Power transmission line tower state early warning method and device based on multi-technology fusion
By extracting features and performing cluster analysis on tower status data and micro-meteorological monitoring data, combined with a digital twin model, the problems of unstable data and large errors in transmission line tower status monitoring have been solved, enabling accurate early warning and intelligent operation and maintenance, and ensuring the safety and stability of transmission lines.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JIAMUSI POWER IND BUREAU
- Filing Date
- 2025-05-28
- Publication Date
- 2026-07-07
AI Technical Summary
Existing technologies for monitoring the condition of transmission line towers face challenges such as unstable data acquisition and transmission in complex environments, large data volumes, and difficulty in accurately extracting valuable information, resulting in large errors in early warning results and hindering efficient and accurate condition assessment and early warning.
By acquiring tower status data and micro-meteorological monitoring data, feature extraction and cluster analysis are performed to establish a digital twin model, divide the operating condition characteristic intervals, calculate the wind deflection coefficient, and construct a digital twin model for early warning.
It enables accurate early warning of tower status in complex environments, improves the accuracy and efficiency of early warning, promotes the intelligent operation and maintenance of transmission lines, and ensures the safe and stable operation of transmission lines.
Smart Images
Figure CN120541550B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of power grid data processing technology, specifically to a method and device for early warning of transmission line tower status based on multi-technology integration. Background Technology
[0002] With the rapid development of power technology, the concepts and methods of transmission line operation and maintenance and technical transformation have undergone significant changes. The transmission line tower condition assessment model based on digital twin technology is gradually becoming the industry mainstream. It works in conjunction with drone tower inspection operations, relying on parameter data collected by real-time monitoring equipment and using intelligent monitoring algorithms to analyze the condition of transmission line towers, thereby achieving the goal of condition early warning.
[0003] However, facing the ever-increasing demand for intelligent processing, the limitations of traditional monitoring methods are becoming increasingly apparent. In the data acquisition and transmission stages, factors such as sensor accuracy and stability, as well as power supply and communication methods, all constrain data quality. Furthermore, in terms of data analysis and processing, existing capabilities struggle to handle complex and massive datasets, and are further hampered by varying operating conditions during actual monitoring and early warning processes, making it impossible to efficiently and accurately extract valuable information.
[0004] For example, the invention patent with publication number CN111223276A proposes a method and device for early warning of tilting of transmission line towers based on ubiquitous Internet of Things. Although the specific implementation process involves real-time acquisition of tilt angle and comparison of early warning values, it is difficult to avoid the influence of different working conditions on the early warning results when facing tower status early warning in complex environments. Summary of the Invention
[0005] In view of the above, it is necessary to provide a method and device for early warning of the status of transmission line towers based on the integration of multiple technologies to solve the above problems.
[0006] The first aspect of this application provides a method for early warning of the status of transmission line towers based on multi-technology integration, the method comprising:
[0007] Acquire various tower status data and various micro-meteorological monitoring data at each acquisition time;
[0008] Feature extraction was performed on tower status data and micrometeorological monitoring data, specifically as follows:
[0009] A1: For micro-meteorological monitoring data, based on the numerical change characteristics of each collection time and adjacent collection times, the operating condition evaluation sample for each sampling time is obtained, and the operating condition evaluation samples for all times are clustered.
[0010] A2: Based on the numerical distribution of all operating condition samples in each cluster under the same micrometeorological monitoring data, the operating condition response value of each cluster for each type of micrometeorological monitoring data is obtained;
[0011] A3: Analyze the distribution of the operating condition response values of all micrometeorological monitoring data in all clusters to obtain a control sample set; based on the sampling time corresponding to each element in the control sample set, obtain several time intervals;
[0012] A4: Analyze the distribution trend and dispersion of various tower status data in each time interval to obtain the feature vector; compare the differences between the feature vectors of the same tower status data in each time interval and other time intervals to obtain the wind deflection coefficient of each time interval.
[0013] A digital twin model is established based on all collected data and feature extraction results to provide early warning of the status of transmission line towers.
