Distribution line tower state monitoring method, system, equipment, medium and product

Abstract

The invention relates to the technical field of power distribution line safety monitoring, and discloses a power distribution line tower state monitoring method, system, device, medium and product, first, initial tilt data of a target tower is obtained, an initial covariance matrix is set, then, a particle swarm optimization algorithm is used to adaptively optimize a noise covariance matrix of a Kalman filter, and a power distribution line tower state monitoring result is obtained. According to the method, real inclination signals and complex environmental noise are effectively separated, then, initial inclination data are iteratively calculated based on an optimized filter, inclination data can be predicted in real time, the hysteresis of manual detection is overcome, and finally, the inclination state of a tower is accurately judged through intelligent comparison with a preset inclination threshold value. Therefore, the precision and real-time performance of tower inclination monitoring are improved, the technical problems that traditional manual or ground instrument measurement is easily interfered by the environment and continuous monitoring cannot be achieved are solved, and reliable guarantee is provided for safe operation of an electric power system.

Description

Technical Field

[0001] This invention relates to the field of power distribution line safety monitoring technology, and in particular to a method, system, equipment, medium and product for monitoring the status of power distribution line towers. Background Technology

[0002] In the daily operation and maintenance of power systems, the tilting state of distribution line towers is one of the key factors affecting the safe and stable operation of the lines. Tower tilting not only threatens the normal operation of the lines themselves but may also pose potential hazards to the surrounding environment and personnel.

[0003] Currently, there are two main traditional methods for detecting tower tilt. One method involves manually climbing the tower, where maintenance personnel must carry measuring tools to manually measure the tilt angle. This method has many drawbacks. Firstly, manual tower climbing is time-consuming, labor-intensive, inefficient, and greatly affected by weather and other environmental factors. Secondly, during the climb, maintenance personnel face safety risks such as falls from heights, posing a threat to their personal safety. The other method involves using surveying instruments such as theodolites to measure from the ground. While this method avoids the safety risks of manual climbing, the measurement accuracy is easily affected by the measurement distance and the on-site environment (obstructions, lighting, etc.), and the data contains a large amount of complex noise, making it difficult to guarantee the accuracy of the measurement results. Moreover, neither manual climbing nor ground-based instrument measurement can achieve real-time monitoring of the tower's tilt status, and potential safety hazards cannot be detected in a timely manner. Summary of the Invention

[0004] This invention provides a method, system, equipment, medium, and product for monitoring the status of power distribution line towers, which solves the technical problems of traditional manual or ground-based instrument measurements being susceptible to environmental interference and unable to provide continuous monitoring.

[0005] The first aspect of this invention provides a method for monitoring the status of power distribution line towers, comprising: Obtain the initial tilt data of the target tower and set the initial covariance matrix; Based on the initial tilt data, the parameters of the preset Kalman filter are optimized using a swarm intelligence algorithm to obtain the target optimized parameters. Based on the target optimization parameters, the initial tilt data, and the initial covariance matrix, the preset Kalman filter is used to perform state prediction operation to obtain the target tilt data; The target tilt data is compared with a preset tilt threshold, and tower status information is generated based on the comparison results.

[0006] Optionally, the swarm intelligence algorithm includes a particle swarm optimization algorithm. The step of optimizing the parameters of a preset Kalman filter using the swarm intelligence algorithm based on the initial tilt data to obtain the target optimization parameters includes: Initialize the preset Kalman filter parameters to be optimized; Multiple particles are randomly generated, wherein each particle represents a set of parameters to be optimized; The preset Kalman filter is assigned parameter values ​​using each of the parameters to be optimized, and a state prediction operation is performed to obtain multiple prediction tilt data. The initial tilt data and each of the predicted tilt data are input into a preset objective function, and the objective function value corresponding to each particle is output. Each objective function value is compared with the individual's historical best objective function value. If the objective function value is less than the individual's historical best objective function value, then the individual best position of the particle is updated; Each objective function value is compared with the historical best objective function value of the population. If the objective function value is less than the historical best objective function value of the population, then the population best position of the particle is updated. Determine whether the preset maximum number of iterations has been reached; If the preset maximum number of iterations is reached, the particle associated with the optimal position of the population is taken as the optimal particle, and the parameter to be optimized associated with the optimal particle is taken as the target optimization parameter.

[0007] Optionally, it also includes: If the preset maximum number of iterations is not reached, the velocity vector and position vector of each particle are updated using a preset particle update function based on the individual optimal position and the population optimal position. Jump to the step of using the initial tilt data and each of the predicted tilt data as input to a preset objective function, and outputting the objective function value corresponding to each particle.

[0008] Optionally, the step of performing state prediction operation using the preset Kalman filter based on the target optimization parameters, the initial tilt data, and the initial covariance matrix to obtain the target tilt data includes: Using the target optimization parameters, the initial tilt data, the initial covariance matrix, and the preset state transition matrix, the intermediate tilt data and the associated intermediate covariance matrix are determined. Acquire actual tilt data measured by the sensor; Using a preset observation matrix, the intermediate tilt data, the intermediate covariance matrix, the sensor measured tilt data, and the target optimization parameters, the measurement residual data and Kalman gain data are determined. The target tilt data is determined using the intermediate tilt data, the measurement residual data, and the Kalman gain data.

[0009] Optionally, it also includes: The first multiplication value is obtained by multiplying the Kalman gain data with the preset observation matrix; The first difference is obtained by performing a difference operation between the first multiplication value and the preset identity matrix; The target covariance matrix is ​​obtained by multiplying the first difference with the intermediate covariance matrix. Use the target tilt data as the new initial tilt data; Use the target covariance matrix as the new initial covariance matrix; Jump to the step of performing state prediction operation using the preset Kalman filter based on the target optimization parameters, the initial tilt data and the initial covariance matrix to obtain the target tilt data.

[0010] Optionally, the target optimization parameters include the system noise covariance matrix, and the step of determining the intermediate tilt data and the associated intermediate covariance matrix using the target optimization parameters, the initial tilt data, the initial covariance matrix, and the preset state transition matrix includes: The initial tilt data is multiplied by a preset state transition matrix to obtain intermediate tilt data; The second multiplication value is obtained by multiplying the preset state transition matrix with the initial covariance matrix. The third multiplication value is obtained by multiplying the second multiplication value with the transpose of the preset state transition matrix. The intermediate covariance matrix is ​​obtained by summing the third multiplier with the system noise covariance matrix.

[0011] Optionally, the target optimization parameters further include a measurement noise covariance matrix. The step of determining the measurement residual data and Kalman gain data using a preset observation matrix, the intermediate tilt data, the intermediate covariance matrix, the sensor measured tilt data, and the target optimization parameters includes: The fourth multiplication value is obtained by multiplying the intermediate tilt data with the preset observation matrix; The difference between the measured tilt data from the sensor and the fourth multiplication value is calculated to obtain the measurement residual data. The intermediate covariance matrix is ​​multiplied by the preset observation matrix to obtain the fifth multiplication value; The sixth multiplier is obtained by multiplying the fifth multiplier with the transpose of the preset observation matrix. The first sum is obtained by performing a summation operation between the sixth multiplier and the measurement noise covariance matrix; Invert the first sum to obtain the target inverse value; The Kalman gain data is obtained by multiplying the target inverse value with the fifth multiplier.

[0012] Optionally, determining the target tilt data using the intermediate tilt data, the measurement residual data, and the Kalman gain data includes: The seventh multiplication value is obtained by multiplying the measurement residual data and the Kalman gain data. The target tilt data is obtained by performing a summation operation using the seventh multiplier and the intermediate tilt data.

[0013] Optionally, the target tilt data includes the target tilt angle and the target tilt angular velocity, the preset tilt threshold includes a preset tilt angle threshold and a preset angular velocity threshold, and the comparison of the target tilt data with the preset tilt threshold, and the generation of tower status information based on the comparison result, includes: The optimized tilt angle is obtained by multiplying the target tilt angle, the target tilt angular velocity, and a preset observation matrix. Compare the optimized tilt angle with the preset tilt angle threshold to generate a first comparison result; Compare the target tilt angular velocity with the preset angular velocity threshold to generate a second comparison result; The tower status information includes the first comparison result and the second comparison result.

[0014] Optionally, the comparison of the optimized tilt angle with the preset tilt angle threshold to generate a first comparison result includes: Compare the optimized tilt angle with the preset tilt angle threshold; When the optimized tilt angle is greater than the preset tilt angle threshold, it is determined that the target tower has a steady-state tilt risk, and a first abnormal state information is generated. When the optimized tilt angle is less than or equal to the preset tilt angle threshold, it is determined that the target tower does not have a steady-state tilt risk, and first normal state information is generated. The first comparison result includes the first abnormal state information and the first normal state information.

[0015] Optionally, the step of comparing the target tilt angular velocity with the preset angular velocity threshold to generate a second comparison result includes: Compare the target tilt angular velocity with the preset angular velocity threshold; When the target tilt angular velocity is greater than the preset angular velocity threshold, it is determined that the target tower has a transient tilt risk, and a second abnormal state information is generated; When the target tilt angular velocity is less than or equal to the preset angular velocity threshold, it is determined that the target tower does not have a transient tilt risk, and a second normal state information is generated; The second comparison result includes the second abnormal state information and the second normal state information.

