Intelligent monitoring method for transmission structure foundation construction quality based on machine learning

Abstract

The present application relates to the technical field of power systems, and in particular to a method for intelligently monitoring the construction quality of power transmission structure foundations based on machine learning. The present application predicts line icing based on line condition data on corresponding installed towers and weather data of corresponding periods, performs tower stress anomaly analysis based on the line icing prediction results and the line conditions, estimates foundation stability in the corresponding direction through the obtained tower stress anomaly analysis results and line foundation connection data, performs foundation reinforcement warning based on future foundation stability prediction results, quickly discovers tower stability anomalies caused by uneven tower stress, and accurately analyzes the direction of stability anomalies based on the correlation between foundation anomalies and stress anomalies in directions, thereby effectively improving the safety of power transmission and distribution and the accuracy of reinforcement directions.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method for intelligently monitoring the construction quality of power transmission structure foundations based on machine learning. Background Art

[0002] In the field of power transmission and distribution, pole towers are important supporting structures for transmission lines, and their stability is directly related to the safety and reliability of power transmission and distribution. However, due to the influence of various factors, pole towers and their foundations face severe challenges, especially icing under extreme weather conditions. In existing technologies, icing prediction mainly relies on simple meteorological data and historical experience, lacking comprehensive analysis of line condition data, resulting in limited prediction accuracy. Accordingly, pole tower force analysis mostly uses static calculation methods, which fail to dynamically reflect actual weather conditions and real-time changes in icing. These methods show obvious limitations when dealing with complex weather conditions and variable load conditions, and cannot effectively warn of potential force anomalies and foundation stability issues.

[0003] When it comes to foundation stability prediction, existing technologies typically use isolated analysis models, separating tower stress from foundation connection data. This lack of a holistic analysis framework leads to deviations between the predicted results and actual conditions. Furthermore, existing technologies struggle to accurately correlate tower stress anomalies with foundation stability, making it impossible to quickly locate and accurately analyze the direction of stability anomalies when they occur. Consequently, they are significantly deficient in foundation reinforcement warning and directional accuracy.

[0004] In summary, existing technologies for icing prediction, tower stress anomaly analysis, and foundation stability estimation have the following major problems: 1. Icing prediction methods rely too much on simple meteorological data and fail to comprehensively utilize line condition data, resulting in low prediction accuracy; tower stress analysis methods lack dynamic real-time performance and cannot effectively reflect changes in actual weather conditions and icing conditions; foundation stability estimation lacks a comprehensive analysis model, making it difficult to accurately correlate tower stress anomalies with foundation connection data, resulting in inaccurate prediction results; 4. The lack of an effective early warning mechanism makes it impossible to quickly detect tower stability anomalies and accurately analyze the direction of the anomaly, affecting the timeliness and accuracy of reinforcement measures. Therefore, there is an urgent need for a comprehensive analysis method that can simultaneously consider multiple factors to achieve more accurate and efficient foundation stability estimation and reinforcement early warning. Summary of the Invention

[0005] In order to overcome the defects and shortcomings of the existing technology, the present application provides an intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning, which predicts line icing based on the line condition data on the corresponding installed tower and the weather data of the corresponding period, and performs tower stress anomaly analysis based on the line icing prediction results and the line conditions. The foundation stability in the corresponding direction is estimated by the obtained tower stress anomaly analysis results and the connection data of the line foundation, and a foundation reinforcement early warning is performed based on the future foundation stability prediction results. The tower stability anomaly caused by uneven tower stress is quickly discovered, and the direction of the stability anomaly is accurately analyzed by comprehensively analyzing the correlation between the foundation anomaly and the stress anomaly in the direction, thereby effectively improving the safety of power transmission and distribution and the accuracy of the reinforcement direction.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a method for intelligently monitoring the construction quality of a power transmission structure foundation based on machine learning, comprising the following steps:

[0008] S1: Obtain the connection data of the line foundation, the line condition data on the corresponding installed tower and the weather data of the corresponding period;

[0009] S2: Build a prediction model to predict line icing based on the line condition data on the corresponding installed towers and the weather data of the corresponding period;

[0010] S3: Analyze tower stress anomalies based on line icing prediction results and line conditions;

[0011] S4: Estimate foundation stability based on the obtained tower stress anomaly analysis results and line foundation connection data;

[0012] S5: Provide early warning of foundation reinforcement based on the future foundation stability prediction results.

