A power tower deformation monitoring and early warning method and system thereof

Abstract

The application discloses a power tower deformation monitoring and early warning method and system, and relates to power equipment operation and maintenance management technology.The method is based on the mechanical transmission law of the foundation, bottom foundation and tower body of the power tower, multi-dimensional data acquisition firmware is arranged at key nodes in combination with actual working conditions, a tower deformation simulation analysis model is designed, the stress distribution and settlement displacement of the tower are analyzed based on real-time acquired dynamic data, then the deformation trend of the power tower in a preset period range is analyzed based on the analysis result of the tower deformation simulation analysis model, in combination with real-time data and external environment characteristics, and key point distribution indications are provided for subsequent tower node reinforcement; meanwhile, the deformation risk of the tower is quantitatively calculated based on deformation trend characteristics, structure strength characteristics and environment influence characteristics by the prediction model, and then an early warning level is output according to the calculation result.

Description

Technical Field

[0001] This invention relates to the field of power equipment operation and maintenance management technology, and in particular to a method and system for monitoring and early warning of power pole deformation. Background Technology

[0002] As the main supporting component for power line erection, the foundation of power poles is usually installed in the ground by pre-casting. During long-term use, especially in some extremely cold regions, the soil structure changes due to freeze-thaw cycles, altering the stress state of the soil. Throughout this process, the cast-in-place foundation at the bottom of the pole will experience varying degrees of settlement and displacement. This alters the stress transmission within the power pole, causing the actual stress points to deviate from the intended design, leading to a risk of deformation for the entire power pole.

[0003] In existing technologies, manual periodic inspections are typically conducted, along with the installation of monitoring units at key nodes. These units determine the deformation risk of power poles by observing concrete deformation and displacement characteristics. However, in practical applications, when the deformation reaches a level that can be observed concretely, power poles may experience serious overturning and damage at any time, leading to greater safety hazards and losses. To achieve the prediction of deformation trends and the assessment of risk levels for power poles, a method and system for monitoring and warning of power pole deformation are provided. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for monitoring and early warning of deformation of power poles and towers, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a method for monitoring and early warning of deformation of power poles, comprising the following steps: S1. Install the data acquisition firmware on the tower to achieve periodic data acquisition; S2. Construct a tower deformation simulation analysis model and analyze stress distribution and settlement displacement based on real-time data; S3. Construct a prediction model to predict potential risks based on simulation analysis results, real-time data, and external environmental characteristics; The prediction model is based on the analysis results of the tower deformation simulation analysis model, and combines real-time data and external environmental characteristics to analyze the deformation trend of power towers within a preset period. The prediction model is based on the deformation trend of power poles, the structural strength of power poles and the characteristics of the external environment to perform feature extraction, and after normalized data processing, the data is deeply fused and then risk quantification calculation is performed. In the process of risk quantification calculation, the prediction model compares the historical trend of environmental characteristics with the current environmental characteristics to dynamically optimize the weights of various features in the risk quantification calculation and achieve dynamic early warning. S4. Output the risk warning level based on the prediction results.

[0006] Preferably, in step S1, based on the mechanical transmission laws of the power pole's foundation, bottom foundation, and tower body, multi-dimensional data acquisition firmware is deployed at key nodes in combination with actual working conditions to monitor the freeze-thaw cycle of the foundation, the displacement and settlement of the bottom foundation, and the stress distribution and deformation of the tower body, thereby realizing the periodic acquisition and synchronous transmission of multi-source data.

[0007] Preferably, during the periodic collection of multi-source data, a differentiated sampling period is adopted based on different stages of freeze-thaw cycles. The sampling period is 5 hours in the early stage of freeze-thaw cycle, 2 hours in the later stage of freeze-thaw cycle, and 1 hour in the thawing stage. At the same time, the sampling period is dynamically adjusted according to the subsequent risk warning level. For each increase in risk level, the current sampling period is shortened by 20%.

[0008] Preferably, in step S2, based on the mechanical transmission law of the foundation, bottom foundation and tower body of the power pole, and the coupling law of freeze-thaw cycle and fatigue load in severe cold regions, a pole deformation simulation analysis model is constructed, and the stress distribution and settlement displacement characteristics of the pole are simulated and analyzed based on the real-time collected data.

