Transmission line freezing disaster detection method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a power transmission line freezing disaster detection method and device, electronic equipment and a storage medium, and the method comprises the steps: employing a KDLV algorithm to fuse with an ALD model, and extracting the dynamic and static features of data, thereby further detecting the freezing disaster condition of a power transmission line through employing an autoregression model in the KDLV algorithm. Wherein the T statistical limit of the first autoregression model constructed based on the training data can represent the condition of the power transmission line which is relatively normal (free of freezing disasters); the T statistical value of the second autoregression model constructed based on the test data can be used for representing the freezing disaster condition of the to-be-tested power transmission line. Therefore, the detection result of the extreme freezing disaster of the power transmission line can be obtained by comparing the T statistical limit corresponding to the training data with the T statistical value corresponding to the test data. On the premise that a small amount of icing weight data is used as a training set, early warning of the extreme freezing disaster of the power transmission line of the power grid system is completed in a self-adaptive mode, and the accuracy of icing disaster detection is improved.

Description

Technical Field

[0001] The present application relates to the technical field of power transmission line inspection, and in particular to a method, device, electronic equipment and storage medium for detecting freezing disasters on power transmission lines. Background Art

[0002] The power system plays a vital role in the development of modern society and daily life. It is not only the cornerstone of industrial production, but also the basic need of residents' daily life. The stable supply of electricity directly affects the stable growth of the economy and the overall function of society. The stable operation of the power system is closely related to weather conditions. Transmission lines are exposed to the air all year round and are constantly exposed to extreme weather conditions such as wind, sun, and even rain and snow, which makes safety problems very likely to occur. Therefore, it is necessary to conduct freezing disaster detection on transmission lines.

[0003] With the continuous improvement of machine learning and data collection capabilities, data-driven methods have gradually become the mainstream of ice detection. However, such methods require a large number of fault samples (samples that have already caused ice disasters) when training the model in order to better identify the ice state. However, when facing an extreme freezing disaster that occurs once in a century, it is difficult to obtain samples with extremely low probability, so the above methods will have difficulties in training the model, which will affect the final ice disaster detection rate. Summary of the invention

[0004] The embodiments of the present application disclose a method, device, electronic device and storage medium for detecting freezing disasters on power transmission lines, which can adaptively complete early warning of extreme freezing disasters on power grid system transmission lines under the premise of using a small amount of ice weight data as a training set, thereby improving the accuracy of ice disaster detection.

[0005] The present application embodiment discloses a method for detecting freezing disasters on power transmission lines, the method comprising:

[0006] Acquire a first data set; the first data set includes ice weight data and meteorological condition data of the transmission line; pre-process the first data set to obtain a second data set;

[0007] Projecting the second data set by using a kernel principal component extraction strategy of a kernel dynamic latent variable (KDLV) algorithm to obtain a principal component matrix;

[0008] Extracting training data and test data from the principal component matrix; wherein the training data is data in the principal component matrix representing that the power transmission line is in a normal state and in a first icing state; the test data is data in the principal component matrix representing that the power transmission line is in a normal state and in a second icing state; the second icing state indicates a higher degree of icing than the first icing state;

[0009] Building a first autoregressive model using the dynamic components in the training data through the KDLV algorithm, and calculating the T statistical limit corresponding to the first autoregressive model;

[0010] Calculating an ALD value of each piece of data in the test data, and filtering out first test sub-data and second test sub-data from the test data according to the ALD value;

[0011] Using the first test sub-data to update the first autoregressive model, so as to update the T statistical limit;

[0012] Using the KDLV algorithm, a second autoregressive model is constructed using the dynamic components in the second test sub-data, and a T statistic corresponding to the second autoregressive model is calculated;

[0013] The detection result of the power transmission line freezing disaster is determined according to the comparison result of the T statistical limit and the T statistical value.

[0014] As an optional implementation manner, determining the detection result of the power transmission line freezing disaster according to the comparison result of the T statistical limit and the T statistical value includes:

[0015] If the T statistic value is greater than the T statistic time limit, an alarm is output; the alarm is used to indicate that there is a freezing disaster on the power transmission line; or,

[0016] If the T statistic is less than or equal to the T statistic, it is determined that there is no freezing disaster on the transmission line.

