Electric power tower environment state intelligent detection system and method

Abstract

The invention discloses a power tower environment state intelligent detection system and method, and relates to the technical field of power detection. The method comprises the following steps: acquiring the attitude, vibration and micrometeorological data of a tower in real time through a multi-dimensional sensing module; performing Kalman filtering and fast Fourier transform by using an edge processing module, and performing de-noising, interpolation completion and space-time alignment on the original data; extracting a structural feature vector representing the stability of the tower and an environmental load vector representing the external pressure, and carrying out feature fusion; constructing a comprehensive risk index model containing an environmental sensitivity coupling factor, and quantitatively evaluating the nonlinear influence of wind load and icing on the structure failure probability; and automatically triggering the unmanned aerial vehicle to inspect or send a power-off suggestion according to the risk index level. Through deep fusion of edge calculation and multi-source data, the problems that traditional monitoring data is large in noise and lacks environment coupling analysis are effectively solved, and accurate hierarchical dynamic early warning is achieved.

Description

Technical Field

[0001] This invention relates to the field of power detection technology, and in particular to an intelligent detection system and method for the environmental condition of power poles. Background Technology

[0002] Power transmission towers, as critical support structures for power transmission lines, are often located in complex terrains and harsh climates, making them highly susceptible to collapse and line breakage due to strong winds, icing, and geological disasters. However, existing tower monitoring methods primarily rely on periodic manual inspections or single-function sensors. This traditional approach has significant drawbacks: firstly, manual inspections are inefficient and struggle to acquire data in real time during disasters. Due to a lack of edge-side data processing capabilities, raw data transmission is often limited by bandwidth and prone to noise from gusts or electromagnetic interference. Secondly, existing monitoring systems typically analyze environmental parameters and structural attitude separately, lacking a mechanism to couple and evaluate environmental pressures such as wind loads and icing with the tower's own deformation characteristics. This makes it difficult to distinguish between temporary elastic deformation caused by strong winds and permanent deformation caused by structural damage, resulting in high false alarm rates or missed detections of major hazards, and failing to provide maintenance personnel with accurate, tiered early warning decisions. Summary of the Invention

[0003] To address the aforementioned problems in the existing technology, the present invention aims to provide an intelligent monitoring system for the environmental status of power poles, the system comprising: The multi-dimensional sensing module is installed at key nodes of the power pole to collect attitude data, vibration data, and micro-meteorological environment data of the power pole.

[0004] The edge processing module, connected to the multi-dimensional perception module, is used to filter and reduce noise and perform spatiotemporal alignment processing on the collected data, and to perform local anomaly screening.

[0005] The comprehensive assessment module is connected to the edge processing module via a wireless communication network to receive processed data and calculate the comprehensive risk index of the power pole using an environmental condition assessment model.

[0006] The early warning interaction module, connected to the comprehensive assessment module, is used to generate a visualized status report or send an emergency alarm command based on the comprehensive risk index.

[0007] Preferably, the multidimensional sensing module specifically includes: A dual-axis tilt sensor is used to monitor the tilt angle of the power pole relative to the vertical line of gravity.

[0008] A triaxial accelerometer is used to monitor the dynamic vibration frequency and amplitude of the power pole under wind load.

[0009] Micro-weather sensor arrays are used to collect data on ambient temperature, relative humidity, wind speed and direction, and ice thickness.

[0010] Preferably, the edge processing module includes: The data cleaning unit is used to remove outliers and noise from the data collected by the sensors.

[0011] The protocol parsing unit is used to convert heterogeneous data from sensors from different manufacturers into a unified JSON format data stream.

[0012] The local cache unit is used to temporarily store monitoring data when the wireless communication network is interrupted and to resume transmission after the network is restored.

[0013] Preferably, the system further includes a power management module, which includes: Solar photovoltaic panels are installed on the tower body or base of the power pole.

[0014] An energy storage lithium battery pack, connected to the solar photovoltaic panel, is used to store electrical energy.

[0015] A power controller is used to monitor the remaining power of the energy storage lithium battery pack and dynamically adjust the data acquisition frequency of the multi-dimensional sensing module according to the remaining power.

[0016] A method for intelligent detection of the environmental condition of power poles, the method comprising the following steps: Step S1: The attitude data, vibration data and micro-meteorological environment data of the power poles are acquired in real time through the multi-dimensional sensing module to form the original monitoring dataset.

