Method and device for monitoring state of power transmission tower in emergency scene

Abstract

The invention discloses a power transmission tower state monitoring method and device in an emergency scene, and the method comprises the steps: obtaining the real-time state data of a power transmission tower through data obtaining modules disposed at the upper part and the middle part of the power transmission tower and a communication module disposed at the bottom of the power transmission tower; screening the real-time state data according to the correlation between the real-time state data and the state of the transmission tower; and sequentially inputting different types of screened real-time state data into input layers in different network layers of the transmission tower state monitoring model, and outputting a transmission tower state monitoring result. According to the invention, the state of the power transmission tower in the emergency scene can be monitored, the state of the power transmission tower can be efficiently and accurately monitored and evaluated in real time, the safety of the power transmission tower is guaranteed, the emergency response capability is effectively improved, and the state monitoring cost of the power transmission tower in the emergency scene is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission tower status monitoring, and in particular to a power transmission tower status monitoring method and device in an emergency scenario. Background Art

[0002] This section is intended to provide a background or context for the embodiments of the invention described herein. No description herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] At present, transmission towers are the backbone of transmission lines in the power system, and the safety and stability of transmission towers are of vital importance. Traditional transmission tower status monitoring adopts the method of periodic manual inspection, which has the disadvantages of low efficiency, high cost, complex work procedures for operators, and poor safety. Moreover, manual inspection not only requires a lot of manpower and material resources, but also makes it difficult to achieve real-time monitoring of transmission towers.

[0004] Moreover, in the face of emergencies (strong winds, earthquakes, fires, floods, etc.), transmission towers may vibrate, tilt, and other safety hazards, which in turn affect the normal operation of the entire power system, and it is not convenient to conduct manual inspections in emergency scenarios. Therefore, it is urgent to provide a transmission tower status monitoring and evaluation method in emergency scenarios, monitor and evaluate the status of transmission towers in emergency scenarios, provide guidance for status monitoring, safety protection, and maintenance and repair of transmission towers, and provide important guarantees for improving the safe operation of transmission lines in the future. Summary of the invention

[0005] The embodiment of the present invention provides a method for monitoring the state of a transmission tower in an emergency scenario, which is used to implement the state monitoring of the transmission tower in an emergency scenario, and to implement real-time, efficient and accurate monitoring and evaluation of the state of the transmission tower, which is conducive to ensuring the safety of the transmission tower, effectively improving the emergency response capability, and reducing the cost of monitoring the state of the transmission tower in an emergency scenario. The method includes:

[0006] Using the data acquisition module arranged at the upper and middle parts of the transmission tower and the communication module arranged at the bottom of the transmission tower, the real-time status data of the transmission tower is obtained; the real-time status data includes one or any combination of vibration data, tilt data and meteorological data;

[0007] According to the correlation between the real-time status data and the status of the transmission tower, the real-time status data is screened;

[0008] Determine a transmission tower state monitoring model from a plurality of pre-trained transmission tower state monitoring models according to the number of types of the screened real-time state data;

[0009] Different types of screened real-time status data are sequentially input into the input layers of different network layers of the transmission tower status monitoring model, and the transmission tower status monitoring results are output; the transmission tower status monitoring results are transmission tower status categories; each network layer includes a convolutional neural network and a long short-term memory network connected to the output layer of the convolutional neural network; the transmission tower status monitoring model also includes a splicing module; the splicing module is used to splice the output of each convolutional neural network layer with the output of the long short-term memory network in the previous network layer.

[0010] The embodiment of the present invention also provides a transmission tower state monitoring device in an emergency scenario, which is used to realize the state monitoring of the transmission tower in an emergency scenario, realize real-time, efficient and accurate monitoring and evaluation of the state of the transmission tower, which is conducive to ensuring the safety of the transmission tower, effectively improving the emergency response capability, and reducing the cost of monitoring the state of the transmission tower in an emergency scenario. The device includes:

[0011] An acquisition module is used to acquire real-time status data of the transmission tower by using a data acquisition module arranged at the upper and middle parts of the transmission tower and a communication module arranged at the bottom of the transmission tower; the real-time status data includes one or any combination of vibration data, tilt data and meteorological data;