[0014] Preferably, obtaining the working condition evaluation sample at each sampling time specifically involves:
[0015] Calculate the change in each type of micro-meteorological monitoring data at each acquisition time compared to the previous time, and use the vector composed of the changes in all micro-meteorological monitoring data at each acquisition time as the operating condition evaluation sample for each acquisition time.
[0016] Preferably, the operating condition response value for each type of micrometeorological monitoring data in each cluster is specifically the mean of the change in each type of micrometeorological monitoring data for all operating condition evaluation samples within each cluster.
[0017] Preferably, obtaining the control sample set specifically involves:
[0018] For each type of micrometeorological monitoring data, obtain the normalized value of the operating condition response value of each type of micrometeorological monitoring data in all clusters; calculate the mean of the normalized value of the operating condition response value of all micrometeorological monitoring data in each cluster, and determine the cluster with the largest normalized mean as the control sample set.
[0019] Preferably, obtaining several time intervals specifically involves:
[0020] Using the collection time of all working condition evaluation samples in the control sample set as the working condition response time, and using the working condition response time as the time division point, several time intervals are obtained.
[0021] Preferably, the feature vector is determined by the trend statistics, variance, and deviation values of each tower status data in each time interval.
[0022] Preferably, the deviation value is specifically the average of the numerical differences between all adjacent moments in each time interval for each type of tower status data.
[0023] Preferably, the wind deflection coefficient for each time interval is obtained using the following formula: ,in, For the first Wind deflection coefficient for each time interval; Indicates the first The time interval and the first Normalized results of the differences in wind deflection angle data within a time interval; Indicates the first The time interval and the first Normalized results of the differences in tensile force data within each time interval; This indicates the number of time intervals; among them, the wind deflection angle data and tension data are both tower status data.
[0024] Preferably, the condition for issuing an early warning for the status of transmission line towers is that the digital twin model detects that the wind deflection angle, tension, and wind deflection coefficient exceed the corresponding early warning values.
[0025] Secondly, embodiments of this application also provide a transmission line tower status early warning device based on multi-technology integration, realizing the transmission line tower status early warning method based on multi-technology integration as described in any one of the above claims, the device comprising:
[0026] Tower status monitoring and acquisition unit: used to acquire various tower status data and various micro-meteorological monitoring data at each acquisition time;
[0027] High-altitude and cold region transmission line tower monitoring system: used to transmit data acquired by the tower status monitoring and acquisition unit to the substation;
[0028] Substation: Used to preprocess the acquired data and transmit the preprocessed data to the data processing unit;
[0029] Data processing unit: Used to obtain the operating condition evaluation sample for each sampling time based on the numerical change characteristics of each collection time and adjacent collection times for micro-meteorological monitoring data, and to cluster the operating condition evaluation samples for all times;
[0030] Based on the numerical distribution of all operating condition samples in each cluster under the same micrometeorological monitoring data, the operating condition response value of each cluster for each type of micrometeorological monitoring data is obtained.
[0031] The distribution of the operating condition response values of all micrometeorological monitoring data in all clusters was analyzed to obtain a control sample set; based on the sampling time corresponding to each element in the control sample set, several time intervals were obtained.
[0032] Analyze the distribution trend and dispersion of various tower status data in each time interval to obtain feature vectors; compare the differences between the feature vectors of the same tower status data in each time interval and other time intervals to obtain the wind deflection coefficient of each time interval.
[0033] Status alarm: Used to establish a digital twin model based on all collected data and feature extraction results, and to provide early warning of the status of transmission line towers.
