External damage detection method and system for power line

Abstract

The invention relates to the technical field of power line detection, and discloses a power line external damage detection method and system, and the method comprises the steps: setting a detection node on a power line; continuously collecting electric power parameters of each detection node; compensating and correcting the electric power parameter of each detection node; establishing a time sequence of electric power parameters for each detection node; obtaining a component sequence of the electric power parameters of each detection node based on the time sequence; calculating a nonlinear characteristic index of each time sequence and a nonlinear characteristic index of each component sequence; performing preliminary external damage detection on each detection node based on the nonlinear characteristic index of the time sequence; performing supplementary external damage detection on each detection node based on the nonlinear characteristic index of the component sequence; according to the invention, the accuracy and early warning capability of external damage detection of the power line can be improved, and the method has good environmental adaptability.

Description

Technical Field

[0001] The present invention relates to the technical field of power line detection, and in particular to a method and system for detecting external damage of a power line. Background Art

[0002] Power lines are widely distributed and exposed to complex natural and social environments for a long time, making them vulnerable to external damage. Traditional power line external damage detection mainly relies on manual inspection or visual inspection, which is inefficient and easy to miss. In the current power industry, there are also some detection methods that use power parameters to determine whether external damage has occurred, which improves the efficiency and accuracy of detection, but there are still some technical defects.

[0003] Existing detection technologies have major problems in data accuracy. Power lines are widely distributed. In some remote areas or harsh environments, sensors are easily disturbed, resulting in errors in the collected data, making the external damage detection judgment at risk of misjudgment, and reducing the reliability of detection. At present, most detection methods are not accurate enough for early identification of external damage of power lines. Existing detection methods often focus on detection after a fault occurs or when obvious abnormalities occur, and cannot detect potential external damage risks in a timely manner. For example, when a power line is slightly damaged in the early stage, the power parameters of the line may only change slightly. It is difficult for existing technologies to capture these subtle changes and issue early warnings, increasing the risk of power supply interruptions. Existing technologies lack in-depth mining of power parameters. However, most current detection systems only perform simple statistics and analysis on data, and cannot make full use of the nonlinear characteristics in the data. In addition, different environmental factors and power system status also have a certain impact on external damage detection, and existing technologies also lack consideration in this regard.

[0004] For example, a Chinese patent with authorization announcement number CN114019318B discloses an indicator for locating faults in power lines in sections, including a walking device that automatically walks on a cable and automatically avoids cable hooks. The walking device is provided with walking wheels, which drive the indicator to move on the cable, and the walking wheels can automatically rise and fall to avoid cable hooks. The walking device is provided with a scanning device for detecting the degree of aging of the cable, and the scanning device is provided with a scanning rod and a scanning motor. The scanning motor drives the scanning rod to scan the cable and analyze the degree of aging of the cable. The walking device is also provided with a touch device for detecting whether the cable is damaged or leaking electricity. The detection wheel is closely attached to the cable through the arrangement of multiple connecting rods. The arrangement of this invention can work on various cables and automatically avoid obstacles on the cable, thereby improving the efficiency of troubleshooting and reducing the danger of troubleshooting.

[0005] For example, the patent application with the authorization announcement number CN212845650U discloses a high-voltage transmission and transformation line detection device, which includes a base and an upper cover. The front and rear sides of the base are fixedly connected to the locking plate by bolts, and the outer wall of the other side of the locking plate is fixedly connected to the upper cover by bolts. The upper side wall of the base and the bottom side wall of the upper cover are both bonded with insulating pads, and a signal antenna is installed inside the signal slot. A limit slot is provided on the upper outer wall of the upper cover, and a photovoltaic panel is embedded inside the limit slot. This technical solution solves the current high-voltage transmission and transformation line detection problem, which mostly uses manual observation or drones to observe whether the line is damaged, and the current high-voltage transmission and transformation line detection device, which can only detect the damaged regional lines and cannot immediately find the line fault during daily inspections.

[0006] The above technical solutions all have the problems raised by the background technology: it is difficult to detect slight wire damage and the environmental adaptability is insufficient.

[0007] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgement or any form of suggestion that the information constitutes the prior art already known to ordinary technicians in this field. Summary of the invention

[0008] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide a method and system for detecting external failure of a power line, thereby improving the accuracy of external failure detection of the power line and the early warning capability.

[0009] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0010] In one aspect, the present invention provides a method for detecting external damage of a power line, comprising the following steps: setting a detection node on the power line; continuously collecting power parameters of each detection node;

[0011] Based on the power parameters of the neighboring nodes of each detection node, the power parameters of each detection node are compensated and corrected;

[0012] Establishing a time series of power parameters for each detection node; acquiring a component series of power parameters of each detection node based on the time series;

[0013] Calculate the nonlinear characteristic index of each time series and the nonlinear characteristic index of each component series;

[0014] A preliminary external failure detection is performed on each detection node based on the nonlinear characteristic index of the time series; a supplementary external failure detection is performed on each detection node based on the nonlinear characteristic index of the component series.

