Sensor deployment methods, devices, electronic equipment, and storage media for tower structures

Abstract

This application relates to the field of sensor deployment technology for tower structures, and discloses a sensor deployment method, device, electronic equipment, and storage medium for tower structures. The method includes: performing uncertainty analysis in pre-set finite element analysis software to identify potential weak areas using a generated heat map; and optimizing the number and location of sensors using an optimization algorithm, thereby significantly reducing costs while ensuring high efficiency in the monitoring system. The beneficial effects of this invention are: significantly improved efficiency and accuracy in monitoring the health status of tower structures; compared with traditional settlement and tilt monitoring devices, it can not only obtain the bearing capacity and damage risk of each structural point of the tower in real time, but also accurately determine the sensor type under different environmental conditions, thereby achieving targeted deployment.

Description

Technical Field

[0001] This invention relates to the field of sensor deployment technology for pole structures, and more particularly to a sensor deployment method, apparatus, electronic device, and storage medium for pole structures. Background Technology

[0002] In modern power systems, the safety and stability of transmission lines are paramount. Transmission towers, as their primary supporting structures, are frequently threatened by geological disasters such as landslides, earthquakes, and storms. These disasters significantly impact the mechanical response of the towers, potentially leading to structural displacement, strain, and failure, posing a risk to power transmission. Therefore, in-depth research into the mechanical response of transmission towers under various geological disasters has become a crucial task in ensuring the safe and stable operation of power systems.

[0003] Currently, monitoring is mainly conducted through settlement and tilt deformation monitoring devices, but this monitoring method cannot clearly reflect the load-bearing capacity and damage risk of the tower structure. Summary of the Invention

[0004] Therefore, it is necessary to address the sensor deployment problem of existing pole and tower structures by proposing a sensor deployment method, device, electronic equipment, and storage medium for pole and tower structures.

[0005] A sensor deployment method for a pole structure, the method comprising: A three-dimensional model of the specified tower structure is obtained by modeling the specified tower structure, and the environmental parameters of the specified tower structure are acquired. Multiple preset structural points are determined in the three-dimensional model; The three-dimensional model and the environmental parameters are input into a preset finite element analysis software for analysis to obtain the analysis parameters of multiple preset structural points in the three-dimensional model; Based on the position of the preset structural points in the 3D model and the analysis parameters, determine the sensor type of each preset structural point; Uncertainty analysis is performed on the three-dimensional model using a preset finite element analysis software to obtain a heat map of each preset structural point; Based on the heat map and sensor type of each preset structural point, the number and location of sensors deployed in the three-dimensional model are optimized according to a preset optimization algorithm to obtain an optimized deployment scheme for the specified tower structure.

[0006] Further, the step of determining the sensor type of each preset structural point based on the position of the preset structural point in the 3D model and the analysis parameters includes: Obtain the three-dimensional position information of each of the preset structural points; The range of first sensor types corresponding to the preset structural points is determined based on the three-dimensional position information; Select the corresponding sensor type from the first sensor type range based on the analysis parameters.

[0007] Furthermore, the step of determining multiple preset structural points in the three-dimensional model includes: The three-dimensional model is input into a preset finite element analysis software to simulate the strain field distribution under various preset environments; High-sensitivity regions are identified based on the strain field distributions described above; Based on the area size of each of the high-sensitivity regions, a preset number of structural points corresponding to the area size is set.

[0008] Further, the step of performing uncertainty analysis on the three-dimensional model using preset finite element analysis software to obtain heat maps of each preset structural point includes: Uncertain variables are set in the preset finite element analysis software; the uncertain variables are load variables and structural variables. Monte Carlo simulations were performed on the uncertain variables to establish a probabilistic capability model of the three-dimensional model and a probabilistic demand model for geological hazards. A heatmap of the three-dimensional model is generated based on the probabilistic capability model and the probabilistic demand model. Based on the position of each preset structural point in the three-dimensional model, a heat map of each preset structural point is obtained.

[0009] Further, the step of optimizing the number and location of sensors in the 3D model based on the heat map and sensor type of each of the preset structural points, and obtaining the optimized deployment scheme for the specified tower structure according to a preset optimization algorithm, includes: The structure point type of each preset structure point is determined based on the heat map of each preset structure point; The preset structural point of type preset is recorded as the target structural point; Set a target sensor of the corresponding sensor type for each target structural point; By sequentially setting the on / off state of each target sensor using a preset optimization algorithm, various simulation scenarios are obtained; Obtain the objective function and calculate the function value for each simulation case; The simulation case with the largest selected function value is used as the optimized deployment scheme for the specified tower structure.

[0010] Furthermore, the preset optimization algorithm is either a simulated annealing algorithm or a genetic algorithm.

[0011] Further, the step of modeling the specified tower structure to obtain a three-dimensional model of the specified tower structure includes: Obtain the CAD model drawing of the specified tower and the material information of each structure; A preliminary model is obtained by performing a preliminary modeling based on the CAD model drawing of the specified tower. The material information of each structure is input into the initial model to obtain the three-dimensional model of the specified tower structure.

[0012] A sensor deployment device for a pole structure, the device comprising: The modeling module is used to model a specified tower structure, obtain a three-dimensional model of the specified tower structure, and acquire the environmental parameters of the specified tower structure. The first determining module is used to determine multiple preset structural points in the three-dimensional model; The input module is used to input the three-dimensional model and the environmental parameters into a preset finite element analysis software for analysis, and to obtain the analysis parameters of multiple preset structural points in the three-dimensional model. The second determining module is used to determine the sensor type of each preset structural point based on the position of the preset structural point in the three-dimensional model and the analysis parameters. The analysis module is used to perform uncertainty analysis on the three-dimensional model in a preset finite element analysis software to obtain the heat map of each preset structural point; The optimization module is used to optimize the number and location of sensors deployed in the three-dimensional model based on the heat map and sensor type of each preset structural point, according to a preset optimization algorithm, to obtain an optimized deployment scheme for the specified tower structure.

