A method and system for monitoring the tilt of transmission line towers

Abstract

The present invention provides a method and system for monitoring the inclination of transmission line towers. The method comprises the following steps: obtaining a top view of a standard tower and determining a reference point of the tower in the top view; obtaining a top view of the tower in a monitoring state and determining offset information of the reference point, wherein the offset information includes an offset direction and an offset distance; clustering analysis is performed on the offset information of all towers to obtain a clustering result; obtaining historical multi-source data based on the clustering result, and analyzing the correlation between the historical multi-source data and the clustering result, wherein the multi-source data includes at least meteorological data and geological disaster data; training a neural network model based on the correlation, using the reference point position of each tower and the historical multi-source data as input, and the offset information of each reference point as output, to obtain a target neural network model; inputting the current reference point position of each tower and the multi-source data into the target neural network model, and outputting the offset information of each tower, thereby improving the efficiency of tower inclination monitoring and performing a tilt warning.

Description

Technical Field

[0001] The present invention belongs to the technical field of transmission line iron tower tilt monitoring, and in particular relates to a transmission line iron tower tilt monitoring method and system. Background Art

[0002] Transmission line towers are tall structures used to support transmission conductors in overhead transmission lines. They can erect transmission conductors at a certain height, keeping a safe distance between the conductors and the ground and surrounding objects, ensuring the safe and reliable transmission of electricity.

[0003] The tilt of transmission line towers is caused by a combination of factors. In terms of geological conditions, insufficient bearing capacity in soft soil or changes in foundation caused by geological disasters can undermine the tower's stable foundation. Problems with foundation construction quality, such as insufficient burial depth or poor concrete placement, can weaken the tower's support. External forces, such as mechanical collisions and illegal earthwork, can directly damage the tower structure. Natural environmental factors, such as strong winds, ice cover, and other extreme weather conditions, can generate enormous loads that exceed the tower's capacity. Furthermore, improper design, inappropriate selection, or calculation errors can lead to inherent performance defects in the tower. These factors can all contribute to the tilt of transmission line towers.

[0004] Currently, the tilt monitoring of transmission line towers is mainly carried out through manual exploration, which is time-consuming and labor-intensive. Therefore, a method is proposed to install multiple monitoring cameras on the transmission line towers, perform image processing based on the images collected by the monitoring cameras, and analyze the tilt situation. Although this method can improve monitoring efficiency, since multiple monitoring cameras need to be installed on each transmission line tower, the installation and maintenance costs are high.

[0005] In addition, at present, remedial measures are only taken when the tilt of the transmission line tower is detected. There is no method to analyze the tilt correlation between the transmission line towers and issue tilt warnings to reduce losses. Summary of the Invention

[0006] Based on this, an embodiment of the present invention provides a method and system for monitoring the tilt of a transmission line tower, which aims to improve the efficiency of monitoring the tilt of a transmission line tower and provide tilt warning.

[0007] A first aspect of an embodiment of the present invention provides a method for monitoring the inclination of a transmission line tower, which is applied to a transmission line tower having a unique vertex. The method includes:

[0008] Obtain a standard tower top view taken by a drone, and determine a reference point of the tower in the standard tower top view;

[0009] Obtaining a top view of the tower in a monitoring state, and determining offset information of a reference point in the top view of the tower, wherein the offset information includes an offset direction and an offset distance;

[0010] Perform cluster analysis on the offset information of all towers to obtain clustering results;

[0011] According to the clustering result, historical multi-source data is acquired, and correlation between the historical multi-source data and the clustering result is analyzed, wherein the multi-source data includes at least meteorological data and geological disaster data;

[0012] According to the correlation, the reference point positions of each tower and the historical multi-source data are used as input, and the offset information of each reference point is used as output to train a neural network model to obtain a target neural network model;

[0013] The current reference point positions of each tower and multi-source data are input into the target neural network model, and the offset information of each tower is output.