[0034] The above scheme first analyzes the micrometeorological monitoring data collected during the tower condition early warning process under different operating conditions. Since the micrometeorological monitoring data exhibits different performance under various operating conditions, an operating condition assessment sample is obtained for each sampling time based on the numerical change characteristics between each acquisition time and adjacent acquisition times. The operating condition assessment samples from all times are then clustered, aggregating a large amount of operating condition data into several main categories, simplifying subsequent data processing and making system monitoring and maintenance more efficient. Based on the numerical distribution of all operating condition samples in each cluster under the same type of micrometeorological monitoring data, the operating condition response value for each type of micrometeorological monitoring data in each cluster is obtained. By analyzing the characteristics of each type of micrometeorological monitoring data in each cluster, it is possible to predict... This application predicts future operating conditions to help maintenance personnel prepare in advance or optimize equipment. It further divides time intervals under different operating conditions, allowing maintenance personnel to more accurately grasp the equipment status in each time period, providing a basis for equipment maintenance and repair. It analyzes the distribution trends and dispersion of various tower status data in each time interval to obtain feature vectors. By comparing the differences between the feature vectors of the same tower status data in each time interval and other time intervals, the wind deflection coefficient of each time interval is obtained, which helps to more accurately grasp and predict wind changes. This application constructs a digital twin model of the towers using feature extraction technology and implements a status early warning function. This method can accurately extract key information from complex data. Simultaneously, the establishment of the digital twin model makes real-time simulation and early warning of tower status possible. This application comprehensively utilizes multiple technical means to significantly improve the accuracy of transmission line tower status early warning, greatly promotes the intelligent process of transmission line operation and maintenance, and effectively ensures the safe and stable operation of transmission lines. Attached Figure Description
[0035] Figure 1 A flowchart illustrating the steps of a transmission line tower status early warning method based on multi-technology fusion, as provided in one embodiment of this application;
[0036] Figure 2 A schematic diagram illustrating the acquisition of wind deflection coefficient according to one embodiment of this application;
[0037] Figure 3This is a block diagram of a transmission line tower status early warning device based on multi-technology integration, provided as an embodiment of this application. Detailed Implementation
[0038] In the description of the embodiments in this application, the words "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary," "or," and "for example" is intended to present the relevant concepts in a specific manner.
[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in this application's specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
[0040] It should also be noted that the terms "first" and "second" in this application and its accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the method. Without departing from the scope of protection of this application, the execution order of multiple steps can be interchanged, and some steps can also be deleted.
[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.
[0042] The following description, in conjunction with the accompanying drawings, details the specific scheme of the transmission line tower status early warning method and device based on multi-technology integration provided in this application.
[0043] Please see Figure 1 The diagram illustrates a flowchart of a method for early warning of transmission line tower status based on multi-technology fusion, according to an embodiment of this application. The method includes the following steps:
[0044] The first step: Acquire various tower status data and various micro-meteorological monitoring data at each acquisition time.
[0045] The transmission line tower status early warning system of this application mainly consists of a tower status monitoring and acquisition unit, a substation, a high-altitude and cold-region transmission line tower monitoring system, a data processing unit, and a status alarm. Both the tower status monitoring and acquisition unit and the substation are installed on the transmission line towers. The acquisition unit collects transmission line tower status data. The acquisition unit includes a conductor / insulator wind deflection angle acquisition unit, a tension monitoring acquisition unit, and an intelligent micro-meteorological acquisition unit, which are used to collect conductor / insulator wind deflection angle data, tension data, and micro-meteorological monitoring data of the transmission line towers, respectively. The micro-meteorological monitoring data includes temperature, humidity, wind speed, wind direction, and air pressure; the conductor / insulator wind deflection angle data and tension data are both considered tower status data.
[0046] The transmission line tower monitoring system in high-altitude and cold regions utilizes wireless radio frequency technology and SMS / GPRS / 5G wireless communication technology to transmit data acquired by the tower status monitoring acquisition unit to the substation. The combination of multiple communication technologies ensures the accuracy, stability, timeliness, and completeness of the data. Considering that the data acquisition and transmission process is susceptible to environmental changes and the stability of the acquisition device, resulting in poor data quality, a Wiener filter is used to reduce noise in the acquired data. The substation then transmits the filtered and noise-reduced tower status data to the data processing module.
[0047] The second step is to extract features from the tower status data and micro-meteorological monitoring data.
