Power transmission line icing type detection method and system based on hyperspectral satellite remote sensing

Abstract

The invention discloses a power transmission line icing type detection method and system based on hyperspectral satellite remote sensing, and the method comprises the steps: carrying out the data fusion of geographic information and spectral remote sensing information of a power transmission line, and obtaining a characteristic standard value; calculating a joint index, obtaining key spectral features related to the icing type according to the joint index, and screening an optimal feature combination; screening the sample data through the optimal feature combination to obtain a training data set, and training the power transmission line icing type prediction model; and predicting the hyperspectral satellite remote sensing data based on the trained power transmission line icing type prediction model to obtain an icing type. Dynamic monitoring and long-time sequence analysis are achieved through satellite remote sensing data, the icing condition is found in time, wide-area monitoring and quick response to sudden weather events are achieved, in addition, a sensor does not need to be installed on a high-voltage power transmission line through hyperspectral satellite remote sensing, and the safety risk of site construction is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of power system operation and maintenance, and in particular to a method and system for detecting ice coating types of power transmission lines based on hyperspectral satellite remote sensing. Background Art

[0002] As an important part of the power system, the stable operation of transmission lines directly affects the continuity and reliability of power supply. However, overhead transmission lines are exposed to complex atmospheric environments for a long time, especially in winter or high altitude areas, and often encounter icing. Icing refers to the ice layer formed on the surface of the line due to low temperature, mainly in the form of rime, rime and mixed rime. In recent years, with the global climate change, extreme weather events have occurred frequently, and the increase in extreme weather conditions such as sudden drop in temperature, invasion of cold air, freezing rain and strong winds has aggravated the icing phenomenon of transmission lines. Especially in mountainous areas, high altitudes and cold northern regions, the icing problem is particularly serious. Icing of transmission lines often causes power accidents and seriously affects the normal operation of the power system.

[0003] In the prior art, a method for monitoring ice thickness on power transmission lines based on fiber grating sensors is proposed. The fiber optic sensing technology is used to monitor the strain and temperature of the power transmission lines in real time. Combined with the data from the wind speed sensor, the line stress is calculated and the ice thickness is inferred. This method solves the problem that traditional ice detection relies on manual inspections, is inaccurate and difficult to monitor in real time. It is particularly suitable for monitoring needs under extreme weather conditions.

[0004] Although the above method has strong real-time performance and relatively high accuracy, it requires laying multiple optical fibers and installing multiple optical fiber sensors, which has high construction and maintenance costs. Moreover, since the optical fiber sensors are installed on the transmission line, maintenance and replacement require power outages, which poses operational and maintenance difficulties. In addition, this method usually chooses to deploy sensors at the connection between the transmission line and the tower. This arrangement can monitor the stress changes of the conductors between the towers, but cannot cover the entire transmission line, and the monitoring range is limited. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method and system for detecting the type of icing on a power transmission line based on hyperspectral satellite remote sensing, which solves the problems of the prior art such as high construction and maintenance costs, difficult operation and maintenance, limited monitoring range, and insufficient reliability in extreme weather.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for detecting the type of icing on a transmission line based on hyperspectral satellite remote sensing, comprising: fusing the geographic information and spectral remote sensing information of the transmission line to obtain characteristic standard values; calculating a joint index based on the characteristic standard values, obtaining key spectral features related to the icing type according to the joint index, and screening the optimal feature combination; screening sample data through the optimal feature combination to obtain a training data set, and using the training data set to train a transmission line icing type prediction model; predicting the hyperspectral satellite remote sensing data based on the trained transmission line icing type prediction model to obtain the icing type.

[0009] As a preferred solution of the method for detecting ice type of power transmission lines based on hyperspectral satellite remote sensing of the present invention, the acquisition of geographic information and spectral remote sensing information of the power transmission lines includes:

[0010] The input hyperspectral satellite remote sensing data bands are selected as near infrared and short-wave infrared bands, and the input hyperspectral satellite remote sensing images are preprocessed by geometric correction, radiation calibration, and atmospheric correction;

[0011] According to the actual ice coverage of the line, the hyperspectral satellite remote sensing data is labeled with ice coverage type and sample cut is performed;

[0012] The geographical information of the transmission line includes the altitude, slope and slope direction information of the location of the transmission line.

[0013] As a preferred solution of the method for detecting ice type of power transmission lines based on hyperspectral satellite remote sensing according to the present invention, the obtaining of characteristic standard values ​​includes:

[0014] The altitude, slope and aspect information of the transmission line location calculated by combining the elevation information of the remote sensing image are fused with the spectral information;

[0015] The features of the data fusion are standardized to obtain feature standard values.

