De-icing status detection method, device, equipment and medium based on multi-source sensing

By using a multi-source sensing method that combines vibration sensors and vision modules, the de-icing status can be monitored in real time, solving the problems of insufficient data reliability and real-time performance in existing technologies, and achieving efficient and accurate detection of the de-icing status.

CN122740430BActive Publication Date: 2026-11-17CHANGCHUN POWER SUPPLY OF JILIN POWER
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202611196885.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-08-07
Publication Date
2026-11-17
Estimated Expiration
2046-08-07

AI Technical Summary

Technical Problem

Existing de-icing status detection methods suffer from poor data reliability and insufficient real-time performance under vibration environments, and also have visual blind spots, making it difficult to achieve real-time and accurate monitoring of the de-icing status.

Method used

A multi-source sensing method is adopted, which collects triaxial vibration data in real time through vibration sensors, and combines the vision module to collect images after the vibration stops. The robot's main body is used for verification, a feature baseline is established, and the de-icing status is determined.

Benefits of technology

It enables real-time and accurate monitoring of de-icing status under vibration, ensuring the continuity and efficiency of de-icing operations and improving the accuracy of detection results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122740430B_ABST
    Figure CN122740430B_ABST
Patent Text Reader

Abstract

This application relates to the field of power operation robot technology, and provides a method, device, equipment, and medium for de-icing status detection based on multi-source sensing. On the one hand, it analyzes the de-icing status of the de-icing robot body in real time based on the triaxial vibration data collected by vibration sensors. It can realize real-time monitoring of the de-icing status based on the changes in data characteristics of vibration sensors during the de-icing process. Moreover, the vibration sensors are not affected by the vibration environment itself, which can effectively avoid the problem of unreliable data in the vibration environment. Furthermore, the analysis process does not require frequent shutdowns, ensuring the continuity and efficiency of de-icing operations. On the other hand, it uses AI vision to assist in secondary verification of the analysis results, which not only leverages the advantages of visual recognition in being intuitive and accurate, but also makes up for its shortcomings in dynamic environments, further improving the accuracy of the de-icing status detection results.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of power operation robot technology, and in particular to a method, device, equipment and medium for de-icing status detection based on multi-source sensing. Background Technology

[0002] Icing on transmission lines is one of the main safety hazards for power system operation in winter. Icing can lead to increased load on transmission lines, conductor galloping, flashover, and other faults. In severe cases, it can even cause line breaks and tower collapses, directly affecting the safe and stable power supply of the power system and causing huge losses to power production and social life. To solve the problem of icing on transmission lines, the use of transmission line de-icing robot systems has been gradually promoted in engineering. These robots are usually mounted on the transmission line through a specially designed onboard subsystem. They use a vibration module (mainly composed of a motor and an eccentric block) carried on their body to generate high-frequency vibration, which drives the transmission line to vibrate. This causes the ice attached to the conductors to break off due to inertial force, thus achieving the de-icing effect.

[0003] During de-icing operations, real-time and accurate monitoring of ice removal is crucial for ensuring efficiency, avoiding ineffective operations (such as continued vibration even after ice has been removed) and excessive operations (such as excessive vibration damaging the lines). It is also a core requirement for improving the intelligence level of the de-icing system.

[0004] Traditional methods primarily rely on manual remote monitoring of camera feeds to assess de-icing effectiveness. In this approach, the de-icing robot is equipped with a high-definition camera. During or after de-icing, it captures images of the power lines and iced areas, using image recognition algorithms to determine if the ice has been cleared. However, this method suffers from the following significant drawbacks: (1) Poor data reliability: When the core vibration module of the robot is working, the entire robot system and the attached power transmission line are under severe high-frequency vibration. In this dynamic environment, the images acquired by the camera will have severe motion blur, jitter and ghosting, resulting in a sharp decline in image quality. The icing recognition results based on such images are extremely unstable and have a very high misjudgment rate, making them difficult to use as a reliable basis for real-time decision-making.

[0005] (2) Insufficient real-time performance: In order to obtain clear images, existing technologies usually require an intermittent working mode of "stop-take-recognition". That is, the vibration de-icing is stopped first, and the image recognition is carried out after the robot stabilizes. This mode interrupts the continuity of the de-icing process and reduces the overall efficiency of the de-icing operation.

[0006] (3) Blind spots: The field of view of smart cameras is limited and easily blocked by ice, snow and water mist, making it difficult to fully and in real time reflect the changes in the icing status of the entire de-icing area.

[0007] Therefore, it is necessary to propose a new method for real-time and reliable sensing of the de-icing status without interrupting de-icing operations. Summary of the Invention

[0008] In view of the above, it is necessary to provide a de-icing status detection method, device, equipment and medium based on multi-source sensing, in order to solve the problems of low accuracy and insufficient real-time performance of existing de-icing status detection.

[0009] In a first aspect, embodiments of this application provide a de-icing status detection method based on multi-source sensing, applied to a power transmission line icing removal system. The power transmission line icing removal system includes a de-icing robot body, a de-icing robot main unit, a vibration module, a vibration sensor, and a vision module. The de-icing status detection method based on multi-source sensing includes: When the vibration module is started by the main body of the de-icing robot and rotates at a preset constant speed, the vibration sensor is simultaneously activated to collect triaxial vibration data in real time. Using the main body of the de-icing robot, the de-icing status of the robot body is analyzed in real time based on the three-axis vibration data; When the de-icing status indicates that the de-icing robot body is in the ice removal stage, the vision module is used to acquire images after the vibration module stops, and the de-icing robot main unit is used to verify the de-icing status based on the acquired images to obtain a verification result, and a decision is generated based on the verification result. The step of using the main body of the de-icing robot to analyze the de-icing state of the robot body in real time based on the three-axis vibration data includes: Establish characteristic baselines; Based on the characteristic baseline and the triaxial vibration data, the detection results are obtained by determining whether the judgment conditions for each stage are met. The de-icing status of the de-icing robot body is determined based on the detection results.