[0013] An electronic device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps: A three-dimensional model of the specified tower structure is obtained by modeling the specified tower structure, and the environmental parameters of the specified tower structure are acquired. Multiple preset structural points are determined in the three-dimensional model; The three-dimensional model and the environmental parameters are input into a preset finite element analysis software for analysis to obtain the analysis parameters of multiple preset structural points in the three-dimensional model; Based on the position of the preset structural points in the 3D model and the analysis parameters, determine the sensor type of each preset structural point; Uncertainty analysis is performed on the three-dimensional model using a preset finite element analysis software to obtain a heat map of each preset structural point; Based on the heat map and sensor type of each preset structural point, the number and location of sensors deployed in the three-dimensional model are optimized according to a preset optimization algorithm to obtain an optimized deployment scheme for the specified tower structure.

[0014] A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the following steps: A three-dimensional model of the specified tower structure is obtained by modeling the specified tower structure, and the environmental parameters of the specified tower structure are acquired. Multiple preset structural points are determined in the three-dimensional model; The three-dimensional model and the environmental parameters are input into a preset finite element analysis software for analysis to obtain the analysis parameters of multiple preset structural points in the three-dimensional model; Based on the position of the preset structural points in the 3D model and the analysis parameters, determine the sensor type of each preset structural point; Uncertainty analysis is performed on the three-dimensional model using a preset finite element analysis software to obtain a heat map of each preset structural point; Based on the heat map and sensor type of each preset structural point, the number and location of sensors deployed in the three-dimensional model are optimized according to a preset optimization algorithm to obtain an optimized deployment scheme for the specified tower structure.

[0015] The beneficial effects of this invention are as follows: By performing uncertainty analysis in pre-set finite element analysis software, the generated heat map identifies potential weak areas. Combined with optimization algorithms, the number and location of sensors are optimized, enabling the monitoring system to significantly reduce costs while maintaining high efficiency. This significantly improves the efficiency and accuracy of monitoring the health status of tower structures. Compared with traditional settlement and tilt monitoring devices, it can not only acquire the bearing capacity and damage risk of each structural point of the tower in real time, but also accurately determine the sensor types under different environmental conditions, thereby achieving targeted deployment. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] in: Figure 1 This is an application environment diagram of a sensor deployment method for a pole structure in one embodiment; Figure 2A flowchart of a sensor deployment method for a pole structure in one embodiment; Figure 3 This is a structural block diagram of a sensor deployment device for a pole structure in one embodiment; Figure 4 This is a structural block diagram of an electronic device in one embodiment. Detailed Implementation

[0018] 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.

[0019] Figure 1 This is a diagram illustrating the sensor deployment environment of a tower structure in one embodiment. (Refer to...) Figure 1 This sensor deployment method for pole structures is applied to a sensor deployment system for pole structures. The sensor deployment system for pole structures includes a terminal 110 and a server 120. The terminal 110 and server 120 are connected via a network. The terminal 110 can be a desktop terminal or a mobile terminal, and the mobile terminal can be at least one of a mobile phone, tablet, or laptop. The server 120 can be a standalone server or a server cluster consisting of multiple servers. The terminal 110 is used to acquire environmental parameters, and the server 120 is used to analyze and optimize the deployment scheme for a specified pole structure.

[0020] like Figure 2 As shown, in one embodiment, a sensor deployment method for a pole structure is provided. This method can be applied to both terminals and servers; this embodiment uses terminal application as an example. The sensor deployment method for the pole structure specifically includes the following steps: S1: Model the specified tower structure to obtain a three-dimensional model of the specified tower structure, and obtain the environmental parameters of the specified tower structure; S2: Determine multiple preset structural points in the three-dimensional model; S3: Input the three-dimensional model and the environmental parameters into a preset finite element analysis software for analysis to obtain the analysis parameters of multiple preset structural points in the three-dimensional model; S4: Determine the sensor type of each preset structural point based on the position of the preset structural point in the three-dimensional model and the analysis parameters; S5: Perform uncertainty analysis on the three-dimensional model using preset finite element analysis software to obtain the heat map of each preset structural point; S6: Based on the heat map and sensor type of each preset structural point, optimize the number and location of sensor deployments in the three-dimensional model according to the preset optimization algorithm to obtain the optimized deployment scheme of the specified tower structure.

[0021] As described in step S1 above, the specified tower structure is modeled. Detailed geometric modeling of the specified tower structure is required, typically using CAD or engineering design software. The aim is to generate a three-dimensional model of the tower, ensuring that the model accurately reflects the structure's scale, shape, and material properties. During modeling, the tower's physical parameters must be considered, including the cross-sectional shape of the members, material properties (such as yield strength and modulus of elasticity), connection methods, and the tower's specific construction (such as crossarms, braces, and foundation structure). Simultaneously, parameters related to the tower's adjacent environment need to be acquired, such as soil properties, climate conditions, and potential geological hazards. These environmental parameters will play a crucial role in subsequent analysis because they affect the tower's mechanical performance and stress state; therefore, ensuring the accuracy and comprehensiveness of the model is fundamental to subsequent analysis. Environmental parameters can be obtained by deploying environmental monitoring sensors around the tower, such as temperature sensors, humidity sensors, anemometers, and barometers, to monitor relevant environmental data in real time. Alternatively, data can be queried from meteorological databases, including soil cohesion and wind speed probability distribution.

[0022] As described in step S2 above, multiple preset structural points are determined in the 3D model. The purpose of this stage is to select several key preset structural points in the 3D model, which will serve as the basis for the subsequent placement of monitoring sensors. These structural points include the main load-bearing parts of the tower, such as the tower base, tower feet, crossarm intersections, and important areas such as connecting welds or bolted connections. The selection of these points is not only influenced by the tower structural design but also based on the previous analysis of the tower's mechanical response, especially those areas where stress concentration or deformation may occur. By rationally selecting these structural points, the comprehensiveness and effectiveness of monitoring can be improved, ensuring that the deployed sensors are concentrated in high-risk areas. This provides the necessary basic information for subsequent sensor type selection and layout, maximizing monitoring effectiveness and thus ensuring tower safety.