[0016] Optionally, it also includes: When the tower status information contains at least one of the first abnormal status information and the second abnormal status information, an early warning information is generated and fed back to the operation and maintenance personnel.

[0017] Optionally, before comparing the target tilt data with a preset tilt threshold and generating tower status information based on the comparison result, the method further includes: The target tilt data is subjected to signal amplification and digital-to-analog conversion.

[0018] A second aspect of the present invention provides a power distribution line tower condition monitoring system, comprising: The data acquisition module is used to acquire the initial tilt data of the target tower and set the initial covariance matrix; The parameter optimization module is used to optimize the parameters of the preset Kalman filter based on the initial tilt data using a swarm intelligence algorithm to obtain the target optimized parameters. The state prediction module is used to perform state prediction operation using the preset Kalman filter based on the target optimization parameters, the initial tilt data and the initial covariance matrix to obtain the target tilt data; The information output module is used to compare the target tilt data with a preset tilt threshold and generate tower status information based on the comparison result.

[0019] A third aspect of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the power distribution line tower status monitoring method as described in any of the preceding claims.

[0020] The fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the power distribution line tower status monitoring method as described in any of the preceding claims.

[0021] The fifth aspect of the present invention provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein, when the program instructions are executed by a computer, the computer performs the power distribution line tower status monitoring method as described in any of the preceding claims.

[0022] As can be seen from the above technical solutions, the present invention has the following advantages: This invention discloses a method, system, device, medium, and product for monitoring the status of power distribution line towers. First, it acquires the initial tilt data of the target tower and sets an initial covariance matrix. Second, it adaptively optimizes the noise covariance matrix of a Kalman filter using a particle swarm optimization algorithm, effectively separating the actual tilt signal from complex environmental noise. Then, iteratively calculates the initial tilt data based on the optimized filter, enabling real-time prediction of the tilt data and overcoming the lag of manual detection. Finally, it accurately determines the tower tilt state through intelligent comparison with a preset tilt threshold, thereby improving the accuracy and real-time performance of tower tilt monitoring. This solves the technical problems of traditional manual or ground-based instrument measurements being susceptible to environmental interference and unable to provide continuous monitoring, thus providing a reliable guarantee for the safe operation of power systems. Attached Figure Description

[0023] 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.

[0024] Figure 1 This is a flowchart illustrating the steps of a power distribution line tower condition monitoring method according to Embodiment 1 of the present invention. Figure 2 This is a flowchart illustrating the steps of a power distribution line tower condition monitoring method provided in Embodiment 2 of the present invention. Figure 3 This is a schematic diagram of the overall structure of the intelligent clamp device according to an embodiment of the present invention; Figure 4 This is a probability distribution diagram of the state estimation of the Kalman filter algorithm according to an embodiment of the present invention; Figure 5 This is another step flowchart of the power distribution line tower condition monitoring method according to an embodiment of the present invention; Figure 6 This is a structural block diagram of a power distribution line tower condition monitoring system provided in Embodiment 3 of the present invention; Figure 7 This is a structural block diagram of a computer device provided in Embodiment 4 of the present invention. Detailed Implementation

[0025] This invention provides a method, system, equipment, medium, and product for monitoring the status of power distribution line towers, which solves the technical problem that traditional manual or ground-based instrument measurements are easily affected by environmental interference and cannot be continuously monitored.

[0026] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0027] In terms of data processing, although the existing Kalman filter algorithm can process tower tilt measurement data to a certain extent, its parameters are difficult to adaptively adjust to the optimal state in complex and ever-changing power environments, which limits its ability to suppress noise and the accuracy of estimating tower tilt status.

[0028] The main drawbacks of existing technologies include: 1. Low detection efficiency: Manual climbing of towers for detection is extremely inefficient and consumes a lot of manpower and time; although ground instrument measurement is relatively labor-saving, its efficiency is not high in complex environments.

[0029] 2. High safety risks: During the manual climbing of the tower, maintenance personnel face serious safety risks such as falls from heights, threatening their personal safety.

[0030] 3. Measurement accuracy is difficult to guarantee: Firstly, ground-based measuring instruments are greatly affected by environmental factors (distance, obstructions, light, electromagnetic interference, etc.), leading to unstable measurement accuracy and introducing a large amount of noise, making it difficult to accurately obtain tower tilt data. Furthermore, the parameters of existing Kalman filter algorithms are difficult to adaptively adjust, further reducing the ability to accurately obtain tower tilt data.

[0031] 4. Inability to monitor in real time: Traditional detection methods cannot monitor the tilt status of towers in real time, and cannot detect potential safety hazards in time, which is not conducive to ensuring the safe and stable operation of power distribution lines.

[0032] The purpose of this invention is to provide an intelligent clamp for rapid measurement of tower tilt in distribution lines by integrating swarm intelligence algorithms and optimized Kalman filtering. By combining modern sensing technology, swarm intelligence algorithms, and Kalman filtering algorithms, noise in the data is effectively filtered out, enabling rapid and accurate measurement of tower tilt status. It also has real-time monitoring and automatic early warning functions, thereby improving detection efficiency, reducing the workload and safety risks of maintenance personnel, ensuring the safe and stable operation of distribution lines, and promoting the intelligent development of distribution network operation and maintenance management.

[0033] Please see Figure 1 , Figure 1 The flowchart illustrates the steps of a power distribution line tower condition monitoring method provided in Embodiment 1 of the present invention.

[0034] This invention provides a method for monitoring the status of power distribution line towers, comprising: Step 101: Obtain the initial tilt data of the target tower and set the initial covariance matrix.

[0035] Initial tilt data refers to the tilt state observations of the target tower at the start of filtering, including the tilt angle. and tilt angular velocity The readings are obtained from the sensor in real time at the initial moment.

[0036] The initial covariance matrix quantifies the uncertainty of initial tilt data, representing the confidence level of the initial state estimate (e.g., sensor error, environmental interference). The diagonal elements of the initial covariance matrix represent the error variance of each state variable, while off-diagonal elements of 0 indicate the initial assumption that the angle and angular velocity errors are independent. This value is typically set based on sensor accuracy or experience; for example, the standard deviation of the sensor angle error might be [value missing]. If the variance is set to 0.1, it can be understood as a manually initialized value that will be dynamically updated in subsequent Kalman filtering.

[0037] In this embodiment of the invention, the initial tilt data of the target tower is acquired by a sensor, and the initial tilt data is converted into a vector representation. And set the initial covariance matrix. , The variance of the error for the initial tilt angle. This represents the variance of the initial angular velocity error.

[0038] Step 102: Based on the initial tilt data, optimize the parameters of the preset Kalman filter using a swarm intelligence algorithm to obtain the target optimized parameters.

[0039] Parameter optimization refers to adjusting the system noise covariance matrix and measurement noise covariance matrix of a preset Kalman filter using swarm intelligence algorithms to minimize state estimation error and thus improve filtering accuracy.

[0040] The target optimization parameters refer to the optimal noise covariance matrix obtained through parameter optimization. These are the optimal configuration parameters for the preset Kalman filter and are used for actual filtering. The target optimization parameters include the optimal system noise covariance matrix and the optimal measurement noise covariance matrix.

[0041] In this embodiment of the invention, the initial tilt data is used as the input to the Kalman filter, i.e., the baseline data for parameter optimization. A swarm intelligence algorithm is then used to optimize the parameter space (i.e., the system noise covariance matrix). Q and measurement noise covariance matrix R Multiple candidate groups formed within the possible value range Q , R(Combined search) to find the optimal solution, and from this search, the optimal set of candidate solutions is selected. Q , R This combination is used in the actual deployment of pre-configured Kalman filters.

[0042] Step 103: Based on the target optimization parameters, initial tilt data and initial covariance matrix, perform state prediction operation using a preset Kalman filter to obtain target tilt data.

[0043] State prediction operation refers to using the system model state equation and the current state estimate to predict the state and covariance matrix at the next moment. In the tower tilt monitoring scenario of this invention, state prediction estimates the tilt angle and angular velocity at the next moment through the dynamic model.

[0044] Target tilt data refers to the output of the state prediction operation, that is, the prediction value of the tower tilt state at the next moment by the preset Kalman filter, including the target tilt angle and the target tilt angular velocity.

[0045] In this embodiment of the invention, based on the target optimization parameters obtained by parameter optimization, combined with the initial tilt data and the initial covariance matrix, a state prediction operation is performed through a preset Kalman filter to obtain the target tilt data at the next moment.

[0046] Step 104: Compare the target tilt data with the preset tilt threshold, and generate tower status information based on the comparison results.

[0047] The preset tilt threshold refers to the pre-set safety limits for the tilt angle and angular velocity of the tower, which is used to determine whether the tower is in a normal or abnormal state. Tower status information refers to the tower health status classification output based on the comparison results of tilt data and thresholds.