[0014] Furthermore, the step of performing cluster analysis on the offset information of all towers to obtain clustering results includes:

[0015] Convert the offset directions of all towers into two-dimensional coordinates on a unit circle, and use the corresponding offset distances as weights to weight the two-dimensional coordinates to obtain a number of target coordinates;

[0016] The target coordinates are normalized, and cluster analysis is performed on the normalized target coordinates according to the DBSCAN clustering algorithm to obtain each cluster area.

[0017] Furthermore, the step of acquiring historical multi-source data based on the clustering result and analyzing the correlation between the historical multi-source data and the clustering result, wherein the multi-source data includes at least meteorological data and geological disaster data, comprises:

[0018] Historical multi-source data within the cluster area is obtained, and the correlation between the corresponding meteorological data and geological disaster data and the comprehensive offset directions of all towers within the cluster area is analyzed respectively.

[0019] Furthermore, in the step of obtaining historical multi-source data within the cluster area and analyzing the correlation between the corresponding meteorological data and geological disaster data and the comprehensive offset direction of all towers within the cluster area, the offset direction and offset distance of all towers within the cluster area are obtained, and the comprehensive offset direction is determined based on the vector relationship;

[0020] Obtaining a wind direction in the meteorological data, and calculating a cosine value of an angle between the wind direction and the integrated offset direction to determine a first correlation between the meteorological data and the integrated offset direction;

[0021] The stress conduction direction in the geological hazard data is obtained, and the cosine value of the angle between the stress conduction direction and the comprehensive offset direction is calculated to determine the second correlation between the geological hazard data and the comprehensive offset direction.

[0022] Furthermore, based on the correlation, the reference point position of each tower and the historical multi-source data are used as input, and the offset information of each reference point is used as output. In the step of training the neural network model, it is determined whether the first correlation and the second correlation are greater than a threshold; if so, the corresponding historical multi-source data are used as input.

[0023] Furthermore, the neural network model is composed of an input layer, a hidden layer and an output layer. The input layer includes a plurality of input nodes, the number of which is the same as the number of input data types, and is used to receive different types of input data.

[0024] The hidden layer consists of five sublayers. The first hidden sublayer has 64 nodes. The LeakyReLU function is used to extract features of the input data and find key features related to the output results. The second and third hidden sublayers each have 128 nodes. The Sigmoid function is used to further explore the features of the output data of the first hidden sublayer and capture the intrinsic connections between nodes. The fourth and fifth hidden sublayers each contain 64 nodes. The ReLU activation function is used to perform secondary processing on the data features output by the third hidden sublayer.

[0025] The output layer is provided with a number of output nodes, the number of which corresponds to the number of output data types. The output layer adopts a linear activation function to output the final prediction result.

[0026] Furthermore, the height and service life of the tower are used as inputs of the neural network model to train the neural network model.

[0027] A second aspect of the embodiments of the present invention provides a transmission line tower tilt monitoring system, which is used to implement the transmission line tower tilt monitoring method described in the first aspect. The system includes:

[0028] The first acquisition module is used to obtain a standard tower top view taken by a drone and determine a reference point of the tower in the standard tower top view;

[0029] A second acquisition module is used to obtain a top view of the tower in a monitoring state and determine offset information of a reference point in the top view of the tower, wherein the offset information includes an offset direction and an offset distance;

[0030] The clustering module is used to perform cluster analysis on the offset information of all towers to obtain clustering results;

[0031] an analysis module, configured to obtain historical multi-source data based on the clustering result, and analyze the correlation between the historical multi-source data and the clustering result, wherein the multi-source data includes at least meteorological data and geological disaster data;

[0032] A training module is configured to train a neural network model based on the correlation, using the reference point positions of each tower and the historical multi-source data as input and the offset information of each reference point as output to obtain a target neural network model;

[0033] The input module is used to input the current reference point positions of each tower and multi-source data into the target neural network model and output the offset information of each tower.

[0034] A third aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the transmission line tower inclination monitoring method provided in the first aspect.

[0035] The fourth aspect of an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the transmission line tower inclination monitoring method provided in the first aspect is implemented.