[0023] As described in step S3 above, the 3D model and environmental parameters are input into the preset finite element analysis software. The established 3D model and collected environmental parameters are input into the preset finite element analysis software (such as ANSYS or Abaqus) for mechanical performance evaluation and analysis. The key at this stage is to apply loads to the entire model to simulate the stress conditions of the tower under different working conditions, including static loads (such as self-weight and wind loads) and dynamic loads (such as earthquakes and snow). Furthermore, the software discretizes the model and uses numerical methods (such as the finite element method) to solve the problem, thereby calculating key analysis parameters such as stress, strain, and displacement at each preset structural point. These results provide important information about the tower's performance under actual working conditions, laying an empirical foundation for subsequent steps in sensor selection and monitoring scheme design.

[0024] As described in step S4 above, the sensor type for the preset structural points is determined. Once the analysis parameters are obtained, the next step is to determine the most suitable sensor type based on the location of the preset structural points in the 3D model and their analysis parameters. Different structural points may bear different loads and have varying strains and stresses. Therefore, multiple factors should be considered when selecting sensors, including the strain amplitude, response speed, durability, and anti-interference capability at that point. For example, for the tower base area under high pressure, strain gauges or fiber optic sensors with high load-bearing capacity can be selected, while for crossarms or rods with greater degrees of freedom, MEMS sensors with fast dynamic response can be used. Ensuring accurate sensor matching can improve the effectiveness and reliability of monitoring, thereby laying the foundation for subsequent data processing and analysis. Each preset structural point has a specific 3D coordinate position in the 3D model. These structural points may exhibit different strain behaviors due to different loads, structural characteristics, or stress modes. For example, the tower base bears the main compressive stress, while the crossarm may be subjected to greater bending and shear stress. Therefore, the sensor type for each preset structural point is mainly based on the location of the preset structural point, and the selected sensor type should also vary depending on the structural point. For components subjected to axial and bending forces, high-precision strain sensors are preferred; while for structural points requiring monitoring of horizontal displacement changes, displacement sensors can be used. Although environmental parameters such as temperature, humidity, and wind speed have a relatively small impact, a certain degree of sensitivity should still be maintained during practical operation. For example, temperature changes can affect the accuracy of sensors, especially when the selected sensor exhibits significant performance deviations in different temperature regions. In this context, it may be necessary to select a sensor with temperature compensation capabilities to ensure measurement accuracy.

[0025] As described in step S5 above, uncertainty analysis is performed on the three-dimensional model. In this step, a preset finite element analysis software is used to perform uncertainty analysis on the three-dimensional model to evaluate the influence of different factors on the tower structure response. The purpose of this analysis is to reveal potential risk points, especially the fluctuations in structural response caused by the randomness of factors such as material properties, load variations, and environmental conditions. In this process, Monte Carlo simulation or other random variable methods are used to generate numerous possible combinations of loads and material strengths, and the model response under each combination is calculated. This will generate multiple response data, and a heat map is generated through statistical analysis to help identify which structural areas are at higher risk, thereby determining the weak points of concern. The analysis results provide important guidance for subsequent optimization of sensor layout.

[0026] Furthermore, after step S5, i.e., after obtaining the heat maps of each of the preset structural points, the sensor type corresponding to each preset structural point can be adjusted according to the heat map. Specifically, the sensor selection can be adjusted based on the strain level of different structural points in the heat map. If the strain value of a structural point is significantly higher than expected, a sensor with a higher range or higher sensitivity can be added to ensure accurate measurement of the peak strain. In high-strain regions (regions greater than the preset strain force are denoted as high-strain regions), strain sensors with high accuracy and fast response speed (such as fiber optic strain sensors) should be selected. For regions with smaller loads or less variation, sensors with standard ranges can be selected to reduce costs. In some embodiments, the number of sensors can be increased at structural points where the heat map shows strain concentration or high-risk areas, i.e., the number of preset structural points can be increased to provide finer-grained monitoring data, thereby improving the sensitivity of anomaly detection.

[0027] As described in step S6 above, an optimized deployment scheme is based on the heat map and sensor types. The final step is to use a preset optimization algorithm to optimize the number and location of sensors based on the heat map and sensor types obtained in the previous steps. This process combines the goals of improving monitoring effectiveness and reducing costs, automatically finding the optimal sensor configuration scheme through algorithm iteration. Optimization considerations include prioritizing the deployment of more sensors in high-risk areas and reducing redundant deployments in low-risk areas. This not only ensures effective monitoring of important structural points but also reduces the number of sensors, thereby reducing the overall system cost. In practical applications, this forms a comprehensive tower health monitoring scheme, providing strong data support for preventive maintenance and safe operation. During the optimization process, the sensor type can be adjusted according to the heat map to adapt to changes in risk. Specifically, if the heat map shows that certain structural points (such as the tower body far from critical load-bearing parts) have small and stable strain, high-cost sensors can be replaced with low-cost standard sensors to reduce the overall system cost. For areas with lower monitoring requirements, the number of sensors installed can be appropriately reduced to reduce system complexity while maintaining necessary monitoring coverage. For dynamic pressures that change frequently (such as wind loads or other environmental influences), MEMS sensors with fast response times can be selected to ensure reliable real-time data acquisition.

[0028] In one embodiment, step S4, which determines the sensor type of each preset structure point based on the position of the preset structure point in the 3D model and analysis parameters, includes: S401: Obtain the three-dimensional position information of each of the preset structural points; S402: Determine the range of first sensor types corresponding to the preset structural points based on the three-dimensional position information; S403: Select the corresponding sensor type from the first sensor type range according to the analysis parameters.

[0029] As described in step S401 above, the three-dimensional position information of each of the preset structural points is obtained. In this step, detailed three-dimensional position information of each preset structural point determined in the three-dimensional model is first obtained. This position information typically includes the coordinate values ​​(X, Y, Z) of each structural point, as well as a description of its relative position in the model. This process often relies on the output of modeling software; by selecting preset structural points in the modeling tool, their spatial coordinates can be directly extracted and recorded. Obtaining this position information is fundamental to subsequent steps, as the spatial position of different structural points directly affects the selection and arrangement of sensors. For example, different parts such as the tower base, crossarms, and connecting nodes have different stress conditions, strain characteristics, and environmental influences. Therefore, accurate three-dimensional coordinates provide the necessary data background, making subsequent sensor selection more targeted and reasonable. Furthermore, recording this position information also provides a basis for later monitoring data analysis and fault location, facilitating subsequent data processing and analysis.