[0017] Step S2: Use the edge processing module to denoise and standardize the original monitoring dataset to generate high-quality time-series feature data.

[0018] Step S3: The time-series feature data is transmitted to the comprehensive evaluation module, the structural feature vector characterizing the tower stability and the environmental load vector characterizing the external pressure are extracted, and feature fusion is performed.

[0019] Step S4: Based on the fused features, calculate the comprehensive risk index of the power poles using a preset pole health algorithm.

[0020] Step S5: Compare the comprehensive risk index with the graded early warning threshold, and execute the corresponding operation and maintenance response strategy through the early warning interaction module.

[0021] Preferably, step S3 includes the following sub-steps: Step S301: Perform long-term trend analysis on the attitude data, extract the permanent deformation component and elastic deformation component of the power pole, and construct the structural feature vector.

[0022] Step S302: Combining wind speed and direction data with icing thickness data, the equivalent wind load and vertical gravity load on the tower are estimated using an aerodynamic model, and the environmental load vector is constructed.

[0023] Step S303: Principal component analysis is used to reduce the dimensionality of the structural feature vector and the environmental load vector and concatenate them to generate a state fusion vector with a unified dimension.

[0024] Preferably, in step S4, the comprehensive risk index is used to quantify the failure probability of the power pole under the coupled action of current environmental load and structural attitude, and its calculation model is as follows: ,in This represents the comprehensive risk index; This indicates the current overall tilt angle offset of the power pole; This indicates the maximum allowable tilt angle threshold according to the specification; This indicates the measured vibration amplitude at the top of the tower; This indicates the allowable vibration amplitude of the tower structure; This represents the dynamic wind load generated by the current measured wind speed; This indicates the measured thickness of the ice layer; This indicates the design bending strength of the power pole tower; This indicates the coefficient of increase in wind resistance due to icing. and These are the preset tilt weight and vibration weight, respectively; This is the environmental sensitivity coupling factor.

[0025] Preferably, in step S2, the denoising and standardization processing of the original monitoring dataset includes: smoothing the attitude data using a Kalman filter algorithm to eliminate instantaneous angle jitter interference caused by gusts; performing a fast Fourier transform on the vibration data to filter out high-frequency noise components caused by electromagnetic interference; checking the timestamps of the micrometeorological environment data and using an interpolation algorithm to fill in missing data points caused by transmission packet loss.

[0026] Preferably, step S5 includes: presetting four levels of graded early warning thresholds corresponding to normal state, attention state, severe warning state and emergency response state in the early warning interaction module; when the comprehensive risk index is in the severe warning state, automatically triggering a drone inspection command to obtain high-definition images of the tower; when the comprehensive risk index is in the emergency response state, immediately sending a power outage suggestion to the maintenance personnel and pushing a repair work order.

[0027] Preferably, prior to step S1, the method further includes a sensor self-calibration step: Under calm and stable weather conditions with no wind and no ice, the zero-point drift data of the dual-axis tilt sensor is collected; the zero-point drift data is stored in the compensation register; when the following step S1 is executed, the data in the compensation register is used to correct the collected attitude data in real time to eliminate the influence of installation error and temperature drift.

[0028] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention constructs a "end-edge-cloud" collaborative monitoring architecture. By performing Kalman filtering, fast Fourier transform, and data interpolation locally through the edge processing module, real-time noise reduction and spatiotemporal alignment of the original data are achieved. Combined with the zero-point drift self-calibration mechanism of the sensor, false signals caused by gusts of wind and electromagnetic interference are effectively eliminated. While reducing the pressure on wireless transmission bandwidth, the accuracy and completeness of monitoring data are significantly improved.

[0029] This invention innovatively proposes a comprehensive risk index assessment model based on environmental sensitivity coupling factors. It deeply integrates the permanent / elastic deformation characteristics that characterize the stability of the power pole structure with the environmental load vector that characterizes external pressure through principal component analysis. The system uses a mathematical model containing exponential terms to quantify the nonlinear amplification effect of wind speed and icing on the probability of structural failure. Based on the calculated risk index, it realizes a four-level dynamic response from routine monitoring to triggering UAV inspections and then to power outage repairs, thereby ensuring accurate assessment and timely handling of the safety status of power poles under complex weather conditions. Attached Figure Description

[0030] Figure 1 This is a schematic diagram of the module structure of the detection system of the present invention.