[0048] In this embodiment of the invention, the target tilt angle output by the state prediction operation needs to be converted with the preset observation matrix to extract the optimized tilt angle. Then, the optimized tilt angle and the target tilt angular velocity are compared with the associated preset tilt thresholds, and the final tower state information is generated based on the comparison results.

[0049] In this invention, firstly, the initial tilt data of the target tower is acquired, and an initial covariance matrix is ​​set. Secondly, the noise covariance matrix of the Kalman filter is adaptively optimized using a particle swarm optimization algorithm to effectively separate the real tilt signal from complex environmental noise. Then, based on the optimized filter, the initial tilt data is iteratively calculated, enabling real-time prediction of the tilt data and overcoming the lag of manual detection. Finally, by intelligently comparing with a preset tilt threshold, the tilt state of the tower is accurately determined, thereby improving the accuracy and real-time performance of tower tilt monitoring. This solves the technical problem that traditional manual or ground-based instrument measurements are easily affected by environmental interference and cannot be continuously monitored, providing a reliable guarantee for the safe operation of the power system.

[0050] Please see Figure 2 and Figure 5 , Figure 2 The flowchart illustrates the steps of a power distribution line tower status monitoring method provided in Embodiment 2 of the present invention.

[0051] Figure 5 This is a flowchart of another step in the power distribution line tower condition monitoring method according to an embodiment of the present invention.

[0052] This invention provides a method for monitoring the status of power distribution line towers, applied to an intelligent clamping device, comprising: Please see Figure 3 The intelligent clamp device includes a sensor module, a data processing module, an adaptive clamp structure, a wireless communication module, and a power supply module. The sensor module is used to collect tower tilt data, the data processing module is responsible for analyzing and processing the collected data, the adaptive clamp structure ensures that the clamp can fit tightly to towers of different specifications and shapes, the wireless communication module realizes remote data transmission, and the power supply module provides power support for the entire intelligent clamp.

[0053] Sensor Module: Employing a high-precision tilt sensor, operating based on gravity or inertia, and integrating components such as an accelerometer and gyroscope, it can accurately measure the tilt angle and angular velocity of the tower in three-dimensional space and generate corresponding electrical signal outputs. To improve measurement accuracy, the sensor undergoes rigorous calibration to determine its zero-point offset, range, accuracy, and other parameters, effectively eliminating the influence of systematic and random errors.

[0054] Data Processing Module: This module integrates a high-performance microprocessor with a Kalman filter. It innovatively incorporates an advanced data processing scheme that fuses a swarm intelligence-optimized Kalman filter algorithm. Upon receiving the electrical signal from the sensor, the Kalman filter, incorporating the swarm intelligence algorithm, is used as the core filtering method. This method utilizes the Particle Swarm Optimization (PSO) algorithm from swarm intelligence optimization to optimize the system noise covariance matrix of the Kalman filter algorithm. Qand measurement noise covariance matrix R The optimization of two parameters involves three stages: parameter initialization, fitness calculation, and particle position update. Once the particle swarm optimization algorithm finds the optimal parameter set, these parameters are applied to the Kalman filter algorithm. The Kalman filter algorithm, based on its unique prediction-update mechanism, effectively eliminates high- and low-frequency noise in the signal. In the prediction stage, the current state is predicted based on the system's state transition model and the state estimate from the previous moment. In the update stage, the prediction result is corrected using the current observations. The weights of the predicted and observed values ​​are dynamically adjusted by calculating the Kalman gain, thereby obtaining the optimal state estimate and achieving efficient filtering of noise interference. The signal processed by the Kalman filter is then amplified and converted, accurately converting the analog signal into a digital signal for subsequent analysis and processing by the microprocessor. With the optimized overall algorithm system of the Kalman filter, the tilt state of the tower can be analyzed more accurately and in real-time. Based on preset, scientifically reasonable thresholds, it can quickly and accurately determine whether there are any abnormal tilt conditions in the tower, providing a solid and reliable guarantee for the safe operation of power distribution line towers.

[0055] Adaptive clamp structure: The clamp adopts an adjustable elastic structure design, composed of multiple movable parts, which can automatically adjust according to the different specifications and shapes of the tower, and fit tightly against the tower surface. The contact part between the clamp and the tower is made of anti-slip and wear-resistant materials to increase friction and ensure the stability and safety of the clamp during the measurement process, avoiding measurement errors caused by loosening.

[0056] Wireless communication module: Utilizing suitable wireless communication technologies such as 4G, 5G, or LoRa (Long Range Radio), the tower tilt data analyzed and processed by the data processing module is transmitted in real-time to the remote monitoring center. Maintenance personnel can view the tilt status information of each tower at any time on the management system at the monitoring center, achieving remote real-time monitoring.

[0057] Power module: The power supply adopts a combination of solar panels and rechargeable batteries. When there is sunlight, the solar panels collect solar energy and convert it into electrical energy to charge the rechargeable batteries; when there is no sunlight or the solar panels provide insufficient power, the rechargeable batteries provide stable power support to the various modules of the smart clamp, ensuring that the smart clamp can continue to work normally.

[0058] It has the following advantages: Intelligent data processing and algorithm optimization: The clamp has a built-in high-performance microprocessor that uses advanced algorithms such as Kalman filtering optimized by swarm intelligence to quickly process measurement data, analyze the tower tilt status in real time, and effectively filter noise and interference, thereby improving measurement stability and reliability.

[0059] Adaptive clamp design: The clamp adopts a special structural design that can closely fit poles of different specifications and shapes, improving measurement versatility and ensuring stability and safety during the measurement process.

[0060] Wireless communication and remote monitoring technology: The smart clamp has wireless communication capabilities, which can transmit measurement data to the remote monitoring center in real time, making it easy for maintenance personnel to remotely monitor the tower tilt and take timely maintenance measures.

[0061] It's worth mentioning that in terms of wireless communication, in addition to 4G, 5G, and LoRa technologies, NB-IoT (Narrowband Internet of Things) technology can also be used. NB-IoT features low power consumption, wide coverage, and low cost, making it suitable for scenarios where data transmission rates are not critical, but power consumption and coverage are critical. It can meet the needs of smart clamps to transmit data to a remote monitoring center.

[0062] Regarding power modules, in addition to combining solar panels with rechargeable batteries, for some special application scenarios, such as where there is a stable power supply source near the tower (with a small substation or other power supply facilities nearby), wired power supply can be considered to avoid insufficient power due to weather or other factors affecting solar power supply, thus ensuring the stable operation of the smart clamp.

[0063] In addition to particle swarm optimization, other newly proposed swarm intelligence algorithms can also be used. These algorithms are constantly being optimized and updated, and can be directly replaced if more advanced algorithms become available in the future.

[0064] Step 201: Obtain the initial tilt data of the target tower and set the initial covariance matrix.

[0065] In this embodiment of the invention, a system state vector is defined. Including tilt angle (Measured by accelerometer) and angular velocity (Measured by a gyroscope), that is , express k The tower tilt angle measured at all times; k express k The tilt angular velocity measured at time t. This state vector. A complete description of the tower in k The tilt motion state at any given time provides the basic data structure for subsequent Kalman filtering. Tilting angle It directly reflects the degree of deviation of the tower from the vertical direction and is one of the key indicators for judging whether the tower is in a safe state. The tilt angular velocity... This reflects the rate of change of the tilt angle over time, which is of great significance for predicting the development trend of the tower's tilt state. The tower in... k The actual tilt angle and tilt angular velocity at time t are respectively and .

[0066] First, determine the estimated value of the initial tilt state of the tower. After the smart clamp is installed, the initial sensor measurements are read. After simple calibration and processing, assuming there is no initial angular velocity, then... .

[0067] At the same time, set the initial state covariance matrix. :

[0068] In the matrix, and The variance of the tilt angle and angular velocity is the error. Used to describe the degree of uncertainty in the state estimate. In practical applications, if the clamp installation environment is relatively stable and the initial sensor measurement is relatively reliable, it can be... The diagonal elements are set to [0.1, 0.1] (corresponding to...). and ).

[0069] The specific implementation process of step 201 is similar to that of step 101, and will not be repeated here.

[0070] Swarm intelligence algorithms: These are optimization algorithms that simulate the intelligent behavior of biological swarms, such as Particle Swarm Optimization (PSO) and Ant Colony Optimization. In this invention embodiment, PSO is used for parameter optimization. PSO refers to simulating the foraging behavior of bird flocks, treating the solution to the problem as particles in a search space. Each particle has its own position and velocity. Based on its own experience and the experience of other particles in the swarm, the particles continuously adjust their positions in the search space, flying towards the direction of the optimal solution, and ultimately finding the global optimum. In this invention, swarm intelligence algorithms are used to optimize the parameters in Kalman filtering, improving its performance in processing tower tilt state measurement data.

[0071] Furthermore, swarm intelligence algorithms include particle swarm optimization algorithms.

[0072] The noise covariance matrix of the traditional Kalman filter algorithm system Q and measurement noise covariance matrix R The initial setup relies too heavily on environmental data and empirical knowledge. Therefore, the particle swarm optimization algorithm from swarm intelligence algorithms is used for optimization to achieve the final accuracy of the Kalman algorithm. The specific process is as follows: Step 202: Based on the initial tilt data, optimize the parameters of the preset Kalman filter using a swarm intelligence algorithm to obtain the target optimized parameters.