[0030] As described in step S402 above, the range of first sensor types corresponding to the preset structural points is determined based on the three-dimensional position information. After obtaining the three-dimensional position information of each preset structural point, the next step is to determine the range of first sensor types corresponding to each structural point based on this information. When determining the range of sensor types, the mechanical role and working conditions of the structural points are mainly considered. The mechanical effects borne by the structural points of the tower at different locations are different. For example, the tower base often bears large compressive stress, while the crossarm needs to monitor bending stress, cross-sectional torsion, etc. Different types of sensors are suitable for each type of structural point, such as pressure sensors, strain sensors, displacement sensors, etc. Therefore, a certain range of sensor types is set according to the extracted three-dimensional position information. For example, high-precision strain gauges or laser displacement sensors can be considered at the tower foot position, while MEMS sensors with faster dynamic response can be considered at the crossarm.

[0031] As described in step S403 above, a corresponding sensor type is selected from the first sensor type range based on the analysis parameters. Once the first sensor type range for each preset structural point is determined, the next step is to select the most suitable specific sensor type from this range based on the analysis parameters. This process mainly relies on the previously mentioned analysis parameters, which generally include strain, pressure, displacement, and load. By evaluating these parameters, the performance of the structural point under stress can be better understood. Specifically, different sensors have specific characteristics in terms of range, accuracy, sensitivity, and response speed, so they need to be matched in conjunction with the analysis parameters. For example, if the analysis results for a preset structural point show that the strain change under stress is expected to be within ±1000με, then a fiber optic strain sensor with a suitable strain range and sufficient sensitivity can be selected from the first sensor type range. This step ensures that the selected sensor can work effectively in actual use to provide accurate on-site monitoring data, thereby providing a reliable basis for subsequent data analysis and structural health assessment. This process emphasizes the scientific and systematic nature of sensor selection to meet the diverse needs of practical applications.

[0032] In one embodiment, step S2, which involves determining multiple preset structural points in the three-dimensional model, includes: S201: Input the three-dimensional model into the preset finite element analysis software to simulate the strain field distribution under various preset environments; S202: Identify high-sensitivity regions based on the strain field distributions described above; S203: Based on the area size of each of the high-sensitivity regions, set a preset number of structural points corresponding to the area size.

[0033] As described in step S201 above, the three-dimensional model is input into a preset finite element analysis software to simulate the strain field distribution under various preset environments. The previously established three-dimensional model is input into a preset finite element analysis software (such as ANSYS or Abaqus) for numerical simulation analysis. This process simulates the strain field distribution of the tower structure under various environmental conditions (such as earthquake wind loads, snow and ice pressure, etc.). Corresponding loads and boundary conditions need to be set for each environmental condition to ensure accurate reflection of the tower's mechanical performance under specific working conditions. Through the software's solver, based on the discretization and numerical calculation of the model, the software generates strain response data for each preset point under different working conditions, forming a numerical representation of the strain field. This result is not only the basic data for subsequent identification of high-sensitivity areas but also a key basis for subsequent sensor selection and configuration. By simulating the strain field distribution, it is possible to understand which parts of the tower may bear greater stress under various adverse conditions, and to identify the key areas that need to be monitored.

[0034] As described in step S202 above, high-sensitivity regions are identified based on the strain field distributions. After successfully simulating the strain field distribution, the next task is to analyze the generated data and identify high-sensitivity regions. High-sensitivity regions typically refer to locations where the strain response values ​​of preset structural points are large and the changes are significant under specific load conditions. These regions often correspond to locations of stress concentration or potential failure risks, such as critical node connections of towers, crossarm intersections, or joint locations. To effectively identify these high-sensitivity regions, a certain strain threshold (e.g., ≥500με) can be set. If the strain value of a node exceeds this threshold, it is marked as a high-sensitivity region. Through such data filtering, high-risk regions can be visualized intuitively in the model, providing clear targets for subsequent sensor deployment. The process of identifying high-sensitivity regions shifts monitoring work from global coverage to more precise and scientific focus, thereby improving the effectiveness and response speed of monitoring and ensuring that potential structural problems can be detected and addressed in a timely manner during actual operation.

[0035] As described in step S203 above, a number of preset structural points corresponding to the area size of each of the high-sensitivity regions are set. After identifying the high-sensitivity regions, the number of preset structural points corresponding to these regions is set according to their area size. The identified high-sensitivity regions are assigned to several monitoring points to ensure that these key areas are covered during monitoring. Specifically, larger high-sensitivity regions can have multiple preset structural points set for more detailed monitoring of strain changes within the region; while smaller high-sensitivity regions can have only one or a few monitoring points set. This approach ensures that even in areas where strain is concentrated, the specific conditions of each point can be recorded in real time by multiple sensors, thereby accurately assessing the overall structural state. Such a monitoring point setup allows the monitoring system to achieve optimal results with limited resources, maximizing the integration and practicality of monitoring. Furthermore, the preset structural points set in this way facilitate subsequent data processing and analysis, allowing data from multiple monitoring points to be combined for a more comprehensive structural health monitoring and assessment.

[0036] In one embodiment, step S5, which involves performing uncertainty analysis on the three-dimensional model using preset finite element analysis software to obtain heat maps of each preset structural point, includes: S501: Set uncertain variables in the preset finite element analysis software; the uncertain variables are load variables and structural variables; S502: Perform Monte Carlo simulation on the uncertain variables to establish the probabilistic capability model of the three-dimensional model and the probabilistic demand model of geological hazards; S503: Generate a heat map of the three-dimensional model based on the probabilistic capability model and the probabilistic demand model; S504: Based on the position of each preset structural point in the three-dimensional model, obtain the heat map of each preset structural point.