[0010] Secondly, embodiments of this application also provide a de-icing status detection device based on multi-source sensing, operating in a power transmission line icing removal system. The power transmission line icing removal system includes a de-icing robot body, a de-icing robot main unit, a vibration module, a vibration sensor, and a vision module. The de-icing status detection device based on multi-source sensing includes: The control unit is used to simultaneously activate the vibration sensor to collect triaxial vibration data in real time when the vibration module is started and rotated at a preset constant speed by the main body of the de-icing robot. The analysis unit is used to analyze the de-icing status of the de-icing robot body in real time based on the three-axis vibration data using the main body of the de-icing robot. The decision unit is used to acquire images using the vision module after the vibration module stops when the de-icing status shows that the de-icing robot body is in the ice removal stage, and to verify the de-icing status using the acquired images using the main body of the de-icing robot to obtain a verification result, and to generate a decision based on the verification result. The analysis unit utilizes the main body of the de-icing robot to analyze the de-icing state of the robot body in real time based on the triaxial vibration data, including: Establish characteristic baselines; Based on the characteristic baseline and the triaxial vibration data, the detection results are obtained by determining whether the judgment conditions for each stage are met. The de-icing status of the de-icing robot body is determined based on the detection results.

[0011] Thirdly, embodiments of this application also provide a computer device, the computer device comprising: A memory for storing at least one instruction; and a processor for executing the instructions stored in the memory to implement the de-icing status detection method based on multi-source sensing.

[0012] Fourthly, embodiments of this application also provide a computer-readable storage medium storing at least one instruction, which is executed by a processor in a computer device to implement the de-icing status detection method based on multi-source sensing.

[0013] This application provides a method, apparatus, device, and medium for de-icing status detection based on multi-source sensing. It offers the following advantages: Firstly, by analyzing the de-icing status of the de-icing robot body in real time based on triaxial vibration data collected by vibration sensors, real-time monitoring of the de-icing status can be achieved based on changes in data characteristics of the vibration sensors during the de-icing process. Furthermore, the vibration sensors are unaffected by the vibration environment itself, effectively avoiding the problem of unreliable data in vibration environments. The analysis process does not require frequent shutdowns, ensuring the continuity and efficiency of the de-icing operation. Secondly, by using AI vision-assisted secondary verification of the analysis results, the advantages of intuitive and accurate visual recognition are leveraged while compensating for its shortcomings in dynamic environments, further improving the accuracy of the de-icing status detection results. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a functional block diagram of a preferred embodiment of the transmission line icing removal system of this application; Figure 2 This is a functional block diagram of another preferred embodiment of the transmission line icing removal system of this application; Figure 3 This is a flowchart of a preferred embodiment of the de-icing status detection method based on multi-source sensing in this application; Figure 4 This is the time-displacement curve of the center mass of the vibration source in this application; Figure 5 This is the trend of the amplitude of the vibration source center mass point changing over time during the de-icing operation of this application; Figure 6 This describes the changing trends of various characteristic parameters over time during the de-icing operation of this application; among them, Figure 6 (a) in the figure represents the trend of total mass change over time; Figure 6 (b) in the figure represents the trend of the average amplitude over time; Figure 6 (c) in the figure represents the natural frequency changing over time; Figure 6 In the figure, (d) represents the trend of the damping ratio over time; Figure 7 This application describes the changing trends of ice thickness and amplitude over time during the de-icing operation. Figure 8 This is a schematic block diagram of a de-icing status detection device based on multi-source sensing provided in an embodiment of this application; Figure 9 This is a schematic block diagram of a computer device provided in an embodiment of this application.

[0016] Explanation of reference numerals in the attached figures: 800. De-icing status detection device based on multi-source sensing; 801. Control unit; 802. Analysis unit; 803. Decision unit; 900. Computer equipment; 901. System bus; 902. Processor; 903. Non-volatile storage medium; 904. Internal memory; 905. Network interface; 9031. Operating system; 9032. Computer program. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] It should be understood that, when used in this specification, the terms “comprising” and “including” indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0019] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” are intended to include the plural forms.

[0020] It should also be further understood that the term "and / or" as used in this application specification means any combination of one or more of the associated listed items, as well as all possible combinations, and includes such combinations.

[0021] This application provides a method, apparatus, device, and medium for detecting de-icing status based on multi-source sensing, wherein the method can be applied to a server.

[0022] The execution subject of the multi-source sensing-based de-icing status detection method can be the multi-source sensing-based de-icing status detection device provided in the embodiments of this application, or a computer device that integrates the multi-source sensing-based de-icing status detection device. The multi-source sensing-based de-icing status detection device can be implemented in hardware or software. The computer device can be a server, specifically a control device in the server, or a terminal that has a communication connection with the control device.

[0023] Please see Figure 1 , Figure 1 This is a functional block diagram of a preferred embodiment of the transmission line icing removal system of this application. The transmission line icing removal system includes an icing robot body, an icing robot main unit, a vibration module, a vibration sensor, and a vision module.

[0024] The main unit of the de-icing robot may include a main control unit, a communication module (supporting image and data transmission), a power module, etc., to provide communication capabilities and peripheral drive capabilities, and to complete control algorithms for real-time detection of de-icing effect.