[0017] As an optional implementation manner, the step of selecting the first test sub-data and the second test sub-data from the test data according to the ALD value includes:

[0018] Filtering out first test sub-data and second test sub-data from the test data according to a comparison result of the ALD value and the error threshold;

[0019] The first test sub-data is the test data whose corresponding ALD value is greater than the error threshold; the second test sub-data is the test data whose corresponding ALD value is greater than or equal to the error threshold.

[0020] As an optional implementation, the first autoregressive model and the second autoregressive model are both AR(2) models; and there are at least three of the second test sub-data between every two adjacent first test sub-data.

[0021] As an optional implementation manner, preprocessing the first data set to obtain the second data set includes:

[0022] Decomposing the data in the first data set into K intrinsic mode functions by using a variational mode decomposition (VMD) algorithm to perform noise reduction processing on the first data set; K is a positive integer greater than or equal to 1;

[0023] The time domain features and frequency features of the K intrinsic mode functions are extracted, and the extracted time domain features and frequency domain features are respectively standardized to obtain a second data set.

[0024] As an optional implementation, the meteorological condition data at least includes average sunshine intensity, and the average sunshine intensity is the average value of sunshine intensity values ​​at N sampling moments; N is a positive integer greater than or equal to 2;

[0025] As an optional implementation manner, the meteorological condition data at least further includes temperature data in the range of -15°C to 0°C; or, the meteorological condition data at least further includes humidity data greater than 80%.

[0026] The present application embodiment discloses a transmission line freezing disaster detection device, comprising:

[0027] An acquisition module, configured to acquire a first data set; the first data set includes ice weight data and meteorological condition data of the transmission line;

[0028] A preprocessing module, used for preprocessing the first data set to obtain a second data set;

[0029] A first processing module is used to project the second data set by using a kernel principal component extraction strategy of a kernel dynamic latent variable (KDLV) algorithm to obtain a principal component matrix;

[0030] An extraction module is used to extract training data and test data from the principal component matrix; wherein the training data is data in the principal component matrix representing that the power transmission line is in a normal state and in a first icing state; the test data is data in the principal component matrix representing that the power transmission line is in a normal state and in a second icing state; the second icing state indicates a higher degree of icing than the first icing state;

[0031] A second processing module is used to build a first autoregressive model using the dynamic components in the training data through a KDLV algorithm, and calculate the T statistical limit corresponding to the first autoregressive model;

[0032] a calculation module, configured to calculate an ALD value of each piece of data in the test data, and filter out first test sub-data and second test sub-data from the test data according to the ALD value;

[0033] An updating module, configured to update the first autoregressive model using the first test sub-data to update the T statistical limit;

[0034] A third processing module, configured to build a second autoregressive model using the dynamic components in the second test sub-data by using a KDLV algorithm, and calculate a T statistic corresponding to the second autoregressive model;

[0035] A determination module is used to determine the detection result of the freezing disaster of the transmission line according to the comparison result of the T statistical limit and the T statistical value.

[0036] An embodiment of the present application discloses an electronic device, which includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the processor implements any one of the power transmission line freezing detection methods disclosed in the embodiments of the present application.

[0037] An embodiment of the present application discloses a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, any one of the power transmission line freezing detection methods disclosed in the embodiment of the present application is implemented.

[0038] Compared with the related art, the embodiments of the present application have the following beneficial effects:

[0039] In an embodiment of the present application, by collecting a small amount of ice weight data and meteorological condition data, and using the KDLV algorithm to fuse the ALD model, the dynamic and static characteristics of the data can be extracted, so that the freezing disaster situation of the transmission line can be detected according to the autoregressive model of the KDLV algorithm. Among them, the T statistical limit of the first autoregressive model constructed based on the training data can characterize the relatively normal (no freezing disaster) transmission line situation; the T statistical value of the second autoregressive model constructed based on the test data can be used to characterize the freezing disaster situation of the transmission line to be tested. Therefore, by comparing the T statistical limit and the T statistical value, the detection result of the extreme freezing disaster of the transmission line can be obtained.

[0040] It can be seen that the implementation of the embodiment of the present application can adaptively complete the early warning of extreme freezing disasters on the power transmission lines of the power grid system under the premise of using a small amount of ice weight data as a training set, thereby improving the accuracy of ice disaster detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 A schematic diagram of a flow chart of a method for detecting freezing disasters of power transmission lines disclosed in an embodiment of the present application;

[0043] Figure 2 It is a structural schematic diagram of a transmission line freezing disaster detection device disclosed in an embodiment of the present application;

[0044] Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present application and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0047] The embodiments of the present application disclose a method, device, electronic device and storage medium for detecting freezing disasters on power transmission lines, which can adaptively complete the early warning of extreme freezing disasters on power transmission lines of a power grid system under the premise of using a small amount of ice weight data as a training set, thereby improving the accuracy of ice disaster detection. The following are detailed descriptions.