[0012] A screening module, used to screen the real-time status data according to the correlation between the real-time status data and the status of the transmission tower;

[0013] A model determination module, used to determine a transmission tower state monitoring model from a plurality of pre-trained transmission tower state monitoring models according to the number of types of screened real-time state data;

[0014] The output module is used to input different types of filtered real-time status data into the input layers of different network layers of the transmission tower status monitoring model in sequence, and output the transmission tower status monitoring results; the transmission tower status monitoring results are the transmission tower status categories; each network layer includes a convolutional neural network and a long short-term memory network connected to the output layer of the convolutional neural network; the transmission tower status monitoring model also includes a splicing module; the splicing module is used to splice the output of each convolutional neural network layer with the output of the long short-term memory network in the previous network layer.

[0015] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for monitoring the status of a transmission tower in an emergency scenario when executing the computer program.

[0016] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for monitoring the state of a transmission tower in an emergency scenario is implemented.

[0017] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method for monitoring the state of a transmission tower in an emergency scenario is implemented.

[0018] In the embodiment of the present invention, the real-time status data of the transmission tower is obtained by using a data acquisition module arranged at the upper and middle parts of the transmission tower and a communication module arranged at the bottom of the transmission tower; the real-time status data includes one or any combination of vibration data, tilt data, and meteorological data; the real-time status data is screened according to the correlation between the real-time status data and the state of the transmission tower; a transmission tower state monitoring model is determined from a plurality of pre-trained transmission tower state monitoring models according to the number of types of the screened real-time status data; different types of screened real-time status data are sequentially input into the input layers of different network layers of the transmission tower state monitoring model, and the transmission tower state is output. The state monitoring result of the transmission tower state monitoring result is the state category of the transmission tower; each network layer includes a convolutional neural network and a long short-term memory network connected to the output layer of the convolutional neural network; the transmission tower state monitoring model also includes a splicing module; the splicing module is used to splice the output of each convolutional neural network layer with the output of the long short-term memory network in the previous network layer. Compared with the periodic manual inspection method in the prior art, the state monitoring of the transmission tower in the emergency scenario is realized, and the state of the transmission tower is monitored and evaluated in real time, efficiently and accurately, which is conducive to ensuring the safety of the transmission tower, effectively improving the emergency response capability, and reducing the cost of state monitoring of the transmission tower in the emergency scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0020] Figure 1 Schematic diagram of the process of a method for monitoring the state of a transmission tower in an emergency scenario in an embodiment of the present invention;

[0021] Figure 2 It is a flowchart of a specific example of a method for monitoring the state of a transmission tower in an emergency scenario in an embodiment of the present invention;

[0022] Figure 3 It is a structural schematic diagram of a transmission tower state monitoring model in an embodiment of the present invention;

[0023] Figure 4 Schematic diagram of a transmission tower state monitoring device in an emergency scenario according to an embodiment of the present invention;

[0024] Figure 5 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0026] At present, transmission towers are the backbone of transmission lines in the power system, and the safety and stability of transmission towers are of vital importance. In the event of an emergency (such as strong winds, earthquakes, fires, and floods), transmission towers may experience safety hazards such as vibration and tilt, which in turn affects the normal operation of the entire power system. In addition, the traditional transmission tower status monitoring method, that is, the manual inspection method, is inconvenient to carry out in emergency scenarios and may also threaten the life safety of the inspection personnel. Therefore, it is urgent to provide a transmission tower status monitoring and evaluation method in emergency scenarios, monitor the status of transmission towers and conduct safety assessment, provide guidance for status monitoring, safety protection, and maintenance and inspection of transmission towers, and provide important guarantees for improving the safe operation of transmission lines in the future.

