A fault self-detection method for a power transmission line pan-tilt mechanism and related device

Abstract

A fault self-detection method and related equipment for PTZ cameras used in power transmission lines are disclosed, relating to the field of PTZ camera fault detection. Implementing this method, the detection system standardizes the vibration, rotational speed, temperature, and current parameters of the PTZ camera to obtain vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values, which are then mapped to a four-dimensional feature space, thus comprehensively characterizing the working status of the PTZ camera. The detection system calculates the Mahalanobis distance between the feature mapping points and the healthy operating area, accurately determining whether the PTZ camera is in an abnormal state. When an abnormality is detected, the detection system can automatically identify the fault type based on the position of the feature mapping points in the four-dimensional feature space and extract corresponding compensation parameter combinations for adaptive adjustment. This self-diagnosis and self-compensation method can promptly take self-protection measures in the event of communication interruption or delayed response, improving the reliability and autonomy of the PTZ camera.

Description

Technical Field

[0001] This application relates to the field of gimbal camera fault detection, and in particular to a fault self-detection method and related equipment for a power transmission line gimbal camera. Background Technology

[0002] With the rapid development of power systems, the safe and stable operation of transmission lines is of great significance to ensuring the reliability of power systems. As a key piece of equipment for transmission line monitoring, the performance of pan-tilt-zoom (PTZ) cameras directly affects the quality and efficiency of transmission line inspections. PTZ cameras are mainly used to carry various monitoring equipment, such as infrared thermal imagers and visible light cameras, achieving omnidirectional monitoring of transmission lines through precise rotation control. Under complex natural environments and long-term operating conditions, PTZ cameras are susceptible to factors such as wind, temperature, and lightning, which may lead to mechanical wear, component aging, and other problems, thus affecting the normal operating performance of the PTZ camera.

[0003] In related technologies, the fault detection method for transmission line PTZ cameras mainly involves installing multiple sensors on the PTZ camera. By transmitting the real-time collected operating parameters of the PTZ camera to a monitoring center for analysis, remote diagnosis of PTZ camera faults can be achieved. When a fault is detected, the monitoring center can promptly notify maintenance personnel to carry out repairs, preventing the fault from escalating.

[0004] However, this method of fault detection for power transmission line PTZ cameras has a significant drawback: because the fault diagnosis and handling process relies on the analysis and manual intervention of the monitoring center, the PTZ camera cannot take timely self-protection measures in the event of communication interruption or untimely response, which can easily cause secondary damage to the equipment. Summary of the Invention

[0005] This application provides a fault self-detection method and related equipment for a PTZ camera on a power transmission line, which can take timely self-protection measures in the event of communication interruption or untimely response, thereby improving the reliability and autonomy of the PTZ camera.

[0006] Firstly, this application provides a fault self-detection method for a transmission line pan-tilt unit, applied to a detection system. The method includes: collecting vibration parameters, rotational speed parameters, temperature parameters, and current parameters of the pan-tilt unit. The vibration parameters characterize the mechanical motion state of the pan-tilt unit, the rotational speed parameters characterize the rotational state, the temperature parameters characterize the thermal load state, and the current parameters characterize the energy consumption state. The vibration parameters, rotational speed parameters, temperature parameters, and current parameters are standardized to obtain vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values. All vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values ​​are located within... Within a preset range, vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values ​​are mapped to a preset four-dimensional characteristic space to obtain characteristic mapping points. A healthy operating area, determined based on historical health operation data of the gimbal, is pre-calibrated within this four-dimensional characteristic space. The Mahalanobis distance between the characteristic mapping points and the healthy operating area is calculated; this distance is used to eliminate the dimensional influence between different characteristic parameters. When the Mahalanobis distance exceeds a preset distance threshold, the fault type is determined based on the position of the characteristic mapping point in the four-dimensional characteristic space. The corresponding compensation parameter combination is extracted from a preset compensation strategy library based on the fault type. This library stores different compensation parameter combinations corresponding to different fault types.

[0007] By adopting the above technical solution, the detection system standardizes the vibration, rotational speed, temperature, and current parameters of the gimbal to obtain vibration, rotational speed, temperature, and current characteristic values, which are then mapped to a four-dimensional feature space, thus comprehensively characterizing the gimbal's working status. The detection system calculates the Mahalanobis distance between the feature mapping point and the healthy working area, accurately determining whether the gimbal is in an abnormal state. When an abnormality is detected, the system automatically identifies the fault type based on the position of the feature mapping point in the four-dimensional feature space and adaptively adjusts by extracting corresponding compensation parameter combinations from a preset compensation strategy library. This self-diagnostic and self-compensating method avoids reliance on manual intervention and can take timely self-protection measures in the event of communication interruption or delayed response, effectively preventing secondary damage to the equipment and improving the reliability and autonomy of the gimbal.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, the vibration parameters, rotational speed parameters, temperature parameters, and current parameters are standardized to obtain vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values, all of which are within a preset interval. Specifically, this includes: performing sample range normalization on the vibration parameters, rotational speed parameters, temperature parameters, and current parameters to obtain normalized vibration parameters, normalized rotational speed parameters, normalized temperature parameters, and normalized current parameters. The sample range normalization includes calculating the difference between the maximum and minimum values ​​and normalizing using the difference between the maximum and minimum values ​​as the denominator; and after filtering and smoothing the normalized vibration parameters, normalized rotational speed parameters, normalized temperature parameters, and normalized current parameters, mapping them to a preset interval to obtain vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values.