[0013] In one implementation of the present application, step S1 includes the following specific steps:

[0014] S11. Collecting data on internal defects of the line foundation using a visual acquisition terminal. The visual acquisition terminal may be an image acquisition terminal that collects data on cracks and shedding on the foundation surface, or an ultrasonic acquisition terminal that obtains the location and size of internal defects of the line foundation.

[0015] S12. Obtaining conductor characteristics such as gravity, tension, and material of the line installed on the corresponding tower, and simultaneously obtaining heat dissipation of the line. The heat dissipation of the line is the energy lost when current flows in the wire. By obtaining the diameter of the wire and comprehensively considering the wire conditions, a rapid estimation of the icing condition of the wire in the environment is performed, thereby comprehensively estimating the amount of ice covering the wire surface.

[0016] S13. Obtain weather data for a corresponding period, wherein the weather data is environmental data that affects the amount of ice covering the power lines. The weather data here is obtained based on weather forecasts, and the impact of future weather on the lines is estimated. The obtained data is stored in a corresponding storage component for easy retrieval and use.

[0017] In one implementation of the present application, the line icing prediction in step S2 includes the following specific steps:

[0018] S21. Build a deep learning neural network model based on historical line condition data on towers and weather data of corresponding historical periods. Through continuous training and verification of historical data, the model obtains an ice prediction model with the line condition data on the corresponding installed towers and weather data of the corresponding period as input and the ice thickness of the corresponding line as output;

[0019] The specific construction steps are:

[0020] S211, extracting historical line condition data on towers, weather data corresponding to historical periods, and line ice thickness during historical corresponding periods, and constructing a deep learning neural network model whose input is the line condition data on towers and weather data corresponding to historical periods, and whose output is the line ice thickness during historical corresponding periods;

[0021] S212. The extracted historical tower line condition data, weather data corresponding to the historical period, and historical line ice thickness data for the corresponding period are used to set a parameter training set and a parameter test set in a ratio of 9:1; 90% of the parameter training set is input into the deep learning neural network model for training to obtain an initial deep learning neural network model; the initial deep learning neural network model is tested using 10% of the parameter test set, and the initial deep learning neural network model that meets the maximum line ice thickness judgment accuracy is output as the deep learning neural network model;

[0022] S22, importing the acquired weather data for the future period and the line condition data on the tower into the constructed deep learning neural network model to obtain line ice thickness condition data for the future period;

[0023] S23. Calculate the average cross-sectional area of ​​ice on the line based on the ice thickness, and then calculate the weight of the ice. The calculation formula is: ,in, is the density of ice, hm is the line length, rs is the radius of the ice cover and the line as a whole, and rc is the line radius.

[0024] In one implementation of the present application, the tower stress anomaly analysis in step S3 includes the following specific steps:

[0025] S31. Analyze abnormal wind load impact based on tower location data, line connection data, and wind condition data estimated by weather forecast, where abnormal wind load impact is: , where T is the future cycle duration, dt is the time integral, Fmax is the maximum safe force of the tower, and vt is the average future wind speed. is the air density, Cd is the wire resistance coefficient, is the sine of the angle between the conductor and the tower and the horizontal plane, is the cosine of the angle between the wind and the conductor. In this formula, the abnormal wind load effect is comprehensively evaluated by analyzing the impact of future periodic wind forces on the conductor after ice coating;

[0026] S32. Analyze the abnormal weight load impact based on the weight of the ice and the weight of the line, where the abnormal weight load impact is: , where Mz is the line weight, g is the acceleration of gravity, and F is the real-time conductor tension;

[0027] S33. Obtain the wind load influence anomaly and the weight load influence anomaly of the line at the corresponding angle in the future period, add them together, and obtain the tower force anomaly at the corresponding angle.