[0025] The vibration module integrates a dedicated vibration motor and a vibration polarization block, and is fixedly deployed at the center of the de-icing robot body as close as possible to the power transmission line to generate vibration.

[0026] The vibration sensor is preferably a triaxial accelerometer, which is fixedly deployed at the center of the de-icing robot body as close as possible to the power transmission line, and is used to collect vibration data such as acceleration, amplitude and frequency on the X, Y and Z axes in real time.

[0027] The vision module is used to capture images of key areas when the robot body is in a stable state, and to perform secondary verification of the de-icing status based on the captured images.

[0028] Please refer to further information. Figure 2 This is a functional block diagram of another preferred embodiment of the transmission line icing removal system of this application. The transmission line icing removal system also includes a clamping and fixing mechanism and a line patrol wheel (including a main line patrol wheel). The vision module includes camera 1 and camera 2. The clamping and fixing mechanism is used to lock the de-icing robot body onto the transmission line during the system's vibration process.

[0029] Please see Figure 3 , Figure 3 This is a flowchart of a preferred embodiment of the de-icing status detection method based on multi-source sensing of this application. Specifically, the de-icing status detection method based on multi-source sensing includes the following steps S110-S130.

[0030] S110, when the vibration module is started by the main unit of the de-icing robot and rotates at a preset constant speed, the vibration sensor is simultaneously started to collect triaxial vibration data in real time.

[0031] In this embodiment, the main control unit of the de-icing robot's main unit can be used to control the motor of the vibration module to start and rotate at a preset constant speed. Simultaneously, the vibration sensor is activated, and the triaxial vibration data is collected and recorded in real time.

[0032] The triaxial vibration data may include acceleration, amplitude, and frequency on the X, Y, and Z axes.

[0033] In this embodiment, feature modeling is required first to facilitate engineering implementation.

[0034] Specifically, after synchronously activating the vibration sensor to collect triaxial vibration data in real time, the method further includes: Calculate the vector sum of the three axial accelerations in the triaxial vibration data to obtain the resultant acceleration; For each sliding time window, the root mean square of the resultant acceleration within the sliding time window is calculated to obtain the short-time average resultant amplitude; The power spectral density is obtained by performing a fast Fourier transform on the resultant acceleration within the sliding time window, and then the power spectral density is normalized to a probability distribution. Calculate the information entropy of the probability distribution within the sliding time window to obtain the spectral entropy; The driving fundamental frequency is obtained by calculating the ratio of the preset constant speed to 60, and the second harmonic frequency is obtained by calculating twice the driving fundamental frequency. Within the sliding time window, the frequency band range is determined based on the preset frequency deviation threshold, the driving fundamental frequency, and the second harmonic frequency. The proportion of energy at the driving frequency is obtained by calculating the sum of energy within the frequency band to the total energy.

[0035] For example: Suppose the vibration sensor collects the following triaxial acceleration data at time t: ; in, This represents the acceleration along the X-axis at time t; This represents the acceleration along the Y-axis at time t; This represents the acceleration along the Z-axis at time t.

[0036] First, define the resultant acceleration a(t) as the vector sum of the accelerations along the X, Y, and Z axes: ; If the vibration module operates at a preset constant speed Rotation generates the fundamental driving frequency. (Unit: Hertz) is: ; To perform real-time analysis, a sliding time window is used, with a window length of L (for example, each sliding time window contains N sampling points, corresponding to time intervals of L and L). (where S is the sampling frequency), and the window slides in steps of S sampling points each time to ensure the real-time performance and smoothness of the analysis.

[0037] Secondly, within each sliding time window, three core features are defined: short-time average summation amplitude, spectral entropy, and the energy percentage of the driving frequency. (1) Short-time average sum amplitude : The short-time average resultant amplitude can be obtained through the envelope or Hilbert transform of the resultant acceleration. In this embodiment, the root mean square value of the resultant acceleration within the window is directly used to characterize the vibration intensity; that is, the short-time average resultant amplitude can be calculated using the following formula: ; Where m represents the sliding time window number; This represents the time corresponding to the k-th sampling point within the window.

[0038] (2) Spectral entropy : The power spectral density is obtained by performing a fast Fourier transform on the a(t) signal within the window. Power spectral density Normalizing to a probability distribution, we obtain the following probability distribution: ; in, This represents the energy percentage of the i-th frequency component; This represents the i-th frequency component; This represents the power spectral density value corresponding to the i-th frequency component; Represents the j-th frequency component The corresponding power spectral density value.

[0039] Furthermore, the spectral entropy is calculated based on the probability distribution. : ; Spectral entropy reflects the degree of energy concentration of a signal in the frequency domain. A smaller spectral entropy value indicates that the energy is more concentrated in a few frequency components (such as the driving fundamental frequency). (and its harmonics); the larger the spectral entropy value, the more dispersed the energy distribution, and the higher the non-stationarity and complexity of the signal.

[0040] (3) Drive frequency energy ratio : In the power spectrum within the calculation window, located at the driving fundamental frequency and its second harmonic frequency (Considering the potential nonlinearity of the actual system) the nearby frequency band (e.g.) The sum of the energies, as a percentage of the total energy, yields the energy percentage of the driving frequency. : ; Among them, This represents the preset frequency deviation threshold.

[0041] S120, using the main body of the de-icing robot, the de-icing status of the de-icing robot body is analyzed in real time based on the three-axis vibration data.

[0042] In this embodiment, the de-icing state includes the initial icing stage, the de-icing process stage, and the icing removal stage.