[0009] By adopting the above technical solution, the detection system uses sample range normalization for various parameters. Normalization is performed by calculating the difference between the maximum and minimum values ​​as the denominator, unifying parameters of different dimensions into the same range. Simultaneously, the detection system filters and smooths the normalized vibration, rotational speed, temperature, and current parameters, effectively suppressing measurement noise and interference, and improving the stability and reliability of the characteristic values. This standardized processing method makes different types of parameters comparable, providing accurate feature representations for subsequent fault diagnosis in the four-dimensional feature space, and enhancing the accuracy of fault detection.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, the Mahalanobis distance between the feature mapping point and the healthy working area is calculated. The Mahalanobis distance is used to eliminate the dimensional influence between different feature parameters. Specifically, this includes: constructing a covariance matrix based on historical health operation data; calculating the difference vector between the feature mapping point and the center point of the healthy working area; substituting the covariance matrix and the difference vector into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance; the Mahalanobis distance calculation formula is: Where D represents the Mahalanobis distance, S represents the covariance matrix, and X represents the difference vector. The matrix representing the transpose of the difference vector. This represents the inverse of the covariance matrix.

[0011] By adopting the above technical solution, the Mahalanobis distance calculation formula comprehensively considers the covariance matrix and the difference vector. The covariance matrix can reflect the correlation and fluctuation degree between various characteristic parameters, eliminating the mutual influence between different characteristic parameters, while the difference vector can accurately describe the deviation of the current working state from the center of the healthy working state. This Mahalanobis distance calculation method provides a rigorous measurement standard for the fault detection of gimbals.

[0012] In conjunction with some embodiments of the first aspect, in some embodiments, a covariance matrix is ​​constructed based on historical health operation data, specifically including: selecting several sets of data samples from the historical health operation data, the data samples including historical vibration characteristic values, historical speed characteristic values, historical temperature characteristic values, and historical current characteristic values; calculating the historical average vibration value, historical average speed value, historical average temperature value, and historical average current value based on the several sets of data samples; calculating the covariance between each pair of the historical average vibration value, historical average speed value, historical average temperature value, and historical average current value; and filling the covariance into a preset four-dimensional matrix to obtain the covariance matrix.

[0013] By employing the above technical solution, multiple data samples are selected from historical health operation data, the historical average values ​​of each dimension's feature values ​​are calculated, and the covariance between each pair of these historical average values ​​is calculated to construct a complete covariance matrix. This construction method fully utilizes the statistical characteristics and correlation information contained in historical data, enabling the covariance matrix to accurately reflect the intrinsic relationship between each feature parameter, providing a reliable mathematical basis for Mahalanobis distance calculation, thereby improving the accuracy and reliability of fault detection.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, before mapping vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values ​​to a preset four-dimensional feature space to obtain feature mapping points, and before pre-marking a healthy working area determined based on the historical healthy operation data of the gimbal in the four-dimensional feature space, the method further includes: determining the statistical mean and statistical standard deviation corresponding to each of the vibration dimension, rotational speed dimension, temperature dimension, and current dimension based on the historical healthy operation data; substituting the statistical mean and statistical standard deviation into preset upper limit calculation formulas and lower limit calculation formulas respectively to obtain the upper limit and lower limit of the standard range corresponding to each of the vibration dimension, rotational speed dimension, temperature dimension, and current dimension; and constructing a healthy working area in the four-dimensional feature space according to the upper limit and lower limit of the standard range corresponding to each of the vibration dimension, rotational speed dimension, temperature dimension, and current dimension.

[0015] By adopting the above technical solution, the detection system determines the statistical mean and standard deviation of each dimension based on historical healthy operation data, and determines the upper and lower limits of the standard range through a preset upper / lower limit calculation formula to construct a healthy working area. This method of constructing a healthy working area based on statistical characteristics can accurately characterize the parameter distribution range when the gimbal is working normally, constructing a healthy working area in a four-dimensional feature space. This provides a clear judgment boundary for subsequent fault detection, enabling the detection system to accurately identify abnormal states and improving the sensitivity and reliability of fault detection.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, after determining the fault type based on the position of the feature mapping point in the four-dimensional feature space when the Mahalanobis distance is greater than a preset distance threshold, and extracting the corresponding compensation parameter combination from the preset compensation strategy library based on the fault type, the method further includes: after applying the compensation parameter combination to the control system of the gimbal, continuously collecting the operating data of the gimbal; based on the operating data, recalculating the feature mapping point in the four-dimensional feature space to redetermine the Mahalanobis distance between the feature mapping point and the healthy working area; if the Mahalanobis distance is stable within the preset distance threshold within a preset time period, the compensation is determined to be successful; if the Mahalanobis distance is still greater than the preset distance threshold within the preset time period, the compensation is determined to be unsuccessful and an alarm is triggered.