[0027] In order to solve the above technical problems, an embodiment of the present invention provides a method for monitoring the status of a transmission tower in an emergency scenario. Figure 1 FIG. 1 is a flow chart of a method for monitoring the state of a transmission tower in an emergency scenario according to an embodiment of the present invention. Figure 1 As shown, the method may include:

[0028] Step 101, using a data acquisition module disposed at the upper and middle parts of a transmission tower and a communication module disposed at the bottom of the transmission tower, real-time status data of the transmission tower is acquired; the real-time status data includes one or any combination of vibration data, tilt data, and meteorological data;

[0029] Step 102, screening the real-time status data according to the correlation between the real-time status data and the status of the transmission tower;

[0030] Step 103, determining a transmission tower state monitoring model from a plurality of pre-trained transmission tower state monitoring models according to the number of types of the screened real-time state data;

[0031] Step 104, input different types of filtered real-time status data into the input layers of different network layers of the transmission tower status monitoring model in sequence, and output the transmission tower status monitoring results; the transmission tower status monitoring results are transmission tower status categories; each network layer includes a convolutional neural network and a long short-term memory network connected to the output layer of the convolutional neural network; the transmission tower status monitoring model also includes a splicing module; the splicing module is used to splice the output of each convolutional neural network layer with the output of the long short-term memory network in the previous network layer.

[0032] In one embodiment, the data acquisition module may include: one or any combination of a vibration sensor, a tilt sensor, a wind speed and direction sensor, and a temperature and humidity sensor.

[0033] First, a monitoring system can be deployed at a preset location on the transmission tower. The monitoring system may include: a data acquisition module, an edge computing module, and a communication module; wherein the data acquisition module is connected to the edge computing module, and the edge computing module is wirelessly connected to the cloud server through the communication module. According to actual needs, the data acquisition module can be deployed at the upper ends and the middle of the transmission tower; and the edge computing module and the communication module can be installed at the bottom of the transmission tower for easy maintenance and inspection.

[0034] Considering that most transmission towers are in the wild environment, solar power supply + wind power supply are also used, and energy storage devices are configured to realize self-power supply of the monitoring system to ensure the long-term stable operation of the monitoring system. In this embodiment, the state of the transmission tower in emergency scenarios (such as strong winds, earthquakes, fires, and floods, etc.) is mainly frequent vibration, tilting, and collapse, etc. Therefore, the data acquisition module preferably includes: vibration sensors, tilt sensors, wind speed and direction sensors, temperature and humidity sensors, and positioning devices, etc., to monitor the physical characteristics of the transmission tower in real time and obtain the location information of the transmission tower; other sensor devices can also be added according to actual needs, which are not specifically limited here.

[0035] In this embodiment, the above-mentioned data acquisition device is used to monitor and acquire status data such as vibration data, tilt data, meteorological data, and location information of the transmission tower in daily or emergency scenarios for subsequent evaluation of the status of the transmission tower.

[0036] Furthermore, considering the transmission efficiency and reducing the pressure on the server, avoiding large amounts of data transmission and cloud server processing burdens that reduce the overall response speed, in one embodiment, after obtaining the real-time status data of the transmission tower, the transmission tower status monitoring method in an emergency scenario may also include: utilizing an edge computing module disposed at the bottom of the transmission tower to perform one or any combination of data cleaning, data conversion, and data dimensionality reduction on the real-time status data.

[0037] In this embodiment, data cleaning of the real-time status data may include: deleting erroneous data and missing data points; using the interquartile range method or the machine learning method to detect outliers in the real-time status data, and deleting or correcting the outliers; and unifying the formats of type-related real-time status data.

[0038] In this embodiment, data conversion of real-time status data may include: using a normalization algorithm or a standardization algorithm to convert real-time status data of different dimensions to the same scale; converting unstructured data into structured data; extracting and creating time series feature variables from the real-time status data.

[0039] In this embodiment, performing data dimensionality reduction on the real-time status data may include: removing redundant features in the real-time status data whose correlation with the transmission tower status is lower than a preset threshold; and performing dimensionality reduction on the real-time status data using principal component analysis.

[0040] In this embodiment, the edge computing device is used to pre-process the acquired data, and the processing process mainly includes:

[0041] 1. Data cleaning: ① Remove invalid data: Delete data points that are obviously wrong or missing. ② Outlier processing: Identify and process outliers. Statistical methods (such as the interquartile range (IQR) method) and machine learning methods can be used to detect outliers and decide whether to delete or correct them. ③ Data consistency check: Ensure that all data formats are consistent, for example, the date and time formats should be unified.