[0073] Furthermore, step 202 may include the following sub-steps: S11. Initialize the preset parameters of the Kalman filter to be optimized.

[0074] It should be noted that the parameter initialization is based on Q and R The parameter combination is used as the particle in the particle swarm algorithm. i During the initialization phase, a certain number of particles are randomly generated, each particle having a position vector. X i and velocity vector V i Two attributes are defined: the position vector, representing the current parameter value, and the velocity vector, which determines the particle's direction and step size in the parameter space. The maximum number of iterations and the initial number of iterations are also set.

[0075] The parameters to be optimized need to be determined, namely the system noise covariance matrix. Q and measurement noise covariance matrix R :

[0076] In the above formula, and It needs to be determined by combining environmental data and experience from the actual scenario. It can be determined based on the sensor's nameplate parameters, among which The system's angular process noise variance. This represents the variance of the system's angular velocity process noise. If detailed environmental data is unavailable, in areas with weak winds and good tower stability, [the following can be considered]: Q The diagonal elements are set to a smaller value, i.e. Near the poles where smart clamps are actually installed, high-precision environmental monitoring equipment such as anemometers and vibration sensors are used to measure the fluctuations of environmental factors over a period of time. The acquired data is statistically analyzed to calculate the variance of the impact of environmental factor changes on the pole's tilt state, and this is used as a basis for setting... Q .

[0077] In this embodiment of the invention, firstly, the relevant parameters of the Kalman filter are initialized, including the state transition matrix, observation matrix, system process noise covariance matrix, measurement noise covariance matrix, initial covariance matrix, and initial state vector (i.e., initial tilt data).

[0078] S12. Randomly generate multiple particles, where each particle represents a set of parameters to be optimized.

[0079] In this embodiment of the invention, multiple particles are randomly generated to form a particle swarm, and each particle represents a set of parameters to be optimized. The specific parameters to be optimized are (… , , ).

[0080] S13. Assign parameters to the preset Kalman filter using each parameter to be optimized, and perform state prediction operation to obtain multiple predicted tilt data.

[0081] Parameter assignment refers to the process of assigning multiple sets of parameters to be optimized to a preset Kalman filter in order to adjust the behavior of the filter to adapt to different system dynamics or noise environments.

[0082] Predicted tilt data refers to the estimation of the tilt angle and tilt angular velocity of a tower at a future moment based on the current state using a preset Kalman filter. The accuracy of the predicted tilt data depends on the setting of the parameters to be optimized.

[0083] In this embodiment of the invention, parameter traversal and assignment are performed on each set of parameters to be optimized, and state prediction operation is performed based on each set of parameters to be optimized to generate multiple sets of prediction results. Each set of parameters to be optimized corresponds to a prediction tilt data.

[0084] S14. Input the initial tilt data and each predicted tilt data into the preset objective function, and output the objective function value corresponding to each particle.

[0085] The preset objective function, also known as the fitness function, is used to evaluate the effectiveness of the Kalman filter parameter set represented by each particle in processing tower tilt measurement data. The fitness function can be based on metrics such as the mean square error (MSE) and mean absolute error (MAE) of the measurement data. This study compares the measurement data processed by Kalman filtering with known accurate tower tilt data, calculating the mean square error (MSE). The smaller the MSE, the better the set of parameters to be optimized performs on data processing, and the higher the particle's fitness.

[0086] It is worth mentioning that the preset objective function provided by the present invention includes a first objective function and a second objective function. Therefore, when calculating the objective function value, either the first objective function or the second objective function can be selected.

[0087] The first objective function only involves the tilt angle and does not introduce angular velocity.

[0088] The first objective function is as follows:

[0089] In the formula, These are the predicted values ​​from the Kalman filter. It is the actual value of the tower's tilt angle. This represents the number of parameter sets to be optimized. Since the core objective of tower tilt monitoring is to accurately measure the tilt angle... Because the angle directly reflects the degree of tilt of the tower, it is a key indicator for judging safety. Angular velocity (the rate of change of tilt) is more often used to predict trends or assist in judging sudden tilting (extreme events such as earthquakes and strong winds), and not all scenarios require high-precision optimization of the estimated angular velocity. Therefore, during the development of this invention, angular velocity was not incorporated into the fitness function MSE. .

[0090] If angular velocity is a factor in practical applications The accuracy of the result is equally crucial; therefore, the errors in both angle and angular velocity should be considered in the fitness function. The following are the considerations... and The second objective function of the subsequent multi-state MSE:

[0091] In the formula, These are the predicted values ​​from the Kalman filter. It is the actual value of the tower's tilt angular velocity. These are weighting coefficients, used to measure... θ and ω The importance of error ( =0.5 means ω The importance of error is θ Half of it.

[0092] In this embodiment of the invention, initial tilt data and each predicted tilt data are input into a preset objective function, and the objective function value corresponding to each particle is output.

[0093] S15. Compare each objective function value with the individual's historical best objective function value.

[0094] The individual's historical optimal objective function value refers to the first... i Each particle independently maintains its own historical best-case scenario (MSE) record, representing the optimal objective function value it has achieved during the search process. This preserves the particle's own "experience" to avoid blindly following the group and losing local optima.

[0095] In this embodiment of the invention, each objective function value is compared with the individual's historical best objective function value.

[0096] S16. When the objective function value is less than the individual's historical best objective function value, the individual best position of the particle is updated.

[0097] In this embodiment of the invention, when the objective function value is less than the individual's historical best objective function value, that is, the objective function value is smaller, the individual best position of the particle associated with the objective function value is updated to the current position, and its individual historical best objective function value is updated to the current objective function value.

[0098] S17. Compare each objective function value with the historical best objective function value of the population.

[0099] The historical optimal objective function value of the population refers to the optimal objective function value (i.e., the global minimum MSE) that all particles in the entire particle swarm have ever reached. All particles share this global record, which is used to guide the entire population to converge toward the global optimal solution.

[0100] In this embodiment of the invention, each objective function value is compared with the historical best objective function value of the population.

[0101] S18. When the objective function value is less than the historical best objective function value of the population, update the population best position of the particle.

[0102] In this embodiment of the invention, when the objective function value is less than the historical best objective function value of the population, that is, the objective function value is smaller, the population best position of the particle associated with the objective function value is updated to the current position, and its historical best objective function value is updated to the current objective function value.

[0103] S19. Determine whether the preset maximum number of iterations has been reached.

[0104] In this embodiment of the invention, it is determined whether the current iteration count has reached the preset maximum iteration count.

[0105] S110. If the preset maximum number of iterations is reached, the particle associated with the optimal position of the population is taken as the optimal particle, and the parameter to be optimized associated with the optimal particle is taken as the target optimization parameter.

[0106] In this embodiment of the invention, if the preset maximum number of iterations is reached, the particle associated with the optimal position of the population is directly selected as the optimal particle, and the parameter to be optimized associated with the optimal particle is used as the target optimization parameter and output.

[0107] It should be noted that through continuous iterative updates, the particles gradually approach the optimal solution. When the maximum number of iterations is reached, the algorithm exits the loop, meaning it has found the optimal combination of Kalman filter parameters (i.e., the target optimization parameters {...}). ， Once the particle swarm optimization algorithm finds the optimal set of parameters, these parameters are applied to the Kalman filter algorithm.

[0108] S111. If the preset maximum number of iterations is not reached, the velocity vector and position vector of each particle are updated by a preset particle update function based on the individual optimal position and the population optimal position.

[0109] In this embodiment of the invention, if the preset maximum number of iterations is not reached, two random numbers r1 and r2 are generated to introduce randomness. Then, the velocity vector of the particles is updated according to the velocity update formula of the particle swarm algorithm. Next, the position vector of the particles is updated according to the updated velocity vector. Finally, in order to prevent the parameter values ​​from being too small, an array limiting function (referring to a function in the numerical computing library used to limit the elements in the array to a specified range) is used to restrict the position of the particles to ensure that the parameter values ​​are within a reasonable range. By continuously iterating the above update process, the particle swarm gradually moves closer to the optimal solution, and the final output is the optimal parameter combination found.

[0110] The specific formula for speed update is as follows:

[0111] in, It is the first i The velocity vector of each particle in the next iteration. It is the first i The velocity vector of each particle in the current iteration It is inertial weight. and It is a learning factor. and It is a random number in the interval [0, 1]. It is the individual's historical optimal position, that is, the first i The optimal position that each particle has reached during the search process. It is the best position in the population's history, that is, the best position found by the entire particle swarm during the search process, which is the best position among all the best positions in the history of all particles. It is the first i The position vector of each particle in the current iteration.

[0112] The specific formula for position update is as follows:

[0113] In the formula, It is the first i The position vector of each particle in the next iteration.

[0114] S112. Jump to the step of inputting the initial tilt data and each predicted tilt data into the preset objective function, and outputting the objective function value corresponding to each particle.