[0017] By adopting the above technical solution, after applying the compensation parameter combination, the detection system continuously monitors the gimbal's operating data and recalculates the Mahalanobis distance between the feature mapping point and the healthy working area, achieving real-time evaluation of the compensation effect. This closed-loop compensation effect evaluation mechanism ensures the effectiveness of fault compensation and improves the operational reliability of the gimbal.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, the fault type is determined based on the position of the feature mapping point in the four-dimensional feature space, specifically including: based on historical fault operation data, pre-marking multiple fault feature regions in the four-dimensional feature space, each fault feature region corresponding to a known fault type; calculating the Euclidean distance between the feature mapping point and the center point of each fault feature region; selecting the target known fault type corresponding to the target fault feature region with the smallest Euclidean distance as the fault type of the gimbal.

[0019] By adopting the above technical solution, the detection system pre-labels multiple fault feature regions in a four-dimensional feature space and calculates the Euclidean distance between the feature mapping point and the center point of each fault feature region. The target fault feature region with the smallest Euclidean distance is selected as the known fault type of the gimbal. This fault type identification method fully utilizes the feature distribution information in historical fault operation data, enabling rapid and accurate identification of the current fault type, providing a reliable basis for selecting appropriate compensation strategies.

[0020] In a second aspect, embodiments of this application provide a detection system comprising: one or more processors and a memory; the memory is coupled to the one or more processors and is used to store computer program code, the computer program code including computer instructions, wherein the one or more processors invoke the computer instructions to cause the detection system to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, embodiments of this application provide a computer program product containing instructions that, when the computer program product is run on a detection system, cause the detection system to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a detection system, cause the detection system to perform the method described in the first aspect and any possible implementation thereof.

[0023] Understandably, the detection system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of this application. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By adopting the above technical solution, the detection system standardizes the vibration, rotational speed, temperature, and current parameters of the gimbal to obtain vibration, rotational speed, temperature, and current characteristic values, which are then mapped to a four-dimensional feature space, thus comprehensively characterizing the gimbal's working status. The detection system calculates the Mahalanobis distance between the feature mapping point and the healthy working area, accurately determining whether the gimbal is in an abnormal state. When an abnormality is detected, the detection system can automatically identify the fault type based on the position of the feature mapping point in the four-dimensional feature space and adaptively adjust by extracting the corresponding compensation parameter combination from the preset compensation strategy library. This self-diagnosis and self-compensation method avoids reliance on manual intervention and can take timely self-protection measures in the event of communication interruption or delayed response, effectively preventing secondary damage to the equipment and improving the reliability and autonomy of the gimbal.

[0025] 2. By adopting the above technical solution, the Mahalanobis distance calculation formula comprehensively considers the covariance matrix and the difference vector. The covariance matrix can reflect the correlation and fluctuation degree between various characteristic parameters, eliminating the mutual influence between different characteristic parameters. The difference vector can accurately describe the deviation of the current working state from the center of the healthy working state. This Mahalanobis distance calculation method provides a rigorous measurement standard for fault detection of gimbals.

[0026] 3. By adopting the above technical solution, the detection system determines the statistical mean and statistical standard deviation of each dimension based on historical healthy operation data, and determines the upper and lower limits of the standard range through a preset upper / lower limit calculation formula to construct a healthy working area. This method of constructing a healthy working area based on statistical characteristics can accurately characterize the parameter distribution range when the gimbal is working normally, constructing a healthy working area in a four-dimensional feature space. This provides a clear judgment boundary for subsequent fault detection, enabling the detection system to accurately identify abnormal states and improving the sensitivity and reliability of fault detection. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating a fault self-detection method for a power transmission line PTZ camera in an embodiment of this application. Figure 2 This is another flowchart illustrating the fault self-detection method for a power transmission line PTZ camera in this application embodiment; Figure 3 This is a schematic diagram of the physical device structure of the detection system in the embodiments of this application. Detailed Implementation

[0028] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0030] The following describes the process of the method provided in this implementation. Please refer to [link / reference]. Figure 1 This is a flowchart illustrating a fault self-detection method for a power transmission line PTZ camera in an embodiment of this application.

[0031] S101. Collect vibration parameters, rotation speed parameters, temperature parameters and current parameters of the gimbal. Vibration parameters are used to characterize the mechanical motion state of the gimbal, rotation speed parameters are used to characterize the rotation state of the gimbal, temperature parameters are used to characterize the thermal load state of the gimbal, and current parameters are used to characterize the energy consumption state of the gimbal. Among them, the pan-tilt unit is a mechanical device used to carry monitoring equipment and achieve precise rotation control; vibration parameters represent the oscillation characteristics generated when the mechanical parts of the pan-tilt unit move, including amplitude and frequency; rotation speed parameters represent the angular velocity and rotation frequency of the pan-tilt unit's rotating mechanism; temperature parameters represent the operating temperature data of key parts of the pan-tilt unit; current parameters represent the power supply current data of the pan-tilt unit's drive motor and control circuit; mechanical motion state refers to the dynamic characteristics of the mechanical parts of the pan-tilt unit during operation; rotation state refers to the motion characteristics of the pan-tilt unit when it rotates horizontally or vertically; thermal load state refers to the heat generation of each component of the pan-tilt unit during operation; and energy consumption state refers to the power consumption of the pan-tilt unit during operation.

[0032] Specifically, the detection system uses vibration sensors to collect vibration signals from the gimbal, obtaining vibration parameters reflecting its mechanical motion state; it uses speed sensors to collect angular velocity signals from the gimbal's rotating mechanism, obtaining speed parameters reflecting its rotation state; it uses temperature sensors to collect temperature signals from key parts of the gimbal, obtaining temperature parameters reflecting its thermal load state; and it uses current sensors to collect the gimbal's operating current signals, obtaining current parameters reflecting its energy consumption state. The sampling frequency of these parameters is set according to actual monitoring needs, typically multiple samples per second to ensure data continuity.

