Power transmission structure foundation construction quality intelligent monitoring method based on machine learning

Abstract

The invention relates to the technical field of power systems, in particular to a power transmission structure foundation construction quality intelligent monitoring method based on machine learning, and the method carries out the line icing prediction based on the line condition data of a correspondingly installed tower and the weather data of a corresponding period. And carrying out tower stress abnormity analysis based on a line icing prediction result and a line condition, carrying out foundation stability estimation in a corresponding direction through an obtained tower stress abnormity analysis result and connection data of a line foundation, and carrying out foundation reinforcement early warning based on a future foundation stability estimation result. According to the method, the stability abnormity of the tower caused by uneven stress of the tower is quickly found, and the stability abnormity direction is accurately analyzed by combining the association of the abnormity of the foundation and the stress abnormity in the direction, so that the safety of power transmission and distribution and the accuracy of the reinforcing direction are effectively improved.

Description

Technical Field

[0001] This application relates to the technical field of power systems, and particularly to an intelligent monitoring method for the construction quality of the foundation of a transmission structure based on machine learning. Background Art

[0002] In the field of power transmission and distribution, as an important support structure for transmission lines, the stability of transmission towers is directly related to the safety and reliability of power transmission and distribution. However, affected by various factors, transmission towers and their foundations face severe challenges, especially the icing phenomenon under extreme weather conditions; in the existing technology, icing prediction mainly relies on simple meteorological data and historical experience, lacking comprehensive analysis of line condition data, resulting in limited prediction accuracy. Correspondingly, the force analysis of transmission towers mostly uses static calculation methods, which fail to dynamically reflect the actual weather conditions and real-time changes in icing. These methods show obvious limitations when dealing with complex weather conditions and variable load situations, and cannot effectively warn of potential abnormal forces and foundation stability problems; In terms of foundation stability prediction, the existing technology usually adopts isolated analysis models, separating the force on the transmission tower from the foundation connection data, lacking an overall analysis framework, resulting in a deviation between the prediction result and the actual situation. In addition, it is difficult for the existing technology to accurately correlate the abnormal force on the transmission tower with the foundation stability, and it is impossible to quickly locate and accurately analyze the abnormal direction when the stability anomaly occurs. Therefore, there are obvious deficiencies in foundation reinforcement warning and direction accuracy; In summary, the existing technology has the following main problems in icing prediction, abnormal force analysis of transmission towers, and foundation stability prediction: the icing prediction method relies too much on simple meteorological data and fails to comprehensively utilize line condition data, resulting in low prediction accuracy; the force analysis method of transmission towers lacks dynamic real-time performance and cannot effectively reflect the changes in actual weather conditions and icing states; the foundation stability prediction lacks a comprehensive analysis model and it is difficult to accurately correlate the abnormal force on the transmission tower with the foundation connection data, resulting in inaccurate prediction results; 4. lack of an effective warning mechanism, unable to quickly detect the abnormal stability of the transmission tower and accurately analyze the abnormal direction, affecting the timeliness and accuracy of reinforcement measures. Therefore, there is an urgent need for a comprehensive analysis method that can consider multiple factors simultaneously to achieve more accurate and efficient foundation stability prediction and reinforcement warning. Summary of the Invention

[0003] In order to overcome the defects and deficiencies of the existing technologies, 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 poles and towers and the weather data for the corresponding period, analyzes the abnormal force on the poles and towers based on the line icing prediction result and the line conditions, estimates the foundation stability in the corresponding direction through the obtained analysis result of the abnormal force on the poles and towers and the connection data of the line foundation, issues a foundation reinforcement warning based on the future foundation stability prediction result, quickly discovers the abnormal stability of the poles and towers caused by uneven force on the poles and towers, and accurately analyzes the abnormal stability direction by comprehensively considering the abnormalities of the foundation and the association of the abnormal force in the direction, thereby effectively improving the safety of power transmission and distribution and the accuracy of the reinforcement direction.