[0016] As a preferred solution of the method for detecting ice types of power transmission lines based on hyperspectral satellite remote sensing according to the present invention, the calculation of the joint index includes:

[0017] In the input feature X = (X1, X2, ..., X n ) is used to make a small disturbance to each variable within the range of , and the Latin hypercube sampling or random path design method is used to calculate the impact of each disturbance on the output on each trajectory. i for:

[0018]

[0019] Among them, Δ represents the step size, and Y represents the model output;

[0020] The absolute mean μ* is calculated as:

[0021]

[0022] Among them, n represents the number of input features;

[0023] The standard deviation σ is calculated as:

[0024]

[0025] The total variance V(Y) of the output Y is expressed as:

[0026]

[0027] Among them, V i Represents a single input feature X i Variance contribution to Y, V ij Represents a single input feature X i X j The interaction effect, V ijk Represents a single input feature X i , X j , X k The third-order interaction effect of

[0028] Using the first-order sensitivity index S i The contribution of the input features to the output uncertainty is analyzed and quantified as:

[0029]

[0030] Total effect sensitivity index S Ti Represents the input feature X i The total contribution of , including its individual effect and the interaction effect with other features, is expressed as:

[0031]

[0032] As a preferred solution of the method for detecting ice types of power transmission lines based on hyperspectral satellite remote sensing according to the present invention, the calculation of the joint index also includes:

[0033] Combining the results of Morris method and Sobol sensitivity analysis, a joint index I is defined. j , expressed as:

[0034]

[0035] in, ω σ ,ωs , Represent the weight of each indicator.

[0036] As a preferred solution of the method for detecting ice types of power transmission lines based on hyperspectral satellite remote sensing according to the present invention, the screening of the optimal feature combination includes:

[0037] The sum of the mean and standard deviation of the joint index is selected as the threshold I, and I j The sample features with >I are taken as the optimal feature combination.

[0038] As a preferred solution of the method for detecting the type of icing on a power line based on hyperspectral satellite remote sensing described in the present invention, the method comprises: obtaining a training data set by screening sample data through the optimal feature combination, and training a transmission line icing type prediction model using the training data set based on a deep learning algorithm; and predicting the hyperspectral satellite remote sensing data based on the trained transmission line icing type prediction model to obtain the icing type, wherein the icing types include three types: rime, fog rime, and mixed rime.

[0039] In a second aspect, the present invention provides a transmission line icing type detection system based on hyperspectral satellite remote sensing, comprising:

[0040] A data fusion module is used to fuse the geographic information and spectral remote sensing information of the transmission line and obtain characteristic standard values;

[0041] An optimal combination screening module, used to calculate a joint index based on the characteristic standard value, obtain key spectral features related to the ice type according to the joint index, and screen the optimal feature combination;

[0042] A model training module, used to filter sample data by the optimal feature combination to obtain a training data set, and use the training data set to train a transmission line icing type prediction model;

[0043] The icing type prediction module is used to predict the hyperspectral satellite remote sensing data based on the trained transmission line icing type prediction model to obtain the icing type.

[0044] In a third aspect, the present invention provides an electronic device, comprising:

[0045] Memory and processor;

[0046] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the method for detecting the type of icing on a power transmission line based on hyperspectral satellite remote sensing are implemented.

[0047] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for detecting the type of icing on a transmission line based on hyperspectral satellite remote sensing.

[0048] Compared with the prior art, the present invention has the following beneficial effects: the present invention provides a method and system for detecting the type of icing on a power transmission line based on hyperspectral satellite remote sensing. Based on a deep learning algorithm, the method uses hyperspectral satellite remote sensing data and the actual icing conditions of the power transmission line for model training, obtains a prediction model for the type of icing on the power transmission line, and uses satellite remote sensing data to achieve dynamic monitoring and long-term series analysis, timely detect icing conditions, conduct wide-area monitoring, and respond quickly to sudden weather events. Hyperspectral data contains rich spectral information, has sufficient data volume, and has high model detection accuracy. Hyperspectral satellite remote sensing is a non-contact monitoring method that does not require the installation of sensors on high-voltage transmission lines, thus avoiding safety risks in on-site construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0050] Figure 1 A schematic diagram of the overall process logic of a method for detecting ice types of power transmission lines based on hyperspectral satellite remote sensing according to an embodiment of the present invention;