[0028] In one implementation of the present application, in step S4, the foundation stability is estimated based on the obtained tower stress anomaly analysis results and the line foundation connection data, including the following specific contents:

[0029] S41. Obtain the stress anomaly of the tower at each angle on the tower to obtain the overall stress anomaly of the tower. Take the tower as the starting point of the vector, the angle of the stress anomaly of the tower as the vector angle, and the corresponding ratio of the magnitude of the stress anomaly of the tower as the length of the vector. Obtain the sum of these vectors and the direction corresponding to the vector and the magnitude of the corresponding stress anomaly of the tower, and set them as the corresponding direction and magnitude of the overall stress anomaly of the tower.

[0030] S42. Obtain the defect conditions of each position of the tower foundation and the closest distance from each position to the corresponding direction of the abnormal stress of the tower as a whole; at the same time, the calculation formula for defect abnormality analysis is: , where m is the number of defects, Vi is the volume of the i-th defect, sr is the distance standard value, and si is the shortest distance from the i-th defect to the corresponding direction of the overall stress anomaly of the tower. The distance standard value is used to eliminate the distance unit.

[0031] S43. Obtain the abnormal magnitude of the overall force on the tower and the abnormal defect analysis results of the corresponding foundation at the future time, and simultaneously obtain the construction strength of the corresponding foundation to estimate the foundation stability. The foundation stability estimation calculation formula is: , where P is the construction strength of the corresponding foundation, Pm is the corresponding safe construction strength, and Fs is the abnormal force size of the entire tower.

[0032] In one implementation of the present application, the foundation reinforcement warning is performed based on the future foundation stability prediction result in step S5, including the following specific contents:

[0033] The calculated foundation stability prediction result is compared with the set foundation stability threshold. If the foundation stability prediction result is greater than or equal to the set foundation stability threshold, it means that the foundation is stable under the action of the next cycle environment and does not need to be reinforced. If the foundation stability prediction result is less than the set foundation stability threshold, it means that the foundation needs to be reinforced in the direction corresponding to the overall stress abnormality of the tower.

[0034] Secondly, this application also provides an intelligent monitoring system for the construction quality of power transmission structure foundations based on machine learning, including:

[0035] The data acquisition module acquires the connection data of the line foundation, the line condition data on the corresponding installed tower and the weather data of the corresponding period;

[0036] Line icing prediction module, which predicts line icing based on line condition data on the corresponding installed towers and weather data of the corresponding period;

[0037] The stress anomaly analysis module performs tower stress anomaly analysis based on line icing prediction results and line conditions;

[0038] The foundation stability prediction module uses the abnormal force analysis results of the tower and the connection data of the line foundation to predict the foundation stability;

[0039] The foundation reinforcement early warning module provides foundation reinforcement early warning based on the future foundation stability prediction results.

[0040] In a third aspect, the present application provides an electronic device comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a machine learning-based intelligent monitoring method for the construction quality of a power transmission structure foundation by calling the computer program stored in the memory.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute a method for intelligently monitoring the construction quality of a power transmission structure foundation based on machine learning.

[0042] Compared with the prior art, this application has the following advantages and beneficial effects:

[0043] The present application predicts line icing based on line condition data on the corresponding installed towers and weather data of the corresponding period, performs tower stress anomaly analysis based on the line icing prediction results and the line conditions, estimates foundation stability in the corresponding direction through the obtained tower stress anomaly analysis results and the connection data of the line foundation, performs foundation reinforcement early warning based on the future foundation stability prediction results, quickly discovers tower stability anomalies caused by uneven tower stress, and accurately analyzes the direction of stability anomalies based on the correlation between foundation anomalies and stress anomalies in the direction, thereby effectively improving the safety of power transmission and distribution and the accuracy of reinforcement directions. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0045] Figure 1 This is a schematic diagram of the overall process of an embodiment of the method of this application;