[0004] To achieve the above object, the present application adopts the following technical solutions: In a first aspect, the present application provides an intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning, including the following steps: S1: Obtain the connection data of the line foundation, as well as the line condition data on the corresponding installed poles and towers and the weather data for the corresponding period; S2: Construct a prediction model and predict line icing based on the line condition data on the corresponding installed poles and towers and the weather data for the corresponding period; S3: Analyze the abnormal force on the poles and towers based on the line icing prediction result and the line conditions; S4: Estimate the foundation stability through the obtained analysis result of the abnormal force on the poles and towers and the connection data of the line foundation; S5: Issue a foundation reinforcement warning based on the future foundation stability prediction result.

[0005] In an implementation manner of the present application, step S1 includes the following specific steps: S11: Collect the internal defect condition data of the line foundation through a visual acquisition terminal. The visual acquisition terminal can be an image acquisition terminal to collect the crack and peeling condition data on the foundation surface, or an ultrasonic acquisition terminal to obtain the internal defect position and size of the line foundation; S12: Obtain the gravity condition, tension condition, material and other conductor characteristics of the line on the corresponding installed poles and towers, and at the same time obtain the heat dissipation condition of the line. Among them, the heat dissipation condition of the line is the loss energy when the current flows in the conductor. By obtaining the diameter condition of the conductor and comprehensively considering the conductor conditions, quickly estimate the icing condition of the conductor in the environment, so as to comprehensively estimate the icing amount on the conductor surface; S13. Obtain the weather data for the corresponding period, where the weather data is the environmental data affecting the ice accretion amount on the wire. Here, the weather data is obtained according to the weather forecast to estimate the impact of the future weather on the line, and the obtained data is stored in the corresponding storage component for easy retrieval and use.

[0006] In an implementation manner of the present application, the prediction of line icing in step S2 includes the following specific steps: S21. Construct a deep learning neural network model based on the line condition data on the historical pole tower and the weather data for the corresponding historical period. Through continuous training and verification of the historical data, a icing prediction model is obtained with the input being the line condition data on the corresponding installed pole tower and the weather data for the corresponding period, and the output being the icing thickness of the corresponding line. The specific construction steps are as follows: S211. Extract the line condition data on the historical pole tower, the weather data for the corresponding historical period, and the historical icing thickness of the line for the corresponding period, and construct a deep learning neural network model with the input being the line condition data on the historical pole tower and the weather data for the corresponding historical period, and the output being the historical icing thickness of the line for the corresponding period. S212. Set the parameter training set and parameter test set according to the ratio of 9:1 for the extracted line condition data on the historical pole tower, the weather data for the corresponding historical period, and the historical icing thickness data for the corresponding period of the line; input 90% of the parameter training set into the deep learning neural network model for training to obtain an initial deep learning neural network model; use 10% of the parameter test set to test the initial deep learning neural network model, and output the initial deep learning neural network model that meets the maximum line icing thickness judgment accuracy rate as the deep learning neural network model. S22. Import the obtained weather data for the future period and the line condition data on the pole tower into the constructed deep learning neural network model to obtain the line icing thickness situation data for the future period. S23. Calculate the average cross-sectional area of the line icing based on the line icing thickness situation, and then calculate the weight data of the icing. The calculation formula is: , where is the density of ice, hm is the line length, rs is the radius of the ice covering and the whole line, and rc is the radius of the line.