[0009] Preferably, the tower deformation simulation analysis model is based on the static structural parameters of the tower, bottom foundation, and subgrade. A coupled mechanical model is constructed using finite element simulation technology, with contact coupling between modules to ensure effective stress and deformation transfer. The subgrade module sets parameter correlations for the dynamic changes of freeze-thaw mechanical properties with temperature, simulating the dynamic changes in soil mechanical properties during freezing and thawing. Then, the real-time monitoring data collected by S1 is dynamically loaded into the model according to a time series to recreate the stress environment of the tower under dynamic conditions. The model outputs a tower stress distribution cloud map, settlement displacement time history curve, and tower body tilt trend data, obtaining quantitative simulation analysis results, including simulated settlement. Simulated tilt angle Simulate maximum strain and stress concentration factor .

[0010] Preferably, in step S3, the prediction model uses a hybrid CNN and LSTM network to extract key features of three types of input data, including deformation trend features, structural strength features, and environmental impact features. The deformation trend characteristics are based on simulated and real-time settlement and skew data. The temporal changes of settlement rate, cumulative skew amount and deformation acceleration are extracted according to the comparison results, thereby quantifying the development trend of deformation. The structural strength characteristics are quantified based on the structural redundancy characteristics, stress accumulation damage characteristics, stress concentration characteristics and critical failure margin characteristics of the tower structure after normalization. The environmental impact characteristics encompass freeze-thaw intensity, extreme weather duration, abrupt environmental changes, and climate synergy. A comprehensive analysis of the impact of environmental changes on tower deformation is conducted through quantitative calculations. Finally, a predictive model is used for quantitative analysis to predict the deformation trend of the tower.

[0011] Preferably, the prediction model is based on the deformation trend characteristics, structural strength characteristics and environmental impact characteristics of the tower, and adopts multi-factor weighted summation and coupling correction to comprehensively and quantitatively judge the potential risk level of the tower. The formula is as follows:

[0012] in This represents the total risk value, and The closer it is to 1, the higher the risk. , respectively representing the weights of the three, and ; Indicates the risk factor for deformation trends; Indicates structural strength risk factor; Indicates environmental factors that exacerbate risk. This represents the coupling correction coefficient for polyphonic characters, and It represents the intensity of the synergistic effect of deformation, structure, and environment, and is determined by fitting historical data; Ultimately, the tower deformation risk level is determined through quantitative calculation, which reflects the current degree of damage caused by tower deformation.

[0013] Preferably, the prediction model integrates big data and embeds deep learning algorithms. It acquires historical environmental data based on big data, then predicts future environmental change trends based on current environmental data characteristics. The weights are then redistributed according to the current freeze-thaw stage and future environmental change characteristics. This optimizes the calculation of the early warning risk level of tower deformation for different characteristics at different stages, and finally obtains the quantitative analysis result that is closest to the current environmental characteristics.

[0014] Preferably, in step S4, by... Threshold division is performed based on the range of values, thereby determining the appropriate threshold. Different warning levels are set for the threshold ranges corresponding to the values.

[0015] A power pole deformation monitoring and early warning system includes: Data acquisition module; Data processing module; Tower deformation simulation analysis model; Predictive models; Early warning module; Data storage module; Network module.

[0016] The technical effects and advantages of this invention are as follows: 1. This method for monitoring and early warning of power pole deformation is based on the mechanical transmission laws of the power pole's foundation, bottom foundation, and tower body. It combines actual working conditions with multi-dimensional data acquisition devices deployed at key nodes to monitor foundation freeze-thaw cycles, bottom foundation displacement and settlement, and tower stress distribution and deformation. A pole deformation simulation analysis model is designed to analyze the stress distribution and settlement displacement of the pole based on real-time acquired dynamic data. Then, a prediction model using a hybrid CNN and LSTM network is used to analyze the deformation trend of the power pole within a preset period, based on the results of the pole deformation simulation analysis model and combined with real-time data and external environmental characteristics. This provides data support for strengthening key nodes of critical poles, and ultimately, reinforcement is carried out based on the node locations described in the deformation trend. Simultaneously, the prediction model quantifies the deformation risk of the pole based on deformation trend characteristics, structural strength characteristics, and environmental impact characteristics, and then outputs an early warning level based on the calculation results.