[0015] As a preferred solution of the power line external damage detection method of the present invention, the method of compensating and correcting the power parameters of each detection node is as follows:

[0016] S100: Collecting power parameters of all detection nodes simultaneously;

[0017] S200: compensating and correcting the power parameters of any detection node, specifically including:

[0018] Obtain power parameters of each neighboring node of the target detection node; obtain historical power parameters of the target detection node and its neighboring nodes;

[0019] Calculating the accuracy of the target detection node and its adjacent nodes based on the historical power parameters; calculating the trust of each adjacent node based on the accuracy;

[0020] Calculate the compensation amount of the target detection node based on the trust of each neighboring node;

[0021] The power parameter of the target detection node is compensated and corrected based on the compensation amount.

[0022] As a preferred solution of the external damage detection method of the power line of the present invention, the accuracy of any detection node is calculated as follows: abnormal power parameters in the historical power parameters of the detection node are counted, and the timestamp corresponding to each abnormal power parameter is recorded;

[0023] Obtain the maintenance records of the power lines, and determine whether each abnormal power parameter corresponds to a line fault based on the maintenance records; mark the abnormal power parameters that do not correspond to the line fault as false alarm power parameters; count the total number of historical power parameters; divide the difference between the total number of historical power parameters and the number of false alarm power parameters by the total number of historical power parameters to obtain the accuracy of the corresponding detection node.

[0024] As a preferred solution of the power line damage detection method of the present invention, the neighboring nodes of the target detection node are determined as follows: any node adjacent to the target detection node on the power line or whose distance to the target detection node is less than a preset distance threshold is a neighboring node of the target detection node; the trust degree of any neighboring node of the target detection node is calculated as follows:

[0025] Calculate the correlation coefficient between the historical power parameters of any adjacent node and the historical power parameters of the target detection node as the correlation degree between the corresponding adjacent node and the target detection node;

[0026] Obtain the distance between any adjacent node and the target detection node; calculate the trust of the corresponding adjacent node based on the correlation and distance between any adjacent node and the target detection node, and the accuracy of the corresponding adjacent node.

[0027] As a preferred solution of the power line external damage detection method described in the present invention, the method of calculating the compensation amount of the target detection node based on the trust of each adjacent node specifically includes: based on the trust of each adjacent node, weighted summing up the power parameters of each adjacent node to obtain the compensation amount of the target detection node; wherein the weight coefficient of the power parameter of any adjacent node is the trust of the corresponding adjacent node divided by the sum of the trusts of all adjacent nodes.

[0028] The compensating and correcting the power parameter of the target detection node based on the compensation amount specifically includes:

[0029] Based on the weighted sum of the original value of the power parameter of the target detection node and the compensation amount, the power parameter of the target detection node is compensated and corrected; wherein the weight coefficients of the compensation amount and the original value are both related to the accuracy of the target detection node.

[0030] As a preferred solution of the power line external damage detection method of the present invention, wherein: the component sequence includes an approximate component sequence and a detail component sequence; obtaining the component sequence of the power parameters of each detection node based on the time series specifically includes: selecting a wavelet basis function and a decomposition scale; performing a wavelet transform on the time series of the power parameters of any detection node based on the selected wavelet basis function and the decomposition scale to obtain the component sequence of the power parameters of the corresponding detection node;

[0031] The nonlinear characteristic indicators of any time series or component series include Lyapunov exponent, correlation dimension, and information entropy.

[0032] As a preferred solution of the power line external damage detection method of the present invention, the preliminary external damage detection specifically includes:

[0033] Collect historical data of power parameters and establish a historical database of power parameters; any historical data in the historical database includes a time series of power parameters of a detection node without external abnormalities, power grid environmental parameters at the corresponding detection node, and power grid system parameters; wherein the power grid system parameters include the total power generation power of the power grid and the total load of the power grid; the power grid environmental parameters include temperature, humidity, wind speed, and power line length;

[0034] Training a threshold prediction model for nonlinear characteristic indicators based on the historical database;

[0035] Collect grid system parameters and grid environment parameters of each detection node in real time;

[0036] Calculate the maximum threshold of each nonlinear characteristic index of the time series of each detection node based on the threshold prediction model;

[0037] A preliminary external failure detection is performed on each detection node based on the nonlinear characteristic indicators of the time series; if any nonlinear characteristic indicator of any time series is greater than the corresponding maximum threshold, the corresponding detection node has an external failure anomaly.