[0048] See also Figure 1 , Figure 1 is a flow chart of a method for detecting freezing disasters of power transmission lines disclosed in an embodiment of the present application, Figure 1 The method shown can be executed by electronic devices with computing capabilities such as personal computers and industrial computers. Figure 1 As shown, the method may include the following steps:

[0049] 110. Obtain a first data set, where the first data set includes ice weight data and meteorological condition data of the transmission line.

[0050] In the embodiment of the present application, the ice weight data and meteorological condition data of the transmission line can be the characteristic data of the transmission line at the same sampling time interval selected from the power grid system. The meteorological condition data can include one or more of the following six meteorological condition data: temperature, humidity, average sunshine intensity, wind speed, wind direction, and air pressure.

[0051] The average sunshine intensity may refer to the average sunshine intensity value at N sampling moments; N is a positive integer greater than or equal to 2. The average value may be an arithmetic mean or a weighted mean, and is not specifically limited. For example, the calculation of the average sunshine intensity may refer to the following formula:

[0052]

[0053] Among them, a1 a2…a r Represents the sunshine intensity value at r sampling moments in a certain day. Due to the revolution of the earth, the daily sunshine time before and after the winter solstice is different, so Q is the balance coefficient for adjustment.

[0054] It is understandable that the instantaneous "sunlight intensity" is only for daytime, and the sunshine intensity value will quickly drop to 0 at night. Therefore, it is not practical to use only the "sunlight intensity" value as a factor affecting the formation of freezing disasters. Therefore, using the average sunshine intensity can more accurately characterize the impact of sunshine on the formation of freezing disasters.

[0055] It should be noted that, except for the average sunshine intensity, other meteorological condition data can be sample values ​​corresponding to the sampling time.

[0056] In addition, in some other possible embodiments, the meteorological condition data may be further screened in combination with the ice formation mechanism in the icing mechanism to remove abnormal values, so as to improve the accuracy of the entire detection algorithm.

[0057] Optionally, the temperature data in the meteorological condition data may be screened according to the temperature range of ice formation in the icing mechanism. For example, the temperature data within the range of -15°C to 0°C may be retained, and the temperature data outside the temperature range may be removed.

[0058] Optionally, the humidity data in the meteorological condition data may be screened according to the humidity range formed by the temperature in the ice-covering mechanism, for example, including retaining humidity data greater than 80% and removing humidity data less than or equal to 80%.

[0059] 120. Preprocess the first data set to obtain a second data set.

[0060] In the embodiment of the present application, the operation of preprocessing the first data set may include but is not limited to one or more of the following: data cleaning, noise reduction, resampling, type conversion, etc. The purpose of preprocessing is to improve the accuracy of the data so that the second data set obtained after preprocessing can more accurately characterize the icing state of the transmission line.

[0061] As an optional implementation, the electronic device may perform noise reduction processing on the first data set by using a VMD algorithm to reduce modal aliasing in the data. Therefore, the electronic device may perform the following steps:

[0062] 1201. Decompose the data in the first data set into K intrinsic mode functions by using a VMD algorithm, where K is a positive integer greater than or equal to 1. Exemplarily, the specific constrained variation process may be as follows:

[0063]

[0064] Among them, {u k} represents the set of variational intrinsic mode function (VIMF) components obtained after decomposition, {ω k} represents the corresponding center frequency set, It means to find the partial derivative, δ(t) represents the unit pulse function, j is the imaginary unit, and f(t) represents the signal before VMD decomposition.

[0065] 1202. Extract time domain features and frequency features of K intrinsic mode functions, and standardize the extracted time domain features and frequency domain features to obtain a second data set.

[0066] Among them, the process of standardizing the extracted time domain features and frequency domain features respectively can be as follows:

[0067]

[0068] Among them, x k ` indicates the input data after standardization, x k is the extracted time domain feature or frequency domain feature, represents the mean of the i-th feature, σ i Indicates the standard deviation of the extracted time domain features or frequency domain features.

