Power transmission line hidden danger discharge identification method and system

Abstract

The invention relates to the field of power systems and automation, and discloses a power transmission line hidden danger discharge identification method and system. The method comprises the steps that power transmission line hidden danger discharge measured data are acquired, power transmission line hidden danger high-frequency discharge waveform data are acquired and processed, and power transmission line hidden danger discharge event data are acquired and processed; establishing and initializing a hidden danger identification demand table, and updating all elements in the table according to a time sequence; and for each collected new waveform segment, looking up the table to determine the operation and maintenance demand degree corresponding to the newly obtained discharge waveform, and carrying out comprehensive judgment and early warning on the hidden danger state of the line. According to the method, the development process of hidden dangers of the power transmission line can be fully considered, especially for insulation degradation and floating foreign matters in nonlinear development, compared with an existing method, the method is suitable for guiding operation and maintenance of the line; the recognition method provided by the invention is simple and clear in implementation process, and compared with methods such as deep learning, the method is low in data volume requirement, low in hardware computing power requirement and wider in application range.

Description

Technical Field

[0001] The present invention relates to the field of power systems and automation, and in particular to a method and system for identifying potential discharge hazards in power transmission lines. Background Art

[0002] The transmission and distribution lines are prone to weakening of insulation strength between the high-voltage side conductors and the ground wires and towers at ground potential due to factors such as insulator degradation, contamination, and floating foreign objects, resulting in hidden discharges. If not cleared in time, it will develop into a fault and eventually cause the line to trip and stop operating, leading to significant economic losses and safety risks.

[0003] In order to accurately and timely identify and eliminate discharges on the line, it is necessary to first identify the existence and type of hidden discharges on the line. Currently, most transmission and distribution lines of various voltage levels have installed distributed traveling wave fault locating devices, which collect high-frequency discharge traveling waves generated and propagated from the discharge point at both ends of the line, calculate their characteristics, and compare and determine whether they have abnormal characteristics, so as to identify the existence and type of discharge, and notify the line operation and maintenance personnel to carry out maintenance work.

[0004] At present, similar technologies mainly extract high-frequency discharge waveform fragments to solve the problem of hidden danger discharge identification and classification, calculate specified features such as amplitude, phase, power frequency accompanying periodicity, etc., use pattern classification algorithms such as decision trees, support vector machines, neural networks, etc., and finally output the existence or type label of hidden dangers. However, in reality, there are many reasons for the occurrence of hidden dangers in transmission lines, and their development process is not linearly increasing until the insulation breakdown trips. For example, small floating objects may cause early discharge, but may fall off after burning and charring during the discharge process, and the discharge process is terminated. Therefore, the existing technology extracts a single or several waveform fragments and calculates features. This method does not take into account the development and accumulation of abnormal hidden dangers in the line, and cannot comprehensively judge the hidden danger status of the line from the entire process and predict future development trends. Therefore, it is easy to produce false alarms and missed alarms. Summary of the invention

[0005] In view of the above existing problems, there are many reasons for the occurrence of hidden dangers in power transmission lines in reality, and their development process does not increase linearly until the insulation breakdown trips. For example, small floating objects may cause early discharge, but they may fall off after burning and charring during the discharge process, and the discharge process is terminated. Therefore, the existing technology extracts a single or several waveform fragments and calculates the features. This method does not take into account the development and accumulation of abnormal hidden dangers in the line, and cannot comprehensively judge the hidden danger status of the line from the entire process and predict future development trends. Therefore, it is easy to produce false alarms and missed alarms.

[0006] In order to solve the above technical problems, a method for identifying hidden danger discharge of transmission lines is proposed, including:

[0007] Obtain the measured data of transmission line hidden danger discharge, obtain and process the high-frequency discharge waveform data of transmission line hidden danger, obtain and process the transmission line hidden danger discharge event data; establish and initialize the hidden danger identification demand table, and update all elements in the table in chronological order; for each new waveform segment collected, look up the table to determine the operation and maintenance demand level corresponding to the newly acquired discharge waveform and make a comprehensive judgment and early warning of the hidden danger status of the line.

[0008] As a preferred solution of the method for identifying hidden danger discharge of a power transmission line described in the present invention, the acquisition of measured data of hidden danger discharge of the power transmission line includes hidden danger high-frequency discharge waveform data and hidden danger discharge event data.