[0033] S102. Standardize the vibration parameters, rotational speed parameters, temperature parameters, and current parameters respectively to obtain vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values. All vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values ​​are within a preset range. Standardization refers to the mathematical process of unifying parameters with different dimensions to the same scale; eigenvalues ​​represent the standardized parameters obtained after standardization; and preset intervals represent the predetermined range of parameter values, usually [0, 1] or [-1, 1].

[0034] Specifically, the following methods can be used to standardize the vibration parameters, rotational speed parameters, temperature parameters, and current parameters to obtain their characteristic values: (1) Piecewise linear mapping method: Set the working safety range for each type of parameter (e.g., vibration 0-10mm, rotation speed 0-300rpm, temperature 20-80℃, current 0-5A), and linearly map each type of parameter to the [0,1] interval according to its working safety range. Cut off the values ​​that exceed the working safety range. Advantages: Maintains the linear relationship of parameters in a physical sense; (2) Adaptive standardization based on statistical characteristics: Collect historical data of each type of parameter under healthy conditions, calculate the statistical mean (μ) and standard deviation (σ) of each type of parameter, map the data to the interval [-1, 1] using (x-μ) / 3σ, and truncate values ​​that exceed [-1, 1]. Advantages: It takes into account the actual distribution characteristics of the parameters; (3) Layered standardization process: Vibration parameters: standardized based on the amplitude spectrum after FFT analysis; Speed ​​parameters: based on the rated speed and standardized by ratio; Temperature parameters: relative temperature rise standardized based on ambient temperature; Current parameters: based on the ratio normalization of rated current; Advantages: Appropriate standardization methods are used for physical properties with different parameters; (4) Fuzzy interval mapping method: Define the ideal interval, warning interval and danger interval for each type of parameter, map the ideal interval to [0.3, 0.7], map the warning interval to [0, 0.3) and (0.7, 0.9], and map the danger interval to (0.9, 1]; Advantages: It introduces safety levels, facilitating fault early warning... Other parameters, such as vibration parameters, rotational speed parameters, temperature parameters, and current parameters, are standardized to obtain vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values, which will not be listed here.

[0035] Optionally, under normal circumstances, the vibration parameters, rotational speed parameters, temperature parameters, and current parameters are standardized to obtain vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values. The vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values ​​all falling within a preset interval can be achieved in the following ways, without limitation: Sample range normalization is performed on the vibration parameters, rotational speed parameters, temperature parameters, and current parameters respectively to obtain normalized vibration parameters, normalized rotational speed parameters, normalized temperature parameters, and normalized current parameters. Sample range normalization includes calculating the difference between the maximum and minimum values ​​and normalizing using the difference between the maximum and minimum values ​​as the denominator; after filtering and smoothing the normalized vibration parameters, normalized rotational speed parameters, normalized temperature parameters, and normalized current parameters respectively, they are mapped to the preset interval to obtain vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values.

[0036] The sample range represents the difference between the maximum and minimum values ​​of each parameter class; normalization represents the mathematical transformation process that maps data to a specific interval; filtering and smoothing represent signal processing methods that remove noise and interference from the data.

[0037] Specifically, firstly, the detection system performs sample range normalization on various parameters. This is done by calculating the difference between the maximum and minimum values ​​of each parameter and using this difference as the denominator to normalize the original data, resulting in normalized parameters. Next, the system applies a digital filtering algorithm to smooth the normalized parameters, removing measurement noise and random interference. Finally, the system maps the processed parameters to a pre-defined standard range, obtaining standardized feature values ​​suitable for comparative analysis. This entire process ensures the comparability between different types of parameters.

[0038] S103. Map the vibration characteristic value, rotation speed characteristic value, temperature characteristic value and current characteristic value to the preset four-dimensional characteristic space to obtain the characteristic mapping point. The four-dimensional characteristic space is pre-calibrated with a healthy working area determined based on the historical healthy operation data of the gimbal. Among them, the four-dimensional feature space refers to the mathematical space established using four types of parameters as coordinate axes; the feature mapping point represents the point obtained by mapping the vibration feature value, rotation speed feature value, temperature feature value and current feature value as coordinates into the four-dimensional feature space; the healthy working area represents the area range in the four-dimensional feature space that represents the normal working state.

[0039] Specifically, the detection system maps vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values ​​as coordinate values ​​into a four-dimensional feature space to obtain the feature mapping points of the current working state. Based on the statistical analysis results of historical health operation data, a healthy working area representing the normal working state is pre-defined in the four-dimensional feature space. The range and shape of this healthy working area reflect the distribution characteristics of each parameter and their interrelationships during normal operation of the gimbal.

[0040] S104. Calculate the Mahalanobis distance between the feature mapping point and the healthy working area. The Mahalanobis distance is used to eliminate the dimensional influence between different feature parameters. Mahalanobis distance is a statistical distance measurement method that takes into account the correlation of data; dimensional influence refers to the incomparability between different physical quantities due to different units of measurement.