[0007] In an implementation manner of the present application, the abnormal analysis of the pole tower force in step S3 includes the following specific steps: S31. Analyze the abnormal influence of the wind load based on the pole tower position data, the line connection data, and the wind force situation data estimated by the weather forecast. Among them, the abnormal influence of the wind load is: , where T is the duration of the future period, dt is the time integral, Fmax is the maximum safe stress of the tower, 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 connection of the wire and the tower and the horizontal plane, is the cosine of the angle between the wind force and the wire. In this formula, the abnormal influence of the wind load is comprehensively evaluated by analyzing the blowing influence of the wind force in the future period on the iced wire; S32. Analyze the abnormal influence of the weight load based on the weight of the ice coating and the influence of the weight of the line. The abnormal influence of the weight load is: , where Mz is the weight of the line, g is the acceleration due to gravity, and F is the real-time wire tension; S33. Obtain the abnormal influence of the wind load on the line at the corresponding angle in the future period and add the abnormal influence of the weight load to obtain the abnormal stress of the tower at the corresponding angle.

[0008] In an implementation manner of the present application, in step S4, the basic stability is estimated through the obtained analysis result of the abnormal stress of the tower and the connection data of the line foundation, including the following specific contents: S41. Obtain the abnormal stress of the tower at each angle on the tower to obtain the overall abnormal stress of the tower. Taking the tower as the vector starting point, the angle of the abnormal stress of the tower as the vector angle, and the corresponding proportion of the magnitude of the abnormal stress of the tower as the length of the vector, obtain the direction of the sum vector corresponding to the addition of these vectors and the magnitude of the abnormal stress of the tower corresponding thereto, and set it as the corresponding direction and magnitude of the overall abnormal stress of the tower; S42. Obtain the defect conditions at each position of the tower foundation and the shortest distance from each position to the corresponding direction of the overall abnormal stress of the tower; at the same time, the calculation formula for defect abnormal 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 abnormal stress of the tower. The distance standard value is used to eliminate the distance unit; S43. Obtain the magnitude of the overall abnormal stress of the tower at the future moment and the analysis result of the defect abnormality of the corresponding foundation, and at the same time obtain the construction strength of the corresponding foundation, and perform basic stability estimation. The calculation formula for basic stability estimation is: , where P is the construction strength of the corresponding foundation, Pm is the corresponding safety construction strength, and Fs is the magnitude of the overall abnormal stress of the tower.

[0009] In an implementation manner of the present application, in step S5, a basic reinforcement warning is performed based on the future basic stability estimation result, including the following specific contents: Compare the calculated estimated result of the foundation stability with the set foundation stability threshold. If the calculated estimated result of the foundation stability is greater than or equal to the set foundation stability threshold, it indicates that the foundation is stable under the action of the next-cycle environment and no reinforcement is required. If the calculated estimated result of the foundation stability is less than the set foundation stability threshold, it indicates that the foundation needs to be reinforced in the corresponding direction where the overall force on the tower pole is abnormal.

[0010] In a second aspect, the present application also provides an intelligent monitoring system for the construction quality of a transmission structure foundation based on machine learning, including: A data acquisition module that acquires connection data of the line foundation, line condition data on the tower pole installed correspondingly, and weather data for the corresponding period; A line icing prediction module that predicts line icing based on the line condition data on the tower pole installed correspondingly and the weather data for the corresponding period; A force abnormal analysis module that analyzes abnormal forces on the tower pole based on the line icing prediction result and the line conditions; A foundation stability estimation module that estimates the foundation stability through the obtained result of the abnormal force analysis on the tower pole and the connection data of the line foundation; A foundation reinforcement warning module that issues a foundation reinforcement warning based on the estimated result of the future foundation stability.

[0011] In a third aspect, an electronic device provided by the present application includes: a processor and a memory. Among them, a computer program that can be called by the processor is stored in the memory, and the processor executes an intelligent monitoring method for the construction quality of a transmission structure foundation based on machine learning by calling the computer program stored in the memory.

[0012] In a fourth aspect, a computer-readable storage medium provided by the present application stores instructions, and when the instructions run on a computer, the computer is enabled to execute an intelligent monitoring method for the construction quality of a transmission structure foundation based on machine learning.