[0115] It should be noted that the iteration stopping condition is as follows: after one iteration of the above process, the number of iterations will increment by 1. The incremented value is compared with the set maximum number of iterations. If it is greater than the maximum number of iterations, the algorithm terminates. Otherwise, it returns to the step of inputting the initial tilt data and each predicted tilt data into the preset objective function and outputting the objective function value corresponding to each particle to continue the iterative calculation.

[0116] In this embodiment of the invention, since the preset maximum number of iterations has not been reached, after updating the velocity vector and position vector of each particle, the process jumps back to the step of inputting the initial tilt data and each predicted tilt data into the preset objective function and outputting the objective function value corresponding to each particle.

[0117] The Kalman filter algorithm is an algorithm that uses the state equations of a linear system to optimally estimate the system state based on system input and output observation data. Its core idea is to establish a dynamic model and an observation model of the system, and then recursively predict and update the state estimates. The prediction step uses the previous state estimate and the system model to predict the current state, while the update step combines the current observation data and the predicted value, using the Kalman gain to calculate a more accurate state estimate. This gain determines the degree of influence of the observation data on the estimate, ultimately ensuring that the estimate remains optimal or near-optimal even in the presence of uncertainties such as noise. It is widely used in navigation, control systems, signal processing, and other fields. (Please refer to...) Figure 4 The blue curve represents state prediction, specifically the prediction of the current system state based on the previous state estimate and the system model. It reflects a preliminary inference of the system state before incorporating current observation data, based on the system's past states and dynamic characteristics. The orange curve represents measurement, specifically the system state-related data obtained through actual measurement methods. Since actual measurements are often subject to various noise interferences, the measurement data has a certain degree of uncertainty. The yellow curve represents prediction correction, specifically the final state estimate curve obtained after processing by the Kalman filter algorithm. It comprehensively considers state prediction and measurement data, fusing them through Kalman gain to ensure that the final state estimate is as close as possible to the true system state, even with uncertainties such as noise.

[0118] Step 203: Based on the target optimization parameters, initial tilt data and initial covariance matrix, perform state prediction operation using a preset Kalman filter to obtain target tilt data.

[0119] Furthermore, step 203 may include the following sub-steps: S21. Using the target optimization parameters, initial tilt data, initial covariance matrix, and preset state transition matrix, determine the intermediate tilt data and the associated intermediate covariance matrix.

[0120] Furthermore, the target optimization parameters include the system noise covariance matrix, and S21 may include the following sub-steps: s211. Multiply the initial tilt data with the preset state transition matrix to obtain intermediate tilt data.

[0121] In this embodiment of the invention, based on the state of the previous time step... And system model predicts the current state For ease of understanding, let's use the initial tilt data. For example, we can understand the state at the previous moment. Initial tilt data .

[0122] In practical implementation, to facilitate the method's implementation, the above process can be converted into a formula encapsulation, where the intermediate slant data can be as follows:

[0123] In the formula, This represents the intermediate tilt data, which is the current state of the preset Kalman filter output. This represents the preset state transition matrix. , Indicates the time interval between two consecutive measurements. This represents the initial tilt data, which is the state at the previous moment.

[0124] s212. The second multiplication value is obtained by multiplying the preset state transition matrix with the initial covariance matrix.

[0125] s213. Perform a multiplication operation by combining the second multiplier with the transpose of the preset state transition matrix to obtain the third multiplier.

[0126] s214. The intermediate covariance matrix is ​​obtained by summing the third multiplier with the system noise covariance matrix.

[0127] In practical implementation, to simplify the method, the above process can be converted into a formulaic encapsulation, where the intermediate covariance matrix can be as follows:

[0128] In the formula, This represents the intermediate covariance matrix, which is also the variance matrix of the current time step of the preset Kalman filter output. This represents the initial covariance matrix, which is also the covariance matrix at the previous time step. This represents the transpose of the preset state transition matrix. This represents the system noise covariance matrix.

[0129] In this embodiment of the invention, the state at the current moment is predicted by using the state information of the previous moment and the system noise characteristics through these two formulas, and intermediate tilt data and associated intermediate covariance matrix are obtained, providing basic data for the subsequent update stage.

[0130] S22. Obtain the actual tilt data measured by the sensor.

[0131] In this embodiment of the invention, measured tilt data (including noise) from the sensor is obtained.

[0132] S23. Using the preset observation matrix, intermediate tilt data, intermediate covariance matrix, sensor measured tilt data, and target optimization parameters, determine the measurement residual data and Kalman gain data.

[0133] Furthermore, the target optimization parameters also include the measurement noise covariance matrix, and S23 may include the following sub-steps: s231. The fourth multiplication value is obtained by multiplying the preset observation matrix with the intermediate tilt data.

[0134] s232. The difference between the actual tilt data measured by the sensor and the fourth multiplier is calculated to obtain the measurement residual data.

[0135] In practical implementation, to facilitate the method's implementation, the above process can be converted into a formulaic encapsulation, where the measurement residual data can be as follows:

[0136] In the formula, This represents the measurement residual data. This represents the actual tilt data measured by the sensor. This represents the preset observation matrix. Only with the state vector The tilt angle of the poles θ Related.

[0137] In this embodiment of the invention, the actual tilt data measured by the sensor is used. The measurement residuals are calculated by comparing the (noise-inclusive) values ​​with the predicted values.

[0138] s233. The intermediate covariance matrix is ​​multiplied by the preset observation matrix to obtain the fifth multiplier.

[0139] s234. The sixth multiplication value is obtained by multiplying the fifth multiplication value with the transpose of the preset observation matrix.

[0140] s235. The first sum is obtained by performing a summation operation on the sixth multiplier and the measurement noise covariance matrix.

[0141] s236. Perform the inverse operation on the first sum to obtain the target inverse value.

[0142] s237. The Kalman gain data is obtained by multiplying the target inverse value with the fifth multiplier.

[0143] In practical implementation, to facilitate the method's implementation, the above process can be converted into a formulaic encapsulation, where the Kalman gain data can be as follows:

[0144] In the formula, This represents the Kalman gain data. This represents the transpose of the preset observation matrix. This represents the measurement noise covariance matrix.

[0145] It is worth mentioning that, It is a key parameter, and the Kalman gain data is based on... , and The weights of predicted and observed values ​​in state updates are dynamically adjusted. If the measurement noise is low (i.e....), If the value is smaller, the observation is more reliable. This will give the observations a greater weight in the state update; conversely, if the predicted state covariance is small (i.e., (Since the value is relatively small, the predicted value is more accurate), and the predicted value will receive more attention in the update.

[0146] S24. Use intermediate tilt data, measurement residual data and Kalman gain data to determine the target tilt data.

[0147] Furthermore, S24 may include the following sub-steps: s241. The seventh multiplication value is obtained by multiplying the measurement residual data and Kalman gain data.

[0148] s242. The target tilt data is obtained by summing the seventh multiplier with the intermediate tilt data.

[0149] In practical implementation, to facilitate the method's implementation, the above process can be converted into a formula encapsulation, where the target tilt data can be as follows:

[0150] In the formula, This indicates the target tilt data.

[0151] In an embodiment of the present invention, according to By integrating prediction and observation results, Update to enable The correction yields a more accurate estimate of the optimal state. .

[0152] S25. Perform a multiplication operation between the Kalman gain data and the preset observation matrix to obtain the first multiplication value.

[0153] S26. Perform a difference operation between the first multiplier and the preset identity matrix to obtain the first difference.

[0154] S27. Multiply the first difference with the intermediate covariance matrix to obtain the target covariance matrix.

[0155] In practical implementation, to facilitate the method's implementation, the above process can be converted into a formulaic encapsulation, where the target covariance matrix can be as follows:

[0156] In the formula, Represents the target covariance matrix. This represents the preset identity matrix.

[0157] In this embodiment of the invention, this step updates the intermediate covariance matrix. Obtain the target covariance matrix This allows the Kalman filter algorithm to more accurately reflect the uncertainty of the current state estimate. After the update phase, the algorithm can comprehensively consider the information from the predicted and observed values, effectively suppress noise interference, and obtain a more accurate estimate of the tower tilt state, providing reliable data support for subsequent judgments on whether the tower tilt state is abnormal.

[0158] S28. Use the target tilt data as the new initial tilt data.

[0159] S29. Use the target covariance matrix as the new initial covariance matrix.

[0160] S210, Jump to the step of performing state prediction operation using a preset Kalman filter based on the target optimization parameters, initial tilt data and initial covariance matrix to obtain the target tilt data.

[0161] In this embodiment of the invention, the state prediction operation for two adjacent time points has been completed at this point, which can be understood as completion. - Next, we need to complete... - If the state prediction is to use the target tilt data as the new initial tilt data and the target covariance matrix as the new initial covariance matrix, then the process jumps to the step of performing state prediction operation using a preset Kalman filter based on the target optimization parameters, initial tilt data, and initial covariance matrix to obtain the target tilt data. Therefore, it can be understood as... As a new Then repeat the above process until all moments are completed.

[0162] Step 204: Perform signal amplification and digital-to-analog conversion on the target tilt data.

[0163] In this embodiment of the invention, the target tilt data is transmitted to the data processing module via a wireless communication module for signal amplification and digital-to-analog conversion.