[0048] Due to the complex environment in which transmission line towers are located, the instantaneous characteristics of tower status data collected under different operating conditions vary greatly. If status assessment and early warning are based solely on comparisons between real-time data and early warning values, significant errors may occur. Therefore, the data processing module needs to extract features from the real-time collected data at different time periods and under different operating conditions during the status early warning monitoring process.
[0049] A1: For micro-meteorological monitoring data, based on the numerical change characteristics of each collection time and adjacent collection times, the operating condition evaluation sample for each sampling time is obtained, and the operating condition evaluation samples for all times are clustered.
[0050] The tower status data collected under different operating conditions exhibit significant differences in instantaneous characteristics, which may lead to a large deviation between the instantaneous characteristics reflected by the real-time tower status data and the actual state. This results in substantial errors in subsequent tower status early warning using digital twin models. Therefore, this paper utilizes micrometeorological monitoring data to calculate the change of each type of micrometeorological monitoring data at each collection moment compared to the previous moment. The vector composed of the changes of all micrometeorological monitoring data at the same moment is used as the instantaneous state data change vector, which serves as the operating condition assessment sample. A cohesive hierarchical clustering algorithm is then used to cluster all operating condition assessment samples. The cohesive hierarchical clustering algorithm is a well-known existing technology and will not be elaborated upon in this application.
[0051] A2: Based on the numerical distribution of all operating condition samples in each cluster under the same micrometeorological monitoring data, the operating condition response value of each cluster for each type of micrometeorological monitoring data is obtained.
[0052] Considering the significant changes in tower status data during transitions under different operating conditions within the tower's environment, a comparative analysis is conducted on the clustered operating condition assessment samples. Specifically, the mean value of the change in each type of micrometeorological monitoring data across all operating condition assessment samples within each cluster is calculated as the operating condition response value for each type of micrometeorological monitoring data in each cluster. A larger operating condition response value indicates a higher likelihood that the corresponding data within the cluster is affected by changes in operating conditions, leading to a change in its status.
[0053] A3: Analyze the distribution of the operating condition response values of all micrometeorological monitoring data in all clusters to obtain a control sample set; based on the sampling time corresponding to each element in the control sample set, obtain several time intervals.
[0054] To further integrate the comprehensive variation characteristics of micrometeorological data under different operating conditions, and thus accurately determine the status data characteristics of tower condition early warning analysis in different time intervals, for each type of micrometeorological monitoring data, the operating condition response values of the same type of micrometeorological monitoring data in all clusters are used as input, and the Z-score algorithm is used for normalization. The mean of the normalized operating condition response values of all micrometeorological monitoring data in each cluster is calculated, and the cluster with the largest mean is determined as the control sample set for tower condition feature extraction.
[0055] Using the collection time of all working condition evaluation samples in the control sample set as the working condition response time, and using the working condition response time as the time division point, several time intervals for tower early warning monitoring are obtained.
[0056] A4: Analyze the distribution trend and dispersion of various tower status data in each time interval to obtain the feature vector; compare the differences between the feature vectors of the same tower status data in each time interval and other time intervals to obtain the wind deflection coefficient of each time interval.
[0057] For each time interval, the trend statistics, variance, and deviation of wind deflection angle and tension data are calculated separately. The trend statistics are calculated using a trend verification algorithm, a well-known existing technology. The deviation is calculated as follows: within a time interval, tower condition data of one type are arranged chronologically, and the numerical differences between adjacent moments are calculated. The average of all numerical differences is taken as the deviation of the corresponding tower condition data within a time interval. The vector formed by the trend statistics, variance, and deviation of wind deflection angle and tension data within each time interval is used as the feature vector for each type of tower condition data in each time interval, thereby achieving accurate extraction of tower condition characteristics under different operating conditions based on micro-meteorological monitoring data.
[0058] Furthermore, a comparison of the state characteristic differences of feature vectors under different operating conditions is conducted. The core purpose is to accurately present the differences in the state change response of transmission line towers under different operating conditions. The greater the difference in state characteristics, the more obvious the characteristic response of the state data to tower state early warning is when dividing the overall state change characteristic interval based on micro-meteorological monitoring data.