[0013] Compared with the prior art, the present application has the following advantages and beneficial effects: The present application predicts line icing based on the line condition data on the tower pole installed correspondingly and the weather data for the corresponding period, analyzes abnormal forces on the tower pole based on the line icing prediction result and the line conditions, estimates the foundation stability in the corresponding direction through the obtained result of the abnormal force analysis on the tower pole and the connection data of the line foundation, and issues a foundation reinforcement warning based on the estimated result of the future foundation stability, quickly discovers abnormal tower pole stability caused by uneven forces on the tower pole, and accurately analyzes the direction of the stability abnormality by integrating the abnormality of the foundation and the association of the abnormal forces in the direction, thereby effectively improving the safety of power transmission and distribution and the accuracy of the reinforcement direction. Description of the Drawings

[0014] Other features, objectives, and advantages of the present application will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 It is a schematic diagram of the overall process of the method embodiment of the present application; Figure 2 It is a flowchart of the operation of S2 in the method embodiment of the present application; Figure 3 It is a flowchart of the operation of S3 in the method embodiment of the present application; Figure 4 It is a schematic diagram of the structure of the system embodiment of the present application. Detailed implementation manners

[0015] The technical solution of the present application will be described in detail below with reference to 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. Without conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0016] Embodiment 1 As Figures 1 to 3 shown, this embodiment provides an intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning, which specifically includes the following steps: S1: Obtain the connection data of the line foundation, as well as the line condition data on the corresponding installed pole tower and the weather data for the corresponding period; In this embodiment, step S1 includes the following specific steps: S11. Collect the internal defect condition data of the line foundation through a visual acquisition terminal. The visual acquisition terminal can be an image acquisition terminal to collect the crack and peeling condition data on the foundation surface, or an ultrasonic acquisition terminal to obtain the internal defect position and size of the line foundation. Based on the obtained defect features, construct a three-dimensional model of the line foundation. The concrete strength, defect size, and position of the line foundation are marked on the three-dimensional model for easy calling; The three-dimensional model is constructed by three-dimensional software, which is a conventional technical means in this field and will not be elaborated in detail here; S12. Obtain the gravity condition, tension condition, and material and other conductor features of the line on the corresponding installed pole tower. At the same time, obtain the heat dissipation condition of the line. Among them, the heat dissipation condition of the line is the loss energy when the current flows in the conductor. By obtaining the diameter condition of the conductor and comprehensively considering the conductor situation, quickly estimate the icing condition of the conductor in the environment, so as to comprehensively estimate the icing amount on the surface of the conductor; S13. Obtain the weather data for the corresponding period, where the weather data is environmental data affecting the ice accretion amount on the wire. Here, the weather data is obtained based on the weather forecast to estimate the impact of future weather on the line. Exemplarily, it includes temperature monitoring: real-time monitoring of the air temperature, especially whether it is close to or below the freezing point; humidity monitoring: high humidity contributes to water condensation and increases the possibility of ice accretion; precipitation forecast: confirm whether there is precipitation, and freezing rain is the main precipitation type leading to ice accretion; wind speed monitoring: wind speed affects water transportation and heat exchange of the wire, and its impact on ice accretion needs to be comprehensively considered. Analyze the ice accretion situation on the wire surface by comprehensively considering the obtained weather data and the thermal expansion and contraction of the wire on the tower, and store the obtained data in the corresponding storage component for easy retrieval and use; S2: Build a prediction model to predict line ice accretion based on the line condition data on the corresponding installed tower and the weather data for the corresponding period; In this embodiment, the line ice accretion prediction in step S2 includes the following specific steps: S21. Build a deep learning neural network model based on the line condition data on historical towers and the weather data for the corresponding historical period. Through continuous training and verification of historical data, obtain an ice accretion prediction model with the line condition data on the corresponding installed tower and the weather data for the corresponding period as the input and the ice accretion thickness of the corresponding line as the output; The specific construction steps are as follows: S211. Extract the line condition data on historical towers, the weather data for the corresponding historical period, and the ice accretion thickness of the line in the corresponding historical period, and build a deep learning neural network model with the line condition data on historical towers and the weather data for the corresponding historical period as the input and the ice accretion thickness of the line in the corresponding historical period as the output; S212. Set the parameter training set and parameter test set according to the ratio of 9:1 for the extracted line condition data on historical towers, the weather data for the corresponding historical period, and the ice accretion thickness data of the line in the corresponding historical period; input 90% of the parameter training set into the deep learning neural network