[0051] Figure 2 This is an overall flow chart of a method for detecting ice types of power transmission lines based on hyperspectral satellite remote sensing according to an embodiment of the present invention;

[0052] Figure 3 A schematic diagram of a basic convolutional block Inception block of a convolutional neural network GoogLeNet used in a method for detecting ice types of transmission lines based on hyperspectral satellite remote sensing according to an embodiment of the present invention;

[0053] Figure 4 A schematic diagram of a GoogLeNet model of a method for detecting ice types of transmission lines based on hyperspectral satellite remote sensing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0055] Example 1

[0056] Reference Figure 1-Figure 2 As one embodiment of the present invention, a method for detecting ice type of a power transmission line based on hyperspectral satellite remote sensing is provided. Figure 1 The specific steps shown include:

[0057] S100: fusing the geographic information and spectral remote sensing information of the transmission line and obtaining characteristic standard values;

[0058] S200: Calculate a joint index based on the characteristic standard value, obtain key spectral features related to the ice cover type according to the joint index, and select the optimal feature combination;

[0059] S300: The sample data is filtered through the optimal feature combination to obtain a training data set, a transmission line icing type prediction model is trained using the training data set, and the hyperspectral satellite remote sensing data is predicted based on the trained transmission line icing type prediction model to obtain the icing type.

[0060] It should be noted that the present invention provides a method and system for detecting the type of icing on a power line based on hyperspectral satellite remote sensing. Based on a deep learning algorithm, the method uses hyperspectral satellite remote sensing data and the actual icing conditions of the power line to train a model, obtains a prediction model for the type of icing on the power line, and uses satellite remote sensing data to achieve dynamic monitoring and long-term series analysis, timely detect icing conditions, and conduct wide-area monitoring and rapid response to sudden weather events. Hyperspectral data contains rich spectral information, has sufficient data volume, and has high model detection accuracy. Hyperspectral satellite remote sensing is a non-contact monitoring method that does not require the installation of sensors on high-voltage transmission lines, thus avoiding the safety risks of on-site construction.

[0061] In the embodiment of the present application, the above step S100 includes the following sub-steps A1-A3;

[0062] In A1: obtain hyperspectral satellite remote sensing data and perform preprocessing;

[0063] In A2: the altitude, slope and aspect information of the location of the transmission line are calculated by combining the elevation information of the remote sensing image;

[0064] In A3: the pre-processed hyperspectral satellite remote sensing data is fused with the calculated altitude, slope, and aspect information of the location of the transmission line, and characteristic standard values ​​are obtained;

[0065] Specifically, the main absorption characteristics of ice are concentrated in the near infrared (NIR) and short wave infrared (SWIR) bands, so the input hyperspectral satellite remote sensing data bands should be selected from the near infrared and short wave infrared bands, with a spectral resolution of no less than 10 nm and a spatial resolution of no less than 30 meters; Figure 2 As shown in the figure, the related tools of the remote sensing image processing platform are used to perform geometric correction, radiation calibration, and atmospheric correction preprocessing operations on the input hyperspectral satellite remote sensing images; the hyperspectral satellite remote sensing data are labeled with ice type labels according to the actual ice coverage of the line, and samples are cropped;

[0066] Specifically, the geographical information of the transmission line includes the altitude, slope, and slope direction information of the location of the transmission line;

[0067] Altitude information is the value of each pixel in the elevation information of the remote sensing image, which can be read directly;

[0068] The elevation change (gradient) of each grid cell in X (east-west direction) and Y (north-south direction) is calculated through the remote sensing image elevation information:

[0069]

[0070] in, and It can be approximated by the difference method:

[0071]

[0072] Calculate the slope magnitude:

[0073]

[0074] Slope aspect indicates the direction of the surface slope (usually north is 0, clockwise 2π). The slope aspect calculation requires the X and Y gradients of the elevation change.

[0075] Calculate the aspect angle (radians):

[0076] Aspect = arctan2(SlopeL y , -Slope x )

[0077] Specifically, the altitude, slope and aspect information of the transmission line location calculated by combining the remote sensing image elevation information are fused with the spectral information; the features of the data fusion are standardized to obtain the feature standard value, where the feature standardization formula is:

[0078]

[0079] Among them, x i is the sample characteristic value, μ is the mean of the sample characteristic, and σ is the standard deviation of the sample characteristic;

[0080] It should be noted that the above step S100 can not only integrate the advantages of multi-source data to provide more comprehensive and accurate transmission line environmental information, but also lay a solid foundation for subsequent icing type prediction, ensure the reliability and representativeness of the characteristic standard value, thereby improving the accuracy and robustness of the entire prediction model.