[0046] Figure 2 This is a workflow diagram of S2 in the embodiment of the method of this application;

[0047] Figure 3 This is a workflow diagram of S3 in the embodiment of the method of this application;

[0048] Figure 4 This is a structural diagram of an embodiment of the system of this application. DETAILED DESCRIPTION

[0049] The technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. Unless there is a conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0050] Example 1

[0051] like Figures 1 to 3 As shown, this embodiment provides a method for intelligently monitoring the construction quality of a power transmission structure foundation based on machine learning, which specifically includes the following steps:

[0052] S1: Obtain the connection data of the line foundation, the line condition data on the corresponding installed tower and the weather data of the corresponding period;

[0053] In this embodiment, step S1 includes the following specific steps:

[0054] S11. Collecting data on internal defects of the line foundation using a visual acquisition terminal. The visual acquisition terminal may be an image acquisition terminal that collects data on cracks and shedding on the foundation surface, or an ultrasonic acquisition terminal that obtains the location and size of internal defects in the line foundation. A three-dimensional model of the line foundation is constructed based on the acquired defect characteristics. The concrete strength of the line foundation, the size and location of the defects are annotated on the three-dimensional model for easy access. The three-dimensional model is constructed using three-dimensional software, which is a conventional technical means in the art and will not be described in detail here.

[0055] S12. Obtaining conductor characteristics such as gravity, tension, and material of the line installed on the corresponding tower, and simultaneously obtaining heat dissipation of the line. The heat dissipation of the line is the energy lost when current flows in the wire. By obtaining the diameter of the wire and comprehensively considering the wire conditions, a rapid estimation of the icing condition of the wire in the environment is performed, thereby comprehensively estimating the amount of ice covering the wire surface.

[0056] S13. Acquire weather data for a corresponding period, wherein the weather data is environmental data that affects the amount of ice covering the power lines. The weather data is acquired based on a weather forecast to estimate the impact of future weather on the power lines. Exemplary weather data include temperature monitoring: real-time monitoring of the air temperature, particularly whether it is close to or below freezing; humidity monitoring: high humidity promotes water condensation, increasing the likelihood of ice covering; precipitation forecast: confirming whether precipitation is expected, with freezing rain being the main type of precipitation that causes ice covering; and wind speed monitoring: wind speed affects water transport and heat exchange in the conductors, and its impact on ice covering needs to be comprehensively considered. The acquired weather data is combined with the thermal expansion and contraction of the conductors on the tower to comprehensively analyze the ice covering on the conductor surface, and the acquired data is stored in a corresponding storage component for easy retrieval and use.

[0057] S2: Build a prediction model to predict line icing based on the line condition data on the corresponding installed towers and the weather data of the corresponding period;

[0058] In this embodiment, the line icing prediction in step S2 includes the following specific steps:

[0059] S21. Build a deep learning neural network model based on historical line condition data on towers and weather data of corresponding historical periods. Through continuous training and verification of historical data, the model obtains an ice prediction model with the line condition data on the corresponding installed towers and weather data of the corresponding period as input and the ice thickness of the corresponding line as output;

[0060] The specific construction steps are:

[0061] S211, extracting historical line condition data on towers, weather data corresponding to historical periods, and line ice thickness during historical corresponding periods, and constructing a deep learning neural network model whose input is the line condition data on towers and weather data corresponding to historical periods, and whose output is the line ice thickness during historical corresponding periods;

[0062] S212. The extracted historical tower line condition data, weather data corresponding to the historical period, and historical line ice thickness data for the corresponding period are used to set a parameter training set and a parameter test set in a ratio of 9:1; 90% of the parameter training set is input into the deep learning neural network model for training to obtain an initial deep learning neural network model; the initial deep learning neural network model is tested using 10% of the parameter test set, and the initial deep learning neural network model that meets the maximum line ice thickness judgment accuracy is output as the deep learning neural network model;

[0063] S22, importing the acquired weather data for the future period and the line condition data on the tower into the constructed deep learning neural network model to obtain line ice thickness condition data for the future period;