[0043] In the initial icing stage, the vibration response (such as amplitude and acceleration) is relatively small due to the increased damping and stiffness of the line caused by icing, and its power spectral density is mainly concentrated at the driving fundamental frequency. (Determined by motor speed) Nearby.

[0044] During the de-icing phase, the vibration and fluctuation process is non-stationary. As the ice gradually falls off, the equivalent mass and damping of the system change dynamically, and the vibration response exhibits non-stationary and violently fluctuating characteristics; moreover, multiple non-driving fundamental frequencies appear in the frequency domain. The energy components.

[0045] During the de-icing phase, which involves a significant increase in vibration amplitude followed by a return to stability, the system reverts to a "conductor-robot" system. Damping and stiffness decrease, the vibration response stabilizes, and the amplitude and acceleration increase significantly (e.g., exceeding 1.5 or 2 times the baseline). Furthermore, the frequency domain energy is once again concentrated at the driving fundamental frequency. nearby.

[0046] In this embodiment, the step of using the de-icing robot main unit to analyze the de-icing state of the de-icing robot body in real time based on the triaxial vibration data includes: Establish characteristic baselines; Based on the characteristic baseline and the triaxial vibration data, the detection results are obtained by determining whether the judgment conditions for each stage are met. The de-icing status of the de-icing robot body is determined based on the detection results.

[0047] Specifically, establishing the feature baseline includes: The average short-time average combined amplitude within all sliding time windows during the original icing stage is calculated to obtain the baseline of the average amplitude. Calculate the average spectral entropy within all sliding time windows of the original icing stage to obtain the average spectral entropy baseline; Calculate the average value of the driving frequency energy percentage within all sliding time windows of the original icing stage to obtain the baseline of the average driving frequency energy percentage.

[0048] For example: Suppose in the initial Within each window (corresponding time) If the ice is in its initial icing stage, the characteristic baseline may include: Mean amplitude baseline : ; Average spectral entropy baseline : ; Average drive frequency energy ratio baseline : .

[0049] During the initial icing stage, (Smaller) (relatively large, close to 1).

[0050] in, This indicates that the vibration intensity is stable and has not changed significantly.

[0051] in, (Smaller) and low spectral entropy value indicate that energy is highly concentrated on a few frequencies, and the signal is regular and stable.

[0052] in, (Large, close to 1) The energy proportion of the driving fundamental frequency and its harmonics is very high, indicating that the vibration is almost entirely dominated by the driving source, without any additional interference.

[0053] Specifically, the step of determining whether the judgment conditions for each stage are met based on the characteristic baseline and the triaxial vibration data, and obtaining the detection result, includes: When the difference between the short-time average combined amplitude and the baseline of the average amplitude in each sliding time window is less than or equal to a first preset value, the difference between the spectral entropy and the baseline of the average spectral entropy in each sliding time window is less than or equal to a second preset value, and the difference between the driving frequency energy ratio and the baseline of the average driving frequency energy ratio in each sliding time window is less than or equal to a third preset value, the detection result is determined to meet the judgment condition of reaching the original icing stage.

[0054] Wherein, the first preset value, the second preset value, and the third preset value are all smaller values, to determine , This further determines the criteria for reaching the initial icing stage.

[0055] Specifically, the step of determining whether the judgment conditions for each stage are met based on the characteristic baseline and the triaxial vibration data, and obtaining the detection result, further includes: Get the current sliding time window; When the ratio of the short-time average sum amplitude within the current sliding time window to the baseline of the average amplitude is greater than a first preset threshold, and the variance of the short-time average sum amplitude within a consecutive preset number of sliding time windows before the current sliding time window is greater than a second preset threshold, it is determined that the first condition is met. When the spectral entropy within the current sliding time window is greater than the product of the average spectral entropy baseline and the first growth coefficient, and the proportion of driving frequency energy within the current sliding time window is less than the product of the average driving frequency energy proportion baseline and the preset decrease coefficient, it is determined that the second condition is met. When the first condition and / or the second condition are met, the detection result is determined to be a condition for reaching the de-icing stage.

[0056] For example, when the ice begins to break and detach, the de-icing stage begins. The core characteristics of this stage are non-stationarity and spectral diffusion. A first condition and a second condition are defined as triggering conditions for this stage, and the entry into the de-icing stage is determined when either one is satisfied.

[0057] The first condition includes: the ratio of the short-time average summation amplitude of the current window to the average amplitude baseline exceeds a first preset threshold. Furthermore, the amplitude variance of Q consecutive windows exceeds the second preset threshold. That is: ; Among them, (e.g., 1.2); This is an empirical threshold.

[0058] Therefore, when the first condition is met, it indicates that the amplitude fluctuates violently.

[0059] The second condition includes: the spectral entropy of the current window increases significantly, while the proportion of driving frequency energy decreases significantly, that is: ; Among them, Indicates the first growth coefficient. (e.g., 1.5); This indicates the preset descent coefficient. (e.g., 0.7).

[0060] Therefore, when the second condition is met, it indicates that the spectrum has significantly diffused.

[0061] Specifically, the step of determining whether the judgment conditions for each stage are met based on the characteristic baseline and the triaxial vibration data, and obtaining the detection result, further includes: When the spectral entropy within the consecutive preset number of sliding time windows before the current sliding time window re-converges to the first steady-state threshold, and the proportion of driving frequency energy within the consecutive preset number of sliding time windows before the current sliding time window re-converges to the second steady-state threshold, it is determined that the third condition is satisfied. When the short-time average combined amplitude within the current sliding time window is greater than the product of the average amplitude baseline and the second growth coefficient, and the short-time average combined amplitude within the current sliding time window is greater than the combined amplitude threshold, the fourth condition is determined to be satisfied. When at least the number of consecutive preset sliding time windows before the current sliding time window simultaneously satisfy the third condition and the fourth condition, the detection result is determined to be a condition for reaching the ice removal stage.