[0081] In the embodiment of the present application, the above step S200 includes the following sub-steps B1-B2;

[0082] In B1: Based on the characteristic standard value, the combined index is calculated using the Morris method and the Sobol sensitivity analysis index;

[0083] In B2: key spectral features related to ice cover types are obtained based on joint indicators, and the optimal feature combination is screened;

[0084] Specifically, in the input feature X = (X1, X2, ..., X n ) is used to make a small disturbance to each variable within the range of , changing the value of one variable each time, keeping other variables unchanged, and using Latin hypercube sampling or random path design to calculate the impact of each disturbance on the output on each trajectory. i for:

[0085]

[0086] Among them, Δ represents the step size, and Y represents the model output;

[0087] Absolute mean μ * The calculation is:

[0088]

[0089] Among them, n represents the number of input features;

[0090] The standard deviation σ is calculated as:

[0091]

[0092] The total variance Y(Y) of the output Y is expressed as:

[0093]

[0094] Among them, V i Represents a single input feature X iVariance contribution to Y, V ij Represents a single input feature X i X j The interaction effect, V ijk Represents a single input feature X i , X j , X k The third-order interaction effect of

[0095] Using the first-order sensitivity index S i The contribution of the quantitative input features to the output uncertainty is:

[0096]

[0097] S i The value range is [0, 1], and the larger the value, the greater the i The greater the impact on Y;

[0098] Total effect sensitivity index S Ti Represents the input feature X i The total contribution of , including its individual effect and the interaction effect with other features, is expressed as:

[0099]

[0100] Combining the results of Morris method and Sobol sensitivity analysis, a joint index I is defined. j , expressed as:

[0101]

[0102] in, ω σ ,ω s , Represent the weight of each indicator.

[0103] Specifically, screening the optimal feature combination includes: selecting the sum of the mean and standard deviation of the joint index as the threshold I, and taking I j The sample features with >I are taken as the optimal feature combination.

[0104] It should be noted that the looser screening criteria are: taking the mean of the index and retaining more features; the moderate screening criteria are: taking the sum of the mean and standard deviation of the index; the strict screening criteria are: taking the sum of the mean and twice the standard deviation of the index and retaining only the most important features; this embodiment adopts the moderate screening criteria.

[0105] It should be noted that the above step S200 calculates the joint index based on the characteristic standard value, obtains the key spectral features related to the ice cover type according to the joint index, and screens out the optimal feature combination. This can not only effectively extract and highlight the most influential features for ice cover type identification, but also reduce data redundancy and noise, improve the representativeness of the features and the prediction accuracy of the model, thereby providing more reliable and efficient feature support for subsequent model training and ice cover type prediction.

[0106] In an embodiment of the present application, the above-mentioned step S300 obtains a training data set by filtering sample data through the optimal feature combination, and trains a transmission line icing type prediction model based on the deep learning algorithm using the training data set; based on the trained transmission line icing type prediction model, the hyperspectral satellite remote sensing data is predicted to obtain the icing type, wherein the icing types include three types: rime, fog rime, and mixed rime.

[0107] It should be noted that the above step S300 can not only ensure the high quality and representativeness of the training data, but also improve the training efficiency and prediction accuracy of the model, thereby providing more accurate and reliable model support for subsequent icing type predictions, and effectively improving the accuracy and real-time performance of icing monitoring.

[0108] The above is a schematic scheme of the method for detecting ice types of transmission lines based on hyperspectral satellite remote sensing in this embodiment. It should be noted that the technical scheme of the system for detecting ice types of transmission lines based on hyperspectral satellite remote sensing and the technical scheme of the method for detecting ice types of transmission lines based on hyperspectral satellite remote sensing belong to the same concept. The details not described in detail in the technical scheme of the system for detecting ice types of transmission lines based on hyperspectral satellite remote sensing in this embodiment can be found in the description of the technical scheme of the method for detecting ice types of transmission lines based on hyperspectral satellite remote sensing.

[0109] This embodiment also provides a transmission line ice type detection system based on hyperspectral satellite remote sensing, including:

[0110] A data fusion module is used to fuse the geographic information and spectral remote sensing information of the transmission line and obtain characteristic standard values;

[0111] The optimal combination screening module is used to calculate the joint index based on the characteristic standard value, obtain the key spectral features related to the ice type according to the joint index, and screen the optimal feature combination;

[0112] A model training module is used to obtain a training data set by screening sample data through an optimal feature combination, and train a transmission line icing type prediction model using the training data set;

[0113] The icing type prediction module is used to predict the hyperspectral satellite remote sensing data based on the trained transmission line icing type prediction model to obtain the icing type.