[0064] S23. Calculate the average cross-sectional area of ​​ice on the line based on the ice thickness, and then calculate the weight of the ice. The calculation formula is: ,in, is the density of ice, hm is the line length, rs is the radius of the ice cover and the line as a whole, and rc is the line radius;

[0065] For example, the density of ice (p) = 900 kg / m 3 , line length (hm) = 100m, outer radius of ice (rs) = 0.05m, conductor radius (rc) = 0.03m, the calculated ice weight is: 452.385kg;

[0066] S3: Analyze tower stress anomalies based on line icing prediction results and line conditions;

[0067] In this embodiment, the tower stress abnormality analysis in step S3 includes the following specific steps:

[0068] S31. Analyze abnormal wind load impact based on tower location data, line connection data, and wind condition data estimated by weather forecast, where abnormal wind load impact is: , where T is the future cycle duration, dt is the time integral, Fmax is the maximum safe force of the tower, and vt is the average future wind speed. is the air density, Cd is the wire resistance coefficient, is the sine of the angle between the conductor and the tower and the horizontal plane, is the cosine of the angle between the wind and the conductor. In this formula, the abnormal wind load effect is comprehensively evaluated by analyzing the impact of future periodic wind forces on the conductor after ice coating;

[0069] For example, in this embodiment, the line length is 100m, the future cycle duration is 600s, the future average wind speed vt is 15m / s, the angle between the wind and the conductor is 70 degrees, the conductor inclination angle of the transmission line connected to the tower in the line connection data is 5, the conductor resistance coefficient defaults to 1.1, and the air density is 1.1kg / m 3 , the radius between ice cover and the entire line is 0.05m, the maximum allowable tension of the transmission line conductor is 75KN, and the dynamic wind load factor is 0.022;

[0070] S32. Analyze the abnormal weight load impact based on the weight of the ice and the weight of the line, where the abnormal weight load impact is: , where Mz is the line weight, g is the acceleration of gravity, and F is the real-time conductor tension;

[0071] S33, obtaining the abnormal wind load influence and the abnormal weight load influence of the line at the corresponding angle in the future period, and adding them to obtain the abnormal tower force at the corresponding angle;

[0072] S4: Estimate foundation stability based on the obtained tower stress anomaly analysis results and line foundation connection data;

[0073] In this embodiment, in step S4, the foundation stability is estimated based on the obtained tower stress anomaly analysis results and the line foundation connection data, including the following specific contents:

[0074] S41. Obtain the stress anomaly of the tower at each angle on the tower to obtain the overall stress anomaly of the tower. Take the tower as the starting point of the vector, the angle of the stress anomaly of the tower as the vector angle, and the corresponding ratio of the magnitude of the stress anomaly of the tower as the length of the vector. Obtain the sum of these vectors and the direction corresponding to the vector and the magnitude of the corresponding stress anomaly of the tower, and set them as the corresponding direction and magnitude of the overall stress anomaly of the tower.

[0075] S42. Obtain the defect conditions of each position of the tower foundation and the closest distance from each position to the corresponding direction of the abnormal stress on the tower as a whole. For example, the closest distance here is the distance from each position to the nearest point on the cutting surface obtained by perpendicularly cutting the tower foundation with a ray starting from the center of the tower and in the direction corresponding to the abnormal stress on the tower as the direction. Perform defect anomaly analysis based on the defect size and the closest distance to the corresponding direction of the abnormal stress on the tower as a whole. In this way, the defect impact is quantified by the distance between the defect and the corresponding direction of the abnormal stress on the tower as a whole, so as to quantitatively analyze the comprehensive impact of the defects at each position. At the same time, the calculation formula for defect anomaly analysis is: , where m is the number of defects, Vi is the volume of the i-th defect, sr is the distance standard value, and si is the shortest distance from the i-th defect to the corresponding direction of the overall stress anomaly of the tower. The distance standard value is used to eliminate the distance unit.