[0062] For example, when the ice has mostly fallen off and the system returns to a "wire-robot" system, the vibration response will tend to be stable, but the amplitude will be significantly higher than the original ice-covering stage. The determination of the ice-removal stage needs to meet two conditions: steady state and high amplitude.

[0063] The third condition includes: the spectral entropy of Q consecutive windows. and the proportion of driving frequency energy It converges back to a stable range, that is: ; in, This represents the first steady-state threshold. This represents the second steady-state threshold.

[0064] Therefore, when the third condition is met, it indicates that the vibration signal has returned to a steady state.

[0065] The fourth condition includes: the amplitude of the current window. Significantly higher than baseline And higher than a preset amplitude threshold. (This threshold can be calibrated through offline experiments), that is: ; in, This represents the second growth coefficient.

[0066] Therefore, when the fourth condition is met, it indicates that the amplitude has increased significantly.

[0067] When the third condition and the fourth condition are met simultaneously and continue for at least Q windows, the condition for determining that the ice removal stage has been reached is determined.

[0068] When determining the de-icing stage, in addition to comparing the absolute values ​​of vibration amplitudes, an analysis of the steady-state properties of the vibration signal (such as short-time variance and frequency domain energy concentration) is also introduced. De-icing is only considered complete when the vibration signal not only has a high amplitude but also returns to stability (i.e., the steady-state property exceeds a certain threshold). This avoids misjudgments caused by instantaneous high-amplitude fluctuations due to accidental large ice chunks falling off and impacting the signal.

[0069] In the above embodiments, the changes in data characteristics of vibration sensors during the de-icing process enable real-time "in-service" monitoring of the ice removal process. Vibration sensors are unaffected by the vibration environment itself, and their data characteristics directly reflect the physical characteristics of the de-icing process, thus completely avoiding the unreliability of data in vibration environments found in existing vision solutions. Furthermore, since the primary judgment basis comes from the vibration sensor, the entire de-icing process does not require frequent shutdowns to "see clearly," ensuring the continuity and efficiency of the de-icing operation and supporting continuous, non-invasive de-icing operations.

[0070] S130, when the de-icing status shows that the de-icing robot body is in the ice removal stage, the vision module is used to acquire images after the vibration module is paused, and the de-icing robot main unit is used to verify the de-icing status based on the acquired images to obtain a verification result, and a decision is generated based on the verification result.

[0071] In this embodiment, generating a decision based on the verification result includes: When the verification result indicates that the ice removal stage is underway, the current de-icing operation is stopped using the main control unit of the de-icing robot; or When the verification result is not in the ice removal stage, the main control unit of the de-icing robot is used to return to the original ice stage and perform the next round of de-icing operation.

[0072] For example, when dynamic feature data indicates that the ice has largely dissipated, the main control unit sends a command to pause the vibration module. After the robot body comes to a complete stop, the vision module is activated to take a picture of the original iced area. The main control unit performs image recognition processing on the image to verify whether the ice has been completely removed. If the judgment results are inconsistent, the vibration de-icing process can be restarted or manual intervention can be performed.

[0073] In the above embodiments, the camera of the vision module performs a final confirmation only after the vibration stops. This leverages the advantages of visual recognition, which is intuitive and accurate, while also compensating for the shortcomings of visual recognition in dynamic environments. This achieves complementary advantages between the two sensing methods and constitutes a highly efficient closed-loop detection and control system.

[0074] In this embodiment, the vibration sensor can not only determine the final state of ice accumulation, but also reflect the intermediate process of ice detachment in real time. Through in-depth analysis of vibration data characteristics (such as fluctuation frequency and amplitude change rate), de-icing efficiency can be further evaluated, and de-icing completion time can be predicted, providing richer data support for intelligent operation and maintenance. For example: Please refer to... Figure 4 , is the time-displacement curve of the mass point at the vibration source center of this application. Figure 4 This shows the relationship between key physical quantities and time during the de-icing stage. Please refer to [the documentation / reference]. Figure 5 , represents the trend of amplitude variation of the vibration source center mass point over time during the de-icing operation of this application. Please refer to this as well. Figure 6 , represents the changing trends of various characteristic parameters over time during the de-icing operation of this application, among which, Figure 6 (a) in the figure represents the trend of total mass change over time, which is used to reflect the change of total mass of the system; Figure 6 (b) in the figure represents the trend of the average amplitude over time, which is used to reflect the change in amplitude response; Figure 6 (c) in the figure represents the trend of natural frequency change over time, which is used to reflect the change of the system's natural frequency; Figure 6 In the diagram, (d) represents the trend of the damping ratio over time, used to reflect changes in system damping. Please refer to [the diagram / reference]. Figure 7 This represents the trend of ice thickness and amplitude over time during the de-icing operation in this application.

