humidity prediction module is used to receive real-time working conditions, match corresponding error correction coefficients from the error correction coefficient knowledge base according to external influence data in the real-time working conditions, match 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 use the error correction coefficient to correct the second temperature and humidity data to obtain predicted temperature and humidity data in the small room.

[0057] As can be seen from the above description, the external influence data of the substation protection chamber and the temperature and humidity data of the chamber wall are collected; a convection heat transfer model is established based on the chamber's own dimensional data, so that the chamber's temperature and humidity data can be calculated using the external influence data, and a database is established that associates the external influence data with the calculated temperature and humidity data; the calculated temperature and humidity data are compared with the actual temperature and humidity data measured on the wall, and the corresponding calculation error coefficient is obtained in combination with the external influence data; therefore, the corresponding temperature and humidity data and error coefficient can be calculated based on the external influence data under real-time working conditions, thereby predicting the temperature and humidity data. In this way, the temperature and humidity can be predicted by combining the external influence factors of the chamber with the factors of the chamber itself, solving the problem of insufficient monitoring accuracy of existing sensors and improving the accuracy of temperature and humidity calculations in substation protection chambers.

[0058] Furthermore, inputting the external influence data into the convection heat transfer model, calculating the 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 includes:

[0059] Performing cluster analysis on the external influence data, exhaustively combining the external influence data of cluster center samples to form input data;

[0060] Inputting the input data into the convection heat transfer model, calculating and obtaining second temperature data and second humidity data in the chamber, and establishing a second temperature data matrix and a second humidity data matrix;

[0061] Construct a temperature and humidity database according to the second temperature data matrix and the second humidity data matrix:

[0062] D=[T,H] T , T=[T1,T2,…,T n ],H=[H1,H2,…,H n ];

[0063] Where T represents the second temperature data matrix, H represents the second humidity data matrix, and n represents the number of exhaustive combinations.

[0064] From the above description, it can be seen that by performing cluster analysis and exhaustive combination on the external influence data, a variety of external influence data combinations can be obtained, thereby improving the working condition coverage of the temperature and humidity database.

[0065] Furthermore, cluster analysis is performed on the external influence data, and the external influence data of the cluster center samples are exhaustively combined to form input data including:

[0066] Establish the sample set Z of the external influence data = [Z1, Z2, ..., Z p], p represents the number of the first temperature and humidity data collected, the i-th sample Z in the sample set i =[S i1 ,S i2 ,…,S iM ], M represents the type of the external impact data;

[0067] Selecting a preset number of samples from the sample set as cluster center samples to form a first cluster center set;

[0068] Iteratively updating the cluster center samples of the first cluster center set to obtain a second cluster center set;

[0069] Exhaustively combine the external influence data of each cluster center sample in the second cluster center set, sort the exhaustive combinations from most to least according to the frequency of occurrence, and use a preset number of combinations before sorting as input data.

[0070] From the above description, it can be seen that exhaustive combinations are performed based on the different external influence data of different cluster center samples, and the final combination is selected as the input data based on the frequency of occurrence. Therefore, filtering out less common combinations can improve the efficiency and accuracy of subsequent temperature and humidity calculations.

[0071] Furthermore, obtaining a temperature and humidity calculation error 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 includes:

[0072] Calculate the second temperature and humidity data corresponding to the nearest cluster center in the temperature and humidity database using Euclidean distance;

[0073] Calculating a temperature and humidity calculation error between the first temperature and humidity data and the second temperature and humidity data, and constructing a change curve based on the external influence data of the nearest cluster center and the temperature and humidity calculation error;

[0074] An error correction coefficient is obtained according to the change curve, and an error correction coefficient knowledge base is constructed by combining the cluster center and its corresponding external influence data and the error correction coefficient.

[0075] From the above description, it can be seen that by constructing an influencing factor-error change curve based on external influencing factors and the calculation error of temperature and humidity, the error correction coefficient can be determined quickly and accurately, which facilitates the subsequent error correction of temperature and humidity data.