[0009] The hidden danger high-frequency discharge waveform data includes cutting the hidden danger high-frequency discharge waveform data into N short waveforms every 10ms, that is, half of the power frequency cycle, and calculating F key features Z for each short waveform. 1 …Z i …Z F , where Z 1 is the maximum amplitude in the short waveform, Z F is the power frequency phase with the maximum amplitude, for each characteristic Z i , extract the maximum value Z in the current feature set of all short waveforms i,max and the minimum value Z i,min , for the amplitude characteristic Z 1 The maximum and minimum amplitudes of all short waveforms are Z 1,max and Z 1,min , where (1) to (n) are the numbers of the short waveforms:

[0010] Z i,max =max(Z i (1),Z i (2),…,Z i (n))

[0011] Z i,min =min(Z i (1),Z i (2),…,Z i (n))

[0012] According to each feature Z i The minimum and maximum values ​​of Y are set up to create a discretization interval, dividing the range from the minimum to the maximum value into Y i Intervals:

[0013] [Z i,min ,Z i,min +Z id ), [Z i,min +Z id ,Z i,min+2×Z id ),…,[Z i,min +(Y i -1)×Z id ,Z i,max ]

[0014] Z id =(Z i,max -Z i,min ) / Y i

[0015] Among them, Z id is the interval width.

[0016] The sum of the number of intervals of all features is recorded as N, N = Y 1 +Y 2 +…Y i +…+Y F , establish an interval number set S = [1,2,…,N], with a total of N elements, where each element corresponds to a discretized interval.

[0017] The key feature of each short waveform, the i-th feature Z of the n-th short waveform i (n), converted to the S value corresponding to the interval, and the interval S values ​​generated by all F features of all n waveforms form a new feature interval matrix C:

[0018]

[0019] Each column of the matrix C represents the feature interval corresponding to all features of a waveform, and each row represents the feature interval of all waveforms under any feature type. The order of the columns is arranged according to the acquisition time of the waveform. The waveform represented by the left column has an acquisition time earlier than the waveform represented by the right column.

[0020] As a preferred solution of the method for identifying potential danger discharge of a transmission line described in the present invention, wherein: the potential danger discharge event data includes obtaining a data set of potential danger discharge events of a transmission line W = [W 1 ,W 2 ,…,W m ], where 1 to m are data numbers, the time range covered by the data includes the time range covered by the discharge waveform data, and the waveform corresponds to the known hidden danger events during the time: W 1 The accumulation of dirt on the insulator begins to cause discharge, W 2 The burning of hanging objects causes more intense discharge. The high vegetation causes discharge. 3 The fault tripping is caused by the failure of the insulator deterioration, W 4 Clear faults and restore power supply for line patrol personnel.

[0021] The hidden danger severity level sequence data includes setting a hidden danger severity level quantization value E in the range of 0-4 for each known hidden danger event according to actual line operation and maintenance requirements, and setting the level range to the range of 0, 1, 2, and 3: E=0 indicates that there is no hidden danger discharge phenomenon.

[0022] E=1 indicates slight discharge to maintain monitoring.

[0023] E=2 means the discharge degree is moderate, which will cause flashover tripping. Local detection is performed during line inspection.

[0024] E=3 means it is very serious and has caused a fault trip, and active maintenance must be carried out immediately.

[0025] W 1 The accumulation of dirt on the insulators begins to cause discharge, which is an early hidden danger with a mild degree. 1 =1.

[0026] W 2 The burning of hanging objects causes more intense discharge. The high vegetation causes discharge, which causes failure in the long term. 2 =2.

[0027] W 3 The fault trip is caused by the failure of the insulator. It is considered to have tripped and must be repaired immediately. 3 =3.

[0028] W 4 The fault is cleared for the line patrol personnel to restore power supply, which means the hidden danger has been cleared and there is no incident. 4 =0.

[0029] The resulting hidden danger level sequence is E = [1, 2, 3, 0].

[0030] As a preferred solution of the method for identifying potential danger discharge of a transmission line according to the present invention, the acquisition and processing of potential danger discharge event data of the transmission line includes evaluating the activity of the potential danger event through the discharge interval time according to the system identification model:

[0031]

[0032] Where n is the number of discharge events that occurred during the evaluation period, E is the severity level of the hidden danger event, and λ j is the decay rate of the jth discharge event, t 1 and t 2 are the start and end time of the evaluation period, t j is the time when the jth discharge event occurs, Φ represents the normalization of the difference in discharge interval time, Δ(t′) represents the discharge interval time at time t′, represents the average value of the discharge interval, σ Δ Represents the standard deviation of the discharge interval.

[0033] When the Φ value is stable between 0.45 and 0.55, it means that the frequency and severity of discharge events match the average level and should be monitored. When the Φ value is greater than 0.55, it means that the discharge interval is longer than the average time and the green light flashes to indicate that the activity of the hidden danger event is weakened.