model for training to obtain an initial deep learning neural network model; use 10% of the parameter test set to test the initial deep learning neural network model, and output the initial deep learning neural network model that meets the maximum judgment accuracy of the line ice accretion thickness as the deep learning neural network model; S22. Import the obtained weather data for the future period and the line condition data on the tower into the built deep learning neural network model to obtain the data on the ice accretion thickness situation of the line for the future period; S23. Calculate the average cross-sectional area of the line ice accretion based on the ice accretion thickness situation, and then calculate the weight data of the ice accretion. The calculation formula is: , where, is the density of ice, hm is the line length, rs is the radius of the ice-covered line as a whole, and rc is the line radius; Exemplarily, if the density of ice (p) = 900 kg / m 3 , the line length (hm) = 100 m, the outer radius of the ice covering (rs) = 0.05 m, and the conductor radius (rc) = 0.03 m, the calculated ice weight is: 452.385 kg; S3: Analyze the abnormal force on the tower based on the line icing prediction result and the line condition; In this embodiment, the abnormal force analysis on the tower in step S3 includes the following specific steps: S31. Analyze the abnormal influence of the wind load based on the tower position data, line connection data, and the wind force condition data estimated by the weather forecast. Among them, the abnormal influence of the wind load is: , where T is the future cycle duration, dt is the time integral, Fmax is the maximum safe force on the tower, vt is the average future wind speed, is the air density, Cd is the conductor resistance coefficient, is the sine of the angle between the connection of the conductor and the tower and the horizontal plane, is the cosine of the angle between the wind force and the conductor. In this formula, the abnormal influence of the wind load is comprehensively evaluated by analyzing the blowing influence of the future cycle wind force on the ice-covered conductor; Exemplarily, for example, in this embodiment, the line length is 100 m, the future cycle duration is 600 s, the average future wind speed vt is 15 m / s, the angle between the wind force and the conductor is 70 degrees, the inclination angle of the conductor of the transmission line connected to the iron tower in the line connection data is 5, the conductor resistance coefficient is defaulted to 1.1, and the air density is 1.1 kg / m 3 , the radius of the ice-covered line as a whole is 0.05 m, and the maximum allowable tension of the conductor of the transmission line is 75 KN, and the dynamic wind load factor is 0.022; S32. Analyze the abnormal influence of the weight load based on the weight of the ice covering and the influence of the line weight. Among them, the abnormal influence of the weight load is: , where Mz is the line weight, g is the acceleration due to gravity, and F is the real-time conductor tension; S33. Obtain the abnormal influence of the wind load and the abnormal influence of the weight load on the line at the corresponding angle in the future cycle and add them to obtain the abnormal force on the tower at the corresponding angle; S4: Estimate the foundation stability through the obtained abnormal force analysis result of the tower and the connection data of the line foundation; In this embodiment, in step S4, estimating the foundation stability through the obtained abnormal force analysis result of the tower and the connection data of the line foundation includes the following specific contents: S41. Obtain the abnormal force of the pole tower at each angle to obtain the overall abnormal force of the pole tower. Taking the pole tower as the vector starting point, the angle of the abnormal force of the pole tower as the vector angle, and the corresponding ratio of the magnitude of the abnormal force of the pole tower as the length of the vector, obtain the direction of the sum vector of these vectors added together and the magnitude of the corresponding abnormal force of the pole tower, which is set as the corresponding direction and magnitude of the overall abnormal force of the pole tower. S42. Obtain the defect conditions at each position of the pole tower foundation and the shortest distance from each position to the corresponding direction of the overall abnormal force of the pole tower. Exemplarily, the shortest distance here is the distance from the center of the pole tower as the starting point, with the corresponding direction of the overall abnormal force of the pole tower as the direction, and the ray perpendicular to the pole tower foundation to obtain the cutting surface. The distance from each position to the nearest point on the cutting surface. Based on the defect size and the shortest distance to the corresponding direction of the overall abnormal force of the pole tower, conduct defect abnormality analysis. In this way, the influence of the defect is quantified by the distance between the defect and the corresponding direction of the overall abnormal force of the pole tower to quantitatively analyze the comprehensive influence of the defects at each position; 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 abnormal force of the pole tower. Among them, the distance standard value is to eliminate the distance unit. S43. Obtain the magnitude of the overall abnormal force of the pole tower at the future moment and the result of defect abnormality analysis of the corresponding foundation, and at the same time obtain the construction strength of the corresponding foundation to conduct foundation stability prediction. Among them, the calculation formula for foundation stability prediction is: , where P is the construction strength of the corresponding foundation, Pm is the corresponding safety construction strength, and Fs is the magnitude of the overall abnormal force of the pole tower. S5: Conduct foundation reinforcement warning based on the future foundation stability prediction result. In this embodiment, it includes the following specific content: Compare the calculated foundation stability prediction result 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 of the overall abnormal force of the pole tower. The reinforcement method can include reinforcement forms such as adding weights at the corresponding angles.