[0114] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0115] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for detecting the type of ice coating on a transmission line based on hyperspectral satellite remote sensing is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0116] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method proposed in the above embodiment is implemented.

[0117] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0118] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0119] Example 2

[0120] Reference Figure 3 and Figure 4 Based on the previous embodiment, this embodiment provides an application example of a method and system for detecting ice types of transmission lines based on hyperspectral satellite remote sensing, in order to verify and illustrate the technical effects adopted in this method.

[0121] This embodiment is applied to the inversion of ice cover types of power transmission lines in Guizhou Province in the past 25 years. First, the GF-5 hyperspectral satellite remote sensing data and the icing conditions of transmission lines in Guizhou Province in the past five years are obtained. The GF-5 spectrum covers 4002500nm, the spectral resolution is 5-10nm, and the spatial resolution is 30 meters. The relevant tools of the remote sensing image processing platform are used. ENVI is used in the example to preprocess the hyperspectral satellite remote sensing data, including geometric correction, radiation calibration and atmospheric correction. Then, the hyperspectral remote sensing data is labeled with the ice cover type according to the actual icing conditions of the line, and finally the sample is cropped. The altitude, slope, slope aspect and other information of the sample data are calculated according to the geographic elevation data (DEM) and the data is fused with the spectral information, and the fused features are standardized.

[0122] Calculate the results of Morris method and Sobol sensitivity analysis to find the combined index I j :

[0123]

[0124] To ensure computational efficiency, the weights are set as follows: ω σ =0.3,ω s =0.2,

[0125] Calculate the distribution of the joint index, select moderate screening, select the threshold I as the sum of the mean and standard deviation of the joint index, and take I j The sample features of >I are taken as the optimal feature combination, and the sample data are screened according to the optimal feature combination to obtain the training set; Figure 3 and Figure 4 The deep learning network used in the figure is GooLeNet. In GoogLeNet, the basic convolution block is called Inception block.

[0126] Through parallel multi-scale convolution operations (1x1, 3x3 and 5x5 convolutions) and maximum pooling operations, features of different scales are extracted; 1x1 convolution is used to reduce the dimension and reduce the amount of calculation. The GooLeNet model has the advantages of small number of parameters, high computational efficiency, and strong scalability: the Inception module can adapt to different tasks by adjusting parameters. The GooLeNet model can solve the gradient vanishing problem of deep networks through auxiliary classifiers. The GooLeNet model is trained using the obtained training set to obtain a prediction model for the type of ice covering on transmission lines.

[0127] Based on the transmission line prediction model, the icing conditions of the transmission lines in Guizhou Province in the past 25 years were inverted, and the icing types of the transmission lines in Guizhou Province in the past 25 years were obtained. The accuracy of the inversion results reached 84.37%.

[0128] It can be seen that the transmission line icing type detection method based on hyperspectral satellite remote sensing provided in this embodiment, the hyperspectral satellite can cover a large area, especially suitable for the situation where the transmission lines are widely distributed, overcomes the shortcomings of the limited monitoring range of ground sensors, and can cover long-distance transmission lines with one imaging, reducing the number of inspections; in addition, the satellite can cross complex terrain areas, overcome the restrictions on the deployment of ground sensors in terrains such as mountains, canyons, and forests, and is particularly suitable for monitoring transmission lines at high altitudes or remote areas; the satellite has regular observation capabilities, can regularly obtain data according to the satellite orbit plan, realize dynamic monitoring and long-term series analysis, and timely discover icing conditions, especially suitable for wide-area monitoring and rapid response to sudden weather events. Hyperspectral remote sensing is a non-contact monitoring method that does not require the installation of sensors on high-voltage transmission lines, avoiding the safety risks of on-site construction, especially under severe weather conditions (such as strong winds, heavy snow, and severe freezing weather). Hyperspectral remote sensing data contains rich spectral information (tens to hundreds of bands), which can capture subtle differences in the spectrum of different substances. Ice-covered and non-ice-covered conductors are different in spectral reflectance characteristics. Hyperspectral data can identify such subtle changes, thereby improving detection accuracy.

[0129] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0130] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages.