[0076] 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 using the error correction coefficient to correct the second temperature and humidity data to obtain predicted temperature and humidity data in the small room includes:

[0077] According to the external influence data in the real-time working condition, the corresponding error correction coefficient matrix P is extracted from the error correction coefficient knowledge base, P = [P1, P2 ... P m ],P1=[P t1 , P h1 ] T , P t1 is the temperature error correction coefficient corresponding to the first parameter, P h1 is the humidity error correction coefficient corresponding to the first parameter, and m is the parameter type;

[0078] According to the external influence data in the real-time working condition, the second temperature and humidity data with the closest Euclidean distance is matched in the temperature and humidity database to obtain the initial temperature and humidity data [T f , H f ];

[0079] Calculate the predicted temperature and humidity data in the small room [T s , H s ]:

[0080] [T s , H s ]=[T f , H f ]+P△s;

[0081] Where, △s=[s1,s2,…,s m ] T Represents the difference between each external impact data and the cluster center.

[0082] From the above description, it can be seen that correcting the initial temperature and humidity data through the error correction coefficient matrix can improve the calculation accuracy of the temperature and humidity of the substation protection room.

[0083] The above-mentioned method and terminal for calculating temperature and humidity in a substation protection chamber of the present invention are suitable for calculating temperature and humidity in a substation protection chamber based on multi-dimensional influence quantities. The following is an explanation of the method and terminal through specific implementation methods:

[0084] Example 1

[0085] Please refer to Figure 1 A method for calculating temperature and humidity in a transformer substation protection chamber comprises the following steps:

[0086] S1. Collect external impact data of the substation protection room and first temperature and humidity data of the room wall.

[0087] Specifically, in this embodiment, the external influence data includes the outdoor environment data and the indoor air conditioning status data. The environmental data includes hourly temperature, relative humidity, global solar radiation, diffuse solar radiation, wind direction, and wind speed; the air conditioning status data includes daily air conditioning set temperature, the number of air conditioners in operation and outages, operating mode, and wind direction.

[0088] S2. Based on the size data of the substation protection chamber, a convection heat transfer model is established in the chamber, the external influence data is input into the convection heat transfer model, the second temperature and humidity data in the chamber are calculated, and a temperature and humidity database is constructed by combining the external influence data and its corresponding second temperature and humidity data.

[0089] S21. Based on the dimension data of the substation protection chamber, a finite element simulation software is used to establish a convection heat transfer model inside the chamber.

[0090] In this embodiment, the dimensional data for the substation protection chamber includes chamber building dimensions, cabinet parameters, and temperature control parameters. The building dimensions include wall dimensions, roof pitch, and interior area; the cabinet parameters include cabinet type, number of chargers, and heating power; and the temperature control parameters include air conditioning layout, cooling power, and number of air conditioners.

[0091] S22. Calculate the temperature and humidity of the small room based on the typical data of the external influencing parameters, and build a typical parameter temperature and humidity database.

[0092] S221 . Perform cluster analysis on the external impact data, and exhaustively combine the external impact data of cluster center samples to form input data.

[0093] S2211: Create a sample set Z of the external impact data = [Z1, Z2, ..., Z p ], p represents the number of the first temperature and humidity data collected, the i-th sample Z in the sample set i =[S i1 ,S i2 ,…,S iM ], M represents the type of the external influence data.

[0094] S2212: Select a preset number of samples from the sample set as cluster center samples to form a first cluster center set.

[0095] Specifically, K samples are selected from the sample set Z as cluster center samples to form the first cluster center set A0 of K categories = [a1, a2, ..., a k ,…aK ], a k is the cluster center sample of the kth class, k = 1, 2,…, K.

[0096] S2213. Iteratively update the cluster center samples of the first cluster center set to obtain a second cluster center set.