[0059] Specifically, the normalized result of the difference between the feature vector corresponding to each type of tower state data in each time interval and the feature vector corresponding to the tower state data in other time intervals is calculated. Methods that can be used to calculate the difference include, but are not limited to, Manhattan distance and Euclidean distance. This embodiment uses Euclidean distance, and the normalization method is the maximum-minimum normalization method. It should be understood that the larger the calculated difference value, the more significant the characteristic response of the tower state warning, and the more sensitive the data change can be to reflect the changes in tower state under different operating conditions.
[0060] Based on the comparison results of monitoring data of different types of towers under different operating conditions, the wind deflection coefficient for each time interval is calculated, and the formula is as follows: ,in, For the first Wind deflection coefficient for each time interval; Indicates the first The time interval and the first Normalized results of the differences in wind deflection angle data within a time interval; Indicates the first The time interval and the first Normalized results of the differences in tensile force data within each time interval; This indicates the number of time intervals. It should be understood that the larger the wind deflection coefficient, the more significant the change in the state data within the time interval under the corresponding working condition during the tower early warning process, and the more helpful it is for the accurate analysis of the state early warning.
[0061] The diagram illustrating the acquisition of the wind deflection coefficient is shown below. Figure 2 As shown.
[0062] The third step is to establish a digital twin model based on all the collected data and feature extraction results to provide early warnings about the status of transmission line towers.
[0063] A digital twin model is constructed based on the feature extraction results to achieve early warning of the status of transmission line towers. The construction of the digital twin model is the core step in achieving accurate early warning, and its specific process is as follows:
[0064] B1: Data Preparation: Summarize the preprocessed data obtained from all the above steps, including micrometeorological monitoring data, conductor / insulator wind deflection angle data, tension data, and wind deflection coefficients for wind deflection angle and tension data within each time interval. The Z-score algorithm is used to unify the dimensions of these data, remove outliers, and ensure that the data quality meets the modeling requirements.
[0065] B2: Determine the modeling technology: Select an appropriate modeling technology based on the physical characteristics, operating principles, and data characteristics of the transmission line towers; specifically, in terms of structural mechanics, use finite element analysis technology to simulate the stress and strain distribution of the towers under different stress conditions; in terms of electrical performance simulation, build a model with the help of circuit theory and electromagnetic principles; when describing the overall dynamic behavior of the system, determine the specific model based on multibody dynamics and control theory.
[0066] B3: Model Construction: A digital twin model is constructed from three dimensions: geometric model, physical model, and behavioral model. Based on the tower's design drawings and actual measurement data, a precise three-dimensional geometric model is built to recreate the tower's shape, dimensions, and the relative positions of its components. Combining the tower's three-dimensional stress state mathematical model and the conductor stress variation mathematical model, physical laws and parameters are incorporated to establish a physical model that simulates the tower's physical processes under various operating conditions. Based on historical and real-time monitoring data, the changing patterns and laws of the tower's operating status are analyzed to establish a behavioral model that predicts the tower's future operating status. Finally, the geometric model, physical model, and behavioral model are organically integrated to form a complete digital twin model framework.
[0067] B4: Status Early Warning: Preprocessed transmission line tower status data, along with wind deflection angle data, tension data, and wind deflection coefficient data at different time intervals, are input into the digital twin model. The model simulates the actual state of the towers, achieving a real-time mapping of the tower status. When the model detects that the wind deflection angle, tension, and wind deflection coefficient exceed the corresponding warning values, the system automatically triggers the early warning mechanism, promptly sending warning information to maintenance personnel to indicate potential safety hazards, enabling appropriate measures to be taken to ensure the safe and stable operation of the transmission line. The warning values consist of the maximum wind deflection angle data, maximum tension data value, and maximum wind deflection coefficient value set for the transmission line tower status.