[0075] In this embodiment, to smooth the processing and avoid noise interference, a finite state machine (FSM) can be used to execute the above decision logic. Specifically, the finite state machine can execute the following steps sequentially: Initial state (S1): The de-icing robot body is mounted and vibration is started. The system learns and establishes a baseline within a certain period of time, and then enters state S2. Iced state (S2): Monitor the characteristic quantity. If the conditions for entering S3 are not met, remain in S2. If the characteristic meets the conditions for the aforementioned "de-icing stage", then proceed to S3. De-icing status (S3): Continuous monitoring. If the characteristics again meet the conditions of the aforementioned "original icing stage" (extremely low probability, meaning de-icing was unsuccessful), the process can jump back to S2. If the conditions of the aforementioned "icing removal stage" are met, the process jumps to S4. Post-de-icing status (S4): Confirmed to have entered the "ice removal stage" and remained stable for a period of time. Vibration pause is then triggered for visual confirmation; Visual confirmation stage (S5): If the visual confirmation is consistent with the above judgment, the current de-icing operation ends; if the visual confirmation is inconsistent with the above judgment, the process jumps back to state S2 and proceeds to the next round of de-icing until the ice is completely removed.

[0076] Through the above mathematical model and state machine design, refined and quantitative real-time monitoring of the de-icing process was achieved.

[0077] As can be seen from the above technical solutions, on the one hand, this invention analyzes the de-icing state of the de-icing robot body in real time based on the triaxial vibration data collected by the vibration sensor. It can realize real-time monitoring of the de-icing state based on the changes in data characteristics of the vibration sensor during the de-icing process. Moreover, the vibration sensor is not affected by the vibration environment itself, which can effectively avoid the problem of unreliable data in the vibration environment. Furthermore, the analysis process does not require frequent shutdowns, ensuring the continuity and efficiency of the de-icing operation. On the other hand, this invention uses AI vision to assist in secondary verification of the analysis results, which not only leverages the advantages of visual recognition in being intuitive and accurate, but also makes up for its shortcomings in dynamic environments, further improving the accuracy of the de-icing state detection results.

[0078] Figure 8 This is a schematic block diagram of a de-icing status detection device based on multi-source sensing provided in an embodiment of this application. Figure 8As shown, corresponding to the above-described de-icing status detection method based on multi-source sensing, this application also provides a de-icing status detection device based on multi-source sensing, which operates in a power transmission line icing removal system. The power transmission line icing removal system includes a de-icing robot body, a de-icing robot main unit, a vibration module, a vibration sensor, and a vision module. This de-icing status detection device based on multi-source sensing includes a unit for executing the above-described de-icing status detection method based on multi-source sensing, and the device can be configured on a server. Specifically, please refer to... Figure 8 The de-icing status detection device 800 based on multi-source sensing includes a control unit 801, an analysis unit 802, and a decision-making unit 803, wherein: The control unit 801 is used to simultaneously start the vibration sensor to collect triaxial vibration data in real time when the vibration module is started and rotated at a preset constant speed by the main body of the de-icing robot. The analysis unit 802 is used to analyze the de-icing status of the de-icing robot body in real time based on the three-axis vibration data using the main body of the de-icing robot. The decision unit 803 is used to, when the de-icing status shows that the de-icing robot body is in the ice removal stage, use the vision module to collect images after the vibration module stops, use the de-icing robot main unit to verify the de-icing status based on the collected images to obtain a verification result, and generate a decision based on the verification result. The analysis unit 802 utilizes the main body of the de-icing robot to analyze the de-icing state of the robot body in real time based on the triaxial vibration data, including: Establish characteristic baselines; Based on the characteristic baseline and the triaxial vibration data, the detection results are obtained by determining whether the judgment conditions for each stage are met. The de-icing status of the de-icing robot body is determined based on the detection results.

[0079] As can be seen from the above technical solutions, on the one hand, this invention analyzes the de-icing state of the de-icing robot body in real time based on the triaxial vibration data collected by the vibration sensor. It can realize real-time monitoring of the de-icing state based on the changes in data characteristics of the vibration sensor during the de-icing process. Moreover, the vibration sensor is not affected by the vibration environment itself, which can effectively avoid the problem of unreliable data in the vibration environment. Furthermore, the analysis process does not require frequent shutdowns, ensuring the continuity and efficiency of the de-icing operation. On the other hand, this invention uses AI vision to assist in secondary verification of the analysis results, which not only leverages the advantages of visual recognition in being intuitive and accurate, but also makes up for its shortcomings in dynamic environments, further improving the accuracy of the de-icing state detection results.

[0080] The aforementioned de-icing status detection device based on multi-source sensing can be implemented as a computer program, which can, for example... Figure 9 It runs on the computer device shown.

[0081] Please see Figure 9 , Figure 9 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 900 may be a server, specifically a control device within the server, or a terminal having a communication connection with the control device.

[0082] See Figure 9 The computer device 900 includes a processor 902, a memory, and a network interface 905 connected via a system bus 901. The memory may include a non-volatile storage medium 903 and internal memory 904.

[0083] The non-volatile storage medium 903 may store an operating system 9031 and a computer program 9032. The computer program 9032 includes program instructions that, when executed, cause the processor 902 to perform a de-icing status detection method based on multi-source sensing.

[0084] The processor 902 provides computing and control capabilities to support the operation of the entire computer device 900.

[0085] The internal memory 904 provides an environment for the operation of the computer program 9032 in the non-volatile storage medium 903. When the computer program 9032 is executed by the processor 902, the processor 902 can execute a de-icing status detection method based on multi-source sensing.