[0017] 2. This power pole deformation monitoring and early warning method adopts differentiated sampling periods based on different stages of freeze-thaw cycles during the periodic collection of multi-source data. The sampling period is 5 hours in the early stage of freeze-thaw, 2 hours in the later stage of freeze-thaw, and 1 hour in the thawing stage. At the same time, the sampling period is dynamically adjusted according to the subsequent risk warning level. For each increase in risk level, the current sampling period is shortened by 20%, thereby achieving intelligent shortening of the sampling period and reducing the possibility of instantaneous dangers.

[0018] 3. The power pole deformation monitoring and early warning method and system compares historical environmental feature trends with current environmental features during the pole deformation risk quantification calculation process. This dynamically optimizes the weights of various features in the risk quantification calculation, achieving dynamic early warning. The prediction model integrates big data and embeds deep learning algorithms. It acquires historical environmental data based on big data and then predicts future environmental change trends based on current environmental data characteristics. The weights are then redistributed according to the current freeze-thaw stage and future environmental change characteristics. This optimizes the calculation of early warning risk levels for pole deformation based on different features at different stages, ultimately obtaining a quantitative analysis result that most closely matches the current environmental characteristics. Attached Figure Description

[0019] Figure 1 This is a flowchart of the power pole deformation monitoring and early warning method of the present invention; Figure 2 This is a diagram illustrating the architecture of the power pole deformation monitoring and early warning system of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] This invention provides, for example Figure 1 The method for monitoring and early warning of deformation of power poles, as shown, includes the following steps: S1. Install the data acquisition firmware on the tower to achieve periodic data acquisition; This step is based on the mechanical transmission laws of the foundation, bottom foundation, and tower body of power poles. Combined with actual working conditions, multi-dimensional data acquisition firmware is deployed at key nodes to monitor the freeze-thaw cycle of the foundation, the displacement and settlement of the bottom foundation, and the stress distribution and deformation of the tower body. It achieves periodic acquisition and synchronous transmission of multi-source data. In the periodic acquisition of multi-source data, a differentiated sampling period is adopted based on different stages of freeze-thaw. The sampling period is 5 hours in the early stage of freeze-thaw; 2 hours in the later stage of freeze-thaw; and 1 hour in the thawing stage. At the same time, the sampling period is dynamically adjusted according to the subsequent risk warning level. For each increase in risk level, the current sampling period is shortened by 20%.

[0022] S2. Construct a pole deformation simulation analysis model. Based on the mechanical transmission law of the foundation, bottom foundation and tower body of the power pole, as well as the coupling law of freeze-thaw cycle and fatigue load in severe cold regions, construct a pole deformation simulation analysis model. Based on the real-time collected data, simulate and analyze the stress distribution and settlement displacement characteristics of the pole.

[0023] The tower deformation simulation analysis model is based on the static structural parameters of the tower, foundation, and ground. A coupled mechanical model is constructed using finite element simulation technology, with contact coupling between modules to ensure effective stress and deformation transfer. The ground module incorporates parameter correlations to simulate the dynamic changes in soil mechanical properties during freezing and thawing. Real-time monitoring data collected by S1 is dynamically loaded into the model in a time series to recreate the tower's stress environment under dynamic conditions. The model outputs a tower stress distribution cloud map, settlement displacement time history curve, and tower tilt trend data, yielding quantitative simulation analysis results, including simulated settlement. Simulated tilt angle Simulate maximum strain and stress concentration factor .