[0097] Specifically, in this embodiment, it is necessary to iterate up to L times. For the lth iteration, l = 1, 2, ..., L, calculate each sample Z in the sample Z i The distance D to the K cluster center samples i , D i =[D il1 ,D il2 ,…,D ilK ], D ilk Represents sample Z i The distance to the kth cluster center sample, the sample Z i Classify into the class with the smallest distance to the cluster center;

[0098] Recalculate the cluster centers a of different categories lj :

[0099]

[0100] Where j = 1, 2, ..., K, c lj Indicates the number of samples belonging to category j in the sample set Z at the lth iteration, I(Z i ,j) represents the indicator function, when Z i When it belongs to category j, I(Z i ,j)=1, otherwise, I(Z i ,j)=0;

[0101] Get the lth cluster center set A l =[a l1 ,a l2 ,…,a lK ].

[0102] S2214. Exhaustively combine the external influence data of each cluster center sample in the second cluster center set, sort the exhaustive combinations from most to least according to the frequency of occurrence, and use a preset number of combinations before sorting as input data.

[0103] Specifically, for the cluster center set A l =[a l1 ,a l2 ,…,a lK ], the kth cluster center a lk The external influence parameter data set is [S k1 ,Sk2 ,…,S kM ], taking the external influence parameter data of the cluster center as the typical value, the mth type of external parameter data, m=1,2…,M, its typical value set is [S 1m ,S 2m ,…,S Km ], exhaustively combine the typical values ​​of M types of external parameters to form K M Typical value combinations are selected, and several combinations that appear more frequently in the sample are selected as input data.

[0104] S222, inputting the input data into the convection heat transfer model, calculating and obtaining second temperature data and second humidity data within the chamber, and establishing a second temperature data matrix T and a second humidity data matrix H;

[0105] Construct a temperature and humidity database according to the second temperature data matrix and the second humidity data matrix:

[0106] D=[T,H] T , T=[T1,T2,…,T n ],H=[H1,H2,…,H n ];

[0107] Where n represents the number of exhaustive combinations.

[0108] S3. Obtain 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 construct an error correction coefficient knowledge base.

[0109] S31. Calculate the second temperature and humidity data corresponding to the nearest cluster center in the temperature and humidity database using Euclidean distance.

[0110] S32. Calculate the temperature and humidity calculation errors ΔT and ΔH between the first temperature and humidity data and the second temperature and humidity data of the nearest cluster center, and construct a change curve based on the external influence data of the nearest cluster center and the temperature and humidity calculation error influence amount-error.

[0111] S33. Obtain an error correction coefficient according to the change curve, and construct an error correction coefficient knowledge base by combining the cluster center and its corresponding external influence data and the error correction coefficient.

[0112] S4. Receive real-time working conditions, match corresponding error correction coefficients from the error correction coefficient knowledge base according to external influence data in the real-time working conditions, match 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 use the error correction coefficients to correct the second temperature and humidity data to obtain predicted temperature and humidity data in the small room.

[0113] According to the external influence data in the real-time working condition, the corresponding error correction coefficient matrix P = [P1, P2, ..., P m ],P1=[P t1 , P h1 ] T , P t1 is the temperature error correction coefficient corresponding to the first parameter, P h1 is the humidity error correction coefficient corresponding to the first parameter, and m is the parameter type.

[0114] According to the external influence data in the real-time working condition, the second temperature and humidity data with the closest Euclidean distance is matched in the temperature and humidity database to obtain the initial temperature and humidity data [T f , H f ];

[0115] Calculate the predicted temperature and humidity data in the small room [T s , H s ]:

[0116] [T s , H s ]=[T f , H f ]+P△s;

[0117] Where, △s=[s1,s2,…,s m ] T Represents the difference between each external impact data and the cluster center.

[0118] Example 2

[0119] Please refer to Figure 2 A temperature and humidity calculation terminal in a transformer substation protection room, characterized by comprising:

[0120] The data acquisition module is used to collect external impact data of the substation protection room and the first temperature and humidity data of the room wall.