[0086] This network interface 905 is used for network communication with other devices. Those skilled in the art will understand that... Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 900 to which the present application is applied. The specific computer device 900 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0087] The processor 902 is used to run a computer program 9032 stored in the memory to perform the following steps: When the vibration module is started by the main body of the de-icing robot and rotates at a preset constant speed, the vibration sensor is simultaneously activated to collect triaxial vibration data in real time. Using the main body of the de-icing robot, the de-icing status of the robot body is analyzed in real time based on the three-axis vibration data; When the de-icing status indicates that the de-icing robot body is in the ice removal stage, the vision module is used to acquire images after the vibration module stops, and the de-icing robot main unit is used to verify the de-icing status based on the acquired images to obtain a verification result, and a decision is generated based on the verification result. The step of using the main body of the de-icing robot to analyze the de-icing state of the robot body in real time based on the three-axis vibration data includes: Establish characteristic baselines; Based on the characteristic baseline and the triaxial vibration data, the detection results are obtained by determining whether the judgment conditions for each stage are met. The de-icing status of the de-icing robot body is determined based on the detection results.

[0088] It should be understood that in the embodiments of this application, the processor 902 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0089] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0090] Therefore, this application also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When executed by a processor, the program instructions cause the processor to perform the following steps: When the vibration module is started by the main body of the de-icing robot and rotates at a preset constant speed, the vibration sensor is simultaneously activated to collect triaxial vibration data in real time. Using the main body of the de-icing robot, the de-icing status of the robot body is analyzed in real time based on the three-axis vibration data; When the de-icing status indicates that the de-icing robot body is in the ice removal stage, the vision module is used to acquire images after the vibration module stops, and the de-icing robot main unit is used to verify the de-icing status based on the acquired images to obtain a verification result, and a decision is generated based on the verification result. The step of using the main body of the de-icing robot to analyze the de-icing state of the robot body in real time based on the three-axis vibration data includes: Establish characteristic baselines; Based on the characteristic baseline and the triaxial vibration data, the detection results are obtained by determining whether the judgment conditions for each stage are met. The de-icing status of the de-icing robot body is determined based on the detection results.

[0091] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0092] It should be noted that all data involved in this application was legally obtained.

[0093] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0095] The steps in the methods of this application embodiment can be adjusted, merged, or deleted according to actual needs. The units in the apparatus of this application embodiment can be merged, divided, or deleted according to actual needs. Furthermore, the functional units in the various embodiments of this application 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.

[0096] 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 storage medium. Based on this understanding, the technical solution of this application, 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, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0097] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A de-icing status detection method based on multi-source sensing, characterized in that, An ice removal system for power transmission lines is used, comprising an ice removal robot body, an ice removal robot main unit, a vibration module, a vibration sensor, and a vision module. The de-icing status detection method based on multi-source sensing includes: When the vibration module is started by the main body of the de-icing robot and rotates at a preset constant speed, the vibration sensor is simultaneously activated to collect triaxial vibration data in real time. Using the main body of the de-icing robot, the de-icing status of the robot body is analyzed in real time based on the three-axis vibration data; When the de-icing status indicates that the de-icing robot body is in the ice removal stage, the vision module is used to acquire images after the vibration module stops, and the de-icing robot main unit is used to verify the de-icing status based on the acquired images to obtain a verification result, and a decision is generated based on the verification result. The step of using the main body of the de-icing robot to analyze the de-icing state of the robot body in real time based on the three-axis vibration data includes: Establish characteristic baselines; Based on the characteristic baseline and the triaxial vibration data, the detection results are obtained by determining whether the judgment conditions for each stage are met. The de-icing status of the de-icing robot body is determined based on the detection results; Specifically, after the vibration sensor is synchronously activated to collect triaxial vibration data in real time, the vector sum of the accelerations of the three axes in the triaxial vibration data is calculated to obtain the resultant acceleration. For each sliding time window, the root mean square of the resultant acceleration within the sliding time window is calculated to obtain the short-time average resultant amplitude. The resultant acceleration within the sliding time window is subjected to a fast Fourier transform to obtain the power spectral density, and the power spectral density is normalized to a probability distribution. The information entropy of the probability distribution within the sliding time window is calculated to obtain the spectral entropy. The ratio of the preset constant rotational speed to 60 is calculated to obtain the driving fundamental frequency, and twice the driving fundamental frequency is calculated to obtain the second harmonic frequency. Within the sliding time window, the frequency band is determined according to the preset frequency deviation threshold, the driving fundamental frequency, and the second harmonic frequency. The proportion of the sum of energy within the frequency band to the total energy is calculated to obtain the driving frequency energy proportion. The establishment of the characteristic baseline includes: calculating the average short-time average combined amplitude within all sliding time windows of the original icing stage to obtain the average amplitude baseline; calculating the average spectral entropy within all sliding time windows of the original icing stage to obtain the average spectral entropy baseline; and calculating the average driving frequency energy percentage within all sliding time windows of the original icing stage to obtain the average driving frequency energy percentage baseline. The step of detecting whether the judgment conditions for each stage are met based on the characteristic baseline and the triaxial vibration data, and obtaining the detection result, includes: when the difference between the short-time average combined amplitude and the average amplitude baseline in each currently passed sliding time window is less than or equal to a first preset value, the difference between the spectral entropy and the average spectral entropy baseline in each sliding time window is less than or equal to a second preset value, and the difference between the driving frequency energy ratio and the average driving frequency energy ratio baseline in each sliding time window is less than or equal to a third preset value, the detection result is determined to be the judgment condition for reaching the original icing stage.