[0034] When the Φ value is less than 0.45, it means that the discharge interval is shorter than the average time, and a level A alarm indicates that the activity of the current hidden danger event is increasing.

[0035] When the F(t) value decreases, the discharge event occurs but the frequency decreases, indicating that the long-term accumulation of current hidden danger events will cause transmission line failures. A Class B alarm is issued to identify hidden dangers and notify staff to carry out maintenance and inspection work.

[0036] When the F(t) value increases, the frequent occurrence of discharge events indicates that the short-term development of the current hidden danger event will cause a transmission line failure and issue a D-level alarm. The hidden danger of the current hidden danger event needs to be identified and maintenance work should be carried out immediately.

[0037] As a preferred solution of a method for identifying hidden danger discharge of a transmission line described in the present invention, wherein: the rule for establishing a hidden danger identification requirement table includes the following: a total of a rows and b columns, a is the number of characteristic intervals obtained from hidden danger discharge waveform data, b is the number of discharge severity levels obtained from hidden danger discharge event data, the initial value of all elements is the level value E corresponding to the column, indicating that when a certain feature of the waveform belongs to the characteristic interval represented by a, the discharge severity level at the current moment is the operation and maintenance requirement degree of b, the column represented by the maximum value of the current row is the operation and maintenance action most needed to be taken in the current characteristic interval, and when F>1, the same waveform has multiple features, the maximum values ​​of each row are compared together, and the maximum value is taken as the operation and maintenance requirement degree of the current waveform.

[0038] According to the characteristic interval matrix C, the shortest waveform u with the earliest acquisition time and the waveform v of the next adjacent time are obtained. Combined with the hidden danger identification requirement table, the characteristic interval value S of the i-th feature of the u-th waveform i (u) represents the row, and the Eu value corresponding to the waveform represents the column. i The element in the row (u) and column (Eu) represents the operation and maintenance requirement of the waveform feature i corresponding to the discharge level Eu. The table element is T(S i (u),Eu).

[0039] For each feature i, update the table element T′(S i (u),Eu):

[0040] T′(S i (u),Eu)=0.9×T(S i (u),Eu)+0.8×(Ev-T(S i (u),Eu))

[0041] Among them, 0.9 represents the guiding role of similar hidden danger discharge characteristics in history in marking the severity of hidden dangers of new discharges, and 0.8 represents the predictive significance of future hidden danger discharges in the same discharge waveform in marking the current severity.

[0042] In the order of acquisition time, update table elements for each waveform and the next waveform at adjacent time in turn until all waveforms are processed and the filling of table content is completed.

[0043] As a preferred solution of the method for identifying potential dangers of power transmission lines described in the present invention, the comprehensive judgment and early warning of the potential danger status of the line includes calculating the current potential danger value Hd:

[0044]

[0045] The larger the Hd value, the more serious the hidden danger is, and the smaller the Hd value, the less serious the hidden danger is. Among them, B represents the discharge amplitude, d m Indicates the shape of the discharge waveform, M indicates the number of waveform parameters, α and β are parameters adjusted according to actual conditions, which are used to control the intensity of exponential decay and information filtering, Norm indicates normalizing the summation result, and Filter is used to filter the waveform shape parameters.

[0046] Predict that accumulation under long-term conditions will cause transmission line failures, and make comprehensive judgments on the status of transmission lines:

[0047]

[0048] When the P value is larger, it means that the hidden danger state of the transmission line is more serious, where P is the comprehensive judgment value of the hidden danger state of the transmission line at time t, t 3 is the initial time of the forecast period, t 4 is the end time of the prediction period, λ Hd is the attenuation coefficient of the speed at which the hidden danger decays over time, K is the number of hidden danger characteristic values, Hd k is the eigenvalue of the i-th hidden danger, σ k is the standard deviation of the eigenvalue of the i-th hidden danger, μ k is the mean of the ith hidden danger characteristic value.

[0049] As a preferred solution of the method for identifying potential discharge hazards of power transmission lines described in the present invention, the comprehensive state judgment includes: when the system collects a new high-frequency discharge waveform, obtains a new potential discharge waveform y, extracts F features, and converts them into F feature interval values ​​S 1 (y),S 2 (y),…,S F (y), according to the rules of the hidden danger identification demand table, look up the table to get the maximum value in the row where the characteristic interval is located and compare it, find the maximum value, the column where the maximum value is located corresponds to the discharge severity level E value, which is the severity level represented by the new hidden danger discharge waveform, and judge it in combination with the comprehensive status of the transmission line:

[0050] When the new quantitative value E is less than 1 and the P value decreases, it means that the current hidden danger level is light and has a long-term decreasing trend. Therefore, monitoring and regular maintenance should be carried out.