[0121] The convection heat transfer calculation module is used to establish a convection heat transfer model in the substation protection chamber based on the size data of the chamber, input the external influence data into the convection heat transfer model, calculate the second temperature and humidity data in the chamber, and construct a temperature and humidity database in combination with the external influence data and its corresponding second temperature and humidity data.

[0122] The convection heat transfer calculation module includes the following components:

[0123] Perform cluster analysis on the external influence data, and exhaustively combine the external influence data of the cluster center samples to form input data:

[0124] Establish the sample set Z of the external influence data = [Z1, Z2, ..., Z p ], p represents the number of the first temperature and humidity data collected, the i-th sample Z in the sample set i =[S i1 ,S i2 ,…,S iM ], M represents the type of the external impact data;

[0125] Selecting a preset number of samples from the sample set as cluster center samples to form a first cluster center set;

[0126] Iteratively updating the cluster center samples of the first cluster center set to obtain a second cluster center set;

[0127] Exhaustively combine the external influence data of each cluster center sample in the second cluster center set, sort the exhaustive combinations from most to least according to the frequency of occurrence, and use a preset number of combinations before sorting as input data.

[0128] The input data is input into the convection heat transfer model, the second temperature data and the second humidity data in the chamber are calculated, and a second temperature data matrix and a second humidity data matrix are established.

[0129] Construct a temperature and humidity database according to the second temperature data matrix and the second humidity data matrix:

[0130] D=[T,H] T , T=[T1,T2,…,T n ],H=[H1,H2,…,H n ];

[0131] Where T represents the second temperature data matrix, H represents the second humidity data matrix, and n represents the number of exhaustive combinations.

[0132] The knowledge base generation module is used to obtain a temperature and humidity calculation error by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and to construct an error correction coefficient knowledge base.

[0133] The knowledge base generation module includes the following components:

[0134] Calculate the second temperature and humidity data corresponding to the nearest cluster center in the temperature and humidity database using Euclidean distance;

[0135] Calculating a temperature and humidity calculation error between the first temperature and humidity data and the second temperature and humidity data, and constructing a change curve based on the external influence data of the nearest cluster center and the temperature and humidity calculation error;

[0136] An error correction coefficient is obtained according to the change curve, and an error correction coefficient knowledge base is constructed by combining the cluster center and its corresponding external influence data and the error correction coefficient.

[0137] The temperature and humidity prediction module is used to receive real-time working conditions, match corresponding error correction coefficients from the error correction coefficient knowledge base according to external influence data in the real-time working conditions, match 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 use the error correction coefficient to correct the second temperature and humidity data to obtain predicted temperature and humidity data in the small room.

[0138] The temperature and humidity prediction module includes:

[0139] According to the external influence data in the real-time working condition, the corresponding error correction coefficient matrix P is extracted from the error correction coefficient knowledge base, P = [P1, P2 ... P m ],P1=[P t1 , P h1 ] T , P t1 is the temperature error correction coefficient corresponding to the first parameter, P h1 is the humidity error correction coefficient corresponding to the first parameter, and m is the parameter type;

[0140] According to the external influence data in the real-time working condition, the second temperature and humidity data with the closest Euclidean distance is matched in the temperature and humidity database to obtain the initial temperature and humidity data [T f , H f ];

[0141] Calculate the predicted temperature and humidity data in the small room [T s , H s ]:

[0142] [T s , H s ]=[T f , H f ]+P△s;

[0143] Where, △s=[s1, s2……s m ] T Represents the difference between each external impact data and the cluster center.