[0041] Specifically, firstly, the detection system constructs a covariance matrix based on historical health operation data. This covariance matrix reflects the correlation and fluctuation patterns among the four characteristic parameters. Then, the system calculates the coordinate difference between the feature mapping point and the center point of the healthy working area, obtaining a difference vector representing the degree of deviation. Finally, the system substitutes the covariance matrix and the difference vector into the Mahalanobis distance calculation formula, obtaining the Mahalanobis distance through matrix operations. The Mahalanobis distance comprehensively considers the correlation between parameters and can accurately reflect the degree of abnormality in the current working state.

[0042] Optionally, in general, the Mahalanobis distance between the feature mapping point and the healthy working area is calculated. The Mahalanobis distance is used to eliminate the influence of different dimensions between feature parameters. This can be achieved in the following ways, without limitation: Construct a covariance matrix based on historical health operation data; calculate the difference vector between the feature mapping point and the center point of the healthy working area; substitute the covariance matrix and the difference vector into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance. The Mahalanobis distance calculation formula is: Where D represents the Mahalanobis distance, S represents the covariance matrix, and X represents the difference vector. The matrix representing the transpose of the difference vector. This represents the inverse of the covariance matrix.

[0043] Among them, the covariance matrix represents the statistical matrix describing the correlation between multiple random variables; the center point of the healthy working region represents the geometric center of the healthy working region in the four-dimensional feature space; the difference vector represents the difference between the coordinates of the feature mapping point and the center point of the healthy working region; the transpose matrix represents the new matrix obtained by interchanging the rows and columns of the original matrix; and the inverse matrix represents the matrix obtained by multiplying the original matrix to obtain the identity matrix.

[0044] The following concrete example illustrates the calculation of Mahalanobis distance: Suppose the feature values ​​collected during the monitoring of the gimbal are: Vibration characteristic value: 0.8; Rotational speed characteristic value: 0.6; Temperature characteristic value: 0.7; Current characteristic value: 0.5; The center point of the healthy work area is: Vibration characteristic value: 0.5; Rotational speed characteristic value: 0.5; Temperature characteristic value: 0.5; Current characteristic value: 0.5; (1) Calculate the difference vector X between the feature mapping point and the center point of the healthy working area: X = [Current Value - Center Value] = = ; (2) Assume that the covariance matrix S is calculated using historical health operation data: S= ; (3) Calculate the inverse of the covariance matrix. : = ; (4) Calculate the Mahalanobis distance Substituting the numerical values ​​into the calculation, D≈0.42.

[0045] Optionally, in general, the covariance matrix can be constructed based on historical health operation data in the following ways, without limitation: Select several sets of data samples from the historical health operation data, including historical vibration characteristic values, historical speed characteristic values, historical temperature characteristic values, and historical current characteristic values; calculate the historical average vibration value, historical average speed value, historical average temperature value, and historical average current value based on the several sets of data samples; calculate the covariance between each pair of the historical average vibration value, historical average speed value, historical average temperature value, and historical average current value; fill the covariance into a preset four-dimensional matrix to obtain the covariance matrix.

[0046] The following uses actual data to demonstrate the calculation process of the covariance matrix, assuming that 5 sets of data samples (standardized data) of gimbals were selected from historical healthy operation data:

[0047] Table 1 Data Sample Table The calculation steps are as follows: 1. Calculate the average value of each type of parameter: μ1 (vibration) = (0.5 + 0.7 + 0.4 + 0.6 + 0.5) / 5 = 0.54; μ2 (rotational speed) = (0.6 + 0.8 + 0.5 + 0.7 + 0.6) / 5 = 0.64; μ3 (temperature) = (0.4 + 0.5 + 0.3 + 0.4 + 0.3) / 5 = 0.38; μ4 (current) = (0.3 + 0.4 + 0.3 + 0.4 + 0.3) / 5 = 0.34; 2. Calculate each element of the covariance matrix: Covariance formula: Cov(X, Y) = E[(X - μx) × (Y - μy)] / n Taking the calculation of the covariance between vibration and rotational speed as an example: Cov(X1,X2)=[(0.5-0.54)×(0.6-0.64)+(0.7-0.54)×(0.8-0.64)+(0.4-0.54) ×(0.5-0.64)+(0.6-0.54)×(0.7-0.64)+(0.5-0.54)×(0.6-0.64)] / 5=0.0152; 3. Obtain the complete covariance matrix:

[0048] Table 2 Covariance Matrix Table 4. Standardized covariance matrix (converted to correlation coefficient matrix):

[0049] Table 3 Standard Covariance Matrix S105. When the Mahalanobis distance is greater than the preset distance threshold, the fault type is determined according to the position of the feature mapping point in the four-dimensional feature space. The corresponding compensation parameter combination is extracted from the preset compensation strategy library according to the fault type. The preset compensation strategy library stores different compensation parameter combinations corresponding to different fault types.

[0050] Among them, the preset distance threshold represents the critical value of Mahalanobis distance used to determine whether a fault has occurred; the fault type represents the classification of various abnormal working states that the gimbal may experience; the preset compensation strategy library represents the database that stores the compensation schemes corresponding to various faults; and the compensation parameter combination represents the set of multiple parameters used for fault correction.