[0042] 2. Data conversion: ① Data standardization: Convert data of different dimensions to the same scale, such as normalization or standardization. For example, normalize the data of vibration sensors and tilt sensors to ensure that they are between 0 and 1. ② Data format conversion: Convert unstructured data to structured data for further analysis. ③ Feature engineering: Create new feature variables to extract useful information from raw data, such as calculating the time series features of sensor data (mean, variance, maximum value, etc.).

[0043] 3. Data dimensionality reduction; ① Feature selection: select the most relevant features to retain, remove redundant features, and reduce data dimensions. ② Principal component analysis (PCA): Use methods such as principal component analysis to reduce dimensionality, reduce data complexity, and maintain the main information of the data.

[0044] Figure 2 FIG. 1 is a flow chart of a specific example of a method for monitoring the state of a transmission tower in an emergency scenario according to an embodiment of the present invention. Figure 2As shown, in one embodiment, the method for monitoring the state of a transmission tower in an emergency scenario may further include:

[0045] Step 201, obtaining historical status data of the transmission tower; the historical status data includes one or any combination of vibration data, tilt data, and meteorological data;

[0046] Step 202, screening the historical status data according to the correlation between the historical status data and the status of the transmission tower;

[0047] Step 203, training neural networks containing different numbers of network layers according to the filtered historical status data to obtain multiple trained transmission tower status monitoring models; the number of training rounds is set to 30, the initial learning rate is set to 0.001, and each batch is set to 64; back propagation is performed using a normalized exponential function to update the weights, and the Adam optimizer is used for optimization. When the number of training rounds reaches a preset value, the training ends and the trained transmission tower status monitoring model is saved;

[0048] Each network layer of the neural network includes a convolutional neural network and a long short-term memory network connected to the output layer of the convolutional neural network; the input of each convolutional neural network is the input of the neural network, and the output of the long short-term memory network in the last network layer is the output of the neural network; the output of the long short-term memory network is the hidden layer state of the input of the long short-term memory network;

[0049] The convolutional neural network includes an input layer, a convolutional layer, a pooling layer, a fully connected layer and an output layer; the convolutional layer is used to extract the features of the input data through convolution operations; the pooling layer is used to reduce the dimension of the input data through downsampling; the neural network also includes a splicing module; the splicing module is used to splice the output of each convolutional neural network layer with the output of the long short-term memory network in the previous network layer; the input of the long short-term memory network in the network layer other than the first network layer is: the splicing result of splicing the output of the convolutional neural network layer of the same network layer as the long short-term memory network with the output of the long short-term memory network in the previous network layer.

[0050] In this embodiment, the pre-processed real-time status data is sent to the cloud server through the communication module, where the communication module can be: 4G module, 5G module or WIFI module. At the same time, data cloud storage can also be performed to prevent data loss, improve security, and also help reduce costs.

[0051] In this embodiment, the cloud server is used to analyze the pre-processed status data based on the deep learning model to evaluate the status of the transmission tower; specifically: the cloud server uses the pre-trained transmission tower status monitoring model to analyze and evaluate the pre-processed real-time status data; the transmission tower status monitoring model is built based on a multi-layer convolutional neural network-long short-term memory network (MultiLayers CNN-LSTM, ML-CNN-LSTM), Figure 3 FIG. 1 is a schematic diagram of the structure of a transmission tower state monitoring model according to an embodiment of the present invention. Figure 3 As shown in the figure, the transmission tower condition monitoring model can be divided into five parts: input, feature extraction, feature learning, feature fusion and output, which is also the training process of the model.

[0052] in:

[0053] Input (such as Figure 3 Input1~Input3) in the control panel receive different types of data, including vibration data, tilt data, and meteorological data.

[0054] Feature extraction, according to the characteristics of convolutional neural network (CNN), use it to extract features from input data. Convolutional neural network generally includes input layer, convolution layer, pooling layer, fully connected layer and output layer. Convolution and pooling are important parts of convolutional neural network: Convolution layer (Conv layer, such as Figure 3 Conv_1~Conv_9) extract features through convolution operation; pooling layer (MP layer, such as Figure 3 MP1 to MP9) reduce the dimension of data by downsampling to prevent overfitting. Feature learning uses LSTM (Long Short-Term Memory Network) to learn the features extracted by CNN.