[0069] 130. The second data set is projected using the kernel principal component extraction strategy of the kernel dynamic latent variable (KDLV) algorithm to obtain a principal component matrix.

[0070] In the embodiment of the present application, the kernel principal component extraction strategy in the KDLV algorithm can be applied to project the data in the second data set to obtain a principal component matrix. Exemplarily, the principal component matrix can be expressed by the following formula:

[0071] X=[x1,...x n ] T (4)

[0072] In addition, it can be further assumed that the matrix of z time delays of the main element matrix is ​​as shown in the following formula, and this assumption is applicable to the subsequent step 150:

[0073] X z =[x q-z , x q-z+1 …x q-z+n-1 ] T (z=0,...,q-1) (5)

[0074] Where q represents the maximum time that can be delayed, and n represents the number of samples.

[0075] 140. Extract training data and test data from the principal component matrix.

[0076] In an embodiment of the present application, the training data may be data in the principal element matrix representing that the power transmission line is in a normal state and in a first icing state; the test data may be data in the principal element matrix representing that the power transmission line is in a normal state and in a second icing state. The second icing state indicates a higher degree of icing than the first icing state. Exemplarily, the second icing state may refer to a more severe icing state, and the first icing state may refer to a slightly icing state. The definition of the degree of icing may be set based on business needs.

[0077] 150. The KDLV algorithm is used to build the first autoregressive model using the dynamic components in the training data, and the T statistical limit corresponding to the first autoregressive model is calculated.

[0078] In step 150, the electronic device may perform the following sub-steps in sequence:

[0079] 1510. Extracting dynamic components from training data;

[0080] 1520. Building a first autoregressive model based on the dynamic components extracted from the training data;

[0081] 1530. Calculate the T statistic limit corresponding to the first autoregressive model.

[0082] The following content describes the above three sub-steps in detail.

[0083] First, sub-step 1510: extracting dynamic components from training data may further include the following steps:

[0084] 1511. Obtain the objective function of the KDLV algorithm.

[0085] Assume that the optimization goal of the KDLV algorithm is as follows:

[0086]

[0087] st||w||=1, ||β||=1 (66-2)

[0088] Where β = [β0, ..., β q-1 ] T Represents X z The weight of w, w as X z The weight vector of .

[0089] Assume that the Kronecker product is used to represent the relationship between β and w, and select U to represent [X0, X1, ...X q-1 ], the corresponding objective function can be expressed as follows:

[0090]

[0091] st||w||=1, ||β||=1 (7-2)

[0092] or

[0093]

[0094] st||w||=1, ||β||=1 (8-2)

[0095] Where I represents the identity matrix.

[0096] 1512. Use an iterative algorithm to solve the aforementioned objective function.

[0097] In step 1511, it is assumed that w i =[1, 0, ... 0] T , the iterative algorithm continues until w i Convergence is the end. Use the obtained w i The dynamic invisible score vector s can be obtained i and the load vector l i , the specific formula is as follows:

[0098] s i =X i w i (9)

[0099]

[0100] 1513. When all the dynamic components in the feature data are extracted (assuming there are A dynamic components), set S = [s1, s2, ..., s A ], L i =[l1 ， l2, ..., l A ],W=[w1,w2,...,w A ]

[0101] And R=W(L T W) -1 , so far, we can get S=XR.

[0102] 1514. Given a new process data x g , whose dynamic score s dg And the corresponding residual e g The calculation method is as follows:

[0103]

[0104] Wherein, g represents the dynamic component of the g-th group of feature data.

[0105] In summary, based on the aforementioned steps 1511 to 1514, the electronic device can extract dynamic components from the training data.

[0106] Then, step 1520: construct a first autoregressive model according to the dynamic components extracted from the training data. The first autoregressive model can be any autoregressive (AR) model, such as a pure autoregressive model, a moving average model, etc.

[0107] Optionally, the first autoregressive model may be a pure autoregressive model, and the model predicts the current value based on the values ​​of the previous two time points. In other words, the first autoregressive model may be an AR(2) model. Exemplarily, the first autoregressive model may be described using an AR(2) model as shown below:

[0108]

[0109] Among them, s` dg represents the dynamic component after autoregression, and is the coefficient of autoregression, η dg is the amount of random error.