[0051] Specifically, the detection system compares the feature mapping points with various fault feature regions pre-marked in a four-dimensional feature space. By calculating the Euclidean distance, it finds the closest fault feature region to determine the current fault type of the gimbal. Based on the determined fault type, the detection system retrieves the corresponding compensation parameter combination from a preset compensation strategy library. These compensation parameters include control parameters for adjusting the control algorithm, drive parameters for optimizing motor performance, and mechanical parameters for improving mechanical characteristics. The detection system applies the compensation parameter combination to the gimbal's control system to achieve automatic fault compensation. The entire process requires no manual intervention and can quickly respond to and handle abnormal situations.

[0052] Optionally, under normal circumstances, determining the fault type based on the position of the feature mapping point in the four-dimensional feature space can be achieved in the following ways, without limitation: Based on historical fault operation data, multiple fault feature regions are pre-marked in the four-dimensional feature space, each fault feature region corresponding to a known fault type; the Euclidean distance between the feature mapping point and the center point of each fault feature region is calculated; the target known fault type corresponding to the target fault feature region with the smallest Euclidean distance is selected as the fault type of the gimbal.

[0053] By adopting the above technical solution, the detection system standardizes the vibration, rotational speed, temperature, and current parameters of the gimbal to obtain vibration, rotational speed, temperature, and current characteristic values, which are then mapped to a four-dimensional feature space, thus comprehensively characterizing the gimbal's working status. The detection system calculates the Mahalanobis distance between the feature mapping point and the healthy working area, accurately determining whether the gimbal is in an abnormal state. When an abnormality is detected, the system automatically identifies the fault type based on the position of the feature mapping point in the four-dimensional feature space and adaptively adjusts by extracting corresponding compensation parameter combinations from a preset compensation strategy library. This self-diagnostic and self-compensating method avoids reliance on manual intervention and can take timely self-protection measures in the event of communication interruption or delayed response, effectively preventing secondary damage to the equipment and improving the reliability and autonomy of the gimbal.

[0054] The following provides a more detailed description of the process of the method provided in this implementation. Please refer to [link / reference]. Figure 2 This is another flowchart illustrating the fault self-detection method for a power transmission line PTZ camera in this application embodiment.

[0055] S201. Collect the vibration parameters, rotation speed parameters, temperature parameters, and current parameters of the gimbal. The vibration parameters are used to characterize the mechanical motion state of the gimbal, the rotation speed parameters are used to characterize the rotation state of the gimbal, the temperature parameters are used to characterize the thermal load state of the gimbal, and the current parameters are used to characterize the energy consumption state of the gimbal.

[0056] For details, please refer to step S101, which will not be repeated here.

[0057] S202. Standardize the vibration parameters, rotational speed parameters, temperature parameters, and current parameters respectively to obtain vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values. All vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values ​​are within the preset range.

[0058] For details, please refer to step S102, which will not be repeated here.

[0059] S203. Based on historical health operation data, determine the statistical mean and statistical standard deviation for each of the vibration, speed, temperature and current dimensions.

[0060] Among them, historical health operation data represents the set of historical parameter records collected by the gimbal under normal working conditions; statistical mean represents the arithmetic mean of various parameters, used to reflect the central tendency of various parameters; statistical standard deviation represents the dispersion of various parameters, used to reflect the fluctuation range of various parameters.

[0061] Specifically, the detection system performs statistical calculations on the historical health operation data for each dimension to obtain the statistical mean and statistical standard deviation for each dimension, providing a mathematical basis for subsequently determining the boundaries of the healthy working area.

[0062] S204. Substitute the statistical mean and statistical standard deviation into the preset upper limit calculation formula and lower limit calculation formula respectively to obtain the upper limit and lower limit of the standard range corresponding to the vibration dimension, rotational speed dimension, temperature dimension and current dimension.

[0063] The upper limit formula represents the mathematical expression used to calculate the maximum allowable value of a parameter, which is usually the mean plus a multiple of the standard deviation; the lower limit formula represents the mathematical expression used to calculate the minimum allowable value of a parameter, which is usually the mean minus a multiple of the standard deviation; the upper limit of the standard range represents the maximum allowable value of each dimension parameter; and the lower limit of the standard range represents the minimum allowable value of each dimension parameter.

[0064] Specifically, the detection system substitutes the statistical mean and standard deviation of each dimension into pre-set upper and lower limit calculation formulas, typically using the mean ± 3 times the standard deviation, to obtain the upper and lower limits of the standard range for each dimension parameter. These upper and lower limits define the reasonable range of variation for each parameter when the gimbal is operating normally.

[0065] S205. Based on the upper and lower limits of the standard ranges corresponding to the vibration, rotational speed, temperature and current dimensions, construct a healthy working area in the four-dimensional feature space.

[0066] Specifically, the detection system constructs a closed geometric region in a four-dimensional feature space, using the upper and lower limits of the standard ranges in each dimension as boundaries. This geometric region may be a hypercube or a hyperellipsoid, and all points within it represent the normal operating state of the gimbal. This healthy operating region provides a basis for subsequent fault detection; when the feature mapping point falls outside the healthy operating region, it indicates that the gimbal may be malfunctioning.

[0067] S206. The vibration characteristic value, rotation speed characteristic value, temperature characteristic value and current characteristic value are mapped to the preset four-dimensional characteristic space to obtain the characteristic mapping point. The four-dimensional characteristic space is pre-calibrated with a healthy working area determined based on the historical healthy operation data of the gimbal.

[0068] For details, please refer to step S103, which will not be repeated here.