[0055] Feature fusion combines the results of LSTM learning, i.e., the hidden layer state, with the features extracted by CNN layer by layer to achieve model-level fusion.

[0056] Output: Use the final fusion features to train the LSTM and output the status categories of the transmission tower (such as safe and stable, frequent vibration, excessive tilt, and meteorological data exceeding the standard).

[0057] In this embodiment, three types of data are taken as examples to introduce the working principle of feature extraction and feature fusion of data. The specific process is as follows:

[0058] The vibration data, tilt data and meteorological data mentioned above are used as three types of data and are input into different network layers of the model respectively;

[0059] Input the first data into the first network layer, obtain the feature 1 of the first data through CNN, and input the feature 1 into LSTM1 to obtain its hidden layer state;

[0060] The second data is input into the second network layer, and feature 2 is obtained through CNN. Feature 2 is concatenated with the hidden layer state of LSTM1 and then input into LSTM2 to obtain its hidden layer state (which can be regarded as the first fusion feature).

[0061] The third type of data is input into the third network layer, and feature three is obtained through CNN. Feature three is concatenated with the hidden layer state of LSTM2 and input into LSTM3 to obtain the final fusion feature.

[0062] In this embodiment, according to the actual situation, when more types of data are involved, feature extraction and feature fusion are performed layer by layer in sequence, which will not be repeated here.

[0063] In one embodiment, neural networks containing different numbers of network layers can be trained according to the filtered historical status data to obtain multiple trained transmission tower status monitoring models. Figure 3 A plurality of neural networks having a similar structure and containing different numbers of network layers are trained to obtain a plurality of trained transmission tower state monitoring models. According to the number of types of screened real-time state data, a transmission tower state monitoring model containing the same number of network layers as the number of types of screened real-time state data is determined from a plurality of pre-trained transmission tower state monitoring models.

[0064] In one embodiment, the fusion feature is used to train the transmission tower state monitoring model, the number of training rounds is set to 30, the initial learning rate is set to 0.001, and each batch is set to 64. The loss function is calculated, the weights are updated by back propagation using the Softmax classification function, and the Adam optimizer is used for optimization. Finally, when the number of training rounds reaches the specified number, the training ends and the transmission tower state monitoring model is saved; in actual application, the trained transmission tower state monitoring model is used to evaluate and diagnose the state of the transmission tower.

[0065] In the embodiment of the present invention, a transmission tower state monitoring model is constructed based on a model-level fusion strategy and a multi-layer convolutional neural network-long short-term memory network (MultiLayers CNN-LSTM, ML-CNN-LSTM), and then the model is trained to realize the evaluation and diagnosis of the state of the transmission tower, which effectively improves the training speed of the model and also improves the accuracy and efficiency of the transmission tower state evaluation.

[0066] In one embodiment, the method for monitoring the status of a transmission tower in an emergency scenario may further include: obtaining the location data of the transmission tower by using a data acquisition module disposed at the upper and middle parts of the transmission tower and a communication module disposed at the bottom of the transmission tower; if the status monitoring result of the transmission tower is a preset result, generating early warning information according to the status monitoring result of the transmission tower and the location data; and sending the early warning information to a monitoring center or terminal device closest to the transmission tower according to the location information.

[0067] In this embodiment, when the transmission tower status monitoring model identifies a potential risk, the early warning mechanism is automatically triggered to send early warning information to the monitoring center or maintenance personnel via SMS, email, etc.

[0068] In one embodiment, the method for monitoring the status of a transmission tower in an emergency scenario may further include: using a high-definition infrared camera set at a preset position near the transmission tower or mounted on a drone to collect images of the transmission tower; identifying the target position of the transmission tower in the transmission tower image according to a preset image recognition algorithm, and determining the status of the target position of the transmission tower; and generating early warning information according to the status of the target position of the transmission tower, the transmission tower status monitoring results and the position data.