[0110] Finally, step 1530: Calculate the T statistical limit corresponding to the first autoregressive model. The T statistical limit can refer to the use of T 2 Statistical method to obtain the statistical limit value T of training data θ . For example, the T statistical limit T θ The calculation method can be shown as follows:

[0111]

[0112] The electronic device can calculate the T statistical limit of the first autoregressive model corresponding to the training data by executing step 150 as described above.

[0113] 160. Calculate the ALD value of each piece of data in the test data, and filter out the first test sub-data and the second test sub-data from the test data according to the ALD value.

[0114] In an embodiment of the present application, the test data may be sample data collected within the same time period as the training data; or, the test data may be sample data newly collected after the training data is selected, as long as the newly collected sample data meets the aforementioned test data requirements.

[0115] In the embodiment of the present application, the electronic device can perform ALD determination on each test data according to the Approximate Linear Dependence (ALD) algorithm to obtain its approximate error value (ALD value). For example, the ALD value corresponding to each test data can be calculated by the following formula:

[0116]

[0117] Among them, x i (i=1,K,z) represents the training data, z represents the number of training data, x z+1 represents the new sample (test data) entering the system, ε z+1 It means the new sample (test data) entering the system relative to the completed statistical limit T θ The error value between the established training data.

[0118] It can be seen that the ALD value ε corresponding to each test data z+1 The error value between the test data and the training data can be indicated, so that the first test sub-data for model updating and the second test sub-data not needed for model updating can be screened out from the test data using the ALD value corresponding to the test data.

[0119] As an optional implementation, an error threshold may be preset, and the error threshold is used to define the degree of difference between the test data and the training data that can be used for model updating. Exemplarily, the operation of selecting the first test sub-data and the second test sub-data from the test data according to the ALD value may be shown as follows:

[0120]

[0121] Among them, v is the set error threshold.

[0122] That is to say, when the ALD value ε of a certain test data z+1 If it is greater than the set threshold v, it means that this test data is relative to the completed statistical limit T θ The training data established are relatively independent of each other, so the statistical limit T has been established. θ The training data cannot be linearly represented for the test data, so it is necessary to put the test data into the training model to update the statistical limit and complete the real-time update of the model; when the ALD value ε of a certain test data z+1 Not greater than the set threshold v, indicating that this test data is relative to the completed statistical limit T θ The training data established have a certain linear relationship, and the statistical limit T can be used to θ The samples of represent the test data linearly, so there is no need to use the test data to update the model.

[0123] It should be noted that in the embodiment of the present application, there is no necessary logical relationship between the execution order of step 150 and step 160.

[0124] 170. Use the first test sub-data to update the first autoregressive model to update the T statistical limit.

[0125] In the embodiment of the present application, updating the first autoregressive model using the first test sub-data may include updating the first autoregressive model using the statistical limit T as shown in formula (13). θ The first test sub-data is added into the calculation.

[0126] 180. Using the KDLV algorithm, a second autoregressive model is constructed using the dynamic components in the second test sub-data, and the T statistic corresponding to the second autoregressive model is calculated.

[0127] In the embodiment of the present application, the specific implementation of step 180 can refer to the aforementioned step 150, including: the method of extracting the second test sub-data dynamic component can refer to the aforementioned step 1510, the method of using the extracted dynamic component to build the second autoregressive model can refer to the aforementioned step 1520, and the method of calculating the T statistic corresponding to the second autoregressive model can refer to the aforementioned step 1530, and the following content will not be repeated. It can be understood that the second autoregressive model can be any autoregressive model, and the T statistic is calculated according to T 2 The statistical limit T of the data in the second autoregressive model obtained by statistical method 2 .

[0128] 190. Determine the detection result of the power transmission line freezing disaster according to the comparison result of the T statistical limit corresponding to the training data and the T statistical value corresponding to the test data.

[0129] In the embodiment of the present application, the statistical limits of each data in the second autoregressive model are set to 2 The statistical limit T calculated with the first autoregressive model θ By making a comparison, the freezing state of the power transmission line at the time of detection can be determined. If the T statistic is less than or equal to the T statistic time limit, it is determined that there is no freezing disaster on the power transmission line. If the T statistic is greater than the T statistic time limit, it is determined that there is a freezing disaster on the power transmission line. Optionally, when it is determined that there is a freezing disaster on the power transmission line, the electronic device can output an alarm to remind the inspection personnel.