2. The de-icing status detection method based on multi-source sensing as described in claim 1, characterized in that, The step of determining whether the judgment conditions for each stage are met based on the characteristic baseline and the triaxial vibration data, and obtaining the detection result, further includes: Get the current sliding time window; When the ratio of the short-time average sum amplitude within the current sliding time window to the baseline of the average amplitude is greater than a first preset threshold, and the variance of the short-time average sum amplitude within a consecutive preset number of sliding time windows before the current sliding time window is greater than a second preset threshold, it is determined that the first condition is met. When the spectral entropy within the current sliding time window is greater than the product of the average spectral entropy baseline and the first growth coefficient, and the proportion of driving frequency energy within the current sliding time window is less than the product of the average driving frequency energy proportion baseline and the preset decrease coefficient, it is determined that the second condition is met. When the first condition and / or the second condition are met, the detection result is determined to be a condition for reaching the de-icing stage.

3. The de-icing status detection method based on multi-source sensing as described in claim 2, characterized in that, The step of determining whether the judgment conditions for each stage are met based on the characteristic baseline and the triaxial vibration data, and obtaining the detection result, further includes: When the spectral entropy within the consecutive preset number of sliding time windows before the current sliding time window re-converges to the first steady-state threshold, and the proportion of driving frequency energy within the consecutive preset number of sliding time windows before the current sliding time window re-converges to the second steady-state threshold, it is determined that the third condition is satisfied. When the short-time average combined amplitude within the current sliding time window is greater than the product of the average amplitude baseline and the second growth coefficient, and the short-time average combined amplitude within the current sliding time window is greater than the combined amplitude threshold, the fourth condition is determined to be satisfied. When at least the number of consecutive preset sliding time windows before the current sliding time window simultaneously satisfy the third condition and the fourth condition, the detection result is determined to be a condition for reaching the ice removal stage.

4. The de-icing status detection method based on multi-source sensing as described in claim 1, characterized in that, The step of generating a decision based on the verification result includes: When the verification result indicates that the ice removal stage is underway, the current ice removal operation is stopped using the main control unit of the de-icing robot. When the verification result is not in the ice removal stage, the main control unit of the de-icing robot is used to return to the original ice stage and perform the next round of de-icing operation.

5. A de-icing status detection device based on multi-source sensing, characterized in that, An ice removal system for power transmission lines is used, which includes an ice removal robot body, an ice removal robot main unit, a vibration module, a vibration sensor, and a vision module. The de-icing status detection device based on multi-source sensing includes: The control unit is used to simultaneously activate the vibration sensor to collect triaxial vibration data in real time when the vibration module is started and rotated at a preset constant speed by the main body of the de-icing robot. The analysis unit is used to analyze the de-icing status of the de-icing robot body in real time based on the three-axis vibration data using the main body of the de-icing robot. The decision unit is used to acquire images using the vision module after the vibration module stops when the de-icing status shows that the de-icing robot body is in the ice removal stage, and to verify the de-icing status using the acquired images using the main body of the de-icing robot to obtain a verification result, and to generate a decision based on the verification result. The analysis unit utilizes the main body of the de-icing robot to analyze the de-icing state of the robot body in real time based on the triaxial vibration data, including: Establish characteristic baselines; Based on the characteristic baseline and the triaxial vibration data, the detection results are obtained by determining whether the judgment conditions for each stage are met. The de-icing status of the de-icing robot body is determined based on the detection results; Specifically, after the vibration sensor is synchronously activated to collect triaxial vibration data in real time, the vector sum of the accelerations of the three axes in the triaxial vibration data is calculated to obtain the resultant acceleration. For each sliding time window, the root mean square of the resultant acceleration within the sliding time window is calculated to obtain the short-time average resultant amplitude. The resultant acceleration within the sliding time window is subjected to a fast Fourier transform to obtain the power spectral density, and the power spectral density is normalized to a probability distribution. The information entropy of the probability distribution within the sliding time window is calculated to obtain the spectral entropy. The ratio of the preset constant rotational speed to 60 is calculated to obtain the driving fundamental frequency, and twice the driving fundamental frequency is calculated to obtain the second harmonic frequency. Within the sliding time window, the frequency band is determined according to the preset frequency deviation threshold, the driving fundamental frequency, and the second harmonic frequency. The proportion of the sum of energy within the frequency band to the total energy is calculated to obtain the driving frequency energy proportion. The establishment of the characteristic baseline includes: calculating the average short-time average combined amplitude within all sliding time windows of the original icing stage to obtain the average amplitude baseline; calculating the average spectral entropy within all sliding time windows of the original icing stage to obtain the average spectral entropy baseline; and calculating the average driving frequency energy percentage within all sliding time windows of the original icing stage to obtain the average driving frequency energy percentage baseline. The step of detecting whether the judgment conditions for each stage are met based on the characteristic baseline and the triaxial vibration data, and obtaining the detection result, includes: when the difference between the short-time average combined amplitude and the average amplitude baseline in each currently passed sliding time window is less than or equal to a first preset value, the difference between the spectral entropy and the average spectral entropy baseline in each sliding time window is less than or equal to a second preset value, and the difference between the driving frequency energy ratio and the average driving frequency energy ratio baseline in each sliding time window is less than or equal to a third preset value, the detection result is determined to be the judgment condition for reaching the original icing stage.

6. A computer device, characterized in that, The computer device includes: A memory for storing at least one instruction; and a processor for executing the instructions stored in the memory to implement the de-icing status detection method based on multi-source sensing as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, which is executed by a processor in a computer device to implement the de-icing status detection method based on multi-source sensing as described in any one of claims 1 to 4.

Citation Information

Patent Citations

  • Power transmission line fault early warning method and device, storage medium and electronic equipment

    CN118334838A

  • Motion control method and equipment for deicing robot of ultra-high voltage transmission line

    CN119658695A

  • Power transmission line icing galloping on-site monitoring and early warning method based on edge calculation

    CN121617200A