[0069] In one embodiment, as a further optimization of the above implementation, the monitoring system may further include an image acquisition module, which may be a high-definition infrared camera, which is set at a preset position near the transmission tower, or carried on a drone, for collecting images of the transmission tower, and sending the collected images of the transmission tower to the monitoring center for display. It can assist the staff in monitoring the status of the transmission tower and conducting further safety assessments. When carried on a drone, the transmission tower can be inspected in the air. The main control of the drone is loaded with a target recognition system to identify the health status of the target position of the transmission tower (for example, whether the fasteners are loose, whether there is rust, whether the supporting components are intact, etc.), so as to ensure the safe operation of high-speed transmission lines in emergency scenarios.

[0070] In one embodiment, as a further optimization of the above-mentioned implementation mode, the monitoring system in the embodiment of the present invention may also include: a mobile terminal, where the mobile terminal may be a laptop computer, a tablet, a mobile phone or a customized terminal device, etc.; the mobile terminal is wirelessly connected to the data acquisition device and / or the image acquisition device, or connected to the cloud server, so that the staff can view the data or images obtained by the monitoring system in real time and conduct remote mobile monitoring of the status of the transmission tower.

[0071] In one embodiment, the method for monitoring the status of a transmission tower in an emergency scenario may further include: using a VR device to visualize the image of the transmission tower, and performing a VR panoramic display of the visualized image of the transmission tower.

[0072] In this embodiment, as a further optimization of the above implementation, a VR device is also used to receive the transmission tower image obtained by the image acquisition module, and a VR panoramic display is performed after visualization processing. Through the VR device, the staff can view the on-site situation of the transmission tower in the monitoring center or outdoors, which greatly facilitates the inspection work and improves the work efficiency.

[0073] The embodiment of the present invention also provides a transmission tower state monitoring device in an emergency scenario, as described in the following embodiment. Since the principle of solving the problem by the device is similar to the transmission tower state monitoring method in an emergency scenario, the implementation of the device can refer to the implementation of the transmission tower state monitoring method in an emergency scenario, and the repeated parts will not be repeated.

[0074] Figure 4 FIG. 1 is a schematic diagram of a transmission tower state monitoring device in an emergency scenario according to an embodiment of the present invention. Figure 4 As shown, the device comprises:

[0075] The acquisition module 401 is used to acquire the real-time status data of the transmission tower by using the data acquisition modules arranged at the upper and middle parts of the transmission tower and the communication module arranged at the bottom of the transmission tower; the real-time status data includes one or any combination of vibration data, tilt data and meteorological data;

[0076] A screening module 402, for screening the real-time status data according to the correlation between the real-time status data and the status of the transmission tower;

[0077] A model determination module 403, for determining a transmission tower state monitoring model from a plurality of pre-trained transmission tower state monitoring models according to the number of types of the filtered real-time state data;

[0078] The output module 404 is used to input different types of filtered real-time status data into the input layers of different network layers of the transmission tower state monitoring model in sequence, and output the transmission tower state monitoring results; the transmission tower state monitoring results are transmission tower state categories; each network layer includes a convolutional neural network and a long short-term memory network connected to the output layer of the convolutional neural network; the transmission tower state monitoring model also includes a splicing module; the splicing module is used to splice the output of each convolutional neural network layer with the output of the long short-term memory network in the previous network layer.

[0079] Figure 5 Schematic diagram of a computer device in an embodiment of the present invention. Figure 5As shown, an embodiment of the present invention further provides a computer device 500, including a processor 510, a memory 520, and a computer program 530 stored in the memory 520 and executable on the processor 510, wherein the processor 510 implements the above-mentioned method for monitoring the state of a transmission tower in an emergency scenario when executing the computer program 530.

[0080] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for monitoring the state of a transmission tower in an emergency scenario is implemented.

[0081] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method for monitoring the state of a transmission tower in an emergency scenario is implemented.