[0036] A method and system for monitoring the tilt of transmission line towers provided in an embodiment of the present invention determines the reference points of the towers in the standard tower view by obtaining a bird's-eye view of the tower taken by an unmanned aerial vehicle; obtains a bird's-eye view of the tower in a monitoring state, and determines the offset information of the reference points in the tower view, the offset information including the offset direction and the offset distance; clusters the offset information of all towers to obtain clustering results; obtains historical multi-source data based on the clustering results, and analyzes the correlation between the historical multi-source data and the clustering results, the multi-source data including at least meteorological data and geological disaster data; based on the correlation, uses the reference point position of each tower and the historical multi-source data as input, and the offset information of each reference point as output, to train a neural network model to obtain a target neural network model; inputs the current reference point position of each tower and the multi-source data into the target neural network model, and outputs the offset information of each tower, thereby improving the efficiency of monitoring the tilt of transmission line towers and performing tilt warnings so that preventive measures can be taken in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flowchart of a method for monitoring the inclination of a transmission line tower provided in the first embodiment of the present invention;

[0038] Figure 2 A structural block diagram of a transmission line tower tilt monitoring system provided in a second embodiment of the present invention;

[0039] Figure 3 This is a structural block diagram of an electronic device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0040] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0041] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0043] Example 1

[0044] According to an embodiment of the present invention, an embodiment of a method for monitoring the inclination of a transmission line tower is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0045] In this embodiment 1, a method for monitoring the tilt of a transmission line tower is provided, which can be used in electronic equipment, such as a computer. Figure 1 , Figure 1 The flowchart of the method for monitoring the inclination of a transmission line tower provided in the first embodiment of the present invention is shown, which specifically includes steps S01 to S06.

[0046] Step S01: obtaining a standard tower top view taken by a drone, and determining a reference point of the tower in the standard tower top view.

[0047] Specifically, in a scenario involving a transmission line tower with a unique vertex, in an embodiment of the present invention, to facilitate drone identification of the reference point, a prominent marker, such as a reflector or LED light, can be placed at the vertex of the transmission line tower. First, the drone is controlled to fly to a preset altitude. Assuming the drone's image resolution meets the requirements, as many reference points as possible are captured. This facilitates subsequent simultaneous tilt monitoring of multiple towers. Meeting the resolution requirements means that the tower's offset information is not affected, and a certain level of accuracy is guaranteed.

[0048] Alternatively, in order to ensure the accuracy of tilt monitoring, photos are taken one by one above the tower, and finally a two-dimensional map of all reference points in the area is drawn, and a rectangular coordinate system is established.

[0049] It can be understood that the standard tower top view refers to a top view of the tower under normal conditions. After the standard tower top view is photographed, the reference points of the tower in the standard tower top view can be marked manually.

[0050] Step S02: obtaining a top view of the tower in a monitoring state, and determining offset information of a reference point in the top view of the tower, wherein the offset information includes an offset direction and an offset distance.

[0051] Specifically, the drone is controlled to fly to the same position. After obtaining the overhead view of the tower in the monitoring state, the reference point of the overhead view of the tower in the monitoring state is identified according to image processing technology, and compared with the reference point in the corresponding standard overhead view of the tower to determine the offset direction and offset distance of the reference point. It can be understood that since the rectangular coordinate system is established, the coordinate positions of the standard reference point and the current reference point can be determined respectively, and the vector is determined according to the successive changes in the two coordinate positions, where the size of the vector is the offset distance, and the direction of the vector is the offset direction.

[0052] It should be noted that the calculation formula for the offset distance is:

[0053] ;

[0054] in, is the offset distance of the i-th tower, is the horizontal coordinate of the i-th tower under monitoring status, is the horizontal coordinate of the i-th tower in the standard tower top view, is the vertical coordinate of the i-th tower under monitoring status, is the vertical coordinate of the i-th tower in the top view of the standard tower. In addition, the offset direction is the direction of the ray from the standard reference point to the current reference point.

[0055] Step S03: cluster analysis is performed on the offset information of all towers to obtain clustering results.