[0038] As a preferred solution of the power line damage detection method of the present invention, the input of the threshold prediction model includes power grid system parameters and power grid environment parameters at any detection node; the output of the threshold prediction model includes the maximum threshold of each nonlinear characteristic index of the time series of the corresponding detection node;

[0039] The threshold prediction model for training nonlinear characteristic indicators based on the historical database specifically includes:

[0040] Setting search conditions; the search conditions include a set of power grid system parameters and a set of power grid environment parameters;

[0041] Mark each piece of historical data in the historical database that meets the search criteria as sample historical data;

[0042] Calculate the nonlinear characteristic index of the time series of each sample historical data;

[0043] The maximum value of each nonlinear characteristic index of the time series of the sample historical data is extracted respectively as the maximum threshold value of each nonlinear characteristic index corresponding to the retrieval condition;

[0044] The retrieval condition and the maximum threshold of each corresponding nonlinear feature index form a piece of training data;

[0045] Repeatedly obtain at least N training data; and train a threshold prediction model based on the training data.

[0046] As a preferred solution of the external failure detection method of the power line of the present invention, the supplementary external failure detection specifically includes:

[0047] Collect power grid system parameters and power grid environment parameters of corresponding detection nodes in real time;

[0048] Encode the grid system parameters and the grid environment parameters of the corresponding detection nodes and form a grid feature vector;

[0049] Encode the nonlinear characteristic index of each component sequence of any detection node into a feature vector of each component sequence;

[0050] The power grid feature vector and the feature vector of each component sequence are input into a trained external failure detection model to obtain a supplementary external failure detection result of a corresponding detection node.

[0051] In a second aspect, the present invention provides a power line external failure detection system, including a data acquisition module, a correction module, a processing module, a prediction module, and an external failure detection module; wherein:

[0052] The data acquisition module is used to continuously collect the power parameters of each detection node, and collect the power grid system parameters and the power grid environment parameters at each detection node;

[0053] The correction module compensates and corrects the power parameters of each detection node according to the power parameters of the neighboring nodes of each detection node;

[0054] The processing module is used to establish a time series and a component series of power parameters for each detection node, and calculate the nonlinear characteristic index of each time series and component series;

[0055] The prediction module predicts the maximum threshold of each nonlinear characteristic index of the time series of each detection node based on the historical database;

[0056] The external breach detection module is used to perform preliminary external breach detection and supplementary external breach detection on each detection node.

[0057] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0058] This application introduces a trust evaluation mechanism for detection nodes, dynamically calculates the trust based on factors such as historical data accuracy, correlation with adjacent node data, and distance between nodes, performs weighted processing on data based on the trust of adjacent nodes, compensates and corrects power parameters, avoids misjudgment due to data errors at individual nodes, realizes multi-point linkage detection, and effectively improves detection accuracy.

[0059] Supplementary external failure detection is performed based on the nonlinear characteristic indicators of the component sequence, and the nonlinear features of multiple scales are integrated. Classifiers such as support vector machines are used to judge the risk of external failure. The fluctuation characteristics of power parameters at different scales and the influence of the power grid and the environment are comprehensively considered to more comprehensively and accurately analyze the abnormal fluctuations of power parameters and detect external failure situations that are difficult to perceive intuitively. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0061] Figure 1 A flow chart of a method for detecting external damage to a power line provided by the present invention;

[0062] Figure 2 A schematic diagram of the structure of a power line external damage detection system provided by the present invention;

[0063] Figure 3 A flow chart of a method for compensating and correcting power parameters of any detection node provided by the present invention. DETAILED DESCRIPTION

[0064] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0065] Example 1

[0066] This embodiment introduces a method for detecting external damage to a power line. Figure 1 , the method comprises the following steps:

[0067] Set up detection nodes on the power line; continuously collect power parameters of each detection node;

[0068] Detection nodes are set up at key locations along the power lines, such as poles, cable branches, etc.; sensors are installed at each detection node to continuously collect power parameters at the detection node; the power parameters can be any one of current, voltage, and power.

[0069] Based on the power parameters of the neighboring nodes of each detection node, the power parameters of each detection node are compensated and corrected; the method is as follows:

[0070] S100: Collecting power parameters of all detection nodes simultaneously;

[0071] S200: Compensate and correct the power parameters of any detection node, refer to Figure 3 , including:

[0072] S201: Obtain power parameters of each neighboring node of the target detection node; obtain historical power parameters of the target detection node and its neighboring nodes; the neighboring nodes of the target detection node are determined as follows: any node that is adjacent to the target detection node on the power line or whose distance to the target detection node is less than a preset distance threshold is a neighboring node of the target detection node.