[0076] S43. Obtain the abnormal magnitude of the overall force on the tower and the abnormal defect analysis results of the corresponding foundation at the future time, and simultaneously obtain the construction strength of the corresponding foundation to estimate the foundation stability. The foundation stability estimation calculation formula is: , where P is the construction strength of the corresponding foundation, Pm is the corresponding safe construction strength, and Fs is the abnormal force magnitude of the tower as a whole;

[0077] S5: Provide early warning of foundation reinforcement based on the future foundation stability prediction results;

[0078] In this embodiment, the following specific contents are included:

[0079] The calculated foundation stability prediction result is compared with the set foundation stability threshold. If the foundation stability prediction result is greater than or equal to the set foundation stability threshold, it means that the foundation is stable under the action of the next cycle environment and does not need to be reinforced. If the foundation stability prediction result is less than the set foundation stability threshold, it means that the foundation needs to be reinforced in the corresponding direction where the overall stress of the tower is abnormal. The reinforcement method may include adding weights at the corresponding angles.

[0080] It should be noted that in this embodiment, the setting parameters in this embodiment are obtained by engineers in this field through experiments on historical data. The specific experimental method is: obtaining the connection data of the historical line foundation, as well as the line condition data on the corresponding installed pole tower and the weather data of the corresponding period, and substituting them into the steps of this embodiment to obtain the stability estimation results of the foundation in the next period, and at the same time obtaining the fact judgment results of whether the foundation will collapse in the next period. The two results are imported into the fitting software to output the setting parameter values ​​that meet the maximum accuracy rate of the fact judgment results of the occurrence of a collapse accident.

[0081] It should be noted that in this embodiment, this embodiment has the following benefits: line icing prediction is performed based on the line condition data on the corresponding installed tower and the weather data of the corresponding period, tower stress anomaly analysis is performed based on the line icing prediction result and the line condition, foundation stability in the corresponding direction is estimated by the obtained tower stress anomaly analysis result and the connection data of the line foundation, foundation reinforcement early warning is performed based on the future foundation stability prediction result, tower stability anomalies caused by uneven tower stress are quickly discovered, and the direction of stability anomalies is accurately analyzed by comprehensively analyzing the correlation between the foundation anomaly and the stress anomaly in the direction, thereby effectively improving the safety of power transmission and distribution and the accuracy of the reinforcement direction.

[0082] Example 2

[0083] like Figure 4 As shown, this embodiment provides a transmission structure foundation construction quality intelligent monitoring system based on machine learning, including:

[0084] The data acquisition module acquires the connection data of the line foundation, as well as the line condition data on the corresponding installed towers and the weather data of the corresponding period. The line icing prediction module predicts line icing based on the line condition data on the corresponding installed towers and the weather data of the corresponding period. The stress anomaly analysis module analyzes the tower stress anomaly based on the line icing prediction results and the line conditions. The foundation stability estimation module estimates the foundation stability based on the obtained tower stress anomaly analysis results and the connection data of the line foundation. The foundation reinforcement warning module issues a foundation reinforcement warning based on the future foundation stability prediction results.

[0085] The above-mentioned parameters and steps for each unit module to achieve corresponding functions in the intelligent monitoring system for the construction quality of power transmission structure foundation based on machine learning of the present invention can refer to the parameters and steps in the embodiment of the intelligent monitoring method for the construction quality of power transmission structure foundation based on machine learning above, and will not be repeated here.

[0086] Example 3

[0087] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0088] The processor executes the above-mentioned method for determining electric energy anomaly of the meter box based on big data evaluation by calling the computer program stored in the memory.

[0089] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors and one or more memories, wherein the memories store at least one computer program, which is loaded and executed by the processor to implement the intelligent monitoring method for power transmission structure foundation construction quality based on machine learning provided by the above method embodiment, including the following steps:

[0090] S1: Obtain the connection data of the line foundation, the line condition data on the corresponding installed tower and the weather data of the corresponding period;

[0091] S2: Build a prediction model to predict line icing based on the line condition data on the corresponding installed towers and the weather data of the corresponding period;

[0092] S3: Analyze tower stress anomalies based on line icing prediction results and line conditions;

[0093] S4: Estimate foundation stability based on the obtained tower stress anomaly analysis results and line foundation connection data;

[0094] S5: Providing a foundation reinforcement warning based on the future foundation stability prediction results. The electronic device may also include other components for implementing device functions. For example, the electronic device may also have components such as a wired or wireless network interface and an input / output interface to facilitate data input and output. This embodiment is not described in detail here.