[0024] S3. Construct a prediction model to predict potential risks based on simulation analysis results, real-time data, and external environmental characteristics; The prediction model is based on the analysis results of the tower deformation simulation analysis model, and combines real-time data and external environmental characteristics to analyze the deformation trend of power towers within a preset period. The prediction model adopts a hybrid CNN and LSTM network to extract key features of three types of input data, including deformation trend features, structural strength features and environmental impact features. The deformation trend characteristics are based on simulated and real-time settlement and skew data. The temporal changes of settlement rate, cumulative skewness, and deformation acceleration are extracted based on the comparison results to quantify the deformation development trend. The settlement rate... Indicates the rate of change of settlement per unit time; cumulative deviation. Deformation acceleration is obtained by accumulating the total amount of skew within a preset period. It indicates the trend of deformation rate change, reflecting whether the current deformation is in an accelerating or decelerating state; at the same time, it combines the deviation data between simulation data and actual measurement data to obtain the calculated deviation characteristics. Then, the four features are fused together to form the final deformation trend feature vector;

[0025] The structural strength characteristics are quantified based on the structural redundancy characteristics, stress accumulation damage characteristics, stress concentration characteristics, and critical failure margin characteristics of the tower structure after normalization. Among them, the structural redundancy characteristics... The remaining load-bearing capacity of the structure is represented by subtracting the allowable strain of the material from the strain in the current actual simulation analysis; stress accumulation damage characteristics. This indicates cumulative damage caused by long-term stress; the stress concentration feature Indicates the risk level of stress concentration areas; critical failure margin characteristics This represents the safety margin from structural failure, and then the four features are fused to form a structural strength feature vector;

[0026] Environmental impact characteristics encompass freeze-thaw intensity, extreme weather duration, abrupt environmental changes, and climate synergy. A comprehensive analysis of the impact of environmental changes on tower deformation is conducted through quantitative calculations. Among these, freeze-thaw intensity characteristics... Indicates the intensity of the freeze-thaw cycle's effect on soil; characteristics of extreme weather persistence. Indicates the duration of extreme environments; characteristics of environmental abrupt changes. Indicates the magnitude of sudden changes in environmental parameters; climate synergy characteristics. The combined effect of temperature, wind speed, and precipitation is represented, and then the four features are fused to form a structural environment impact feature vector.

[0027] After the above calculations, three core feature vectors are output at each acquisition time, with dimensions of deformation trend feature, structural strength feature, and environmental impact feature, respectively. To capture long-term trends, feature vectors from the last m acquisition times are taken and concatenated to form a temporal feature matrix with dimensions of m x 12 (10 rows x 12 columns), covering all indicators of the three types of features. This temporal feature matrix is ​​directly input into the CNN and LSTM hybrid network of the prediction model for deep feature extraction and fusion to predict the deformation trend of the tower.

[0028] The prediction model performs feature extraction based on the deformation trend of power poles, the structural strength of power poles and the characteristics of the external environment. After normalized data processing, the data is deeply fused and then risk quantification calculation is performed. The prediction model is based on the deformation trend characteristics, structural strength characteristics and environmental impact characteristics of the tower. It adopts multi-factor weighted summation and coupling correction to comprehensively and quantitatively judge the potential risk level of the tower. The formula is as follows:

[0029] in This represents the total risk value, and The closer it is to 1, the higher the risk. , respectively representing the weights of the three, and ; Indicates the risk factor for deformation trends; Indicates structural strength risk factor; Indicates environmental factors that exacerbate risk. This represents the coupling correction coefficient for polyphonic characters, and It represents the intensity of the synergistic effect of deformation, structure, and environment, and is determined by fitting historical data; Ultimately, the tower deformation risk level was determined through quantitative calculation, reflecting the current degree of damage caused by tower deformation.

[0030] In the process of risk quantification calculation, the predictive model compares historical trends in environmental characteristics with current environmental characteristics to dynamically optimize the weights of various features in the risk quantification calculation, thereby achieving dynamic early warning. The predictive model integrates big data and embeds deep learning algorithms. It acquires historical environmental data based on big data, then predicts future environmental change trends based on current environmental data characteristics, thus adjusting the risk assessment based on the current freeze-thaw cycle and future environmental change characteristics. The risk levels of tower deformation warnings are redistributed at different stages to optimize the calculation of different characteristics at different stages, and finally obtain the quantitative analysis results that are closest to the current environmental characteristics.

[0031] S4. Output the risk warning level based on the prediction results. During this process, the risk warning level is determined by... Threshold division is performed based on the range of values, thereby determining the appropriate threshold. Different warning levels are set for the threshold ranges corresponding to the values.