[0073] S202: Calculating the accuracy of the target detection node and its adjacent nodes based on the historical power parameters; calculating the trust of each adjacent node based on the accuracy;

[0074] The accuracy of any detection node is calculated as follows: count the abnormal power parameters in the historical power parameters of the detection node, and record the timestamp corresponding to each abnormal power parameter; the abnormal power parameter can be identified by setting the threshold range of normal fluctuation of the power parameter, or based on the moving average method, the average value of several continuous historical power parameters is calculated, and the historical power parameters that deviate greatly from the average value are abnormal power parameters. Obtain the maintenance record of the power line, and determine whether each abnormal power parameter corresponds to a line fault based on the maintenance record; mark the abnormal power parameters that do not correspond to the line fault as false alarm power parameters; count the total number of historical power parameters; divide the difference between the total number of historical power parameters and the number of false alarm power parameters by the total number of historical power parameters to obtain the accuracy of the corresponding detection node.

[0075] The trust of any neighboring node of the target detection node is calculated as follows:

[0076] The correlation coefficient between the historical power parameters of any adjacent node and the historical power parameters of the target detection node is calculated as the correlation between the corresponding adjacent node and the target detection node; preferably, the embodiment of the present application pre-aligns the historical power parameters of the adjacent node and the target detection node in time, and then calculates the Pearson correlation coefficient as the correlation. The greater the correlation, the higher the consistency and the stronger the correlation of the power parameters between the adjacent node and the target detection node.

[0077] Get the distance between any adjacent node and the target detection node; calculate the trust of the corresponding adjacent node based on the correlation and distance between any adjacent node and the target detection node, as well as the accuracy of the corresponding adjacent node. The formula is as follows:

[0078] ;

[0079] Among them, C represents the trust of any neighboring node of the target detection node; A represents the accuracy of the corresponding neighboring node; R represents the correlation between the corresponding neighboring node and the target detection node; d represents the distance between the corresponding neighboring node and the target detection node; Indicates the preset distance threshold.

[0080] S203: Calculate the compensation amount of the target detection node based on the trust of each neighboring node; the method is as follows: based on the trust of each neighboring node, perform weighted summation on the power parameters of each neighboring node to obtain the compensation amount of the target detection node; wherein, the weight coefficient of the power parameter of any neighboring node is the trust of the corresponding neighboring node divided by the sum of the trusts of all neighboring nodes.

[0081] S204: Based on the compensation amount, the power parameter of the target detection node is compensated and corrected; the power parameter of the target detection node after compensation and correction is set to E, and the original value of the power parameter of the target detection node is , the compensation amount is , then E is given by and The weighted sum is obtained; among them, The weight coefficient is w, The weight coefficient is 1 minus w; w is proportional to the accuracy of the target detection node. The calculation formula of w is as follows:

[0082] ;

[0083] in, Indicates the accuracy of the target detection node; Represents the maximum value of the accuracy of all detection nodes; It represents the adjustment coefficient, which is set by technicians in this field based on actual needs.

[0084] This application introduces a trust evaluation mechanism for each detection node, and dynamically calculates the trust of the node based on factors such as the accuracy of the node's historical data, the correlation with the adjacent node data, and the distance between nodes. For any node, the node data is weighted according to the trust of nearby nodes, which can avoid misjudgment caused by errors in individual detection node data to a certain extent, realize multi-point linkage power line external damage detection, and improve the accuracy of detection, thereby solving the problem that the accuracy of each detection node data in a long-distance power line is affected by factors such as sensor accuracy and communication interference.

[0085] Establishing a time series of power parameters for each detection node; acquiring a component series of power parameters of each detection node based on the time series;

[0086] This application continuously collects the power parameters of each detection node, and after compensation and correction, organizes them into a time series of power parameters. The compensated and corrected power parameters can provide a more accurate and comprehensive data basis for the subsequent nonlinear index extraction, meet the very high requirements for data quality when calculating nonlinear indicators, and avoid the problem that noise and other interference factors in the power system affect the data quality and further affect the accuracy of nonlinear index calculation.

[0087] For example, in the power system, the power parameters of a detection node with obvious sensor system errors can be compensated and corrected through the relatively stable and accurate power parameters of the adjacent nodes. The balancing effect of these adjacent nodes can be utilized to avoid misjudgment and make the final external failure detection more accurate.

[0088] In addition, the present application can also specifically set the time series length and sampling frequency of the power parameters according to the characteristics of the power system where the power line is located, thereby avoiding the problem that the time series cannot contain enough data to accurately calculate the nonlinear characteristic indicators; for example, for a high-frequency circuit system with faster changes, the length of the time series can be slightly shorter, but a higher sampling frequency is required.

[0089] Furthermore, in order to improve data quality, after the time series of power parameters is established, a stationarity test is performed on it. If the time series is not stationary, operations such as differentiation are performed to stabilize it to prevent errors in calculation results caused by the instability of the time series.