[0056] Specifically, the offset directions of all towers are converted into two-dimensional coordinates on the unit circle, which can be expressed as:

[0057] ;

[0058] Among them, θ is the offset direction angle, which can be determined by unifying the reference direction. x and y are the converted horizontal and vertical coordinates respectively. The corresponding offset distance is used as the weight to weight the two-dimensional coordinates to obtain several target coordinates, which can be expressed as:

[0059] ;

[0060] in, , are the horizontal and vertical coordinates of the target coordinates respectively;

[0061] The target coordinates are normalized. The normalization can be Min-Max scaling. According to the DBSCAN clustering algorithm, the normalized target coordinates are clustered and analyzed to obtain each cluster area. Specifically, by setting the neighborhood radius ϵ and the minimum number of points MinPts, density-connected point clusters are identified.

[0062] Step S04: acquiring historical multi-source data according to the clustering result, and analyzing the correlation between the historical multi-source data and the clustering result, wherein the multi-source data at least includes meteorological data and geological disaster data.

[0063] Specifically, through the cluster analysis in the above steps, several cluster areas can be divided, and historical multi-source data in the cluster areas can be obtained. The corresponding meteorological data and geological disaster data are analyzed separately for correlation with the comprehensive offset direction of all towers in the cluster areas. It can be understood that through cluster analysis, the commonalities between the data can be found, and the occurrence of commonalities in tower tilt is mostly related to weather changes and crustal movement. In order to further determine whether there is a certain correlation between them, correlation calculations are performed in the embodiments of the present invention.

[0064] First, the offset direction and offset distance of all towers in the cluster area are obtained, and the comprehensive offset direction is determined based on the vector relationship. It should be noted that the vector segments formed by the offset of the reference points in the cluster area are obtained, and the starting points of each vector segment are overlapped. Since the direction and size of each vector segment are known, a unique final synthetic vector segment can be determined by vector addition to determine the comprehensive offset direction;

[0065] Obtaining wind direction from meteorological data, and calculating a cosine value of an angle between the wind direction and the integrated offset direction to determine a first correlation between the meteorological data and the integrated offset direction, wherein the wind direction within the cluster area can be obtained from a meteorological monitoring platform;

[0066] The stress conduction direction in the geological hazard data is obtained, and the cosine value of the angle between the stress conduction direction and the comprehensive offset direction is calculated to determine the second correlation between the geological hazard data and the comprehensive offset direction. The stress conduction direction can be obtained through platforms such as China Geological Environment Monitoring. In addition, the closer the cosine value of the angle is to 1, the greater the correlation.

[0067] Step S05 , based on the correlation, takes the reference point positions of each tower and the historical multi-source data as input, and the offset information of each reference point as output, and trains a neural network model to obtain a target neural network model.

[0068] In an embodiment of the present invention, before training the neural network model, appropriate data is determined for training to improve the efficiency and accuracy of model training. Specifically, it is determined whether the first correlation and the second correlation are greater than a threshold value; if there is a correlation greater than the threshold value, the corresponding historical multi-source data is used as input, that is, when the first correlation is greater than the threshold value, it means that it is highly correlated with meteorology, and the meteorological data in the cluster area is input into the neural network model for training; when the second correlation is greater than the threshold value, it means that it is highly correlated with geological disasters, and the geological disaster data in the cluster area is input into the neural network model for training; when both the first correlation and the second correlation are greater than the threshold value, it means that they are highly correlated with both meteorology and geological disasters, and the meteorological data and geological disaster data in the cluster area are input into the neural network model for training.

[0069] Step S06: input the current reference point positions of each tower and multi-source data into the target neural network model, and output the offset information of each tower.

[0070] Specifically, the neural network model consists of an input layer, a hidden layer, and an output layer. The input layer includes a number of input nodes, the number of which is the same as the number of input data types, and is used to receive different types of input data.

[0071] The hidden layer consists of five sublayers. The first hidden sublayer has 64 nodes. The LeakyReLU function is used to extract features of the input data and find key features related to the output results. The second and third hidden sublayers each have 128 nodes. The Sigmoid function is used to further explore the features of the output data of the first hidden sublayer and capture the intrinsic connections between nodes. The fourth and fifth hidden sublayers each contain 64 nodes. The ReLU activation function is used to perform secondary processing on the data features output by the third hidden sublayer.