[0131] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0134] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0135] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for detecting ice types of power transmission lines based on hyperspectral satellite remote sensing, characterized in that: include: The geographic information and spectral remote sensing information of the transmission line are fused to obtain characteristic standard values; Calculating a joint index based on the characteristic standard value, obtaining key spectral features related to the ice type according to the joint index, and screening the optimal feature combination; The sample data is filtered by the optimal feature combination to obtain a training data set, and the transmission line icing type prediction model is trained by using the training data set; Based on the trained transmission line icing type prediction model, the hyperspectral satellite remote sensing data is predicted to obtain the icing type.

2. The method for detecting ice type of power transmission lines based on hyperspectral satellite remote sensing according to claim 1, characterized in that: The acquisition of the geographic information and spectral remote sensing information of the transmission line includes: The input hyperspectral satellite remote sensing data bands are selected as near infrared and short-wave infrared bands, and the input hyperspectral satellite remote sensing images are preprocessed by geometric correction, radiation calibration, and atmospheric correction; According to the actual ice coverage of the line, the hyperspectral satellite remote sensing data is labeled with ice coverage type and sample cut is performed; The geographical information of the transmission line includes the altitude, slope and slope direction information of the location of the transmission line.

3. The method for detecting ice type of power transmission lines based on hyperspectral satellite remote sensing according to claim 2, characterized in that: The obtaining of characteristic standard values ​​comprises: The altitude, slope and aspect information of the transmission line location calculated by combining the elevation information of the remote sensing image are fused with the spectral information; The features of the data fusion are standardized to obtain feature standard values.

4. The method for detecting ice type of power transmission lines based on hyperspectral satellite remote sensing according to claim 3, characterized in that: The calculation of the joint index includes: In the input feature X = (X1, X2, ..., X n ) is used to make a small disturbance to each variable within the range of , and the Latin hypercube sampling or random path design method is used to calculate the impact of each disturbance on the output on each trajectory. i for: Among them, Δ represents the step size, and Y represents the model output; Absolute mean μ * The calculation is: Among them, n represents the number of input features; The standard deviation σ is calculated as: The total variance V(Y) of the output Y is expressed as: Among them, V i Represents a single input feature X i Variance contribution to Y, V ij Represents a single input feature X i X j The interaction effect, V ijk Represents a single input feature X i , X j , X k The third-order interaction effect of Using the first-order sensitivity index S i The contribution of the input features to the output uncertainty is analyzed and quantified as: Total effect sensitivity index S Ti Represents the input feature X i The total contribution of , including its individual effect and the interaction effect with other features, is expressed as:

5. The method for detecting ice type of power transmission lines based on hyperspectral satellite remote sensing according to claim 4, characterized in that: The calculation of the joint index also includes: Combining the results of Morris method and Sobol sensitivity analysis, a joint index I is defined. j , expressed as: in, ω σ ,ω s , Represent the weight of each indicator.

6. The method for detecting ice type of power transmission lines based on hyperspectral satellite remote sensing according to claim 5, characterized in that: The screening of the optimal feature combination comprises: Select the sum of the mean and standard deviation of the joint index as the threshold I, and take I j The sample features with >I are taken as the optimal feature combination.

7. The method for detecting ice type of power transmission lines based on hyperspectral satellite remote sensing according to claim 6, characterized in that: The sample data is filtered through the optimal feature combination to obtain a training data set, and the training data set is used to train a transmission line icing type prediction model based on a deep learning algorithm; based on the trained transmission line icing type prediction model, the hyperspectral satellite remote sensing data is predicted to obtain the icing type, wherein the icing types include rime, fog rime, and mixed rime.

8. A system using the method for detecting ice type of power transmission lines based on hyperspectral satellite remote sensing as claimed in any one of claims 1 to 7, characterized in that: include: A data fusion module is used to fuse the geographic information and spectral remote sensing information of the transmission line and obtain characteristic standard values; An optimal combination screening module, used to calculate a joint index based on the characteristic standard value, obtain key spectral features related to the ice type according to the joint index, and screen the optimal feature combination; A model training module, used to filter sample data by the optimal feature combination to obtain a training data set, and use the training data set to train a transmission line icing type prediction model; The icing type prediction module is used to predict the hyperspectral satellite remote sensing data based on the trained transmission line icing type prediction model to obtain the icing type.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for detecting the type of icing on a transmission line based on hyperspectral satellite remote sensing as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for detecting ice type of transmission lines based on hyperspectral satellite remote sensing as described in any one of claims 1 to 7.

Images