[0031] Figure 2 This is a schematic diagram of the unit structure of the edge processing module of the present invention.

[0032] Figure 3 This is an exemplary flowchart of the detection method of the present invention.

[0033] Figure 4 This is an exemplary flowchart of the feature fusion process of the present invention. Detailed Implementation

[0034] The present invention will be further described below with reference to specific embodiments.

[0035] like Figure 1 As shown in this embodiment, an intelligent environmental status detection system for power poles is provided. The system includes: The multi-dimensional sensing module, installed at key nodes of power poles, is used to collect attitude data, vibration data, and micro-meteorological environment data of the power poles. In practice, key nodes are typically selected at the top of the tower, the center of the crossarm, and the four corners of the tower base. The multi-dimensional sensing module is encapsulated in an industrial-grade shell with IP67 protection rating and integrates microelectromechanical systems (MEMS) sensors internally. The data acquisition frequency can be set to an adjustable range from 1Hz to 100Hz to adapt to different monitoring needs.

[0036] The multi-dimensional sensing module specifically includes: a dual-axis tilt sensor for monitoring the tilt angle of the power pole relative to the vertical line of gravity; a triaxial accelerometer for monitoring the dynamic vibration frequency and amplitude of the power pole under wind load; and a micro-meteorological sensor group for collecting data on ambient temperature, relative humidity, wind speed and direction, and ice thickness.

[0037] The edge processing module, connected to the multi-dimensional perception module, is used to filter and reduce noise and perform spatiotemporal alignment on the collected data, and to perform local anomaly screening.

[0038] The comprehensive assessment module connects to the edge processing module via a wireless communication network to receive processed data and calculate the comprehensive risk index of power poles using an environmental condition assessment model. The comprehensive assessment module is deployed on a cloud server or in the power bureau's data center.

[0039] The early warning interaction module, connected to the comprehensive assessment module, is used to generate visualized status reports or send emergency alarm commands based on the comprehensive risk index.

[0040] like Figure 2 As shown, the edge processing module in this embodiment includes: a data cleaning unit for removing outliers and noise from sensor-collected data; a protocol parsing unit for converting heterogeneous data from sensors of different manufacturers into a unified JSON format data stream; and a local caching unit for temporarily storing monitoring data when the wireless communication network is interrupted and resuming transmission after the network is restored. In specific implementations, the data cleaning unit uses median filtering or a moving average algorithm. The local caching unit is equipped with an industrial-grade SD card or eMMC storage chip of 32GB or more, supports power-off protection, and ensures that data is not lost during communication interruptions in extreme weather conditions.

[0041] The system also includes a power management module, which comprises: solar photovoltaic panels installed on the tower body or base of the power pole; an energy storage lithium battery pack connected to the solar photovoltaic panels for storing electrical energy; and a power controller for monitoring the remaining power of the energy storage lithium battery pack and dynamically adjusting the data acquisition frequency of the multi-dimensional sensing module based on the remaining power. For example, when the power is sufficient, the acquisition frequency is set to 10Hz; when continuous rain causes the power to drop below 20%, the system automatically enters a low-power mode, reducing the acquisition frequency to once per minute and shutting off power to unnecessary sensors.

[0042] like Figure 3 As shown in this embodiment, a method for intelligent detection of the environmental status of power poles is provided. The method includes the following steps: Step S1: The system acquires the attitude data, vibration data, and micro-meteorological environment data of the power poles in real time through the multi-dimensional sensing module to form the original monitoring dataset. At the data transmission level, in order to ensure real-time performance and reliability, the system uses the MQTT protocol for data publishing and subscription. All data packets are timestamped and device IDs are added, and they are transmitted through SSL / TLS encryption to prevent data from being tampered with.

[0043] Prior to step S1, the method also includes a sensor self-calibration step: Under calm and stable weather conditions with no wind and no icing, zero-point drift data of the dual-axis tilt sensor is collected; the zero-point drift data is stored in the compensation register; in subsequent step S1, the data in the compensation register is used to correct the collected attitude data in real time to eliminate the influence of installation error and temperature drift.