[0144] In summary, the present invention provides a method and terminal for calculating temperature and humidity in a transformer substation protection chamber, which collects external influence data of the transformer substation protection chamber and temperature and humidity data of the chamber wall; establishes a convection heat transfer model based on the chamber's own size data, so that the chamber's temperature and humidity data can be calculated through external influence data, and establishes a database associated with the external influence data and the calculated temperature and humidity data; compares the calculated temperature and humidity data with the actual temperature and humidity data measured on the wall, and obtains the corresponding calculation error coefficient based on the external influence data; therefore, the corresponding temperature and humidity data and error coefficient can be calculated based on the external influence data under real-time working conditions, thereby predicting the temperature and humidity data. In this way, the temperature and humidity can be predicted by combining the external influence factors of the chamber and the factors of the body, solving the problem of insufficient monitoring accuracy of existing sensors and improving the accuracy of temperature and humidity calculation of the transformer substation protection chamber.

[0145] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's description and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for calculating temperature and humidity in a transformer substation protection room, characterized in that: Including steps: Collect external impact data of the substation protection room and the first temperature and humidity data of the room wall; Based on the dimension data of the substation protection chamber, a convection heat transfer model is established in the chamber, the external influence data is input into the convection heat transfer model, the second temperature and humidity data in the chamber is calculated, and a temperature and humidity database is constructed by combining the external influence data and the corresponding second temperature and humidity data; Obtaining a temperature and humidity calculation error 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 includes: calculating the second temperature and humidity data corresponding to the nearest cluster center in the temperature and humidity database using Euclidean distance; calculating the temperature and humidity calculation error between the first temperature and humidity data and the second temperature and humidity data, constructing a change curve based on the external influence data of the nearest cluster center and the temperature and humidity calculation error; obtaining an error correction coefficient based on the change curve, and constructing an error correction coefficient knowledge base in combination with the cluster center and its corresponding external influence data and the error correction coefficient; Receiving a real-time operating condition, matching a corresponding error correction coefficient from the error correction coefficient knowledge base according to external influence data in the real-time operating condition, matching corresponding second temperature and humidity data in the temperature and humidity database according to the external influence data in the real-time operating condition, and correcting the second temperature and humidity data using the error correction coefficient to obtain predicted temperature and humidity data in the small room includes: According to the external influence data in the real-time working condition, the corresponding error correction coefficient matrix P is extracted from the error correction coefficient knowledge base, P=[P1, P2...P m ],P1=[P t1 , P h1 ] T , P t1 is the temperature error correction coefficient corresponding to the first parameter, P h1 is the humidity error correction coefficient corresponding to the first parameter, and m is the parameter type; According to the external influence data in the real-time working condition, the second temperature and humidity data with the closest Euclidean distance is matched in the temperature and humidity database to obtain the initial temperature and humidity data [T f , H f ]; Calculate the predicted temperature and humidity data in the small room [T s , H s ]: ； Where, Represents the difference between each external impact data and the cluster center.

2. The method for calculating temperature and humidity in a transformer substation protection room according to claim 1, characterized in that: Inputting the external influence data into the convection heat transfer model, calculating the second temperature and humidity data in the small room, and building a temperature and humidity database by combining the external influence data and the corresponding second temperature and humidity data includes: Performing cluster analysis on the external influence data, exhaustively combining the external influence data of cluster center samples to form input data; Inputting the input data into the convection heat transfer model, calculating and obtaining second temperature data and second humidity data in the chamber, and establishing a second temperature data matrix and a second humidity data matrix; Construct a temperature and humidity database according to the second temperature data matrix and the second humidity data matrix: D=[T,H] T ,T=[T1,T2,…,T n ],H=[H1,H2,…,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 for calculating temperature and humidity in a transformer substation protection room according to claim 2, characterized in that: Perform cluster analysis on the external impact data, exhaustively combine the external impact data of the cluster center samples, and form input data including: Establish the sample set Z=[Z1,Z2,…,Z p ], p represents the number of the first temperature and humidity data collected, the i-th sample Z in the sample set i =[S i1 ,S i2 ,…,S iM ], M represents the type of the external impact data; Selecting a preset number of samples from the sample set as cluster center samples to form a first cluster center set; Iteratively updating the cluster center samples of the first cluster center set to obtain a second cluster center set; Exhaustively combine the external influence data of each cluster center sample in the second cluster center set, sort the exhaustive combinations from most to least according to the frequency of occurrence, and use a preset number of combinations before sorting as input data.