[0051] When the new quantitative value E is less than 1 and the P value increases, it means that the current hidden danger is light, but it is increasing in the long term. It is believed that no failure will occur within the predicted period and the failure period will be delayed. A Class B alarm is used for local detection and local repair.

[0052] When the new quantitative value E is greater than 1 and the P value decreases, it means that the current hidden danger level is serious, but it is showing a decreasing trend in the long term. It is believed that the transmission line will fail within the forecast period. A level D alarm is used, and maintenance is carried out immediately and the long-term trend is re-forecasted until the hidden danger events show a decreasing trend.

[0053] When the new quantitative value E is greater than 1 and the P value increases, it means that the current hidden danger is serious and has a long-term increasing trend. It is believed that the transmission line will fail before the predicted period. A G-level alarm is used, and work is stopped immediately to take maintenance measures.

[0054] Another object of the present invention is to provide a transmission line hidden danger discharge identification system, which accurately identifies and evaluates the hidden danger status of the line by real-time monitoring and analyzing the hidden danger discharge data of the transmission line, issues early warning in time, and provides a basis for the maintenance and inspection of the line, thereby ensuring the safe and stable operation of the transmission line.

[0055] As a preferred solution of the transmission line hidden danger discharge identification system described in the present invention, it is characterized by including a data acquisition and processing module, a hidden danger identification demand table module and an early warning and status assessment module.

[0056] The data acquisition and processing module is responsible for obtaining the measured data of hidden danger discharge of the transmission line, including hidden danger high-frequency discharge waveform data and hidden danger discharge event data, processing the hidden danger high-frequency discharge waveform data, extracting key features, and establishing a feature interval matrix, processing the hidden danger discharge event data, and establishing a hidden danger severity level sequence.

[0057] The hidden danger identification requirement table module establishes a hidden danger identification requirement table according to the characteristic interval matrix and the hidden danger severity level sequence, updates all elements in the table in chronological order, obtains the operation and maintenance requirement degree corresponding to the discharge waveform, and makes a comprehensive judgment and early warning on the hidden danger status of the line.

[0058] The early warning and status assessment module, based on the system identification model, assesses the activity of hidden danger events through the discharge interval time, and calculates the current hidden danger value and the comprehensive status judgment value of the transmission line. According to the assessment results, different levels of early warnings are issued, and corresponding maintenance and repair measures are taken.

[0059] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of a method for identifying potential discharge hazards in a transmission line are implemented.

[0060] A computer-readable storage medium stores a computer program thereon, wherein when the computer program is executed by a processor, the steps of a method for identifying potential discharge hazards in a transmission line are implemented.

[0061] Beneficial effects of the present invention: The advantages of the present invention are reflected in three aspects. First, it can fully consider the development process of hidden dangers in transmission lines, especially for nonlinear development of insulation degradation, hanging foreign objects, etc., the discharge trend is difficult to predict, and it is possible to terminate without tripping, or the development speed is too fast, and the existing technology is difficult to predict. Therefore, the accuracy and reliability are higher. Second, the present invention fully integrates the degree indicators of known hidden danger discharge into the parameter matrix. Compared with the existing methods such as machine learning or deep learning, it has stronger interpretability and observability during implementation, and is therefore suitable for guiding line operation and maintenance; third, the identification method proposed by the present invention has a simple and clear implementation process. Compared with the methods such as deep learning, the data volume requirement is not high, the hardware computing power requirement is lower, and the application range is wider.

[0062] In addition, the present invention establishes a hidden danger warning demand table, and realizes the functional requirements from discharge data to hidden danger identification through the special design of the element update process in the table, and fully combines historical data and future data to improve the reliability and reference significance of identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0064] Figure 1 An overall flow chart of a method for identifying potential discharge hazards in a power transmission line provided by an embodiment of the present invention.

[0065] Figure 2 A system solution flow chart of a transmission line hidden danger discharge identification system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0067] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0068] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0069] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0070] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0071] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0072] Example 1

[0073] Reference Figure 1 , which is the first embodiment of the present invention, provides a method for identifying potential discharge hazards in a power transmission line, comprising:

[0074] S1: Acquire the measured data of the transmission line hidden danger discharge, acquire and process the transmission line hidden danger high-frequency discharge waveform data, and acquire and process the transmission line hidden danger discharge event data.

[0075] Furthermore, the actual measured data of hidden danger discharge of transmission lines are obtained, including hidden danger high-frequency discharge waveform data and hidden danger discharge event data.