[0017] It should be noted that in this embodiment, the method for obtaining the set parameters is that engineers in this field obtain them through experiments on historical data. The specific experimental method is as follows: Obtain the connection data of the historical line foundation, the line condition data on the corresponding installed tower, and the weather data of the corresponding period, substitute them into each step of this embodiment to obtain the predicted result of the foundation stability in the next period. At the same time, obtain the factual judgment result of whether the foundation collapses in the next period. The two results are imported into the fitting software to output the set parameter value that meets the highest accuracy rate of the factual judgment result of the collapse accident.

[0018] It should be noted that in this embodiment, the following advantages exist. Based on the line condition data on the corresponding installed tower and the weather data of the corresponding period, line icing prediction is carried out. Based on the line icing prediction result and the line condition, abnormal force analysis of the tower is carried out. Through the obtained abnormal force analysis result of the tower and the connection data of the line foundation, the foundation stability in the corresponding direction is predicted. Based on the predicted result of the future foundation stability, foundation reinforcement warning is carried out. The abnormal stability of the tower caused by uneven force on the tower is quickly discovered. By comprehensively considering the abnormality of the foundation and the association of the abnormal force in the direction, the abnormal stability direction is accurately analyzed, thereby effectively improving the safety of power transmission and distribution and the accuracy of the reinforcement direction.

[0019] Embodiment 2 As Figure 4 shown, this embodiment provides an intelligent monitoring system for the construction quality of the transmission structure foundation based on machine learning, including: A data acquisition module that 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; a line icing prediction module that performs line icing prediction based on the line condition data on the corresponding installed tower and the weather data of the corresponding period; an abnormal force analysis module that performs abnormal force analysis of the tower based on the line icing prediction result and the line condition; a foundation stability prediction module that predicts the foundation stability through the obtained abnormal force analysis result of the tower and the connection data of the line foundation; a foundation reinforcement warning module that performs foundation reinforcement warning based on the predicted result of the future foundation stability; For the parameters and the steps of each unit module in the above-mentioned intelligent monitoring system for the construction quality of the transmission structure foundation based on machine learning of the present invention to achieve the corresponding functions, reference can be made to the parameters and steps in the embodiment of the intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning in the above text, which will not be elaborated here.