[0044] Step S2 involves using the edge processing module to denoise and standardize the original monitoring dataset, generating high-quality time-series feature data. The denoising and standardization process in Step S2 includes: using a Kalman filter algorithm to smooth the attitude data to eliminate instantaneous angle jitter interference caused by gusts; performing a fast Fourier transform on the vibration data to filter out high-frequency noise components caused by electromagnetic interference; and checking the timestamps of the micro-meteorological environment data and using interpolation algorithms to fill in missing data points caused by transmission packet loss.

[0045] Step S3: Transmit the time-series feature data to the comprehensive evaluation module, extract the structural feature vector characterizing the tower stability and the environmental load vector characterizing the external pressure, and perform feature fusion.

[0046] like Figure 4 As shown, step S3 includes the following sub-steps: Step S301: Perform long-term trend analysis on the attitude data, extract the permanent deformation component and elastic deformation component of the power pole, and construct the structural feature vector.

[0047] Step S302: Combining wind speed and direction data with icing thickness data, the equivalent wind load and vertical gravity load on the tower are estimated using an aerodynamic model to construct an environmental load vector.

[0048] Step S303: Principal component analysis is used to reduce the dimensionality of the structural feature vector and the environmental load vector and splice them together to generate a state fusion vector with a unified dimension.

[0049] Step S4: Based on the fused features, calculate the comprehensive risk index of the power poles using a preset pole health algorithm.

[0050] In step S4, the comprehensive risk index is used to quantify the failure probability of power poles under the coupled effects of current environmental loads and structural attitude. Its calculation model is as follows: ,in This represents the comprehensive risk index; the value range is normalized to 0 to 100. This indicates the current overall tilt angle offset of the power pole tower; This indicates the maximum allowable tilt angle threshold according to the specification; This indicates the measured vibration amplitude at the top of the tower; This indicates the allowable vibration amplitude of the tower structure; This represents the dynamic wind load generated by the current measured wind speed; This indicates the measured thickness of the ice layer; Indicates the design bending strength of the power pole tower; This indicates the coefficient of increase in wind resistance due to icing. and These are the preset tilt weight and vibration weight, respectively; This is the environmental sensitivity coupling factor.

[0051] Step S5: Compare the comprehensive risk index with the graded early warning threshold, and execute the corresponding operation and maintenance response strategy through the early warning interaction module.

[0052] Step S5 includes: presetting tiered warning thresholds for four levels in the early warning interaction module, namely normal state, attention state, severe warning state, and emergency response state; automatically triggering a drone inspection command to obtain high-definition images of the tower when the comprehensive risk index is in the severe warning state; and immediately sending a power outage suggestion and pushing a repair work order to the maintenance personnel when the comprehensive risk index is in the emergency response state.

[0053] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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 this application, and should all be included within the protection scope of this application.

Claims

1. An intelligent monitoring system for the environmental condition of power poles, characterized in that, The system includes: A multi-dimensional sensing module is installed at key nodes of the power pole to collect attitude data, vibration data, and micro-meteorological environment data of the power pole. The edge processing module, connected to the multi-dimensional perception module, is used to filter and reduce noise and perform spatiotemporal alignment processing on the collected data, and to perform local anomaly screening. The comprehensive assessment module is connected to the edge processing module via a wireless communication network to receive processed data and calculate the comprehensive risk index of the power pole using an environmental status assessment model. The early warning interaction module, connected to the comprehensive assessment module, is used to generate a visualized status report or send an emergency alarm command based on the comprehensive risk index.

2. The intelligent environmental condition detection system for power poles according to claim 1, characterized in that, The multi-dimensional sensing module specifically includes: A dual-axis tilt sensor is used to monitor the tilt angle of the power pole relative to the vertical line of gravity; A triaxial accelerometer is used to monitor the dynamic vibration frequency and amplitude of the power pole under wind load. Micro-weather sensor arrays are used to collect data on ambient temperature, relative humidity, wind speed and direction, and ice thickness.

3. The intelligent environmental condition detection system for power poles according to claim 3, characterized in that, The edge processing module includes: The data cleaning unit is used to remove outliers and noise from the data collected by the sensors. The protocol parsing unit is used to convert heterogeneous data from sensors from different manufacturers into a unified JSON format data stream; The local cache unit is used to temporarily store monitoring data when the wireless communication network is interrupted and to resume transmission after the network is restored.