[0076] The hidden danger high-frequency discharge waveform data includes cutting the hidden danger high-frequency discharge waveform data into N short waveforms every 10ms, that is, half of the power frequency cycle, and calculating F key features Z for each short waveform. 1 …Z i …Z F For example, F = 2, that is, two features are calculated, where Z 1 is the maximum amplitude in the short waveform, Z 2 It is the power frequency phase where the maximum amplitude is located.

[0077] Among them, Z 1 is the maximum amplitude in the short waveform, Z F is the power frequency phase with the maximum amplitude, for each characteristic Z i , extract the maximum value Z in the current feature set of all short waveforms i,max and the minimum value Z i,min , for the amplitude characteristic Z 1 The maximum and minimum amplitudes of all short waveforms are Z1,max and Z 1,min , where (1) to (n) are the numbers of the short waveforms:

[0078] Z i,max =max(Z i (1),Z i (2),…,Z i (n))

[0079] Z i,min =min(Z i (1),Z i (2),…,Z i (n))

[0080] For example, for the amplitude feature Z 1 The maximum and minimum amplitudes of all short waveforms are Z 1,max and Z 1,min :

[0081] Z 1,max =max(Z 1 (1),Z 1 (2),…,Z 1 (n))

[0082] Z 1,min =min(Z 1 (1),Z 1 (2),…,Z 1 (n))

[0083] Similarly, for the phase characteristic Z 2 , the largest phase among all short waveforms is Z 2,max , the smallest one is Z 2,min .

[0084] According to each feature Z i The minimum and maximum values ​​of Y are set up to create a discretization interval, dividing the range from the minimum to the maximum value into Y i Intervals:

[0085] [Z i,min ,Z i,min +Z id ), [Z i,min +Z id ,Z i,min +2×Z id ),…,[Z i,min +(Y i -1)×Z id ,Z i,max ]

[0086] Z id =(Z i,max -Zi,min ) / Y i

[0087] Among them, Z id is the interval width.

[0088] For example, for the amplitude feature Z 1 , establish three discretization intervals, Y 1 =3, respectively:

[0089] [Z 1,min ,Z 1,min +Z 1d ), [Z 1,min +Z 1d ,Z 1,min +2×Z 1d ),…,[Z 1,min +(Y 1 -1)×Z 1d ,Z 1,max ]

[0090] Z 1d =(Z 1,max -Z 1,min ) / 3

[0091] Similarly, establish three phase value discretization intervals (Y 2 =3): [Z 2,min ,Z 2,min +Z 2d ), [Z 2,min +Z 2d ,Z 2,min +2×Z 2d ), [Z 2,min +(Y 2 -1)×Z 2d ,Z 2,max ]

[0092] The sum of the number of intervals of all features is recorded as N, N = Y 1 +Y 2 +…Y i +…+Y F For example, in the previous example, N=3+3=6, and an interval number set S=[1,2,…,N] is established, with a total of N elements, where each element corresponds to a discretized interval.

[0093] For example, 1, 2, and 3 represent the amplitude characteristics Z 1 The three intervals of 4, 5, and 6 represent the phase Z 2 If the amplitude of a waveform is 1, and the three established amplitude intervals are [-1,0), [0,1), [1,2], then the feature belongs to the third one in the amplitude interval, then Si(j) =3.

[0094] For another example, if the phase feature of a waveform is -π / 2, and the three established phase intervals are [-π, -π / 3), [-π / 3, π / 3), [π / 3, π], then this feature belongs to the first phase interval and is also the fourth phase interval in the S set. Then S i(j) =4.

[0095] The key feature of each short waveform, the i-th feature Z of the n-th short waveform i (n), converted to the S value corresponding to the interval, and the interval S values ​​generated by all F features of all n waveforms form a new feature interval matrix C:

[0096]

[0097] Each column of the matrix C represents the feature interval corresponding to all features of a waveform, and each row represents the feature interval of all waveforms under any feature type. The order of the columns is arranged according to the acquisition time of the waveform. The waveform represented by the left column has an acquisition time earlier than the waveform represented by the right column.

[0098] It should be noted that the data set of transmission line hidden danger discharge events W = [W 1 ,W 2 ,…,W m ], where 1 to m are data numbers, the time range covered by the data includes the time range covered by the discharge waveform data, and the waveform corresponds to the known hidden danger events during the time: W 1 The accumulation of dirt on the insulator begins to cause discharge, W 2 The burning of hanging objects causes more intense discharge. The high vegetation causes discharge. 3 The fault tripping is caused by the failure of the insulator deterioration, W 4 Clear faults and restore power supply for line patrol personnel.