[0164] Step 205: Compare the target tilt data with the preset tilt threshold, and generate tower status information based on the comparison results.

[0165] Furthermore, the target tilt data includes the target tilt angle and the target tilt angular velocity; the preset tilt threshold includes a preset tilt angle threshold and a preset angular velocity threshold; the tower status information includes a first comparison result and a second comparison result; step 205 may include the following sub-steps: S31. The target tilt angle, target tilt angular velocity and preset observation matrix are multiplied to obtain the optimized tilt angle.

[0166] In practical implementation, to simplify the method, the above process can be converted into a formula, where the optimized tilt angle can be as follows:

[0167] In the formula, This indicates an optimized tilt angle.

[0168] S32. Compare the optimized tilt angle with the preset tilt angle threshold to generate the first comparison result.

[0169] Furthermore, the first comparison result includes first abnormal state information and first normal state information, and S32 may include the following sub-steps: s321. Compare and optimize the tilt angle with the preset tilt angle threshold.

[0170] In this embodiment of the invention, the tilt angle is compared and optimized. With preset tilt angle threshold .

[0171] s322. When the optimized tilt angle is greater than the preset tilt angle threshold, it is determined that the target tower has a steady-state tilt risk and the first abnormal state information is generated.

[0172] In this embodiment of the invention, when the optimized tilt angle is greater than a preset tilt angle threshold, that is... The state is determined to be abnormal, indicating a risk of steady-state tilt (i.e., a risk of long-term tilt), and the first abnormal state information is generated.

[0173] s323. When the optimized tilt angle is less than or equal to the preset tilt angle threshold, it is determined that there is no steady-state tilt risk in the target tower, and the first normal state information is generated.

[0174] In this embodiment of the invention, when the optimized tilt angle is less than or equal to a preset tilt angle threshold, that is... It is determined to be in a normal state, and the first normal state information is generated.

[0175] S33. Compare the target tilt angular velocity with the preset angular velocity threshold to generate a second comparison result.

[0176] Furthermore, the second comparison result includes second abnormal state information and second normal state information, and S33 may include the following sub-steps: s331. Compare the target tilt angular velocity with the preset angular velocity threshold.

[0177] In this embodiment of the invention, the target tilt angular velocity is compared. With preset angular velocity threshold .

[0178] s332. When the target tilt angular velocity is greater than the preset angular velocity threshold, it is determined that the target tower has a transient tilt risk and a second abnormal state information is generated.

[0179] In this embodiment of the invention, when the target tilt angular velocity is greater than a preset angular velocity threshold, that is... The state is determined to be abnormal, indicating a risk of transient tilt (i.e., a risk of rapid tilting), and a second abnormal state information is generated.

[0180] s333. When the target tilt angular velocity is less than or equal to the preset angular velocity threshold, it is determined that there is no risk of transient tilting of the target tower, and a second normal state information is generated.

[0181] In this embodiment of the invention, when the target tilt angular velocity is less than or equal to a preset angular velocity threshold, that is... It is determined to be in a normal state, and a second normal state information is generated.

[0182] Step 206: When the tower status information contains at least one of the first abnormal status information and the second abnormal status information, generate an early warning message and provide feedback to the operation and maintenance personnel.

[0183] In this embodiment of the invention, when at least one of the first abnormal state information and the second abnormal state information exists in the tower status information, the data processing module controls the wireless communication module to immediately send alarm information to the remote monitoring center. At the same time, the intelligent clamp device intuitively displays the tilt over-limit information, reminding the operation and maintenance personnel to deal with it in time until the crisis is resolved and it is determined that there is no crisis.

[0184] The workflow of this invention is as follows: After the smart clamp is installed on the power distribution line tower, the sensor module collects the tower's tilt-related data in real time and transmits the data to the data processing module. The data processing module first finds the optimal Kalman filter parameters through a swarm intelligence optimization algorithm, and then performs Kalman filtering processing and analysis on the data based on these parameters to determine the tower's tilt status. If the tilt angle and angular velocity are within the normal range, the tower is determined to be safe, and real-time monitoring continues. If one or both of the tilt angle and angular velocity exceed a preset threshold simultaneously, the data processing module controls the wireless communication module to immediately send an alarm message to the remote monitoring center. At the same time, the local display device on the smart clamp will also visually display the tilt exceeding the limit information, reminding nearby maintenance personnel to handle the situation promptly. Once the crisis is resolved, the system determines that the tower has entered a safe state and real-time monitoring resumes.

[0185] To compare the performance of the traditional Kalman filter algorithm and the swarm intelligence-optimized Kalman filter algorithm, this invention conducted comparative experiments.

[0186] (1) Experimental setup

[0187] 1. Experimental subjects: Five power line towers with different wind speeds were selected as monitoring subjects.

[0188] 2. Data Acquisition: A smart clamp is installed at the waist of each tower. The high-precision tilt sensor in the clamp continuously collects the tilt angle data of the tower for 1 hour, with a collection frequency of once per second, and a total of 21,600 sets of raw data are obtained (4,320 sets for each tower).

[0189] 3. Algorithm Application: Traditional Kalman filtering algorithm: The system noise covariance matrix is ​​set empirically. Q and measurement noise covariance matrix R The raw data collected is then processed.

[0190] Swarm intelligence optimized Kalman filter algorithm: PSO optimization algorithm is used to optimize the Kalman filter. Q and RTo optimize the process, based on experimental experience, the particle swarm size was set to 30, the maximum number of iterations to 60, the inertia weight w to 0.7, and the learning factors c1 and c2 to 1.5, while processing the same original data.

[0191] 4. Evaluation index: Mean square error (MSE) is used to evaluate the error between the data processed by the two algorithms and the actual tilt angle data obtained by measuring with a high-precision total station under ideal conditions.

[0192] (2) Experimental results

[0193] 1. Mean Square Error (MSE): The average MSE of the data processed by the traditional Kalman filter algorithm on 5 towers is 0.065; while the average MSE of the data processed by the swarm intelligence optimized Kalman filter algorithm is reduced to 0.018.

[0194] (3) Results Analysis

[0195] Experimental results clearly demonstrate that, compared to the traditional Kalman filter algorithm, the swarm intelligence-optimized Kalman filter algorithm proposed in this patent exhibits significant advantages in processing power line tower tilt measurement data. By optimizing the Kalman filter parameters using a swarm intelligence optimization algorithm, the optimized algorithm achieves a lower mean square error (MSE) as a key performance indicator. The MSE decreases by 0.047, which fully proves that the swarm intelligence-optimized Kalman filter algorithm can more effectively suppress noise interference and significantly improve the accuracy of tower tilt estimation, thus providing more reliable data support for the safety monitoring of power line towers.

[0196] This invention has the following advantages: 1. High detection efficiency: The intelligent clamp uses an automated measurement method, eliminating the need for manual climbing of the tower. It can quickly obtain tower tilt data and transmit it to the remote monitoring center in real time, greatly improving detection efficiency and saving manpower and time costs.

[0197] 2. Low safety risk: It avoids the safety risks of falling from heights caused by manual climbing of towers, ensuring the personal safety of maintenance personnel and reducing their workload.

[0198] 3. High Measurement Accuracy: Employing a high-precision tilt sensor with precise calibration, combined with a swarm intelligence-optimized Kalman filter algorithm, interference noise is effectively filtered out, resulting in accurate and reliable measurement results that provide strong support for operation and maintenance decisions. The swarm intelligence-optimized Kalman filter is better adapted to complex power environments, further improving measurement accuracy.

[0199] 4. Real-time monitoring and early warning: Equipped with real-time monitoring function, it can promptly detect abnormal tower tilting and automatically issue early warning signals, facilitating maintenance personnel to take timely measures to avoid line faults and power outages caused by tower tilting, thereby improving the safety and reliability of the distribution network.

[0200] 5. Broad application prospects: With the development of technologies such as the Internet of Things and big data, smart clamps can be linked with other smart devices to achieve more intelligent and automated distribution network operation and maintenance management, providing strong support for the intelligent development of distribution network operation and maintenance management.

[0201] In this invention, firstly, the initial tilt data of the target tower is acquired, and an initial covariance matrix is ​​set. Secondly, the noise covariance matrix of the Kalman filter is adaptively optimized using a particle swarm optimization algorithm to effectively separate the real tilt signal from complex environmental noise. Then, based on the optimized filter, the initial tilt data is iteratively calculated, enabling real-time prediction of the tilt data and overcoming the lag of manual detection. Finally, by intelligently comparing with a preset tilt threshold, the tilt state of the tower is accurately determined, thereby improving the accuracy and real-time performance of tower tilt monitoring. This solves the technical problem that traditional manual or ground-based instrument measurements are easily affected by environmental interference and cannot be continuously monitored, providing a reliable guarantee for the safe operation of the power system.

[0202] Please see Figure 6 , Figure 6 This is a structural block diagram of a power distribution line tower condition monitoring system provided in Embodiment 3 of the present invention.