[0037] As described in step S501 above, uncertainties are set in the preset finite element analysis software. In this step, uncertainties related to the model need to be set in the finite element analysis software to reflect the changes and uncertainties that may occur in real engineering. These uncertainties typically include load variables and structural variables. Load variables may be caused by environmental factors, such as wind speed, ice thickness, and seismic wave intensity, which affect the stress state of the tower under different working conditions. Structural variables are related to the characteristics of the tower components themselves, such as the dispersion of material strength, the quality fluctuation of joints and welds, and the geometric dimensions of the tower. The purpose of this step is to introduce the randomness present in reality into the model, thereby conducting more realistic simulation calculations. By reasonably selecting and setting these variables, the necessary data foundation can be provided for subsequent probabilistic analysis, ensuring the reliability and accuracy of the model. This process also lays the foundation for subsequent Monte Carlo simulations, enabling the analysis results to more effectively describe the true response sensitivity of the tower under different environments and conditions.

[0038] As described in step S502 above, Monte Carlo simulation is performed on the uncertain variables to establish the probabilistic capability model of the three-dimensional model and the probabilistic demand model for geological hazards. After setting the uncertain variables, Monte Carlo simulation will be performed on these variables. Monte Carlo simulation is a numerical calculation method based on random sampling, used to handle complex problems in systems containing many uncertain variables. Specifically, 1000 sets of random variables can be generated through Latin hypercube sampling to simulate the probability distribution of load and structural variables. In this process, a large number of new samples are generated to represent various possible loads and structural conditions, simulating the model's response. By performing finite element analysis on these samples, the stress, strain, and other key performance indicators of the structure under different conditions can be understood, thereby establishing a probabilistic capability model of the tower structure, which characterizes the reliability of the system under different random conditions. At the same time, a probabilistic demand model for geological hazards can also be constructed, and by analyzing the hazard load conditions, the performance of the structure under specific hazard conditions can be depicted.

[0039] As described in step S503 above, a heat map of the three-dimensional model is generated based on the probabilistic capability model and the probabilistic demand model. After obtaining the probabilistic capability model and the probabilistic demand model for geological hazards through Monte Carlo simulation, these models are used to generate a heat map of the three-dimensional model. A heat map is a visualization tool used to show the distribution of strain, stress, or failure probability at different locations. In this stage, statistical processing is performed on key response indicators (such as strain and load) obtained from previous simulations, specifically calculating the average and distribution of strain values ​​or failure probabilities at different locations in multiple simulations. Furthermore, the corresponding standard deviations can be analyzed to further quantify the risk level of different parts. Through such analysis, high-risk areas can be clearly visually compared with low-risk areas, enabling engineers to intuitively identify structural parts that require priority monitoring. The generated heat map not only helps decision-makers set effective monitoring plans but also provides an important basis for the subsequent deployment and optimization of sensor schemes, ensuring an optimal balance between structural safety and cost-effectiveness.

[0040] As described in step S504 above, a heat map of each preset structural point is obtained based on its position in the 3D model. After generating the heat map, the final step is to extract the corresponding heat map data based on the specific location of the preset structural points in the 3D model. The heat map is then combined with the previously selected preset structural points to perform spatial data mapping, facilitating the analysis of the thermal values ​​corresponding to each structural point. Typically, this involves identifying the specific stress and strain values ​​of each preset structural point from the heat map, and based on this data, determining the expected performance and monitoring priority of each sensor during actual deployment. This not only identifies which preset point is more necessary to monitor (e.g., high-risk areas) but also assesses the overall safety and stability of the physical structure. Through this process, engineers can clearly understand the thermal state of each structural point, providing a basis for decision-making regarding subsequent sensor configuration and monitoring scheme optimization, ensuring that the implementation of the monitoring system can effectively address potential safety hazards and guarantee the long-term stable operation of the transmission towers.

[0041] In one embodiment, step S6, which optimizes the number and location of sensors in the 3D model based on the heat map and sensor type of each preset structural point according to a preset optimization algorithm to obtain an optimized deployment scheme for the specified tower structure, includes: S601: Determine the structure point type of each preset structure point based on the heat map of each preset structure point; S602: Record the preset structural point of type preset as the target structural point; S603: Set the target sensor of the corresponding sensor type for each target structure point; S604: By using a preset optimization algorithm, the on / off states of each target sensor are sequentially set to obtain various simulation scenarios; S605: Obtain the objective function and calculate the function value for each simulation case; S606: Select the simulation case with the largest filter function value as the optimized deployment scheme for the specified tower structure.

[0042] As described in step S601 above, the structural point type of each preset structural point is determined based on the heat map of each preset structural point. According to the data and information obtained from the heat map, the structural type of each preset structural point is determined. These structural points may include different components of the tower, such as the tower base, main pole, crossarm, etc. Each part experiences significantly different mechanical behavior within the tower, and therefore is classified into different structural point types. In this process, based on the strain values ​​of the heat map, structural points are classified into high-risk, medium-risk, and low-risk types. The strain or stress values ​​shown in the heat map are evaluated to classify structural points into different types such as high-risk, low-risk, critical monitoring, and ordinary monitoring. For example, structural points with higher strain values ​​may be marked as "high-risk structural points" requiring focused monitoring, while those with relatively lower strain values ​​may be classified as "ordinary monitoring points." These classifications help optimize sensor deployment by employing appropriate monitoring strategies for different types of structural points, thereby improving the overall monitoring effect and efficiency of the system. Determining the structural point type is the basis for developing deployment plans in subsequent steps, ensuring that the selection and location distribution of sensors meet monitoring requirements and prevent potential failure risks.