[0099] The hidden danger severity level sequence data includes setting a hidden danger severity level quantization value E in the range of 0-4 for each known hidden danger event according to actual line operation and maintenance requirements, and setting the level range to the range of 0, 1, 2, and 3: E=0 indicates that there is no hidden danger discharge phenomenon.

[0100] E=1 indicates slight discharge to maintain monitoring.

[0101] E=2 means the discharge degree is moderate, which will cause flashover tripping. Local detection is performed during line inspection.

[0102] E=3 means it is very serious and has caused a fault trip, and active maintenance must be carried out immediately.

[0103] W 1 The accumulation of dirt on the insulators begins to cause discharge, which is an early hidden danger with a mild degree. 1 =1.

[0104] W 2 The burning of hanging objects causes more intense discharge. The high vegetation causes discharge, which causes failure in the long term. 2 =2.

[0105] W 3 The fault trip is caused by the failure of the insulator. It is considered to have tripped and must be repaired immediately. 3 =3.

[0106] W 4 The fault is cleared for the line patrol personnel to restore power supply, which means the hidden danger has been cleared and there is no incident. 4 =0.

[0107] The resulting hidden danger level sequence is E = [1, 2, 3, 0].

[0108] It should also be noted that the activity of potential hazards is assessed by the discharge interval:

[0109]

[0110] Where n is the number of discharge events that occurred during the evaluation period, E is the severity level of the hidden danger event, and λ j is the decay rate of the jth discharge event, t 1 and t 2 are the start and end time of the evaluation period, t j is the time when the jth discharge event occurs, Φ represents the normalization of the difference in discharge interval time, Δ(t′) represents the discharge interval time at time t′, represents the average value of the discharge interval, σ Δ Represents the standard deviation of the discharge interval.

[0111] When the Φ value is stable between 0.45 and 0.55, it means that the frequency and severity of discharge events match the average level and should be monitored. When the Φ value is greater than 0.55, it means that the discharge interval is longer than the average time and the green light flashes to indicate that the activity of the hidden danger event is weakened.

[0112] When the Φ value is less than 0.45, it means that the discharge interval is shorter than the average time, and a level A alarm indicates that the activity of the current hidden danger event is increasing.

[0113] When the F(t) value decreases, the discharge event occurs but the frequency decreases, indicating that the long-term accumulation of current hidden danger events will cause transmission line failures. A Class B alarm is issued to identify hidden dangers and notify staff to carry out maintenance and inspection work.

[0114] When the F(t) value increases, the frequent occurrence of discharge events indicates that the short-term development of the current hidden danger event will cause a transmission line failure and issue a D-level alarm. The hidden danger of the current hidden danger event needs to be identified and maintenance work should be carried out immediately.

[0115] S2: Create and initialize a hidden danger identification requirement table, and update all elements in the table in chronological order.

[0116] Furthermore, the rules of the hidden danger identification requirement table are: a total of a rows and b columns, a is the number of feature intervals obtained from the hidden danger discharge waveform data, b is the number of discharge severity levels obtained from the hidden danger discharge event data, and the initial value of all elements is the level value E corresponding to the column, indicating that when a certain feature of the waveform belongs to the feature interval represented by a, the discharge severity level at the current moment is the operation and maintenance requirement level of b, and the maximum value of the current row represents the operation and maintenance action most needed to be taken in the current feature interval. When F>1, and the same waveform has multiple features, the maximum values ​​of each row are compared together, and the maximum value is taken as the operation and maintenance requirement level of the current waveform.

[0117] For example, according to the above example, the table has 6 rows and 4 columns. If the amplitude of the xth waveform is 1, the characteristic interval value S 1 (x) = 3. This corresponds to the third row in the table. Assume that the four values ​​in this row are [1, 5, 15, 2]. The third value 15 is the largest, which means that the severity level corresponding to the amplitude of 1 is 2 (the third value in the range of 0, 1, 2, 3).

[0118] If the phase characteristic interval S of the waveform 2 (x)=4, and the 4 values ​​in the 4th row are [11, 9, 8, 2], among which the first value 11 is the largest, indicating that the severity level corresponding to the phase feature is the first level 0.

[0119] Comparing the maximum values ​​in the rows corresponding to the two characteristic intervals, it can be seen that 15>11, and the larger one is taken, so the discharge severity level corresponding to the entire waveform is 2.

[0120] According to the characteristic interval matrix C, the shortest waveform u with the earliest acquisition time and the waveform v of the next adjacent time are obtained. Combined with the hidden danger identification requirement table, the characteristic interval value S of the i-th feature of the u-th waveform i (u) represents the row, and the Eu value corresponding to the waveform represents the column. i The element in the row (u) and column (Eu) represents the operation and maintenance requirement of the waveform feature i corresponding to the discharge level Eu. The table element is T(S i (u),Eu).