[0090] The component sequence includes an approximate component sequence and a detail component sequence; obtaining the component sequence of the power parameters of each detection node based on the time series specifically includes: selecting a wavelet basis function and a decomposition scale; performing a wavelet transform on the time series of the power parameters of any detection node based on the selected wavelet basis function and the decomposition scale to obtain the component sequence of the power parameters of the corresponding detection node.

[0091] In the embodiment of the present application, the selected wavelet basis function and decomposition scale are used to perform wavelet transform on the time series of the preprocessed power parameters, and the time series is decomposed into different scales. For example, a three-layer wavelet decomposition is performed to obtain an approximate component sequence with a scale of 3 and three detail component sequences. The component sequences of the present application describe the characteristics of the power parameters from different scales and frequency perspectives. The approximate component sequence retains the main trend and low-frequency information of the power parameters, while the detail component sequence contains the high-frequency details and fluctuation information of the power parameters at different scales.

[0092] Calculate the nonlinear characteristic index of each time series and the nonlinear characteristic index of each component series;

[0093] The nonlinear characteristic indicators of any time series or component series include Lyapunov exponent, correlation dimension, and information entropy.

[0094] The size of the Lyapunov index reflects the speed of system state separation. When the power system is operating normally, the Lyapunov index of power parameters such as current is usually in a relatively stable small range. When the power line is broken, the changes in power parameters will become complex and unstable, and the Lyapunov index will increase abnormally. Therefore, in the preferred preliminary external damage detection method of the embodiment of the present application, the Lyapunov index exceeding a certain threshold is used as one of the characteristics of wire external damage judgment. The correlation dimension describes the complexity of the system, and can reflect the complex laws of power parameter changes in the power system. When the power system is operating normally, the correlation dimension of power parameters such as current is relatively stable. The external damage of the wire causes irregular changes in the power parameters, and the correlation dimension will also mutate. Therefore, in the preferred preliminary external damage detection method of the embodiment of the present application, the correlation dimension exceeding the corresponding threshold is used as one of the characteristics of wire external damage judgment. Information entropy is used to measure the uncertainty or chaos of the system, and the information entropy of the power parameter can reflect the disorder of its change. Line damage will increase the disorder of power parameters and the information entropy will increase accordingly. Therefore, in the preferred preliminary damage detection method of the embodiment of the present application, the information entropy exceeding the corresponding threshold is used as one of the characteristics for judging wire damage.

[0095] This application captures abnormal fluctuations in power parameters such as current and voltage caused by power line failure by calculating nonlinear indicators of the time series of power parameters, thereby discovering tiny signs of failure and achieving early warning of large-scale failure risks. This is more forward-looking than conducting power line failure screening after a failure occurs.

[0096] Based on the nonlinear characteristic index of time series, preliminary external damage detection is performed on each detection node; specifically including:

[0097] S10: Collect historical data of power parameters and establish a historical database of power parameters; any historical data in the historical database includes a time series of power parameters of a detection node without external abnormality, power grid environment parameters at the corresponding detection node, and power grid system parameters; wherein the power grid system parameters include the total power generation power of the power grid and the total load of the power grid; the power grid environment parameters include temperature, humidity, wind speed, and power line length;

[0098] The present application reduces the misjudgment of wire breakage by considering the grid system parameters and grid environment parameters. More specifically, the present application dynamically adjusts the maximum threshold of nonlinear characteristic indicators such as Lyapunov exponent and correlation dimension according to the real-time collected grid system parameters and grid environment parameters, so as to adapt to the changes of power parameters under different environments and working conditions, and avoid the false alarm or omission of abnormal external breakage. For example, when the total power generation power and total load of the power grid change (such as the change of power generation of renewable energy and the access of large-scale power load), the stability of the power grid will be disturbed, so that the power parameters such as grid frequency, power, current and voltage will still fluctuate in the absence of wire breakage. Temperature and humidity will affect the physical properties of power equipment, further leading to fluctuations in power parameters. Strong winds can cause the transmission line to dance, phase-to-phase discharge and other phenomena, thereby causing drastic fluctuations in power parameters. The length of the wire is the distance between the detection node and the starting end of the wire, and the starting end of the wire includes but is not limited to power stations, distribution stations, substations, etc. Longer transmission lines will increase the loss and signal delay during power transmission, affecting the stability of power parameters.