[0020] Embodiment 3 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; The processor executes the above method for determining abnormal electric energy of the metering box based on big data evaluation by calling the computer program stored in the memory.

[0021] This electronic device can have relatively large differences due to different configurations or performances, and can include one or more processors and one or more memories. Among them, at least one computer program is stored in the memory, and this computer program is loaded and executed by the processor to implement the intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning provided by the above method embodiment, including the following steps: S1: Obtain the connection data of the line foundation, as well as the line condition data on the corresponding installed pole tower and the weather data for the corresponding period; S2: Construct a prediction model, and perform line icing prediction based on the line condition data on the corresponding installed pole tower and the weather data for the corresponding period; S3: Analyze the abnormal force of the pole tower based on the line icing prediction result and the line condition; S4: Estimate the foundation stability through the obtained analysis result of the abnormal force of the pole tower and the connection data of the line foundation; S5: Issue a foundation reinforcement warning based on the future foundation stability estimation result. This electronic device can also include other components for realizing the device functions. For example, this electronic device can also have components such as wired or wireless network interfaces and input / output interfaces for data input / output. This embodiment will not be elaborated here.

[0022] Embodiment 4 This embodiment proposes a computer-readable storage medium, on which a rewritable computer program is stored; When the computer program runs on the computer device, it enables the computer device to execute the above intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning.

[0023] For example, the computer-readable storage medium can be a read-only memory, a random access memory, a compact disc read-only memory, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0024] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted 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. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains a collection of one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0025] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various changes and modifications can be made to the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. An intelligent monitoring method for the construction quality of the foundation of a transmission structure based on machine learning, characterized in that, It includes the following steps: Obtain the connection data of the line foundation, as well as the line condition data on the corresponding installed tower and the weather data for the corresponding period; Construct a prediction model to predict line icing based on the line condition data on the corresponding installed tower and the weather data for the corresponding period; Conduct an abnormal analysis of the tower stress based on the line icing prediction result and the line conditions; Estimate the foundation stability through the obtained abnormal analysis result of the tower stress and the connection data of the line foundation; Conduct a foundation reinforcement warning based on the future foundation stability estimation result.

2. The intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning according to claim 1, characterized in that, The specific steps of the line icing prediction include: Construct a deep learning neural network model based on the line condition data on historical towers and the weather data for the corresponding historical period. Through continuous training and verification of the historical data, obtain an icing prediction model with the line condition data on the corresponding installed tower and the weather data for the corresponding period as the input and the icing thickness of the corresponding line as the output; Import the obtained 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 icing thickness data for the future period; Calculate the average cross-sectional area of the line icing based on the line icing thickness data, and then calculate the weight data of the icing.

3. The intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning according to claim 2, wherein The specific steps of the abnormal analysis of the tower stress include: Analyze the abnormal influence of wind load based on the pole position data, line connection data, and wind condition data estimated by weather forecast. Among them, the abnormal influence of wind load is as follows: , where T is the duration of the future period, dt is the time integral, Fmax is the maximum safe stress of the pole, 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 connection of the wire and the pole and the horizontal plane, is the cosine of the angle between the wind and the wire, and rs is the radius of the ice coating and the overall line; Analyze the abnormal influence on the weight load based on the weight of the ice coating and the influence of the weight of the line. Among them, the abnormal influence on the weight load is as follows: , where Mz is the weight of the line, g is the acceleration due to gravity, F is the real-time tension of the conductor, and Mf is the weight data of the ice coating; Obtain the abnormal influence of the wind load and the abnormal influence of the weight load on the line at the corresponding angle in the future period, and add them to obtain the abnormal tower stress at the corresponding angle.