[0130] In some possible embodiments, the aforementioned first autoregressive model and the second autoregressive model are both AR(2) models. Since the establishment of the AR(2) model requires the dynamic latent variable values ​​at this moment and the two moments before this moment, this causes problems in the fusion process between the KDLV algorithm and the ALD algorithm. For example: after a test data is judged by the ALD rule and is found to meet the update strategy, it is put into the first autoregressive model to update the statistical limit, and a test data that is later in time than the test data is judged by the ALD rule and is found not to meet the update strategy, then the KDLV decomposition is continued in the second autoregressive model, but during the decomposition process, it is found that the latter test data cannot be used to build the AR(2) model, because the test data at the previous moment of this test data is in the first autoregressive model.

[0131] Therefore, when the electronic device selects the first test sub-data and the second test sub-data, the electronic device may further use the following rule: at least three second test sub-data are separated in time between every two adjacent first test sub-data. In other words, if a test data meeting the update condition shown in formula (15) is not separated from the previous first test sub-data by at least three second test sub-data that do not meet the update condition, then the test data meeting the update condition shown in formula (15) will not be determined as the first test sub-data.

[0132] Exemplarily, the above rule can be expressed as follows:

[0133] GZ = {gz c |c=1,2,...H} (16)

[0134] GZ′=gz′ c |c=1,2,...H-1} (17)

[0135]

[0136] Among them, c represents the index of test data that meets the update strategy, H represents the total number of test data that meets the update strategy, and gz` c Indicates the difference between every two test data that meet the update strategy. In the embodiment of the present application, the points required by the GZY set are saved, and the points required by the GZN set are regarded as invalid points.

[0137] At this point, even if the first autoregressive model and the second autoregressive model adopt the AR(2) model, the KDLV algorithm can be effectively combined with the ALD algorithm. The test data that does not meet the ALD rule can be effectively decomposed by the KDLV algorithm in the second autoregressive model to obtain its dynamic latent variable value (dynamic component).

[0138] It can be seen that the implementation of the transmission line freezing disaster detection method disclosed in the embodiment of the present application can integrate the KDLV algorithm and the ALD model, and adaptively complete the early warning of extreme freezing disasters on the power grid system transmission lines under the premise of using a small amount of ice weight data as a training set, thereby improving the accuracy of ice disaster detection.

[0139] Furthermore, in the preprocessing of data, considering the time specificity of the "sunshine intensity" feature and the problem of solar term specificity, the average sunshine intensity is used as meteorological data. On this basis, the embodiment of the present application can also filter the temperature and humidity data in combination with the icing mechanism. Therefore, the embodiment of the present application combines the icing mechanism with machine learning to detect freezing disasters on power transmission lines, which can effectively avoid the limitations of using only mechanism models for detection, and solve the problem that only using machine learning does not fully consider the influence of natural climate factors on the formation of icing disasters.

[0140] Furthermore, considering the possible noise problem of the data, the embodiment of the present application combines the VMD algorithm to perform noise reduction processing on the data, so that the system can not only effectively filter out the noise in the data preprocessing stage, but also realize adaptive detection while fully extracting the dynamic and static features of the data. Based on good noise reduction, the data input to the model has high validity and good completeness, ensuring that only a small amount of ice weight data is used as a training set to accurately detect freezing disasters, and can detect extreme freezing disasters that occur once in a century, which can alleviate the problems of difficult calculations and high complexity in previous methods.

[0141] Furthermore, in the process of integrating the KDLV algorithm and the ALD model, there may be problems with the expression of the AR(2) model. The embodiment of the present application sets conditional rules for the screening of test sub-data, so that the KDLV algorithm can be effectively combined with the ALD algorithm, and the dynamic and static characteristics of the data can be fully extracted while completing the adaptive detection of extreme freezing disasters on the transmission line, thereby ensuring the practicality of the method.

[0142] See also Figure 2 , Figure 2 The present application discloses a transmission line freezing disaster detection device. The transmission line freezing disaster detection device can be applied to any electronic device as described above. Figure 2 As shown, the device comprises:

[0143] The acquisition module 210 is used to acquire a first data set; the first data set includes ice weight data and meteorological condition data of the transmission line;

[0144] A preprocessing module 220, configured to preprocess the first data set to obtain a second data set;

[0145] A first processing module 230 is used to project the second data set using a kernel principal component extraction strategy of a kernel dynamic latent variable (KDLV) algorithm to obtain a principal component matrix;