[0099] S20: training a threshold prediction model of a nonlinear characteristic index based on the historical database;

[0100] The input of the threshold prediction model includes the power grid system parameters and the power grid environment parameters at any detection node; the output of the threshold prediction model includes the maximum threshold of each nonlinear characteristic index of the time series of the corresponding detection node;

[0101] The threshold prediction model for training nonlinear characteristic indicators based on the historical database specifically includes:

[0102] Setting search conditions; the search conditions include a set of power grid system parameters and a set of power grid environment parameters; in more detail, a set of power grid system parameters includes a value of the total power generation of the power grid and a value of the total load of the power grid; a set of power grid environment parameters includes a value of temperature, humidity, wind speed, and power line length;

[0103] Mark each piece of historical data in the historical database that meets the search criteria as sample historical data;

[0104] Meeting the search conditions does not necessarily mean that each power grid system parameter and power grid environment parameter is completely equal to the corresponding item in the search conditions; preferably, the embodiment of the present application sets a certain error range for each parameter to prevent the retrieval of historical data that meets the conditions from failing. For example, the search conditions include a power line length of 10km, and the error range set for the power line length is 5%. Historical data with a power line length of 9.5km to 10.5km all meet the search condition regarding the power line length.

[0105] Calculate the nonlinear characteristic index of the time series of each sample historical data;

[0106] The maximum value of each nonlinear characteristic index of the time series of the sample historical data is extracted respectively as the maximum threshold value of each nonlinear characteristic index corresponding to the retrieval condition;

[0107] The retrieval condition and the maximum threshold of each corresponding nonlinear feature index form a piece of training data;

[0108] Repeatedly obtain at least N training data; train the threshold prediction model based on the training data. N is a positive integer. The threshold training model is any one of a linear regression model, a polynomial regression model, and a support vector regression model; when the collected sample data is sufficient, the trained threshold prediction model can calculate the maximum threshold of each nonlinear characteristic indicator under different power grid environment parameters and power grid system parameters, that is, the maximum normal value of each nonlinear characteristic indicator in the absence of external abnormalities.

[0109] S30: collecting grid system parameters and grid environment parameters of each detection node in real time;

[0110] S40: Calculating the maximum threshold of each nonlinear characteristic index of the time series of each detection node based on the threshold prediction model;

[0111] S50: Perform preliminary external failure detection on each detection node based on the nonlinear characteristic index of the time series; if any nonlinear characteristic index of any time series is greater than the corresponding maximum threshold, the corresponding detection node has an external failure anomaly. When a detection node has an external failure anomaly, it means that there is an external failure of the power line at the detection node, thereby affecting the stability of the change law of the power parameters of the detection node.

[0112] Preferably, an abnormal redundancy is set for each nonlinear characteristic indicator; if any nonlinear characteristic indicator of any time series is greater than the sum of the corresponding maximum threshold and the corresponding abnormal redundancy, then the corresponding detection node has an external failure anomaly. The present application further prefers 5% as the abnormal redundancy of the corresponding nonlinear characteristic indicator, which can reduce a certain amount of misjudgment without significantly affecting the sensitivity of the preliminary external failure detection.

[0113] A supplementary external failure detection is performed on each detection node based on the nonlinear characteristic index of the component sequence.

[0114] The supplementary external damage detection specifically includes:

[0115] Collect power grid system parameters and power grid environment parameters of corresponding detection nodes in real time;

[0116] Encode the grid system parameters and the grid environment parameters of the corresponding detection nodes and form a grid feature vector;

[0117] Encode the nonlinear characteristic index of each component sequence of any detection node into a feature vector of each component sequence;

[0118] The power grid feature vector and the feature vector of each component sequence are input into a trained external failure detection model to obtain a supplementary external failure detection result of a corresponding detection node.

[0119] The external damage detection model is a classifier constructed based on any one of support vector machines, Gaussian mixture models, and variational autoencoders; the external damage detection model is iteratively trained through an optimization algorithm so that it can integrate the characteristics of power parameters at various scales (i.e., each component sequence) and the influence of the power grid and the environment, and output external damage detection results that are difficult to intuitively perceive. Among them, the nonlinear characteristic indicators of the high-frequency scale can highlight the rapid changes in power parameters caused by sudden external force impacts, and the nonlinear characteristic indicators of the low-frequency scale can reflect the changes in power parameters caused by long-term environmental factors, such as the influence of slow temperature changes on line resistance. Existing external damage detection based on power parameters is basically based on time series, ignoring the characteristics of power parameter fluctuations at different scales. In contrast, the present application can more comprehensively and accurately analyze the abnormal fluctuations of power parameters and improve the accuracy of external damage detection.