[0095] Example 4

[0096] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0097] When the computer program runs on a computer device, the computer device executes the above-mentioned intelligent monitoring method for the construction quality of a power transmission structure foundation based on machine learning.

[0098] For example, the computer readable storage medium can be a read-only memory, a random access memory, a read-only CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0099] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. A computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

[0100] The above are merely embodiments of the present invention and are not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A machine learning-based intelligent monitoring method for the construction quality of power transmission structure foundations, characterized in that: The steps include: Obtain connection data of the line foundation, line condition data on the corresponding installed towers, and weather data for the corresponding period; Build a prediction model to predict line icing based on the line condition data on the corresponding installed towers and the weather data of the corresponding period; Based on the line icing prediction results and line conditions, the tower stress anomaly analysis is performed. Specifically, the wind load anomaly and weight load anomaly of the line at the corresponding angle in the future period are obtained and added together to obtain the tower stress anomaly at the corresponding angle. The foundation stability is estimated based on the abnormal tower stress analysis results and the connection data of the line foundation; Provide foundation reinforcement warning based on future foundation stability prediction results.

2. The method for intelligent monitoring of power transmission structure foundation construction quality based on machine learning according to claim 1, characterized in that: The line icing prediction includes the following specific steps: A deep learning neural network model is constructed based on historical line condition data on towers and weather data of corresponding historical periods. Through continuous training and verification of historical data, the input is the line condition data on the corresponding installed towers and weather data of the corresponding period, and the output is an ice coverage prediction model for the ice thickness of the corresponding line; Import the acquired weather data for the future period and the line condition data on the tower into the constructed deep learning neural network model to obtain the line ice thickness condition data for the future period; The average cross-sectional area of ​​ice covering the line is calculated based on the ice thickness of the line, and then the weight data of the ice covering is calculated.

3. The method for intelligent monitoring of power transmission structure foundation construction quality based on machine learning according to claim 2, characterized in that: The tower stress abnormality analysis includes the following specific steps: The abnormal wind load impact is analyzed based on tower location data, line connection data, and wind conditions data estimated by weather forecasts. The abnormal wind load impact is as follows: , where T is the future cycle duration, dt is the time integral, Fmax is the maximum safe force of the tower, and vt is the average future wind speed. is the air density, Cd is the wire resistance coefficient, is the sine of the angle between the conductor and the tower and the horizontal plane, is the cosine of the angle between the wind and the conductor, rs is the radius of the ice cover and the entire line, and hm is the line length; The abnormal weight load effect is analyzed based on the weight of ice and the weight of the line. The abnormal weight load effect is as follows: , where Mz is the line weight, g is the acceleration of gravity, F is the real-time conductor tension, and Mf is the weight data of ice cover; Obtain the abnormal wind load influence and the abnormal weight load influence of the line at the corresponding angle in the future period, add them together and obtain the abnormal tower force at the corresponding angle.