[0043] As described in step S602 above, the preset structural points of a preset type are recorded as target structural points. Structural points that conform to a specific predefined type are designated as "target structural points." Target structural points typically refer to critical locations with higher risks or more complex structural features, playing a crucial role in the overall stability and safety of the tower. By selecting these target structural points from the identified structural points, engineers can ensure that monitoring support is prioritized for these points during subsequent sensor deployment. Specifically, target structural points may have different monitoring requirements due to their location in strain concentration areas or their exposure to large alternating loads. In this step, specific recording or labeling methods are also defined so that subsequent analysis and optimization algorithms can accurately identify and reference these target structural points. Furthermore, the definition of target structural points lays the foundation for subsequent sensor selection and configuration, ensuring that the monitoring scheme can focus on covering these risk areas and improve monitoring effectiveness.

[0044] As described in step S603 above, target sensors of corresponding sensor types are set for each target structural point. A corresponding target sensor is assigned to each identified target structural point. This process involves selecting the most suitable sensor type based on the characteristics and monitoring requirements of each target structural point. The selection of sensors depends not only on the type and function of the structural point but also on the specific load it bears. For example, for a tower base subjected to significant compressive stress, a high-precision strain gauge or fiber optic strain sensor can be selected; while for a crossbar with rapid dynamic changes, a MEMS sensor with a fast frequency response can be considered. Selecting appropriate target sensors will ensure that the monitoring system can efficiently and accurately capture changes in the structural state and provide timely early warning information. Furthermore, considering that the arrangement and connection method of the sensors are also crucial, it is essential to ensure that the selected sensors can conveniently and reliably acquire data in actual operation. By clearly defining the sensor type for each target structural point, it is ensured that the subsequent implementation plan can be smoothly executed and its design objectives achieved.

[0045] As described in step S604 above, the on / off states of each target sensor are sequentially set using a preset optimization algorithm to obtain multiple simulation scenarios. The preset optimization algorithm is used to sequentially set the on / off states of each target sensor to generate various simulation scenarios. This process involves constructing decision variables so that each sensor can be set to "on" or "off". By combining each possible sensor configuration, a large number of simulation scenarios are generated, thereby evaluating the impact of different sensor layouts on the overall monitoring effect. The optimization algorithm can be a genetic algorithm, particle swarm optimization algorithm, or other algorithms suitable for large-scale combinatorial optimization. Its main purpose is to reduce the number of sensors used while ensuring the monitoring of key risk points, thereby reducing the overall cost. All possible simulation scenarios generated will serve as the basis for subsequent algorithm analysis. This step, through an efficient search algorithm, not only provides effective monitoring layout options but also ensures the flexibility and adaptability of the monitoring scheme, providing valuable data support for subsequent functional evaluation. In one embodiment, multiple configuration schemes can be generated by iteratively changing the state of one sensor at a time.

[0046] As described in step S605 above, the objective function is obtained and the function value for each simulation scenario is calculated. By executing the various simulation scenarios generated in the previous step, the objective function value for each configuration is calculated. The objective function is typically a quantitative indicator used to evaluate the effectiveness of different sensor layouts. These indicators can be the coverage of the monitoring range, the cost of the configuration, the sensitivity of the monitoring, the response time, or even analytical data directly related to structural safety. For example, the objective function can be set as the sum of strain monitoring in the key areas covered by the sensors, or the total cost of sensors required for each configuration. The calculation of the objective function will provide a basis for subsequent simulation scenario selection, helping to judge the merits of each scheme and determine the optimal strategy. This step emphasizes the importance of in-depth data analysis, enabling decision-makers to compare quantitative values ​​and intuitively identify the best sensor deployment scheme and the most cost-effective option based on the combined evaluation results. Obtaining the objective function and calculating its value is a crucial step in the optimization process, ensuring that subsequent decision-making is based on clear and sufficient information.

[0047] As described in step S606 above, the simulation case with the largest objective function value is selected as the optimal deployment scheme for the specified tower structure. After filtering all simulation cases obtained through the aforementioned calculations, the simulation case with the largest objective function value is identified and determined as the final optimal deployment scheme. By comparing the function values, the sensor layout configuration that achieves the best balance between response performance and cost-effectiveness can be intuitively identified. The largest function value indicates that the simulation case has the highest effectiveness or lowest cost while meeting monitoring performance requirements, ensuring the project's economic viability. At this point, it is necessary to comprehensively consider the complexity involving environmental factors and structural strain to ensure that the final scheme can accurately monitor key areas without wasting resources or increasing system complexity due to over-deployment.

[0048] In one embodiment, the preset optimization algorithm is a simulated annealing algorithm or a genetic algorithm.

[0049] In one embodiment, step S1, which involves modeling a specified tower structure to obtain a three-dimensional model of the specified tower structure, includes: S101: Obtain the CAD model drawing of the specified tower and the material information of each structure; S102: Based on the CAD model drawing of the specified tower, perform preliminary modeling to obtain the initial model; S103: Input the material information of each structure into the initial model to obtain the three-dimensional model of the specified tower structure.

[0050] As described in step S101 above, the CAD model drawings of the specified tower and the material information of each structure are obtained. The CAD drawings provide crucial information such as the tower's geometry, dimensions, and specific design parameters to ensure the accuracy of subsequent modeling. CAD drawings typically include multiple perspectives, including top views, side views, and sectional views. The material information for each structural component should be listed in detail, including material type (e.g., steel, concrete), and the material's physical and mechanical properties (e.g., elastic modulus, yield strength, density, coefficient of thermal expansion). These properties directly affect the tower's mechanical performance in subsequent finite element analysis.

[0051] As described in step S102 above, a preliminary model is created based on the CAD model drawing of the specified tower to obtain an initial model. The obtained CAD drawings and structural information are used for preliminary modeling to generate the initial model of the tower. This initial model is a geometric model based on the CAD drawings and does not include material properties. This process is typically performed using CAD software (such as AutoCAD, SolidWorks, or Revit). Modelers need to construct the three-dimensional geometry of each structural component according to the geometric information shown in the drawings. Special attention must be paid to the connection relationships between components, such as welding and bolt connections, to ensure the accuracy of the model. Furthermore, modeling must adhere to certain design procedures and standards, such as the "Code for Design of Steel Structures," to ensure that the chamfers, slopes, and other design requirements of each component are met. The generation of the preliminary model requires verification through multiple steps to ensure that it reflects the actual design intent. At this stage, the preliminary model is only a rough representation; subsequent additions and refinements of material properties will achieve more accurate structural simulation. The quality of this step directly affects the effectiveness of subsequent finite element analysis, therefore, modelers must treat it with utmost care.