[0120] Example 2

[0121] This embodiment is the second embodiment of the present invention; it is based on the same inventive concept as embodiment 1, Figure 2 This embodiment introduces a power line external damage detection system, including a data acquisition module, a correction module, a processing module, a prediction module, an external damage detection module, and a display module; wherein:

[0122] The data acquisition module is used to continuously collect the power parameters of each detection node, and collect the power grid system parameters and the power grid environment parameters at each detection node;

[0123] The correction module compensates and corrects the power parameters of the detection nodes according to the power parameters of the adjacent nodes of each detection node; the module first obtains the power parameters of the adjacent nodes and historical power parameters of the target detection node, calculates the accuracy and confidence, and then calculates the compensation amount; the power parameters of the target detection node are corrected based on the compensation amount, thereby improving data accuracy and providing a reliable data basis for subsequent analysis.

[0124] The processing module is used to establish the time series and component series of power parameters for each detection node, and calculate the nonlinear characteristic indicators of each time series and component series; this module selects the appropriate wavelet basis function and decomposition scale, performs wavelet transform on the time series, obtains the approximate component series and the detail component series, and then calculates the nonlinear characteristic indicators of the time series and component series (including Lyapunov exponent, correlation dimension, information entropy), and mines the nonlinear characteristics of power parameters from different scales and frequency angles.

[0125] The prediction module predicts the maximum threshold of each nonlinear characteristic indicator of the time series of each detection node based on the historical database; the module first establishes a historical database, and then trains the threshold prediction model of the nonlinear characteristic indicator based on the historical data; the trained model input is the power grid system parameters and power grid environment parameters, and the output is the maximum threshold of each nonlinear characteristic indicator of the time series of the corresponding detection node.

[0126] The external failure detection module is used to perform preliminary external failure detection and supplementary external failure detection on each detection node. The preliminary external failure detection includes judging whether each nonlinear characteristic index of the time series exceeds the corresponding maximum threshold to determine whether there is an external failure anomaly in the detection node; the supplementary external failure detection includes inputting the characteristic vector encoded by the nonlinear characteristic index of the power grid characteristic vector and the component sequence into the external failure detection model to obtain the supplementary external failure detection result.

[0127] The display module is used to summarize the results of preliminary external failure detection and supplementary external failure detection, and output the detection results in an intuitive manner (such as interface display, alarm prompts, etc.). When an abnormal external failure of the power line is detected, relevant personnel are notified in time for processing.

[0128] The specific functions of the above modules are realized by referring to the relevant contents of the external damage detection method for power lines described in Example 1, which will not be described in detail.

[0129] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0130] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the purpose and scope of protection of the present invention, which are all within the protection of the present invention.

Claims

1. A method for detecting external damage of a power line, characterized in that: The following steps are involved: Setting up detection nodes on power lines; Continuously collect power parameters of each detection node; Based on the power parameters of the neighboring nodes of each detection node, the power parameters of each detection node are compensated and corrected; Establishing a time series of power parameters for each detection node; Acquire a component sequence of a power parameter of each detection node based on the time series; Calculate the nonlinear characteristic index of each time series and the nonlinear characteristic index of each component series; Conduct preliminary external damage detection of each detection node based on nonlinear characteristic indicators of time series; A supplementary external failure detection is performed on each detection node based on the nonlinear characteristic index of the component sequence.

2. A method for detecting external damage to a power line according to claim 1, characterized in that: The method for compensating and correcting the power parameters of each detection node is as follows: S100: Collecting power parameters of all detection nodes simultaneously; S200: compensating and correcting the power parameters of any detection node, specifically including: Obtain power parameters of each neighboring node of the target detection node; obtain historical power parameters of the target detection node and its neighboring nodes; Calculating the accuracy of the target detection node and its adjacent nodes based on the historical power parameters; calculating the trust of each adjacent node based on the accuracy; Calculate the compensation amount of the target detection node based on the trust of each neighboring node; The power parameter of the target detection node is compensated and corrected based on the compensation amount.

3. A method for detecting external damage to a power line according to claim 2, characterized in that: The accuracy of any detection node is calculated as follows: count the abnormal power parameters in the historical power parameters of the detection node, and record the timestamp corresponding to each abnormal power parameter; Obtain maintenance records of power lines, and determine whether each abnormal power parameter corresponds to a line fault based on the maintenance records; Marking abnormal power parameters that do not correspond to line faults as false alarm power parameters; Count the total number of historical power parameters; The difference between the total number of historical power parameters and the number of false alarm power parameters is divided by the total number of historical power parameters to obtain the accuracy of the corresponding detection node.

4. A method for detecting external damage to a power line as claimed in claim 3, characterized in that: The neighboring nodes of the target detection node are determined as follows: any node that is adjacent to the target detection node on the power line or whose distance to the target detection node is less than a preset distance threshold is a neighboring node of the target detection node; the trustworthiness of any neighboring node of the target detection node is calculated as follows: Calculate the correlation coefficient between the historical power parameters of any adjacent node and the historical power parameters of the target detection node as the correlation degree between the corresponding adjacent node and the target detection node; Get the distance between any adjacent node and the target detection node; The trust of any adjacent node is calculated based on the correlation and distance between any adjacent node and the target detection node, as well as the accuracy of the corresponding adjacent node.