[0069] S207. Calculate the Mahalanobis distance between the feature mapping point and the healthy working area. The Mahalanobis distance is used to eliminate the dimensional influence between different feature parameters.

[0070] For details, please refer to step S104, which will not be repeated here.

[0071] S208. When the Mahalanobis distance is greater than the preset distance threshold, the fault type is determined according to the position of the feature mapping point in the four-dimensional feature space. The corresponding compensation parameter combination is extracted from the preset compensation strategy library according to the fault type. The preset compensation strategy library stores different compensation parameter combinations corresponding to different fault types.

[0072] For details, please refer to step S105, which will not be repeated here.

[0073] S209. After applying the compensation parameter combination to the control system of the gimbal, continuously collect the operating data of the gimbal.

[0074] The control system refers to the hardware and software system responsible for the motion control of the gimbal; the operating data refers to the various parameter data collected in real time after the gimbal is compensated, including data such as vibration, speed, temperature and current.

[0075] Specifically, the detection system continuously collects operational data from the gimbal using various sensors, including vibration parameters, rotational speed parameters, temperature parameters, and current parameters for each sampling cycle. The sampling frequency is typically set to multiple times per second to ensure timely detection of changes in the gimbal's status.

[0076] S210. Based on the running data, recalculate the feature mapping points in the four-dimensional feature space to redetermine the Mahalanobis distance between the feature mapping points and the healthy working area.

[0077] Among them, the feature mapping point represents the point in the four-dimensional feature space that represents the current working state; the healthy working region represents the region in the four-dimensional feature space that represents the normal working state; and the Mahalanobis distance represents a statistical distance metric that takes into account the correlation of parameters.

[0078] Specifically, the detection system first standardizes the newly acquired operational data to obtain new feature values; then it maps these feature values ​​to a four-dimensional feature space to obtain new feature mapping points; finally, it recalculates the Mahalanobis distance between these feature mapping points and the healthy operating area. This process uses the same calculation method as the initial fault detection to ensure consistency in the evaluation criteria.

[0079] S211. If the Mahalanobis distance remains stable within the preset distance threshold within the preset time period, the compensation is deemed successful.

[0080] Among them, the preset duration represents the observation period used to judge the stability of the compensation effect; stability means that the Mahalanobis distance is maintained within a certain range; and successful compensation means that the fault state is effectively corrected.

[0081] Specifically, the detection system continuously monitors the Mahalanobis distance within a preset time period (usually several minutes to several hours). If the Mahalanobis distance remains within the preset distance threshold and there is no significant fluctuation, the compensation parameter combination is deemed effective, the gimbal has returned to normal working status, and the compensation process is successfully completed.

[0082] S212. If the Mahalanobis distance is still greater than the preset distance threshold within the preset time period, the compensation is deemed to have failed and an alarm is triggered.

[0083] Among them, "compensation failure" means that the combination of compensation parameters failed to effectively correct the fault state; "triggered alarm" means that the action of issuing a fault alarm is to send fault information to the monitoring center or maintenance personnel, including fault type, fault severity and other information.

[0084] Specifically, the detection system continuously evaluates the Mahalanobis distance within a preset time period. If the Mahalanobis distance fails to decrease to within a preset distance threshold or fluctuates repeatedly, the current compensation parameter combination is deemed invalid, and compensation fails. In this case, the detection system will automatically trigger an alarm mechanism, sending an alarm message containing fault information to the monitoring center to remind maintenance personnel to perform manual intervention and repair.

[0085] The detection system in the embodiments of this invention is described below from the perspective of hardware processing. Please refer to [link / reference]. Figure 3 This is a schematic diagram of the physical device structure of the detection system in this application embodiment.

[0086] It should be noted that, Figure 3 The structure of the detection system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0087] like Figure 3 As shown, the detection system includes a CPU 301, which can perform various appropriate actions and processes according to a program stored in the read-only memory ROM 302 or a program loaded from the storage section 308 into the random access memory RAM 303, such as performing the methods described in the above embodiments. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0088] The following components are connected to I / O interface 305: input section 306 including audio input devices, push-button switches, etc.; output section 307 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 308 including a hard disk, etc.; and communication section 309 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0089] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by CPU 301, it performs the various functions defined in the present invention.

[0090] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0091] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0092] Specifically, the detection system in this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements the fault self-detection method for the PTZ camera of the power transmission line provided in the above embodiment.

[0093] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the detection system described in the above embodiments; or it may exist independently and not assembled into the detection system. The storage medium carries one or more computer programs that, when executed by a processor of the detection system, cause the detection system to implement the fault self-detection method for a transmission line PTZ camera provided in the above embodiments.

[0094] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. 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 scope of the technical solutions of the embodiments of this application.