[0052] As described in step S103 above, the material information of each structure is input into the initial model to obtain the three-dimensional model of the specified tower structure. The material information of each component is input into the preliminary model to generate a complete three-dimensional model. Based on the collected material data, appropriate material properties are specified for each structural component. For example, parameters such as elastic modulus, yield strength, Poisson's ratio, and density need to be defined for steel; for concrete, the corresponding compressive strength and other relevant physical properties need to be input. All geometric information and material properties are integrated to generate the final three-dimensional model.

[0053] Reference Figure 3 The present invention also provides a sensor deployment device for a pole structure, the device comprising: Modeling module 902 is used to model a specified tower structure, obtain a three-dimensional model of the specified tower structure, and acquire environmental parameters of the specified tower structure. The first determining module 904 is used to determine multiple preset structural points in the three-dimensional model; Input module 906 is used to input the three-dimensional model and the environmental parameters into a preset finite element analysis software for analysis, and obtain the analysis parameters of multiple preset structural points in the three-dimensional model; The second determining module 908 is used to determine the sensor type of each preset structure point based on the position of the preset structure point in the three-dimensional model and the analysis parameters. Analysis module 910 is used to perform uncertainty analysis on the three-dimensional model in a preset finite element analysis software to obtain a heat map of each preset structural point; The optimization module 912 is used to optimize the number and location of sensors deployed in the three-dimensional model based on the heat map and sensor type of each of the preset structural points and according to a preset optimization algorithm, so as to obtain an optimized deployment scheme for the specified tower structure.

[0054] In one embodiment, the second determining module 908 includes: The three-dimensional position information acquisition submodule is used to acquire the three-dimensional position information of each of the preset structural points; The first sensor type range determination submodule is used to determine the first sensor type range corresponding to the preset structural point based on the three-dimensional position information. The sensor type selection submodule selects the corresponding sensor type from the first sensor type range based on the analysis parameters.

[0055] In one embodiment, the first determining module 904 includes: The strain field distribution simulation submodule is used to input the three-dimensional model into a preset finite element analysis software to simulate the strain field distribution under various preset environments; A high-sensitivity region identification submodule is used to identify high-sensitivity regions based on the distribution of each strain field. The preset structure point setting submodule is used to set a number of preset structure points corresponding to the area size of each of the high-sensitivity regions.

[0056] In one embodiment, the analysis module 910 includes: The uncertain variable setting submodule is used to set uncertain variables in the preset finite element analysis software; the uncertain variables are load variables and structural variables; The probability demand model establishment submodule is used to perform Monte Carlo simulation on the uncertain variables and establish the probability capability model of the three-dimensional model and the probability demand model of geological hazards. A heatmap generation submodule is used to generate a heatmap of the three-dimensional model based on the probability capability model and the probability demand model. The heat map acquisition submodule is used to obtain the heat map of each preset structural point based on the position of each preset structural point in the three-dimensional model.

[0057] In one embodiment, the optimization module 912 includes: The structure point type determination submodule is used to determine the structure point type of each preset structure point based on the heat map of each preset structure point. The target structure point marking submodule is used to mark the preset structure points of a preset type as target structure points; The target sensor setting submodule is used to set the target sensor of the corresponding sensor type for each target structure point; The simulation scenario acquisition submodule is used to sequentially set the on / off state of each of the target sensors through a preset optimization algorithm to obtain multiple simulation scenarios; The function value acquisition submodule retrieves the target function and calculates the function value for each simulation case; The filtering submodule is used to filter the simulation case with the largest function value as the optimized deployment scheme for the specified tower structure.

[0058] In one embodiment, the preset optimization algorithm is a simulated annealing algorithm or a genetic algorithm.

[0059] In one embodiment, the modeling module 902 includes: The material information acquisition submodule is used to acquire the CAD model drawing structure of the specified tower and the material information of each structure; The initial model acquisition submodule is used to perform preliminary modeling based on the CAD model drawing structure of the specified tower to obtain the initial model; The 3D model acquisition submodule is used to input the material information of each structure into the initial model to obtain the 3D model of the specified tower structure.

[0060] Figure 4 An internal structural diagram of an electronic device in one embodiment is shown. This electronic device can specifically be a terminal or a server, and more specifically, a computer device. Figure 4As shown, the electronic device includes a processor, a memory, and a network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program enables the processor to implement a sensor deployment method for the tower structure. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to implement the sensor deployment method for the tower structure. Those skilled in the art will understand that... Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0061] In one embodiment, an electronic device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps: A three-dimensional model of the specified tower structure is obtained by modeling the specified tower structure, and the environmental parameters of the specified tower structure are acquired. Multiple preset structural points are determined in the three-dimensional model; The three-dimensional model and the environmental parameters are input into a preset finite element analysis software for analysis to obtain the analysis parameters of multiple preset structural points in the three-dimensional model; Based on the position of the preset structural points in the 3D model and the analysis parameters, determine the sensor type of each preset structural point; Uncertainty analysis is performed on the three-dimensional model using a preset finite element analysis software to obtain a heat map of each preset structural point; Based on the heat map and sensor type of each preset structural point, the number and location of sensors deployed in the three-dimensional model are optimized according to a preset optimization algorithm to obtain an optimized deployment scheme for the specified tower structure.

[0062] By performing uncertainty analysis in pre-set finite element analysis software, the generated heat map identifies potential weak areas. Combined with optimization algorithms, the number and location of sensors are optimized, enabling the monitoring system to significantly reduce costs while maintaining high efficiency. This significantly improves the efficiency and accuracy of monitoring the health status of tower structures. Compared to traditional settlement and tilt monitoring devices, it can not only acquire the load-bearing capacity and damage risk of each structural point of the tower in real time, but also accurately determine the type of sensor required under different environmental conditions, thus enabling targeted deployment.