[0121] For each feature i, update the table element T′(S i(u),Eu):

[0122] T′(S i (u),Eu)=0.9×T(S i (u),Eu)+0.8×(Ev-T(S i (u),Eu))

[0123] Among them, 0.9 represents the guiding role of similar hidden danger discharge characteristics in history in marking the severity of hidden dangers of new discharges, and 0.8 represents the predictive significance of future hidden danger discharges in the same discharge waveform in marking the current severity.

[0124] In the order of acquisition time, update table elements for each waveform and the next waveform at adjacent time in turn until all waveforms are processed and the filling of table content is completed.

[0125] S3: For each new waveform segment collected, a table is looked up to determine the operation and maintenance demand level corresponding to the newly acquired discharge waveform and a comprehensive judgment and early warning of the hidden danger status of the line is made.

[0126] Furthermore, the current hidden danger value Hd is calculated:

[0127]

[0128] The larger the Hd value, the more serious the hidden danger is, and the smaller the Hd value, the less serious the hidden danger is. Among them, B represents the discharge amplitude, d m Indicates the shape of the discharge waveform, M indicates the number of waveform parameters, α and β are parameters adjusted according to actual conditions, which are used to control the intensity of exponential decay and information filtering, Norm indicates normalizing the summation result, and Filter is used to filter the waveform shape parameters.

[0129] Predict that accumulation under long-term conditions will cause transmission line failures, and make comprehensive judgments on the status of transmission lines:

[0130]

[0131] When the P value is larger, it means that the hidden danger state of the transmission line is more serious, where P is the comprehensive judgment value of the hidden danger state of the transmission line at time t, t 3 is the initial time of the forecast period, t 4 is the end time of the prediction period, λ Hd is the attenuation coefficient of the speed at which the hidden danger decays over time, K is the number of hidden danger characteristic values, Hd k is the eigenvalue of the i-th hidden danger, σ k is the standard deviation of the eigenvalue of the i-th hidden danger, μ k is the mean of the ith hidden danger characteristic value.

[0132] It should be noted that when the system collects a new high-frequency discharge waveform, obtains a new hidden danger discharge waveform y, extracts F features, and converts them into F feature interval values ​​S 1 (y),S 2 (y),…,S F (y), according to the rules of the hidden danger identification demand table, look up the table to get the maximum value in the row where the characteristic interval is located and compare it, find the maximum value, the column where the maximum value is located corresponds to the discharge severity level E value, which is the severity level represented by the new hidden danger discharge waveform, and judge it in combination with the comprehensive status of the transmission line:

[0133] When the new quantitative value E is less than 1 and the P value decreases, it means that the current hidden danger level is light and has a long-term decreasing trend. Therefore, monitoring and regular maintenance should be carried out.

[0134] When the new quantitative value E is less than 1 and the P value increases, it means that the current hidden danger is light, but it is increasing in the long term. It is believed that no failure will occur within the predicted period and the failure period will be delayed. A Class B alarm is used for local detection and local repair.

[0135] When the new quantitative value E is greater than 1 and the P value decreases, it means that the current hidden danger level is serious, but it is showing a decreasing trend in the long term. It is believed that the transmission line will fail within the forecast period. A level D alarm is used, and maintenance is carried out immediately and the long-term trend is re-forecasted until the hidden danger events show a decreasing trend.

[0136] When the new quantitative value E is greater than 1 and the P value increases, it means that the current hidden danger is serious and has a long-term increasing trend. It is believed that the transmission line will fail before the predicted period. A G-level alarm is used, and work is stopped immediately to take maintenance measures.

[0137] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0138] Example 2

[0139] The second embodiment of the present invention provides a method for identifying discharge hazards in power transmission lines. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0140] We first collected high-frequency discharge waveform data of the transmission line under normal working conditions and recorded relevant discharge event data. These data were used to establish an initial hidden danger identification requirements table.

[0141] At intervals of 10ms, we cut the collected waveform data into multiple short waveforms and calculated F key features of each short waveform. These features include the maximum amplitude and power frequency phase in the short waveform; based on the collected data, we initialized the hidden danger identification demand table and updated all elements in the table in chronological order; for each newly collected waveform segment, we determined the corresponding operation and maintenance demand level by looking up the table, and made a comprehensive judgment and early warning of the line hidden danger status.

[0142] During the data collection and processing process, we recorded the characteristic values ​​of different discharge events, the sequence data of hidden danger severity levels, and the discharge interval time evaluation results as shown in Table 1.