[0068] Based on the same inventive concept as the above method, this application also provides a transmission line tower status early warning device based on multi-technology integration, the device comprising:
[0069] Tower status monitoring and acquisition unit: used to acquire various tower status data and various micro-meteorological monitoring data at each acquisition time;
[0070] High-altitude and cold region transmission line tower monitoring system: used to transmit data acquired by the tower status monitoring and acquisition unit to the substation;
[0071] Substation: Used to preprocess the acquired data and transmit the preprocessed data to the data processing unit;
[0072] Data processing unit: Used to obtain the operating condition evaluation sample for each sampling time based on the numerical change characteristics of each collection time and adjacent collection times for micro-meteorological monitoring data, and to cluster the operating condition evaluation samples for all times;
[0073] Based on the numerical distribution of all operating condition samples in each cluster under the same micrometeorological monitoring data, the operating condition response value of each cluster for each type of micrometeorological monitoring data is obtained.
[0074] The distribution of the operating condition response values of all micrometeorological monitoring data in all clusters was analyzed to obtain a control sample set; based on the sampling time corresponding to each element in the control sample set, several time intervals were obtained.
[0075] Analyze the distribution trend and dispersion of various tower status data in each time interval to obtain feature vectors; compare the differences between the feature vectors of the same tower status data in each time interval and other time intervals to obtain the wind deflection coefficient of each time interval.
[0076] Status alarm: Used to establish a digital twin model based on all collected data and feature extraction results, and to provide early warning of the status of transmission line towers.
[0077] The block diagram of the transmission line tower status early warning device based on multi-technology integration is as follows: Figure 3 As shown.
[0078] In summary, this application first analyzes the characteristics of micrometeorological monitoring data collected during the tower condition early warning process under different operating conditions. Due to the performance of micrometeorological monitoring data under different operating conditions, operating condition evaluation samples for each sampling time are obtained based on the numerical change characteristics between each collection time and adjacent collection times. These operating condition evaluation samples are then clustered, a large amount of operating condition data is aggregated into several main categories, simplifying the subsequent data processing and making the system monitoring and maintenance more efficient. Based on the numerical distribution of all operating condition samples in each cluster under the same type of micrometeorological monitoring data, the operating condition response value for each type of micrometeorological monitoring data in each cluster is obtained. By analyzing the characteristics of each type of micrometeorological monitoring data in each cluster, it is possible to... This application predicts future operating conditions, helping maintenance personnel prepare in advance or optimize equipment. It further divides time intervals under different operating conditions, allowing maintenance personnel to more accurately grasp the equipment status in each time period, providing a basis for equipment maintenance and repair. It analyzes the distribution trends and dispersion of various tower status data in each time interval to obtain feature vectors. By comparing the differences between the feature vectors of the same tower status data in each time interval and other time intervals, the wind deflection coefficient of each time interval is obtained, which helps to more accurately grasp and predict wind changes. This application constructs a digital twin model of the towers using feature extraction technology and implements a status early warning function. This method can accurately extract key information from complex data. Simultaneously, the establishment of the digital twin model makes real-time simulation and early warning of tower status possible. This application comprehensively utilizes multiple technical means to significantly improve the accuracy of transmission line tower status early warning, greatly promotes the intelligent process of transmission line operation and maintenance, and effectively ensures the safe and stable operation of transmission lines.
[0079] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description; sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0080] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from its essential characteristics. Therefore, the embodiments described above should be considered exemplary and non-limiting in all respects; modifications to the technical solutions described in the foregoing embodiments, or equivalent substitutions of some technical features, without causing the essence of the corresponding technical solutions to deviate from the scope of the technical solutions in the embodiments of this application, should all be included within the protection scope of this application.