[0203] This invention provides a power distribution line tower condition monitoring system, comprising: The data acquisition module 301 is used to acquire the initial tilt data of the target tower and set the initial covariance matrix; The parameter optimization module 302 is used to optimize the parameters of a preset Kalman filter based on the initial tilt data using a swarm intelligence algorithm to obtain the target optimized parameters. The state prediction module 303 is used to perform a state prediction operation based on the target optimization parameters, initial tilt data and initial covariance matrix, and to obtain the target tilt data by using a preset Kalman filter. The information output module 304 is used to compare the target tilt data with the preset tilt threshold and generate tower status information based on the comparison results.

[0204] Furthermore, the swarm intelligence algorithm includes a particle swarm optimization algorithm, and the parameter optimization module 302 includes: The initialization submodule is used to initialize the parameters to be optimized in the preset Kalman filter; The particle generation submodule is used to randomly generate multiple particles, where each particle represents a set of parameters to be optimized. The predicted tilt data submodule is used to assign parameter values ​​to the preset Kalman filter using each parameter to be optimized, and to perform state prediction operations to obtain multiple predicted tilt data. The objective function value submodule is used to input the preset objective function with the initial tilt data and each predicted tilt data, and output the objective function value corresponding to each particle. The first comparison submodule is used to compare each objective function value with the individual's historical best objective function value; The first update submodule is used to update the individual optimal position of a particle when the objective function value is less than the individual's historical best objective function value. The second comparison submodule is used to compare each objective function value with the population's historical best objective function value, respectively. The second update submodule is used to update the population-optimal position of particles when the objective function value is less than the population's historical best objective function value. The judgment submodule is used to determine whether the preset maximum number of iterations has been reached; The first judgment result submodule is used to determine, if the preset maximum number of iterations is reached, the particle associated with the optimal position of the population as the optimal particle, and the parameter to be optimized associated with the optimal particle as the target optimization parameter.

[0205] Furthermore, it also includes: The second judgment result submodule is used to update the velocity vector and position vector of each particle based on the individual optimal position and the population optimal position if the preset maximum number of iterations has not been reached. The first jump rotor module is used to jump to the step of inputting the initial tilt data and each predicted tilt data into a preset objective function and outputting the objective function value corresponding to each particle.

[0206] Furthermore, the state prediction module 303 includes: The intermediate covariance matrix submodule is used to determine the intermediate skew data and the associated intermediate covariance matrix using the target optimization parameters, initial skew data, initial covariance matrix and preset state transition matrix; The sensor measured tilt data submodule is used to acquire sensor measured tilt data. The measurement residual data and Kalman gain data submodule is used to determine the measurement residual data and Kalman gain data using a preset observation matrix, intermediate tilt data, intermediate covariance matrix, sensor measured tilt data and target optimization parameters; The target tilt data submodule is used to determine the target tilt data by using intermediate tilt data, measurement residual data, and Kalman gain data.

[0207] Furthermore, the state prediction module 303 also includes: The first multiplication submodule is used to perform multiplication operations on the Kalman gain data and the preset observation matrix to obtain the first multiplication value. The first difference submodule is used to perform a difference operation between the first multiplication value and the preset identity matrix to obtain the first difference value. The target covariance matrix submodule is used to perform a multiplication operation between the first difference and the intermediate covariance matrix to obtain the target covariance matrix. The third update submodule is used to use the target tilt data as the new initial tilt data. The fourth update submodule is used to take the target covariance matrix as the new initial covariance matrix; The second jump rotor module is used to jump to the step of performing state prediction operation based on target optimization parameters, initial tilt data and initial covariance matrix, and obtaining target tilt data by using a preset Kalman filter.

[0208] Furthermore, the target optimization parameters include the system noise covariance matrix, and the intermediate covariance matrix submodule includes: The intermediate tilt data unit is used to perform a multiplication operation between the initial tilt data and a preset state transition matrix to obtain intermediate tilt data. The second multiplication unit is used to perform a multiplication operation between a preset state transition matrix and an initial covariance matrix to obtain the second multiplication value. The third multiplication unit is used to perform a multiplication operation by using the second multiplication value and the transpose of the preset state transition matrix to obtain the third multiplication value; The intermediate covariance matrix output unit is used to perform a summation operation between the third multiplier and the system noise covariance matrix to obtain the intermediate covariance matrix.

[0209] Furthermore, the target optimization parameters also include the measurement noise covariance matrix, measurement residual data, and Kalman gain data submodules, which include: The fourth multiplication unit is used to perform multiplication operations with the preset observation matrix and intermediate tilt data to obtain the fourth multiplication value; The measurement residual data unit is used to perform difference calculations between the sensor's measured tilt data and the fourth multiplier to obtain the measurement residual data. The fifth multiplication unit is used to perform a multiplication operation between the intermediate covariance matrix and the preset observation matrix to obtain the fifth multiplication value; The sixth multiplication unit is used to perform a multiplication operation by using the fifth multiplication value and the transpose of the preset observation matrix to obtain the sixth multiplication value; The first sum unit is used to perform a sum operation with the sixth multiplier and the measurement noise covariance matrix to obtain the first sum. The target inverse value unit is used to perform the inverse operation on the first sum value to obtain the target inverse value; The Kalman gain data unit is used to perform a multiplication operation between the target inverse value and the fifth multiplier to obtain the Kalman gain data.

[0210] Furthermore, the target tilt data submodule includes: The seventh multiplication unit is used to perform multiplication operations using measurement residual data and Kalman gain data to obtain the seventh multiplication value; The target tilt data output unit is used to perform a summation operation with the seventh multiplier and the intermediate tilt data to obtain the target tilt data.

[0211] Furthermore, the target tilt data includes the target tilt angle and the target tilt angular velocity; the preset tilt threshold includes a preset tilt angle threshold and a preset angular velocity threshold; the tower status information includes a first comparison result and a second comparison result; and the information output module 304 includes: The optimized tilt angle submodule is used to perform a multiplication operation between the target tilt angle, the target tilt angular velocity and the preset observation matrix to obtain the optimized tilt angle. The first comparison result submodule is used to compare the optimized tilt angle with the preset tilt angle threshold and generate the first comparison result. The second comparison result submodule is used to compare the target tilt angular velocity with a preset angular velocity threshold and generate a second comparison result.

[0212] Furthermore, the first comparison result includes first abnormal state information and first normal state information, and the first comparison result submodule includes: The tilt angle comparison unit is used to compare the optimized tilt angle with the preset tilt angle threshold. The first abnormal state information unit is used to determine that the target tower has a steady-state tilt risk when the optimized tilt angle is greater than the preset tilt angle threshold, and to generate the first abnormal state information. The first normal state information unit is used to determine that there is no steady-state tilt risk in the target tower when the optimized tilt angle is less than or equal to the preset tilt angle threshold, and to generate the first normal state information.

[0213] Furthermore, the second comparison result includes second abnormal state information and second normal state information. The second comparison result submodule includes: An angular velocity comparison unit is used to compare the target tilt angular velocity with a preset angular velocity threshold. The second abnormal state information unit is used to determine that the target tower has a transient tilt risk when the target tilt angular velocity is greater than the preset angular velocity threshold, and to generate the second abnormal state information. The second normal state information unit is used to determine that there is no risk of transient tilting of the target tower when the target tilt angular velocity is less than or equal to a preset angular velocity threshold, and to generate the second normal state information.

[0214] Furthermore, it also includes: The feedback module is used to generate early warning information and provide feedback to maintenance personnel when at least one of the first and second abnormal status information exists in the tower status information.

[0215] Furthermore, it also includes: The data conversion module is used to amplify the signal and convert the target tilt data into digital data.

[0216] In this invention, firstly, the initial tilt data of the target tower is acquired, and an initial covariance matrix is ​​set. Secondly, the noise covariance matrix of the Kalman filter is adaptively optimized using a particle swarm optimization algorithm to effectively separate the real tilt signal from complex environmental noise. Then, based on the optimized filter, the initial tilt data is iteratively calculated, enabling real-time prediction of the tilt data and overcoming the lag of manual detection. Finally, by intelligently comparing with a preset tilt threshold, the tilt state of the tower is accurately determined, thereby improving the accuracy and real-time performance of tower tilt monitoring. This solves the technical problem that traditional manual or ground-based instrument measurements are easily affected by environmental interference and cannot be continuously monitored, providing a reliable guarantee for the safe operation of the power system.

[0217] Please see Figure 7 , Figure 7 This is a structural block diagram of a computer device provided in Embodiment 4 of the present invention.

[0218] An electronic device according to an embodiment of the present invention includes: a memory 401 and a processor 402. The memory 401 stores a computer program. When the computer program is executed by the processor 402, the processor 402 performs the power distribution line tower status monitoring method as described in any of the above embodiments.

[0219] Memory 401 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Memory 401 has storage space 403 for program code 413 for performing any of the method steps described above. For example, storage space 403 for program code may include individual program codes 413 for implementing the various steps in the methods described above. This program code may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, CDs, memory cards, or floppy disks. The program code may be compressed, for example, in a suitable form. When run by a computing processing device, this code causes the computing processing device to perform the various steps in the methods described above. This program code may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, CDs, memory cards, or floppy disks. The program code may be compressed, for example, in a suitable form. When these codes are run by a computing processing device, the device causes it to perform the various steps in the power line tower condition monitoring method described above.