[0072] The output layer is provided with a number of output nodes, the number of which corresponds to the number of output data types. The output layer adopts a linear activation function to output the final prediction result.

[0073] Specifically, 80% of the randomly shuffled data set samples are used as training set samples, and the remaining 20% ​​are used as test set samples. The neuron formulas of the hidden layer and the output layer can be expressed as:

[0074] First hidden sublayer:

[0075] ;

[0076] Second hidden sublayer:

[0077] ;

[0078] The third hidden sublayer:

[0079] ;

[0080] Fourth hidden sublayer:

[0081] ;

[0082] Fifth hidden sublayer:

[0083] ;

[0084] Output layer:

[0085] ;

[0086] Among them, x j and y i represent the jth node of the input layer and the ith node of the output layer respectively, Indicates the connection The weight of the j-th node in the input layer and the i-th node in the output layer, Indicates the The bias term of the i-th node in the layer, for example, is represented as the i-th neuron in the first hidden sublayer, is represented as the i-th neuron in the second hidden sublayer, is represented as the i-th neuron in the third hidden sublayer, is represented as the i-th neuron in the fourth hidden sublayer, Represented as the i-th neuron in the fifth hidden sublayer. Similarly, is represented as the jth neuron in the first hidden sublayer, is represented as the jth neuron in the second hidden sublayer, is represented as the jth neuron in the third hidden sublayer, is represented as the jth neuron in the fourth hidden sublayer, It represents the jth neuron in the fifth hidden sublayer. LeakyReLU, Sigmoid, and ReLU are activation functions.

[0087] It can be understood that when training the neural network model, the input includes at least the location of each cluster area, the location of the benchmark point in the corresponding cluster area, the historical multi-source data in the corresponding cluster area, and the time, which includes the duration of severe weather and geological disasters. The output is the changed benchmark point location, which can also determine the offset information.

[0088] In some other embodiments of the present invention, the height and service life of the tower can also be used as inputs of the neural network model to train the neural network model to increase the prediction accuracy of the model.

[0089] In summary, the transmission line tower inclination monitoring method in the above-mentioned embodiment of the present invention determines the reference point of the tower in the standard tower overhead view by obtaining a standard tower top view taken by a drone; obtains the tower overhead view in the monitoring state, and determines the offset information of the reference point in the tower overhead view, the offset information includes the offset direction and the offset distance; clusters the offset information of all towers to obtain clustering results; according to the clustering results, obtains historical multi-source data, and analyzes the correlation between the historical multi-source data and the clustering results, the multi-source data at least including meteorological data and geological disaster data; according to the correlation, takes the reference point position of each tower and the historical multi-source data as input, and the offset information of each reference point as output, and trains a neural network model to obtain a target neural network model; inputs the current reference point position of each tower and the multi-source data into the target neural network model, and outputs the offset information of each tower, so as to improve the efficiency of transmission line tower inclination monitoring and perform tilt warning, so that measures can be taken in advance to prevent it.

[0090] Example 2

[0091] See also Figure 2 , Figure 2This is a block diagram of a transmission line tower tilt monitoring system provided in Example 2 of the present invention. This transmission line tower tilt monitoring system 200 is used to implement the aforementioned embodiments and preferred implementations, and details already described will not be repeated. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. While the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

[0092] Specifically, the transmission line tower tilt monitoring system 200 includes: a first acquisition module 21, a second acquisition module 22, a clustering module 23, an analysis module 24, a training module 25 and an input module 26, wherein:

[0093] The first acquisition module 21 is configured to acquire a standard tower top view taken by a drone and determine a reference point of the tower in the standard tower top view;

[0094] A second acquisition module 22 is configured to acquire a top view of the tower in a monitoring state and determine offset information of a reference point in the top view of the tower, wherein the offset information includes an offset direction and an offset distance;

[0095] Clustering module 23, used to perform cluster analysis on the offset information of all towers to obtain clustering results;