Claims
1. A method for early warning of transmission line tower status based on multi-technology integration, characterized in that, The method includes the following steps: Acquire various tower status data and various micro-meteorological monitoring data at each acquisition time; the micro-meteorological monitoring data includes temperature, humidity, wind speed, wind direction and air pressure; the tower status data includes conductor / insulator wind deflection angle data and tension data; Feature extraction was performed on tower status data and micrometeorological monitoring data, specifically as follows: A1: For micro-meteorological monitoring data, calculate the change of each type of micro-meteorological monitoring data between each collection time and the previous time to obtain the operating condition evaluation sample at each sampling time, and cluster the operating condition evaluation samples at all times. A2: Based on the numerical distribution of all operating condition samples in each cluster under the same micro-meteorological monitoring data, the operating condition response value of each micro-meteorological monitoring data in each cluster is obtained; the operating condition response value of each micro-meteorological monitoring data in each cluster is specifically the mean of the change in each micro-meteorological monitoring data of all operating condition evaluation samples in each cluster; A3: Analyze the distribution of the operating condition response values of all micrometeorological monitoring data in all clusters to obtain a control sample set; based on the sampling time corresponding to each element in the control sample set, obtain several time intervals; The obtained control sample set is specifically as follows: For each type of micrometeorological monitoring data, obtain the normalized value of the operating condition response value of each type of micrometeorological monitoring data in all clusters; calculate the mean of the normalized value of the operating condition response value of all micrometeorological monitoring data in each cluster, and determine the cluster with the largest mean of the normalized value as the control sample set; A4: Analyze the distribution trend characteristics of various tower status data in each time interval to obtain the feature vector; compare the differences between the feature vectors of the same tower status data in each time interval and the other time intervals to obtain the wind deflection coefficient of each time interval. The wind deflection coefficient for each time interval is obtained by the following formula: ,in, For the first Wind deflection coefficient for each time interval; Indicates the first The time interval and the first Normalized results of the differences in wind deflection angle data within a time interval; Indicates the first The time interval and the first Normalized results of the differences in tensile force data within each time interval; This indicates the number of time intervals; among them, the wind deflection angle data and tension data are both tower status data; A digital twin model is established based on all collected data and feature extraction results to provide early warning of the status of transmission line towers; The operational condition evaluation sample at each sampling time is specifically a vector composed of the changes in all micrometeorological monitoring data at each sampling time; The resulting number of time intervals are as follows: Using the collection time of all working condition evaluation samples in the control sample set as the working condition response time, and using the working condition response time as the time division point, several time intervals are obtained; The feature vector is determined by the trend statistics, variance, and deviation value obtained by the trend verification algorithm for each type of tower status data in each time interval. Specifically, the deviation value is the mean of the numerical differences of each type of tower status data at all adjacent moments in each time interval. The conditions for issuing early warnings about the status of transmission line towers are: the digital twin model detects that the wind deflection angle, tension, and wind deflection coefficient exceed the corresponding early warning values.
2. A transmission line tower status early warning device based on multi-technology integration, implementing the transmission line tower status early warning method based on multi-technology integration as described in claim 1, wherein the device comprises: Tower status monitoring and acquisition unit: used to acquire various tower status data and various micro-meteorological monitoring data at each acquisition time; High-altitude and cold region transmission line tower monitoring system: used to transmit data acquired by the tower status monitoring and acquisition unit to the substation; Substation: Used to preprocess the acquired data and transmit the preprocessed data to the data processing unit; Data processing unit: Used to calculate the change of each type of micro-meteorological monitoring data at each collection time compared with the previous time, obtain the working condition evaluation sample at each sampling time, and cluster the working condition evaluation samples at all times; Based on the numerical distribution of all operating condition samples in each cluster under the same micrometeorological monitoring data, the operating condition response value of each cluster for each type of micrometeorological monitoring data is obtained. The distribution of the operating condition response values of all micrometeorological monitoring data in all clusters was analyzed to obtain a control sample set; based on the sampling time corresponding to each element in the control sample set, several time intervals were obtained. Analyze the distribution trend of various tower status data in each time interval to obtain feature vectors; compare the differences between the feature vectors of the same tower status data in each time interval and other time intervals to obtain the wind deflection coefficient of each time interval. Status alarm: Used to establish a digital twin model based on all collected data and feature extraction results, and to provide early warning of the status of transmission line towers.