[0032] Working Principle: This method is based on the mechanical transmission laws of the foundation, bottom foundation, and tower body of power poles. Combined with actual working conditions, multi-dimensional data acquisition devices are deployed at key nodes to monitor foundation freeze-thaw cycles, bottom foundation displacement and settlement, and tower stress distribution and deformation. It achieves periodic acquisition and synchronous transmission of multi-source data. Simultaneously, a pole deformation simulation analysis model is designed to analyze the stress distribution and settlement displacement of the pole based on real-time acquired dynamic data. Then, a prediction model using a hybrid CNN and LSTM network is used to analyze the pole deformation trend within a preset period, based on the simulation model results and combined with real-time data and external environmental characteristics. This provides data support for strengthening key nodes of critical poles, allowing for reinforcement based on the node locations described in the deformation trend during pole maintenance. Furthermore, the prediction model quantifies the deformation risk of the pole based on deformation trend characteristics, structural strength characteristics, and environmental impact characteristics, and then outputs a warning level based on the calculation results. Furthermore, during the periodic acquisition of multi-source data, this method adopts differentiated sampling periods based on different stages of freeze-thaw cycles: a sampling period of 5 hours in the early stage of freeze-thaw, 2 hours in the later stage of freeze-thaw, and 1 hour in the thawing stage. At the same time, the sampling period is dynamically adjusted according to the subsequent risk warning level. For each increase in risk level, the sampling period is shortened by 20% based on the current sampling period, thereby intelligently shortening the sampling period and reducing the possibility of instantaneous emergencies. Meanwhile, in the process of quantifying the deformation risk of towers, this method compares the historical change trends of environmental characteristics with the current environmental characteristics to dynamically optimize the weights of various features in the risk quantification calculation, thereby achieving dynamic early warning. The prediction model integrates big data and embeds deep learning algorithms to obtain historical environmental data based on big data, and then predicts future environmental change trends based on the characteristics of current environmental data. In this way, the weights are redistributed according to the current freeze-thaw stage and future environmental change characteristics, thereby optimizing the calculation of the early warning risk level of tower deformation for different features at different stages, and finally obtaining the quantitative analysis results that are closest to the current environmental characteristics.

[0033] Example 2, as Figure 2 As shown, this embodiment provides a power pole deformation monitoring and early warning system, including: The data acquisition module is used to collect data on the tower, its foundation, and the ground. The data processing module is used to clean the collected dynamic data to ensure its validity. The tower deformation simulation analysis model is used to simulate the deformation of towers based on the collected and processed data, thereby analyzing their offset settlement and stress distribution; Predictive models are used to predict the degree of deformation risk of towers; The early warning module outputs the risk level of tower deformation. The data storage module stores the collected data and historical analysis and prediction data, and provides an encapsulated storage environment for the tower deformation simulation analysis model and prediction model. The network module is used for data transmission and signal reception.

[0034] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for monitoring and early warning of deformation of power poles, characterized in that, Includes the following steps: S1. Install the data acquisition firmware on the tower to achieve periodic data acquisition; S2. Construct a tower deformation simulation analysis model and analyze stress distribution and settlement displacement based on real-time data; S3. Construct a prediction model to predict potential risks based on simulation analysis results, real-time data, and external environmental characteristics; The prediction model is based on the analysis results of the tower deformation simulation analysis model, and combines real-time data and external environmental characteristics to analyze the deformation trend of power towers within a preset period. The prediction model is based on the deformation trend of power poles, the structural strength of power poles and the characteristics of the external environment to perform feature extraction, and after normalized data processing, the data is deeply fused and then risk quantification calculation is performed. In the process of risk quantification calculation, the prediction model compares the historical trend of environmental characteristics with the current environmental characteristics to dynamically optimize the weights of various features in the risk quantification calculation and achieve dynamic early warning. S4. Output the risk warning level based on the prediction results.

2. The method for monitoring and early warning of deformation of power poles according to claim 1, characterized in that, In step S1, based on the mechanical transmission laws of the power pole's foundation, bottom foundation, and tower body, and combined with actual working conditions, multi-dimensional data acquisition firmware is deployed at key nodes to monitor the freeze-thaw cycle of the foundation, the displacement and settlement of the bottom foundation, and the stress distribution and deformation of the tower body, thereby achieving periodic acquisition and synchronous transmission of multi-source data.