[0082] In the embodiment of the present invention, the real-time status data of the transmission tower is obtained by using a data acquisition module arranged at the upper and middle parts of the transmission tower and a communication module arranged at the bottom of the transmission tower; the real-time status data includes one or any combination of vibration data, tilt data, and meteorological data; the real-time status data is screened according to the correlation between the real-time status data and the state of the transmission tower; a transmission tower state monitoring model is determined from a plurality of pre-trained transmission tower state monitoring models according to the number of types of the screened real-time status data; different types of screened real-time status data are sequentially input into the input layers of different network layers of the transmission tower state monitoring model, and the transmission tower state is output. The state monitoring result of the transmission tower state monitoring result is the state category of the transmission tower; each network layer includes a convolutional neural network and a long short-term memory network connected to the output layer of the convolutional neural network; the transmission tower state monitoring model also includes a splicing module; the splicing module is used to splice the output of each convolutional neural network layer with the output of the long short-term memory network in the previous network layer. Compared with the periodic manual inspection method in the prior art, the state monitoring of the transmission tower in the emergency scenario is realized, and the state of the transmission tower is monitored and evaluated in real time, efficiently and accurately, which is conducive to ensuring the safety of the transmission tower, effectively improving the emergency response capability, and reducing the cost of state monitoring of the transmission tower in the emergency scenario.

[0083] The beneficial effects of the embodiments of the present invention are as follows:

[0084] 1. The embodiment of the present invention provides a method for monitoring and evaluating the status of a transmission tower in an emergency scenario, which is convenient for real-time, efficient and accurate monitoring and evaluation of the status of a transmission tower in daily or emergency scenarios, and is conducive to ensuring the safety of the transmission tower.

[0085] 2. The embodiments of the present invention combine and utilize multiple advanced technologies such as sensing technology, edge processing technology, wireless communication technology, cloud computing technology, artificial intelligence technology, and drones to monitor the status of transmission towers and conduct safety assessments, which can effectively improve the emergency response capabilities, reduce the risk of power outages in emergency scenarios, provide important guarantees for the safe operation of transmission lines, and reduce maintenance costs, which is helpful to improve the level of safety risk management of transmission tower status.

[0086] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take 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.) containing computer-usable program code.

[0087] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 produce 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.

[0088] 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.

[0089] 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.

[0090] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for monitoring the state of a transmission tower in an emergency scenario, characterized in that: include: Using the data acquisition module arranged at the upper and middle parts of the transmission tower and the communication module arranged at the bottom of the transmission tower, the real-time status data of the transmission tower is obtained; the real-time status data includes one or any combination of vibration data, tilt data and meteorological data; According to the correlation between the real-time status data and the status of the transmission tower, the real-time status data is screened; Determine a transmission tower state monitoring model from a plurality of pre-trained transmission tower state monitoring models according to the number of types of the screened real-time state data; Different types of screened real-time status data are sequentially input into the input layers of different network layers of the transmission tower status monitoring model, and the transmission tower status monitoring results are output; the transmission tower status monitoring results are transmission tower status categories; each network layer includes a convolutional neural network and a long short-term memory network connected to the output layer of the convolutional neural network; the transmission tower status monitoring model also includes a splicing module; the splicing module is used to splice the output of each convolutional neural network layer with the output of the long short-term memory network in the previous network layer.

2. The method for monitoring the state of a transmission tower in an emergency scenario according to claim 1, characterized in that: The data acquisition module includes: one or any combination of a vibration sensor, a tilt sensor, a wind speed and direction sensor, and a temperature and humidity sensor.

3. The method for monitoring the state of a transmission tower in an emergency scenario according to claim 1, characterized in that: Also includes: Obtaining historical status data of transmission towers; the historical status data includes one or any combination of vibration data, tilt data, and meteorological data; Filter the historical status data according to the correlation between the historical status data and the status of the transmission tower; According to the filtered historical status data, neural networks containing different numbers of network layers are trained to obtain multiple trained transmission tower status monitoring models; the number of training rounds is set to 30, the initial learning rate is set to 0.001, and each batch is set to 64; the normalized exponential function is used to back-propagate and update the weights, and the Adam optimizer is used for optimization. When the number of training rounds reaches the preset value, the training ends and the trained transmission tower status monitoring model is saved; The input of each convolutional neural network is the input of the neural network, the output of the long short-term memory network in the last network layer is the output of the neural network; the output of the long short-term memory network is the hidden layer state of the input of the long short-term memory network; The convolutional neural network includes an input layer, a convolutional layer, a pooling layer, a fully connected layer and an output layer; the convolutional layer is used to extract the features of the input data through convolution operations; the pooling layer is used to reduce the dimension of the input data through downsampling; the neural network also includes a splicing module; the splicing module is used to splice the output of each convolutional neural network layer with the output of the long short-term memory network in the previous network layer; the input of the long short-term memory network in the network layer other than the first network layer is: the splicing result of splicing the output of the convolutional neural network layer of the same network layer as the long short-term memory network with the output of the long short-term memory network in the previous network layer.