[0096] An analysis module 24 is configured to obtain historical multi-source data based on the clustering results, and analyze the correlation between the historical multi-source data and the clustering results, wherein the multi-source data includes at least meteorological data and geological disaster data;

[0097] A training module 25 is configured to train a neural network model based on the correlation, using the reference point positions of each tower and the historical multi-source data as input and the offset information of each reference point as output, to obtain a target neural network model, wherein the first correlation and the second correlation are respectively determined to be greater than a threshold; if so, the corresponding historical multi-source data is used as input, and the neural network model is composed of an input layer, a hidden layer, and an output layer, wherein the input layer includes a plurality of input nodes, the number of input nodes being the same as the number of types of input data, and is configured to receive different types of input data;

[0098] The hidden layer consists of five sublayers. The first hidden sublayer has 64 nodes. The LeakyReLU function is used to extract features of the input data and find key features related to the output results. The second and third hidden sublayers each have 128 nodes. The Sigmoid function is used to further explore the features of the output data of the first hidden sublayer and capture the intrinsic connections between nodes. The fourth and fifth hidden sublayers each contain 64 nodes. The ReLU activation function is used to perform secondary processing on the data features output by the third hidden sublayer.

[0099] The output layer is provided with a number of output nodes, the number of which corresponds to the number of output data types, and the output layer adopts a linear activation function to output the final prediction result;

[0100] Furthermore, the height and service life of the tower are used as inputs of the neural network model to train the neural network model;

[0101] The input module 26 is used to input the current reference point position of each tower and multi-source data into the target neural network model, and output the offset information of each tower.

[0102] Furthermore, in some optional embodiments of the present invention, the clustering module 23 includes:

[0103] a conversion unit, configured to convert the offset directions of all towers into two-dimensional coordinates on a unit circle, and weight the two-dimensional coordinates using the corresponding offset distances as weights to obtain a plurality of target coordinates;

[0104] The clustering unit is used to normalize the target coordinates and perform cluster analysis on the normalized target coordinates according to the DBSCAN clustering algorithm to obtain each cluster area.

[0105] Furthermore, in some optional embodiments of the present invention, the analysis module 24 includes:

[0106] an analysis unit, configured to obtain historical multi-source data within the clustering area, and respectively analyze the correlation between the corresponding meteorological data and geological disaster data and the comprehensive offset direction of all towers within the clustering area, wherein the offset direction and offset distance of all towers within the clustering area are obtained, and the comprehensive offset direction is determined based on a vector relationship;

[0107] Obtaining a wind direction in the meteorological data, and calculating a cosine value of an angle between the wind direction and the integrated offset direction to determine a first correlation between the meteorological data and the integrated offset direction;

[0108] The stress conduction direction in the geological hazard data is obtained, and the cosine value of the angle between the stress conduction direction and the comprehensive offset direction is calculated to determine the second correlation between the geological hazard data and the comprehensive offset direction.

[0109] Example 3

[0110] Another aspect of the present invention provides an electronic device, see Figure 3 , shown is an electronic device in embodiment 3 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, the transmission line tower tilt monitoring method described above is implemented.

[0111] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0112] The memory 20 includes at least one type of readable storage medium, including flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 20 may be an internal storage unit of the electronic device, such as the hard disk of the electronic device. In other embodiments, the memory 20 may also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Furthermore, the memory 20 may include both an internal storage unit of the electronic device and an external storage device. The memory 20 can be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or is about to be output.

[0113] It should be pointed out that Figure 3 The structure shown does not constitute a limitation to the electronic device. In other embodiments, the electronic device may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0114] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for monitoring the inclination of a transmission line tower as described above is implemented.