4. A temperature and humidity calculation terminal in a transformer substation protection room, characterized in that: include: A data acquisition module is used to collect external impact data of the substation protection chamber and first temperature and humidity data of the chamber wall; a convection heat transfer calculation module, configured to establish a convection heat transfer model within the substation protection chamber based on the dimension data of the chamber, input the external influence data into the convection heat transfer model, calculate the second temperature and humidity data within the chamber, and construct 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 configured to obtain a temperature and humidity calculation error by comparing the first temperature and humidity data with the second temperature and humidity data corresponding to each external influence data, and to construct an error correction coefficient knowledge base, including: using Euclidean distance to calculate the second temperature and humidity data corresponding to the nearest cluster center in the temperature and humidity database; calculating the temperature and humidity calculation error between the first temperature and humidity data and the second temperature and humidity data, and constructing a change curve based on the external influence data of the nearest cluster center and the temperature and humidity calculation error; obtaining an error correction coefficient based on the change curve, and constructing an error correction coefficient knowledge base by combining the cluster center and its corresponding external influence data and the error correction coefficient; The temperature and humidity prediction module is configured to receive real-time operating conditions, match corresponding error correction coefficients from the error correction coefficient knowledge base based on external influence data in the real-time operating conditions, match corresponding second temperature and humidity data in the temperature and humidity database based on the external influence data in the real-time operating conditions, and use the error correction coefficients to correct the second temperature and humidity data to obtain predicted temperature and humidity data in the small room, including: According to the external influence data in the real-time working condition, the corresponding error correction coefficient matrix P is extracted from the error correction coefficient knowledge base, P=[P1, P2...P m ],P1=[P t1 , P h1 ] T , P t1 is the temperature error correction coefficient corresponding to the first parameter, P h1 is the humidity error correction coefficient corresponding to the first parameter, and m is the parameter type; According to the external influence data in the real-time working condition, the second temperature and humidity data with the closest Euclidean distance is matched in the temperature and humidity database to obtain the initial temperature and humidity data [T f , H f ]; Calculate the predicted temperature and humidity data in the small room [T s , H s ]: ； Where, Represents the difference between each external impact data and the cluster center.

5. The temperature and humidity calculation terminal in the transformer substation protection room according to claim 4, characterized in that: Inputting the external influence data into the convection heat transfer model, calculating the second temperature and humidity data in the small room, and building a temperature and humidity database by combining the external influence data and the corresponding second temperature and humidity data includes: Performing cluster analysis on the external influence data, exhaustively combining the external influence data of cluster center samples to form input data; Inputting the input data into the convection heat transfer model, calculating and obtaining second temperature data and second humidity data in the chamber, and establishing a second temperature data matrix and a second humidity data matrix; Construct a temperature and humidity database according to the second temperature data matrix and the second humidity data matrix: D=[T,H] T ,T=[T1,T2,…,T n ],H=[H1,H2,…,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.

6. The temperature and humidity calculation terminal in the transformer substation protection room according to claim 5, characterized in that: Perform cluster analysis on the external impact data, exhaustively combine the external impact data of the cluster center samples, and form input data including: Establish the sample set Z=[Z1,Z2,…,Z p ], p represents the number of the first temperature and humidity data collected, the i-th sample Z in the sample set i =[S i1 ,S i2 ,…,S iM ], M represents the type of the external impact data; Selecting a preset number of samples from the sample set as cluster center samples to form a first cluster center set; Iteratively updating the cluster center samples of the first cluster center set to obtain a second cluster center set; Exhaustively combine the external influence data of each cluster center sample in the second cluster center set, sort the exhaustive combinations from most to least according to the frequency of occurrence, and use a preset number of combinations before sorting as input data.

Images