4. The method for intelligent monitoring of power transmission structure foundation construction quality based on machine learning according to claim 3, characterized in that: The foundation stability estimation based on the obtained abnormal tower stress analysis results and the line foundation connection data includes the following specific contents: S41. Obtain the stress anomaly of the tower at each angle on the tower to obtain the overall stress anomaly of the tower. Take the tower as the starting point of the vector, the angle of the stress anomaly of the tower as the vector angle, and the corresponding ratio of the magnitude of the stress anomaly of the tower as the length of the vector. Obtain the sum of these vectors and the direction corresponding to the vector and the magnitude of the corresponding stress anomaly of the tower, and set them as the corresponding direction and magnitude of the overall stress anomaly of the tower. S42. Obtain the defect conditions at each location of the tower foundation and the closest distance from each location to the corresponding direction of the abnormal stress on the tower as a whole. The calculation formula for defect abnormality analysis is: , where m is the number of defects, Vi is the volume of the i-th defect, sr is the standard value of distance, and si is the shortest distance from the i-th defect to the corresponding direction of the overall stress anomaly of the tower; S43. Obtain the abnormal magnitude of the overall force on the tower and the abnormal defect analysis results of the corresponding foundation at the future time, and simultaneously obtain the construction strength of the corresponding foundation to estimate the foundation stability. The foundation stability estimation calculation formula is: , where P is the construction strength of the corresponding foundation, Pm is the corresponding safe construction strength, and Fs is the abnormal force size of the entire tower.

5. The method for intelligent monitoring of power transmission structure foundation construction quality based on machine learning according to claim 4 is characterized in that: The foundation reinforcement early warning based on the future foundation stability prediction results includes the following specific contents: The calculated foundation stability prediction result is compared with the set foundation stability threshold. If the foundation stability prediction result is greater than or equal to the set foundation stability threshold, it means that the foundation is stable under the action of the next cycle environment and does not need to be reinforced. If the foundation stability prediction result is less than the set foundation stability threshold, it means that the foundation needs to be reinforced in the direction corresponding to the overall stress abnormality of the tower.

6. The method for intelligent monitoring of power transmission structure foundation construction quality based on machine learning according to claim 2, characterized in that: The specific steps of constructing the ice cover prediction model are: Extract historical line condition data on towers, weather data corresponding to historical periods, and line ice thickness during the corresponding historical periods. Build a deep learning neural network model whose input is the line condition data on towers and weather data corresponding to historical periods, and whose output is the line ice thickness during the corresponding historical periods. The extracted historical line condition data on the towers, the weather data of the corresponding historical period, and the historical line ice thickness data of the corresponding period are used to set the parameter training set and the parameter test set in a ratio of 9:1; 90% of the parameter training set is input into the deep learning neural network model for training to obtain the initial deep learning neural network model; the initial deep learning neural network model is tested using the 10% parameter test set, and the initial deep learning neural network model that meets the maximum line ice thickness judgment accuracy is output as the deep learning neural network model.

7. The method for intelligent monitoring of power transmission structure foundation construction quality based on machine learning according to claim 1, characterized in that: The step of obtaining the connection data of the line foundation, the line condition data on the corresponding installed tower, and the weather data of the corresponding period includes the following specific steps: Collect internal defect data of the line foundation through the visual acquisition terminal; Obtain the gravity, tension, material and other conductor characteristics of the line on the corresponding installed tower, and also obtain the heat dissipation of the line; Weather data of a corresponding period is obtained, wherein the weather data is environmental data that affects the amount of ice covering the power lines, and the obtained data is stored in a corresponding storage component for easy retrieval and use.

8. A system for intelligently monitoring the construction quality of power transmission structure foundations based on machine learning, which is implemented based on the method for intelligently monitoring the construction quality of power transmission structure foundations based on machine learning according to any one of claims 1 to 7, and is characterized in that: The system includes: The data acquisition module acquires the connection data of the line foundation, the line condition data on the corresponding installed tower and the weather data of the corresponding period; Line icing prediction module, which predicts line icing based on line condition data on the corresponding installed towers and weather data of the corresponding period; The stress anomaly analysis module performs tower stress anomaly analysis based on the line icing prediction results and line conditions. Specifically, the module obtains the wind load influence anomaly and weight load influence anomaly of the line at the corresponding angle in the future period and adds them together to obtain the tower stress anomaly at the corresponding angle. The foundation stability prediction module uses the abnormal force analysis results of the tower and the connection data of the line foundation to predict the foundation stability; The foundation reinforcement early warning module provides foundation reinforcement early warning based on the future foundation stability prediction results.

9. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the intelligent monitoring method for the construction quality of the power transmission structure foundation based on machine learning as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

Images