3. The method for monitoring and early warning of deformation of power poles according to claim 2, characterized in that, During the periodic acquisition of the multi-source data, a differentiated sampling period is adopted based on different stages of freeze-thaw cycles. The sampling period is 5 hours in the early stage of freeze-thaw and 2 hours in the later stage of freeze-thaw. The sampling period during the melting phase is 1 hour; at the same time, the sampling period is dynamically adjusted according to the subsequent risk warning level. For each increase in the risk level, the current sampling period is shortened by 20%.

4. The method for monitoring and early warning of deformation of power poles according to claim 1, characterized in that, In step S2, based on the mechanical transmission laws of the foundation, bottom foundation and tower body of the power pole, as well as the coupling law of freeze-thaw cycle and fatigue load in frigid regions, a pole deformation simulation analysis model is constructed, and the stress distribution and settlement displacement characteristics of the pole are simulated and analyzed based on real-time collected data.

5. The method for monitoring and early warning of deformation of power poles according to claim 4, characterized in that, The tower deformation simulation analysis model is based on the static structural parameters of the tower, bottom foundation, and ground. It uses finite element simulation technology to construct a coupled mechanical model, and the modules adopt contact coupling design to ensure the effective transmission of stress and deformation. The ground module sets the parameter correlation of freeze-thaw mechanical properties with dynamic temperature changes to simulate the dynamic changes of soil mechanical properties during freezing and thawing. Then, the real-time monitoring data collected by S1 is dynamically loaded into the model according to the time series to restore the stress environment of the tower under dynamic working conditions. The model outputs tower stress distribution cloud map, settlement displacement time history curve, and tower body tilt trend data to obtain quantitative simulation analysis results, including simulated settlement, simulated tilt angle, simulated maximum strain, and stress concentration factor.

6. The method for monitoring and early warning of deformation of power poles according to claim 5, characterized in that, In step S3, the prediction model uses a hybrid CNN and LSTM network to extract key features of three types of input data, including deformation trend features, structural strength features, and environmental impact features. The deformation trend characteristics are based on simulated and real-time settlement and skew data. The temporal changes of settlement rate, cumulative skew amount and deformation acceleration are extracted according to the comparison results, thereby quantifying the development trend of deformation. The structural strength characteristics are quantified based on the structural redundancy characteristics, stress accumulation damage characteristics, stress concentration characteristics and critical failure margin characteristics of the tower structure after normalization. The environmental impact characteristics include freeze-thaw intensity characteristics, extreme weather persistence characteristics, environmental abruptness characteristics, and climate synergy characteristics. The impact of environmental changes on tower deformation is comprehensively analyzed through quantitative calculations. Finally, a predictive model is used for quantitative analysis to predict the deformation trend of the tower.

7. The method for monitoring and early warning of deformation of power poles according to claim 6, characterized in that, The prediction model is based on the deformation trend characteristics, structural strength characteristics and environmental impact characteristics of the tower. It adopts multi-factor weighted summation and coupling correction to comprehensively and quantitatively judge the potential risk level of the tower. Finally, the tower deformation risk level is obtained through quantitative calculation, which reflects the current degree of deformation hazard of the tower.

8. The method for monitoring and early warning of deformation of power poles according to claim 7, characterized in that, The prediction model integrates big data and embeds deep learning algorithms. It acquires historical environmental data based on big data, then predicts future environmental change trends based on current environmental data characteristics. It then redistributes feature weights according to the current freeze-thaw stage and future environmental change characteristics. This optimizes the calculation of early warning risk levels for tower deformation based on different features at different stages, ultimately obtaining a quantitative analysis result that most closely approximates the current environmental characteristics.

9. A method for monitoring and early warning of deformation of power poles according to claim 7, characterized in that, In step S4, the range of tower deformation risk values ​​is divided into thresholds, and different early warning levels are set according to the threshold intervals corresponding to the risk values.

10. A power pole deformation monitoring and early warning system, used to execute the power pole deformation monitoring and early warning method according to any one of claims 1 and 9, characterized in that, include: Data acquisition module; Data processing module; Tower deformation simulation analysis model; Predictive models; Early warning module; Data storage module; Network module.

Images