[0220] Embodiment 5 of the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the power distribution line tower status monitoring method as described in any of the above embodiments.

[0221] Embodiment 6 of the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer performs the power distribution line tower status monitoring method as described in any of the above embodiments.

[0222] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0223] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0224] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0225] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0226] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0227] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring the condition of power distribution line towers, characterized in that, include: Obtain the initial tilt data of the target tower and set the initial covariance matrix; Based on the initial tilt data, the parameters of the preset Kalman filter are optimized using a swarm intelligence algorithm to obtain the target optimized parameters. Based on the target optimization parameters, the initial tilt data, and the initial covariance matrix, the preset Kalman filter is used to perform state prediction operation to obtain the target tilt data; The target tilt data is compared with a preset tilt threshold, and tower status information is generated based on the comparison results.

2. The method for monitoring the condition of power distribution line towers according to claim 1, characterized in that, The swarm intelligence algorithm includes a particle swarm optimization algorithm. Based on the initial tilt data, the swarm intelligence algorithm is used to optimize the parameters of a preset Kalman filter to obtain the target optimization parameters, including: Initialize the preset Kalman filter parameters to be optimized; Multiple particles are randomly generated, wherein each particle represents a set of parameters to be optimized; The preset Kalman filter is assigned parameter values ​​using each of the parameters to be optimized, and a state prediction operation is performed to obtain multiple prediction tilt data. The initial tilt data and each of the predicted tilt data are input into a preset objective function, and the objective function value corresponding to each particle is output. Each objective function value is compared with the individual's historical best objective function value. If the objective function value is less than the individual's historical best objective function value, then the individual best position of the particle is updated; Each objective function value is compared with the historical best objective function value of the population. If the objective function value is less than the historical best objective function value of the population, then the population best position of the particle is updated. Determine whether the preset maximum number of iterations has been reached; If the preset maximum number of iterations is reached, the particle associated with the optimal position of the population is taken as the optimal particle, and the parameter to be optimized associated with the optimal particle is taken as the target optimization parameter.

3. The method for monitoring the condition of power distribution line towers according to claim 2, characterized in that, Also includes: If the preset maximum number of iterations is not reached, the velocity vector and position vector of each particle are updated using a preset particle update function based on the individual optimal position and the population optimal position. Jump to the step of using the initial tilt data and each of the predicted tilt data as input to a preset objective function, and outputting the objective function value corresponding to each particle.

4. The method for monitoring the condition of power distribution line towers according to claim 1, characterized in that, The process of obtaining target tilt data by performing state prediction operation using the preset Kalman filter based on the target optimization parameters, the initial tilt data, and the initial covariance matrix includes: Using the target optimization parameters, the initial tilt data, the initial covariance matrix, and the preset state transition matrix, the intermediate tilt data and the associated intermediate covariance matrix are determined. Acquire actual tilt data measured by the sensor; Using a preset observation matrix, the intermediate tilt data, the intermediate covariance matrix, the sensor measured tilt data, and the target optimization parameters, the measurement residual data and Kalman gain data are determined. The target tilt data is determined using the intermediate tilt data, the measurement residual data, and the Kalman gain data.

5. The method for monitoring the condition of power distribution line towers according to claim 4, characterized in that, Also includes: The first multiplication value is obtained by multiplying the Kalman gain data with the preset observation matrix; The first difference is obtained by performing a difference operation between the first multiplication value and the preset identity matrix; The target covariance matrix is ​​obtained by multiplying the first difference with the intermediate covariance matrix. Use the target tilt data as the new initial tilt data; Use the target covariance matrix as the new initial covariance matrix; Jump to the step of performing state prediction operation using the preset Kalman filter based on the target optimization parameters, the initial tilt data and the initial covariance matrix to obtain the target tilt data.

6. The method for monitoring the condition of power distribution line towers according to claim 4, characterized in that, The target optimization parameters include the system noise covariance matrix. The step of determining intermediate tilt data and the associated intermediate covariance matrix using the target optimization parameters, the initial tilt data, the initial covariance matrix, and the preset state transition matrix includes: The initial tilt data is multiplied by a preset state transition matrix to obtain intermediate tilt data; The second multiplication value is obtained by multiplying the preset state transition matrix with the initial covariance matrix. The third multiplication value is obtained by multiplying the second multiplication value with the transpose of the preset state transition matrix. The intermediate covariance matrix is ​​obtained by summing the third multiplier with the system noise covariance matrix.

7. The method for monitoring the condition of power distribution line towers according to claim 4, characterized in that, The target optimization parameters also include a measurement noise covariance matrix. The process of determining the measurement residual data and Kalman gain data using a preset observation matrix, the intermediate tilt data, the intermediate covariance matrix, the sensor measured tilt data, and the target optimization parameters includes: The fourth multiplication value is obtained by multiplying the intermediate tilt data with the preset observation matrix; The difference between the measured tilt data from the sensor and the fourth multiplication value is calculated to obtain the measurement residual data. The intermediate covariance matrix is ​​multiplied by the preset observation matrix to obtain the fifth multiplication value; The sixth multiplier is obtained by multiplying the fifth multiplier with the transpose of the preset observation matrix. The first sum is obtained by performing a summation operation between the sixth multiplier and the measurement noise covariance matrix; Invert the first sum to obtain the target inverse value; The Kalman gain data is obtained by multiplying the target inverse value with the fifth multiplier.

8. The method for monitoring the condition of power distribution line towers according to claim 4, characterized in that, The process of determining the target tilt data using the intermediate tilt data, the measurement residual data, and the Kalman gain data includes: The seventh multiplication value is obtained by multiplying the measurement residual data and the Kalman gain data. The target tilt data is obtained by performing a summation operation using the seventh multiplier and the intermediate tilt data.

9. The method for monitoring the condition of power distribution line towers according to claim 1, characterized in that, The target tilt data includes the target tilt angle and the target tilt angular velocity; the preset tilt threshold includes a preset tilt angle threshold and a preset angular velocity threshold; the comparison of the target tilt data with the preset tilt threshold, and the generation of tower status information based on the comparison result, includes: The optimized tilt angle is obtained by multiplying the target tilt angle, the target tilt angular velocity, and a preset observation matrix. Compare the optimized tilt angle with the preset tilt angle threshold to generate a first comparison result; Compare the target tilt angular velocity with the preset angular velocity threshold to generate a second comparison result; The tower status information includes the first comparison result and the second comparison result.

10. The method for monitoring the condition of power distribution line towers according to claim 9, characterized in that, The comparison of the optimized tilt angle with the preset tilt angle threshold generates a first comparison result, including: Compare the optimized tilt angle with the preset tilt angle threshold; When the optimized tilt angle is greater than the preset tilt angle threshold, it is determined that the target tower has a steady-state tilt risk, and a first abnormal state information is generated. When the optimized tilt angle is less than or equal to the preset tilt angle threshold, it is determined that the target tower does not have a steady-state tilt risk, and first normal state information is generated. The first comparison result includes the first abnormal state information and the first normal state information.

11. The method for monitoring the condition of power distribution line towers according to claim 9, characterized in that, The comparison of the target tilt angular velocity with the preset angular velocity threshold to generate a second comparison result includes: Compare the target tilt angular velocity with the preset angular velocity threshold; When the target tilt angular velocity is greater than the preset angular velocity threshold, it is determined that the target tower has a transient tilt risk, and a second abnormal state information is generated; When the target tilt angular velocity is less than or equal to the preset angular velocity threshold, it is determined that the target tower does not have a transient tilt risk, and a second normal state information is generated; The second comparison result includes the second abnormal state information and the second normal state information.

12. The method for monitoring the condition of power distribution line towers according to claim 9, characterized in that, Also includes: When the tower status information contains at least one of the first abnormal status information and the second abnormal status information, an early warning information is generated and fed back to the operation and maintenance personnel.

13. The method for monitoring the condition of power distribution line towers according to any one of claims 1-12, characterized in that, Before comparing the target tilt data with a preset tilt threshold and generating tower status information based on the comparison result, the method further includes: The target tilt data is subjected to signal amplification and digital-to-analog conversion.

14. A power distribution line tower condition monitoring system, characterized in that, include: The data acquisition module is used to acquire the initial tilt data of the target tower and set the initial covariance matrix; The parameter optimization module is used to optimize the parameters of the preset Kalman filter based on the initial tilt data using a swarm intelligence algorithm to obtain the target optimized parameters. The state prediction module is used to perform state prediction operation using the preset Kalman filter based on the target optimization parameters, the initial tilt data and the initial covariance matrix to obtain the target tilt data; The information output module is used to compare the target tilt data with a preset tilt threshold and generate tower status information based on the comparison result.

15. An electronic device, characterized in that, The method includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor causes the processor to perform the steps of the power distribution line tower condition monitoring method as described in any one of claims 1-13.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed, it implements the power distribution line tower status monitoring method as described in any one of claims 1-13.

17. A computer program product, characterized in that, The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, wherein when the program instructions are executed by a computer, the computer performs the power distribution line tower condition monitoring method as described in any one of claims 1-13.

Images