4. The intelligent environmental condition detection system for power poles according to claim 1, characterized in that, The system also includes a power management module, which comprises: Solar photovoltaic panels are installed on the tower body or base of the power pole; An energy storage lithium battery pack, connected to the solar photovoltaic panel, is used to store electrical energy; A power controller is used to monitor the remaining power of the energy storage lithium battery pack and dynamically adjust the data acquisition frequency of the multi-dimensional sensing module according to the remaining power.

5. A method for intelligent detection of the environmental condition of power poles, characterized in that, The method includes the following steps: Step S1: The attitude data, vibration data and micro-meteorological environment data of the power pole are acquired in real time through the multi-dimensional sensing module to form the original monitoring dataset; Step S2: The original monitoring dataset is denoised and standardized using the edge processing module to generate high-quality time-series feature data; Step S3: The time-series feature data is transmitted to the comprehensive evaluation module, the structural feature vector characterizing the tower stability and the environmental load vector characterizing the external pressure are extracted, and feature fusion is performed. Step S4: Based on the fused features, calculate the comprehensive risk index of the power poles using a preset pole health algorithm; Step S5: Compare the comprehensive risk index with the graded early warning threshold, and execute the corresponding operation and maintenance response strategy through the early warning interaction module.

6. The method for intelligent detection of the environmental condition of power poles according to claim 5, characterized in that, Step S3 includes the following sub-steps: Step S301: Perform long-term trend analysis on the attitude data, extract the permanent deformation component and elastic deformation component of the power pole, and construct the structural feature vector; Step S302: Combining wind speed and direction data with icing thickness data, the equivalent wind load and vertical gravity load on the tower are estimated using an aerodynamic model, and the environmental load vector is constructed. Step S303: Principal component analysis is used to reduce the dimensionality of the structural feature vector and the environmental load vector and concatenate them to generate a state fusion vector with a unified dimension.

7. The method for intelligent detection of the environmental condition of power poles according to claim 5, characterized in that, In step S4, the comprehensive risk index is used to quantify the failure probability of the power pole under the coupled action of current environmental load and structural attitude. Its calculation model is as follows: ,in This represents the comprehensive risk index; This indicates the current overall tilt angle offset of the power pole; This indicates the maximum allowable tilt angle threshold according to the specification; This indicates the measured vibration amplitude at the top of the tower; This indicates the allowable vibration amplitude of the tower structure; This represents the dynamic wind load generated by the current measured wind speed; This indicates the measured thickness of the ice layer; This indicates the design bending strength of the power pole tower; This indicates the coefficient of increase in wind resistance due to icing. and These are the preset tilt weight and vibration weight, respectively; This is the environmental sensitivity coupling factor.

8. The method for intelligent detection of the environmental condition of power poles according to claim 5, characterized in that, In step S2, the denoising and standardization processing of the original monitoring dataset includes: using a Kalman filter algorithm to smooth the attitude data to eliminate the interference of instantaneous angle jitter caused by gusts; performing a fast Fourier transform on the vibration data to filter out high-frequency noise components caused by electromagnetic interference; checking the timestamps of the micro-meteorological environment data and using an interpolation algorithm to fill in the missing data points caused by transmission packet loss.

9. The method for intelligent detection of the environmental condition of power poles according to claim 5, characterized in that, Step S5 includes: presetting graded warning thresholds corresponding to four levels in the early warning interaction module: normal state, attention state, severe warning state, and emergency response state; when the comprehensive risk index is in the severe warning state, automatically triggering a drone inspection command to obtain high-definition images of the tower; when the comprehensive risk index is in the emergency response state, immediately sending a power outage suggestion to the maintenance personnel and pushing a repair work order.

10. The method for intelligent detection of the environmental condition of power poles according to claim 5, characterized in that, Prior to step S1, the method further includes a sensor self-calibration step: Under calm and stable weather conditions with no wind and no ice, the zero-point drift data of the dual-axis tilt sensor is collected; the zero-point drift data is stored in the compensation register; when the following step S1 is executed, the data in the compensation register is used to correct the collected attitude data in real time to eliminate the influence of installation error and temperature drift.

Images