5. A method for detecting external damage to a power line as claimed in claim 4, characterized in that: The method of calculating the compensation amount of the target detection node based on the trust of each neighboring node specifically includes: based on the trust of each neighboring node, performing weighted summation on the power parameters of each neighboring node to obtain the compensation amount of the target detection node; wherein the weight coefficient of the power parameter of any neighboring node is the trust of the corresponding neighboring node divided by the sum of the trusts of all neighboring nodes; The compensating and correcting the power parameter of the target detection node based on the compensation amount specifically includes: Based on the weighted sum of the original value of the power parameter of the target detection node and the compensation amount, the power parameter of the target detection node is compensated and corrected; wherein the weight coefficients of the compensation amount and the original value are both related to the accuracy of the target detection node.

6. A method for detecting external damage to a power line according to claim 5, characterized in that: The component sequence includes an approximate component sequence and a detail component sequence; obtaining a component sequence of the power parameters of each detection node based on the time sequence specifically includes: selecting a wavelet basis function and a decomposition scale; performing a wavelet transform on the time series of the power parameters of any detection node based on the selected wavelet basis function and the decomposition scale to obtain a component sequence of the power parameters of the corresponding detection node; The nonlinear characteristic indicators of any time series or component series include Lyapunov exponent, correlation dimension, and information entropy.

7. A method for detecting external damage to a power line according to claim 6, characterized in that: The preliminary external damage detection specifically includes: Collect historical data of power parameters and establish a historical database of power parameters; any historical data in the historical database includes a time series of power parameters of a detection node without external abnormalities, power grid environmental parameters at the corresponding detection node, and power grid system parameters; wherein the power grid system parameters include the total power generation power of the power grid and the total load of the power grid; the power grid environmental parameters include temperature, humidity, wind speed, and power line length; Training a threshold prediction model for nonlinear characteristic indicators based on the historical database; Collect grid system parameters and grid environment parameters of each detection node in real time; Calculate the maximum threshold of each nonlinear characteristic index of the time series of each detection node based on the threshold prediction model; A preliminary external failure detection is performed on each detection node based on the nonlinear characteristic indicators of the time series; if any nonlinear characteristic indicator of any time series is greater than the corresponding maximum threshold, the corresponding detection node has an external failure anomaly.

8. A method for detecting external damage to a power line according to claim 7, characterized in that: The input of the threshold prediction model includes the power grid system parameters and the power grid environment parameters at any detection node; the output of the threshold prediction model includes the maximum threshold of each nonlinear characteristic index of the time series of the corresponding detection node; The threshold prediction model for training nonlinear characteristic indicators based on the historical database specifically includes: Setting search conditions; the search conditions include a set of power grid system parameters and a set of power grid environment parameters; Mark each piece of historical data in the historical database that meets the search criteria as sample historical data; Calculate the nonlinear characteristic index of the time series of each sample historical data; The maximum value of each nonlinear characteristic index of the time series of the sample historical data is extracted respectively as the maximum threshold value of each nonlinear characteristic index corresponding to the retrieval condition; The retrieval condition and the maximum threshold of each corresponding nonlinear feature index form a piece of training data; Repeatedly obtain at least N training data; and train a threshold prediction model based on the training data.

9. A method for detecting external damage to a power line according to claim 8, characterized in that: The supplementary external damage detection specifically includes: Collect power grid system parameters and power grid environment parameters of corresponding detection nodes in real time; Encode the grid system parameters and the grid environment parameters of the corresponding detection nodes and form a grid feature vector; Encode the nonlinear characteristic index of each component sequence of any detection node into a feature vector of each component sequence; The power grid feature vector and the feature vector of each component sequence are input into a trained external failure detection model to obtain a supplementary external failure detection result of a corresponding detection node.

10. A power line external failure detection system, used to implement a power line external failure detection method according to any one of claims 1 to 9, characterized in that: It includes data acquisition module, correction module, processing module, prediction module and external damage detection module; among which: The data acquisition module is used to continuously collect the power parameters of each detection node, and collect the power grid system parameters and the power grid environment parameters at each detection node; The correction module compensates and corrects the power parameters of each detection node according to the power parameters of the neighboring nodes of each detection node; The processing module is used to establish a time series and a component series of power parameters for each detection node, and calculate the nonlinear characteristic index of each time series and component series; The prediction module predicts the maximum threshold of each nonlinear characteristic index of the time series of each detection node based on the historical database; The external breach detection module is used to perform preliminary external breach detection and supplementary external breach detection on each detection node.

Images