[0146] Extraction module 240, used to extract training data and test data from the principal component matrix; wherein the training data is data in the principal component matrix representing that the power transmission line is in a normal state and in a first icing state; the test data is data in the principal component matrix representing that the power transmission line is in a normal state and in a second icing state; the second icing state indicates that the degree of icing is higher than that of the first icing state;

[0147] The second processing module 250 is used to build a first autoregressive model using the dynamic components in the training data through the KDLV algorithm, and calculate the T statistical limit corresponding to the first autoregressive model;

[0148] A calculation module 260, configured to calculate an ALD value of each piece of data in the test data, and filter out first test sub-data and second test sub-data from the test data according to the ALD value;

[0149] An updating module 270, configured to update the first autoregressive model using the first test sub-data to update the T statistical limit;

[0150] The third processing module 280 is used to build a second autoregressive model using the dynamic components in the second test sub-data through the KDLV algorithm, and calculate the T statistic corresponding to the second autoregressive model;

[0151] The determination module 290 is used to determine the detection result of the freezing disaster of the power transmission line according to the comparison result of the T statistical limit and the T statistical value.

[0152] As an optional implementation, the determination module 290 is also used to output an alarm when the T statistical value is greater than the T statistical limit; the alarm is used to indicate that there is a freezing disaster in the transmission line; or, when the T statistical value is less than or equal to the T statistical limit, it is determined that there is no freezing disaster in the transmission line.

[0153] As an optional implementation, the calculation module 260 is also used to filter out first test sub-data and second test sub-data from the test data according to the comparison result between the ALD value and the error threshold; wherein the first test sub-data is the test data whose corresponding ALD value is greater than the error threshold; and the second test sub-data is the test data whose corresponding ALD value is greater than or equal to the error threshold.

[0154] As an optional implementation, the first autoregressive model and the second autoregressive model are both AR(2) models; and at least three second test sub-data are temporally spaced between every two adjacent first test sub-data.

[0155] As an optional implementation, the preprocessing module 220 is also used to decompose the data in the first data set into K intrinsic mode functions through a variational mode decomposition (VMD) algorithm; K is a positive integer greater than or equal to 1; and, to extract the time domain features and frequency features of the K intrinsic mode functions, and to standardize the extracted time domain features and frequency domain features, respectively, to obtain a second data set.

[0156] As an optional implementation, the meteorological condition data at least includes average sunshine intensity, and the average sunshine intensity is the average of sunshine intensity values ​​at N sampling moments; N is a positive integer greater than or equal to 2. Further optionally, the meteorological condition data at least includes temperature data within the range of -15°C to 0°C; or, the meteorological condition data at least includes humidity data greater than 80%.

[0157] The power transmission line freezing detection device disclosed in the embodiment of the present application can integrate the KDLV algorithm and the ALD model to adaptively complete the early warning of extreme freezing disasters for the power grid system transmission lines under the premise of using a small amount of ice weight data as a training set, thereby improving the accuracy of ice disaster detection.

[0158] See also Figure 3 , Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0159] like Figure 3 As shown, the test equipment may include:

[0160] A memory 310 storing a computer program;

[0161] a processor 320 coupled to the memory 310;

[0162] When the computer program stored in the memory 310 is executed by the processor 320, the processor 320 implements any one of the methods for detecting freezing of power transmission lines disclosed in the embodiments of the present application.

[0163] It should be noted that Figure 3 The electronic device shown may also include components not shown, such as a power supply, input buttons, a screen, an RF circuit, a Wi-Fi module, a Bluetooth module, etc., which are not described in detail in this embodiment.

[0164] The present application embodiment discloses a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements any one of the transmission line freezing detection methods disclosed in the present application embodiment.

[0165] An embodiment of the present application discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute any one of the power transmission line freezing detection methods disclosed in the embodiments of the present application.

[0166] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. Those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required for the present application.

[0167] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the above-mentioned processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0168] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0170] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for a computer device (which can be a personal computer, a server or a network device, etc., specifically a processor in a computer device) to perform some or all of the steps of the above-mentioned methods of various embodiments of the present application.