4. The intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning according to claim 3, wherein The specific content of estimating the foundation stability through the obtained abnormal analysis result of the tower stress and the connection data of the line foundation includes: S41. Obtain the abnormal tower stress at each angle on the tower to obtain the overall tower stress. Taking the tower as the vector starting point, the angle of the abnormal tower stress as the vector angle, and the corresponding proportion of the magnitude of the abnormal tower stress as the length of the vector, obtain the direction of the sum vector corresponding to the addition of these vectors and its corresponding magnitude of the abnormal tower stress, and set it as the corresponding direction and magnitude of the overall tower stress; S42. Obtain the defect conditions at various positions of the tower foundation and the shortest distances from each position to the corresponding directions of the abnormal overall force of the tower. The calculation formula for defect abnormality analysis is as follows: , 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 abnormal overall force of the tower; S43. Obtain the abnormal magnitude of the overall force on the pole tower at a future moment and the analysis result of the defect abnormality of the corresponding foundation. At the same time, obtain the construction strength of the corresponding foundation and conduct a prediction of the foundation stability. The calculation formula for the foundation stability prediction is as follows: , where P is the construction strength of the corresponding foundation, Pm is the corresponding safe construction strength, and Fs is the abnormal magnitude of the overall force on the pole tower.

5. The intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning according to claim 4, wherein The specific content of conducting a foundation reinforcement warning based on the future foundation stability estimation result includes: Compare the calculated foundation stability estimation result with the set foundation stability threshold. If the foundation stability estimation result is greater than or equal to the set foundation stability threshold, it indicates that the foundation is stable under the action of the next-period environment and does not need to be reinforced. If the foundation stability estimation result is less than the set foundation stability threshold, it indicates that the foundation needs to be reinforced in the corresponding direction of the overall tower stress.

6. The intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning according to claim 2, wherein, The specific construction steps of the icing prediction model are: Extract the line condition data on historical towers, the weather data for the corresponding historical period, and the line icing thickness for the corresponding historical period, and construct a deep learning neural network model with the line condition data on historical towers and the weather data for the corresponding historical period as the input and the line icing thickness for the corresponding historical period as the output; Set the parameter training set and parameter test set according to the ratio of 9:1 for the line condition data extracted from historical poles, the weather data of the corresponding historical period, and the line icing thickness data of the historical corresponding period; input 90% of the parameter training set into the deep learning neural network model for training to obtain the initial deep learning neural network model; use 10% of the parameter test set to test the initial deep learning neural network model, and output the initial deep learning neural network model that meets the maximum line icing thickness judgment accuracy as the deep learning neural network model.

7. The intelligent monitoring method for the construction quality of the transmission structure foundation based on machine learning according to claim 1, wherein The acquisition of the connection data of the line foundation, as well as the line condition data on the corresponding installed poles and the weather data of the corresponding period, includes the following specific steps: Collect the internal defect condition data of the line foundation through the visual acquisition terminal. Obtain the wire characteristics such as the gravity condition, tension condition, and material of the line on the corresponding installed pole, and at the same time obtain the heat dissipation condition of the line. Obtain the weather data of the corresponding period, where the weather data is the environmental data affecting the ice accretion amount of the wire, and the obtained data is stored in the corresponding storage component for easy retrieval and use.

8. An intelligent monitoring system for the construction quality of transmission structure foundations based on machine learning, which is implemented based on the intelligent monitoring method for the construction quality of transmission structure foundations based on machine learning according to any one of claims 1-7, characterized in that, The system includes: A data acquisition module that acquires the connection data of the line foundation, as well as the line condition data on the corresponding installed pole and the weather data of the corresponding period; A line icing prediction module that predicts line icing based on the line condition data on the corresponding installed pole and the weather data of the corresponding period; A force abnormal analysis module that analyzes the abnormal force of the pole based on the line icing prediction result and the line condition; A foundation stability estimation module that estimates the foundation stability through the obtained pole force abnormal analysis result and the connection data of the line foundation; A foundation reinforcement warning module that issues a foundation reinforcement warning based on the future foundation stability estimation result.

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

Images