4. The method for monitoring the state of a transmission tower in an emergency scenario according to claim 1, characterized in that: Also includes: The location data of the transmission tower is obtained by using a data acquisition module arranged at the upper part and the middle part of the transmission tower and a communication module arranged at the bottom of the transmission tower; If the transmission tower status monitoring result is the preset result, generate warning information according to the transmission tower status monitoring result and location data; According to the location information, early warning information is sent to the monitoring center or terminal device closest to the transmission tower.

5. The method for monitoring the state of a transmission tower in an emergency scenario according to claim 4, characterized in that: Also includes: Use a high-definition infrared camera set at a preset position near the transmission tower or mounted on a drone to collect images of the transmission tower; Identify the target position of the transmission tower in the transmission tower image according to a preset image recognition algorithm, and determine the state of the target position of the transmission tower; Generate early warning information based on the status of the target location of the transmission tower, the status monitoring results of the transmission tower and the location data.

6. The method for monitoring the state of a transmission tower in an emergency scenario according to claim 5, characterized in that: Also includes: The transmission tower image is visualized using VR equipment, and the visualized transmission tower image is displayed in a VR panoramic view.

7. The method for monitoring the state of a transmission tower in an emergency scenario according to claim 1, characterized in that: After obtaining the real-time status data of the transmission tower, it also includes: The edge computing module installed at the bottom of the transmission tower is used to perform one or any combination of data cleaning, data conversion, and data dimension reduction on the real-time status data.

8. The method for monitoring the state of a transmission tower in an emergency scenario according to claim 7, characterized in that: Perform data cleaning on real-time status data, including: Delete erroneous data and missing data points; use the interquartile range method or machine learning method to detect outliers in real-time status data, and delete or correct the outliers; unify the format of type-related real-time status data.

9. The method for monitoring the state of a transmission tower in an emergency scenario according to claim 7, characterized in that: Perform data conversion on real-time status data, including: Use normalization algorithm or standardization algorithm to convert real-time status data of different dimensions to the same scale; convert unstructured data into structured data; extract and create time series feature variables from real-time status data.

10. The method for monitoring the state of a transmission tower in an emergency scenario according to claim 7, characterized in that: Perform data dimension reduction on real-time status data, including: Redundant features in real-time status data whose correlation with the status of transmission towers is lower than a preset threshold are removed; the real-time status data is reduced in dimension using principal component analysis.

11. A transmission tower status monitoring device in an emergency scenario, characterized in that: include: An acquisition module is used to acquire real-time status data of the transmission tower by using a data acquisition module arranged at the upper and middle parts of the transmission tower and a communication module arranged at the bottom of the transmission tower; the real-time status data includes one or any combination of vibration data, tilt data and meteorological data; A screening module, used to screen the real-time status data according to the correlation between the real-time status data and the status of the transmission tower; A model determination module, used to determine a transmission tower state monitoring model from a plurality of pre-trained transmission tower state monitoring models according to the number of types of screened real-time state data; The output module is used to input different types of filtered real-time status data into the input layers of different network layers of the transmission tower status monitoring model in sequence, and output the transmission tower status monitoring results; the transmission tower status monitoring results are the transmission tower status categories; each network layer includes a convolutional neural network and a long short-term memory network connected to the output layer of the convolutional neural network; the transmission tower status monitoring model also includes a splicing module; the splicing module is used to splice the output of each convolutional neural network layer with the output of the long short-term memory network in the previous network layer.

12. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for monitoring the status of a transmission tower in an emergency scenario according to any one of claims 1 to 10 is implemented.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for monitoring the state of a transmission tower in an emergency scenario according to any one of claims 1 to 10 is implemented.

14. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the method for monitoring the state of a transmission tower in an emergency scenario according to any one of claims 1 to 10 is implemented.

Images