[0095] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0096] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A fault self-detection method for a pan-tilt unit used in power transmission lines, characterized in that, The method, applied to a detection system, includes: collecting vibration parameters, rotational speed parameters, temperature parameters, and current parameters of a gimbal; the vibration parameters characterize the mechanical motion state of the gimbal, the rotational speed parameters characterize the rotational state of the gimbal, the temperature parameters characterize the thermal load state of the gimbal, and the current parameters characterize the energy consumption state of the gimbal; standardizing the vibration parameters, rotational speed parameters, temperature parameters, and current parameters respectively to obtain vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values, all of which are within a preset range; and then setting the vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values ​​within a preset range. The eigenvalues ​​are mapped to a preset four-dimensional feature space to obtain feature mapping points. A healthy operating area, determined based on the historical healthy operating data of the gimbal, is pre-calibrated in this four-dimensional feature space. The Mahalanobis distance between the feature mapping points and the healthy operating area is calculated. This Mahalanobis distance is used to eliminate the dimensional influence between different feature parameters. When the Mahalanobis distance is greater than a preset distance threshold, the fault type is determined based on the position of the feature mapping point in the four-dimensional feature space. The corresponding compensation parameter combination is extracted from a preset compensation strategy library based on the fault type. This library stores different compensation parameter combinations corresponding to different fault types. The compensation parameters include control parameters for adjusting the control algorithm, drive parameters for optimizing motor performance, and mechanical parameters for improving mechanical characteristics.

2. The method according to claim 1, characterized in that, The standardization process for the vibration parameters, rotational speed parameters, temperature parameters, and current parameters to obtain vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values, all of which are located within a preset interval, specifically includes: performing sample range normalization on the vibration parameters, rotational speed parameters, temperature parameters, and current parameters to obtain normalized vibration parameters, normalized rotational speed parameters, normalized temperature parameters, and normalized current parameters. The sample range normalization process includes calculating the difference between the maximum and minimum values ​​and using the difference between the maximum and minimum values ​​as the denominator for normalization; and then filtering and smoothing the normalized vibration parameters, normalized rotational speed parameters, normalized temperature parameters, and normalized current parameters, mapping them to the preset interval to obtain the vibration characteristic values, rotational speed characteristic values, temperature characteristic values, and current characteristic values.

3. The method according to claim 1, characterized in that, The calculation of the Mahalanobis distance between the feature mapping point and the healthy working area, whereby the Mahalanobis distance is used to eliminate the dimensional influence between different feature parameters, specifically includes: constructing a covariance matrix based on the historical health operation data; calculating the difference vector between the feature mapping point and the center point of the healthy working area; and substituting the covariance matrix and the difference vector into the Mahalanobis distance calculation formula to obtain the Mahalanobis distance. The Mahalanobis distance calculation formula is as follows: Where D represents the Mahalanobis distance, S represents the covariance matrix, and X represents the difference vector. The matrix representing the transpose of the difference vector. The inverse matrix of the covariance matrix is ​​represented by .

4. The method according to claim 3, characterized in that, The step of constructing a covariance matrix based on the historical health operation data specifically includes: selecting several sets of data samples from the historical health operation data, wherein the data samples include historical vibration characteristic values, historical speed characteristic values, historical temperature characteristic values, and historical current characteristic values; calculating the historical average vibration value, historical average speed value, historical average temperature value, and historical average current value based on the several sets of data samples; calculating the covariance between each pair of the historical average vibration value, historical average speed value, historical average temperature value, and historical average current value; and filling the covariance into a preset four-dimensional matrix to obtain the covariance matrix.

5. The method according to claim 1, characterized in that, Before the step of mapping the vibration characteristic value, the rotational speed characteristic value, the temperature characteristic value, and the current characteristic value to a preset four-dimensional feature space to obtain feature mapping points, wherein a healthy working area determined based on the historical healthy operation data of the gimbal is pre-calibrated in the four-dimensional feature space, the method further includes: determining the statistical mean and statistical standard deviation corresponding to each of the vibration dimension, rotational speed dimension, temperature dimension, and current dimension based on the historical healthy operation data; substituting the statistical mean and statistical standard deviation into preset upper limit calculation formulas and lower limit calculation formulas respectively to obtain the upper limit and lower limit of the standard range corresponding to each of the vibration dimension, rotational speed dimension, temperature dimension, and current dimension; and constructing a healthy working area in the four-dimensional feature space according to the upper limit and lower limit of the standard range corresponding to each of the vibration dimension, rotational speed dimension, temperature dimension, and current dimension.

6. The method according to claim 1, characterized in that, After the steps of determining the fault type based on the position of the feature mapping point in the four-dimensional feature space when the Mahalanobis distance is greater than a preset distance threshold, and extracting the corresponding compensation parameter combination from a preset compensation strategy library based on the fault type, the method further includes: continuously collecting the operating data of the gimbal after applying the compensation parameter combination to the control system of the gimbal; recalculating the feature mapping point in the four-dimensional feature space based on the operating data to redetermine the Mahalanobis distance between the feature mapping point and the healthy working area; if the Mahalanobis distance is stable within the preset distance threshold within a preset time period, the compensation is deemed successful; if the Mahalanobis distance is still greater than the preset distance threshold within the preset time period, the compensation is deemed to have failed and an alarm is triggered.

7. The method according to claim 1, characterized in that, The step of determining the fault type based on the position of the feature mapping point in the four-dimensional feature space specifically includes: pre-marking multiple fault feature regions in the four-dimensional feature space based on historical fault operation data, with each fault feature region corresponding to a known fault type; calculating the Euclidean distance between the feature mapping point and the center point of each fault feature region; and selecting the target known fault type corresponding to the target fault feature region with the smallest Euclidean distance as the fault type of the gimbal.

8. A detection system, characterized in that, The detection system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the detection system to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on the detection system, the detection system performs the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on the detection system, the detection system performs the method as described in any one of claims 1-7.

Images