[0063] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the following steps: A three-dimensional model of the specified tower structure is obtained by modeling the specified tower structure, and the environmental parameters of the specified tower structure are acquired. Multiple preset structural points are determined in the three-dimensional model; The three-dimensional model and the environmental parameters are input into a preset finite element analysis software for analysis to obtain the analysis parameters of multiple preset structural points in the three-dimensional model; Based on the position of the preset structural points in the 3D model and the analysis parameters, determine the sensor type of each preset structural point; Uncertainty analysis is performed on the three-dimensional model using a preset finite element analysis software to obtain a heat map of each preset structural point; Based on the heat map and sensor type of each preset structural point, the number and location of sensors deployed in the three-dimensional model are optimized according to a preset optimization algorithm to obtain an optimized deployment scheme for the specified tower structure.

[0064] By performing uncertainty analysis in pre-set finite element analysis software, the generated heat map identifies potential weak areas. Combined with optimization algorithms, the number and location of sensors are optimized, enabling the monitoring system to significantly reduce costs while maintaining high efficiency. This significantly improves the efficiency and accuracy of monitoring the health status of tower structures. Compared to traditional settlement and tilt monitoring devices, it can not only acquire the load-bearing capacity and damage risk of each structural point of the tower in real time, but also accurately determine the type of sensor required under different environmental conditions, thus enabling targeted deployment.

[0065] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0066] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0067] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A sensor deployment method for a pole-tower structure, characterized in that, The method includes: A three-dimensional model of the specified tower structure is obtained by modeling the specified tower structure, and the environmental parameters of the specified tower structure are acquired. Multiple preset structural points are determined in the three-dimensional model; The three-dimensional model and the environmental parameters are input into a preset finite element analysis software for analysis to obtain the analysis parameters of multiple preset structural points in the three-dimensional model; Based on the position of the preset structural points in the 3D model and the analysis parameters, determine the sensor type of each preset structural point; Uncertainty analysis is performed on the three-dimensional model using a preset finite element analysis software to obtain a heat map of each preset structural point; Based on the heat map and sensor type of each preset structural point, the number and location of sensors deployed in the three-dimensional model are optimized according to a preset optimization algorithm to obtain an optimized deployment scheme for the specified tower structure.

2. The sensor deployment method for the pole structure according to claim 1, characterized in that, The step of determining the sensor type of each preset structural point based on the position of the preset structural point in the 3D model and the analysis parameters includes: Obtain the three-dimensional position information of each of the preset structural points; The range of first sensor types corresponding to the preset structural points is determined based on the three-dimensional position information; Select the corresponding sensor type from the first sensor type range based on the analysis parameters.

3. The sensor deployment method for the pole structure according to claim 1, characterized in that, The step of determining multiple preset structural points in the three-dimensional model includes: The three-dimensional model is input into a preset finite element analysis software to simulate the strain field distribution under various preset environments; High-sensitivity regions are identified based on the strain field distributions described above; Based on the area size of each of the high-sensitivity regions, a preset number of structural points corresponding to the area size is set.

4. The sensor deployment method for the pole structure according to claim 1, characterized in that, The step of performing uncertainty analysis on the three-dimensional model using preset finite element analysis software to obtain heat maps of each preset structural point includes: Uncertain variables are set in the preset finite element analysis software; the uncertain variables are load variables and structural variables. Monte Carlo simulations were performed on the uncertain variables to establish a probabilistic capability model of the three-dimensional model and a probabilistic demand model for geological hazards. A heatmap of the three-dimensional model is generated based on the probabilistic capability model and the probabilistic demand model. Based on the position of each preset structural point in the three-dimensional model, a heat map of each preset structural point is obtained.

5. The sensor deployment method for the tower structure according to claim 1, characterized in that, The step of optimizing the number and location of sensors in the 3D model based on the heat map and sensor type of each preset structural point, and obtaining the optimized deployment scheme for the specified tower structure, includes: The structure point type of each preset structure point is determined based on the heat map of each preset structure point; The preset structural point of type preset is recorded as the target structural point; Set a target sensor of the corresponding sensor type for each target structural point; By sequentially setting the on / off state of each target sensor using a preset optimization algorithm, various simulation scenarios are obtained; Obtain the objective function and calculate the function value for each simulation case; The simulation case with the largest selected function value is used as the optimized deployment scheme for the specified tower structure.

6. The sensor deployment method for the pole structure according to claim 5, characterized in that, The preset optimization algorithm is either simulated annealing or a genetic algorithm.

7. The sensor deployment method for the tower structure according to claim 1, characterized in that, The step of modeling a specified tower structure to obtain a three-dimensional model of the specified tower structure includes: Obtain the CAD model drawing of the specified tower and the material information of each structure; A preliminary model is obtained by performing a preliminary modeling based on the CAD model drawing of the specified tower. The material information of each structure is input into the initial model to obtain the three-dimensional model of the specified tower structure.

8. A sensor deployment device with a pole-tower structure, characterized in that, The device includes: The modeling module is used to model a specified tower structure, obtain a three-dimensional model of the specified tower structure, and acquire the environmental parameters of the specified tower structure. The first determining module is used to determine multiple preset structural points in the three-dimensional model; The input module is used to input the three-dimensional model and the environmental parameters into a preset finite element analysis software for analysis, and to obtain the analysis parameters of multiple preset structural points in the three-dimensional model. The second determining module is used to determine the sensor type of each preset structural point based on the position of the preset structural point in the three-dimensional model and the analysis parameters. The analysis module is used to perform uncertainty analysis on the three-dimensional model in a preset finite element analysis software to obtain the heat map of each preset structural point; The optimization module is used to optimize the number and location of sensors deployed in the three-dimensional model based on the heat map and sensor type of each preset structural point, according to a preset optimization algorithm, to obtain an optimized deployment scheme for the specified tower structure.

9. A computer-readable storage medium, characterized in that, The device contains a computer program that, when executed by a processor, causes the processor to perform the steps of the sensor deployment method for the tower structure as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, The device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the sensor deployment method for the pole structure as described in any one of claims 1 to 7.

Images