[0171] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, the storage medium including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0172] The test method, test equipment, test system and storage medium of the telemetry equipment disclosed in the embodiments of the present application are introduced in detail above. The principles and implementation methods of the present application are explained in detail using specific examples herein. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A method for detecting freezing disasters of power transmission lines, characterized in that: The method comprises: Acquire a first data set; the first data set includes ice weight data and meteorological condition data of the transmission line; Preprocessing the first data set to obtain a second data set; Projecting the second data set using a kernel principal component extraction strategy of a kernel dynamic latent variable (KDLV) algorithm to obtain a principal component matrix; Extracting training data and test data from the principal component matrix; wherein the training data is data in the principal component matrix representing that the power transmission line is in a normal state and in a first icing state; the test data is data in the principal component matrix representing that the power transmission line is in a normal state and in a second icing state; the second icing state indicates a higher degree of icing than the first icing state; Building a first autoregressive model using the dynamic components in the training data through the KDLV algorithm, and calculating the T statistical limit corresponding to the first autoregressive model; Calculating an ALD value of each piece of data in the test data, and filtering out first test sub-data and second test sub-data from the test data according to the ALD value; Using the first test sub-data to update the first autoregressive model, so as to update the T statistical limit; Using the KDLV algorithm, a second autoregressive model is constructed using the dynamic components in the second test sub-data, and a T statistic corresponding to the second autoregressive model is calculated; The detection result of the power transmission line freezing disaster is determined according to the comparison result of the T statistical limit and the T statistical value.

2. The method according to claim 1, characterized in that The step of determining the detection result of the power transmission line freezing disaster according to the comparison result of the T statistical limit and the T statistical value includes: If the T statistic value is greater than the T statistic time limit, an alarm is output; the alarm is used to indicate that there is a freezing disaster on the power transmission line; or, If the T statistic value is less than or equal to the T statistic time limit, it is determined that there is no freezing disaster on the transmission line.

3. The method according to claim 1, characterized in that The step of selecting first test sub-data and second test sub-data from the test data according to the ALD value includes: Filtering out first test sub-data and second test sub-data from the test data according to a comparison result of the ALD value and the error threshold; The first test sub-data is the test data whose corresponding ALD value is greater than the error threshold; the second test sub-data is the test data whose corresponding ALD value is greater than or equal to the error threshold.

4. The method according to claim 3, characterized in that The first autoregressive model and the second autoregressive model are both AR(2) models; and there are at least three second test sub-data intervals in time between every two adjacent first test sub-data.

5. The method according to any one of claims 1 to 4, characterized in that: The preprocessing of the first data set to obtain a second data set includes: Decomposing the data in the first data set into K intrinsic mode functions by using a variational mode decomposition (VMD) algorithm; K is a positive integer greater than or equal to 1; The time domain features and frequency features of the K intrinsic mode functions are extracted, and the extracted time domain features and frequency domain features are respectively standardized to obtain a second data set.

6. The method according to any one of claims 1 to 4, characterized in that: The meteorological condition data at least includes average sunshine intensity, and the average sunshine intensity is the average value of sunshine intensity values ​​at N sampling moments; N is a positive integer greater than or equal to 2.

7. The method according to claim 6, characterized in that The meteorological condition data at least further includes temperature data in the range of -15°C to 0°C; or, the meteorological condition data at least further includes humidity data greater than 80%.

8. A transmission line freezing disaster detection device, characterized in that: include: An acquisition module, used for acquiring a first data set; The first data set includes ice weight data and meteorological condition data of the transmission line; A preprocessing module, used for preprocessing the first data set to obtain a second data set; A first processing module is used to project the second data set by using a kernel principal component extraction strategy of a kernel dynamic latent variable (KDLV) algorithm to obtain a principal component matrix; An extraction module is used to extract training data and test data from the principal component matrix; wherein the training data is data in the principal component matrix representing that the power transmission line is in a normal state and in a first icing state; the test data is data in the principal component matrix representing that the power transmission line is in a normal state and in a second icing state; the second icing state indicates a higher degree of icing than the first icing state; A second processing module is used to build a first autoregressive model using the dynamic components in the training data through a KDLV algorithm, and calculate the T statistical limit corresponding to the first autoregressive model; a calculation module, configured to calculate an ALD value of each piece of data in the test data, and filter out first test sub-data and second test sub-data from the test data according to the ALD value; An updating module, configured to update the first autoregressive model using the first test sub-data to update the T statistical limit; A third processing module, configured to build a second autoregressive model using the dynamic components in the second test sub-data by using a KDLV algorithm, and calculate a T statistic corresponding to the second autoregressive model; A determination module is used to determine the detection result of the freezing disaster of the transmission line according to the comparison result of the T statistical limit and the T statistical value.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images