[0115] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0116] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0117] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0118] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0119] The above embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for monitoring the inclination of a transmission line tower, characterized in that: Applied to a scenario of a transmission line tower with a unique vertex, the method includes: Obtain a standard tower top view taken by a drone, and determine a reference point of the tower in the standard tower top view; Obtaining a top view of the tower in a monitoring state, and determining offset information of a reference point in the top view of the tower, wherein the offset information includes an offset direction and an offset distance; Perform cluster analysis on the offset information of all towers to obtain clustering results; According to the clustering result, historical multi-source data is acquired, and correlation between the historical multi-source data and the clustering result is analyzed, wherein the multi-source data includes at least meteorological data and geological disaster data; According to the correlation, the reference point positions of each tower and the historical multi-source data are used as input, and the offset information of each reference point is used as output to train a neural network model to obtain a target neural network model; Inputting the current reference point positions of each tower and multi-source data into the target neural network model, and outputting the offset information of each tower; The step of clustering the offset information of all towers to obtain clustering results includes: Convert the offset directions of all towers into two-dimensional coordinates on a unit circle, and use the corresponding offset distances as weights to weight the two-dimensional coordinates to obtain a number of target coordinates; The target coordinates are normalized, and cluster analysis is performed on the normalized target coordinates according to the DBSCAN clustering algorithm to obtain each cluster area; The step of acquiring historical multi-source data based on the clustering result and analyzing the correlation between the historical multi-source data and the clustering result, wherein the multi-source data includes at least meteorological data and geological disaster data, comprises: Obtaining historical multi-source data within the cluster area, and analyzing the correlation between the corresponding meteorological data and geological disaster data and the comprehensive offset direction of all towers within the cluster area. Specifically, obtaining the wind direction in the meteorological data, and calculating the cosine value of the angle between the wind direction and the comprehensive offset direction to determine a first correlation between the meteorological data and the comprehensive offset direction; Obtaining a stress conduction direction in the geological hazard data, and calculating a cosine value of an angle between the stress conduction direction and the comprehensive offset direction to determine a second correlation between the geological hazard data and the comprehensive offset direction; According to the correlation, the reference point position of each tower and the historical multi-source data are used as input, and the offset information of each reference point is used as output. In the step of training the neural network model, it is determined whether the first correlation and the second correlation are greater than a threshold; if so, the corresponding historical multi-source data is used as input.

2. The method for monitoring the inclination of a transmission line tower according to claim 1, wherein: The neural network model is composed of an input layer, a hidden layer and an output layer. The input layer includes a number of input nodes, the number of which is the same as the number of input data types, and is used to receive different types of input data; The hidden layer consists of five sublayers. The first hidden sublayer has 64 nodes. The LeakyReLU function is used to extract features of the input data and find key features related to the output results. The second and third hidden sublayers each have 128 nodes. The Sigmoid function is used to further explore the features of the output data of the first hidden sublayer and capture the intrinsic connections between nodes. The fourth and fifth hidden sublayers each contain 64 nodes. The ReLU activation function is used to perform secondary processing on the data features output by the third hidden sublayer. The output layer is provided with a number of output nodes, the number of which corresponds to the number of output data types. The output layer adopts a linear activation function to output the final prediction result.

3. The method for monitoring the inclination of a transmission line tower according to claim 1, wherein: The height and service life of the tower are used as inputs to train the neural network model.

4. A transmission line tower tilt monitoring system, characterized in that: For implementing the transmission line tower tilt monitoring method according to any one of claims 1 to 3, the system comprises: The first acquisition module is used to obtain a standard tower top view taken by a drone and determine a reference point of the tower in the standard tower top view; A second acquisition module is used to obtain a top view of the tower in a monitoring state and determine offset information of a reference point in the top view of the tower, wherein the offset information includes an offset direction and an offset distance; The clustering module is used to perform cluster analysis on the offset information of all towers to obtain clustering results; an analysis module, configured to obtain historical multi-source data based on the clustering result, and analyze the correlation between the historical multi-source data and the clustering result, wherein the multi-source data includes at least meteorological data and geological disaster data; A training module is configured to train a neural network model based on the correlation, using the reference point positions of each tower and the historical multi-source data as input and the offset information of each reference point as output to obtain a target neural network model; The input module is used to input the current reference point positions of each tower and multi-source data into the target neural network model and output the offset information of each tower.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for monitoring the inclination of a transmission line tower as described in any one of claims 1 to 3 is implemented.

6. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for monitoring the inclination of a transmission line tower according to any one of claims 1 to 3 is implemented.

Images