[0143] Table 1

[0144]

[0145] On the transmission line C, the discharge severity level and the comprehensive judgment value of the hidden danger state are high, indicating that the line has a relatively serious hidden danger. By using the method of the present invention, we can more accurately identify and warn these hidden dangers, thereby improving the efficiency and safety of operation and maintenance.

[0146] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0147] Example 3

[0148] The third embodiment of the present invention is different from the first two embodiments in that:

[0149] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0150] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0151] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0152] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0153] Example 4

[0154] Reference Figure 2 , which is the fourth embodiment of the present invention, provides a transmission line hidden danger discharge identification system, including a data acquisition and processing module, a hidden danger identification demand table module and an early warning and status assessment module.

[0155] The data acquisition and processing module is responsible for obtaining the measured data of hidden danger discharge of transmission lines, including hidden danger high-frequency discharge waveform data and hidden danger discharge event data, processing the hidden danger high-frequency discharge waveform data, extracting key features, and establishing a feature interval matrix, processing the hidden danger discharge event data, and establishing a hidden danger severity level sequence.

[0156] The hidden danger identification demand table module establishes a hidden danger identification demand table according to the characteristic interval matrix and the hidden danger severity level sequence, and updates all elements in the table in chronological order, obtains the operation and maintenance demand level corresponding to the discharge waveform, and makes a comprehensive judgment and early warning on the hidden danger status of the line.

[0157] The early warning and status assessment module evaluates the activity of hidden danger events through the discharge interval time according to the system identification model, and calculates the current hidden danger value and the comprehensive status judgment value of the transmission line. According to the assessment results, different levels of early warnings are issued and corresponding maintenance and repair measures are taken.

[0158] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for identifying potential discharge hazards in power transmission lines, characterized in that: include, Obtain the measured data of the hidden danger discharge of the transmission line, obtain and process the high-frequency discharge waveform data of the hidden danger of the transmission line, and obtain and process the hidden danger discharge event data of the transmission line; Establish and initialize the hidden danger identification requirement table, and update all elements in the table in chronological order; For each new waveform segment collected, a table is looked up to determine the degree of operation and maintenance demand corresponding to the newly acquired discharge waveform, and a comprehensive judgment and early warning of the hidden danger status of the line is made.

2. A method for identifying potential discharge hazards in power transmission lines according to claim 1, characterized in that: The acquisition of the actual measured data of hidden danger discharge of the transmission line includes hidden danger high-frequency discharge waveform data and hidden danger discharge event data; The hidden danger high-frequency discharge waveform data includes cutting the hidden danger high-frequency discharge waveform data into N short waveforms every 10ms, that is, half of the power frequency cycle, and calculating F key features Z1...Z for each short waveform. i …Z F , where Z1 is the maximum amplitude in the short waveform, Z F is the power frequency phase with the maximum amplitude, for each characteristic Z i , extract the maximum value Z in the current feature set of all short waveforms i,max and the minimum value Z i,min For the amplitude characteristic Z1, the maximum and minimum amplitudes of all short waveforms are Z 1,max and Z 1,min , where (1) to (n) are the numbers of the short waveforms: WITH i,max =max(Z i (1),From i (2),…,From i (n)) WITH i,min =min(Z i (1),From i (2),…,From i (n)) According to each feature Z i The minimum and maximum values ​​of Y are set up to create a discretization interval, dividing the range from the minimum to the maximum value into Y i Intervals: [WITH i,min ,WITH i,min +Z id ),[WITH i,min +Z id ,WITH i,min +2×Z id ),…,[WITH i,min +(Y i -1)×Z id ,WITH i,max ] Z id =(Z i,max -Z i,min ) / Y i Among them, Z id is the interval width; The sum of the number of intervals of all features is recorded as N, N = Y1 + Y2 + ... Y i +…+Y F , establish an interval number set S = [1, 2, ..., N], with a total of N elements, where each element corresponds to a discretized interval; The key feature of each short waveform, the i-th feature Z of the n-th short waveform i (n), converted to the S value corresponding to the interval, and the interval S values ​​generated by all F features of all n waveforms form a new feature interval matrix C: Each column of the matrix C represents the feature interval corresponding to all features of a waveform, and each row represents the feature interval of all waveforms under any feature type. The order of the columns is arranged according to the acquisition time of the waveform. The waveform represented by the left column has an acquisition time earlier than the waveform represented by the right column.

3. A method for identifying potential discharge hazards in power transmission lines according to claim 2, characterized in that: The hidden danger discharge event data includes obtaining a transmission line hidden danger discharge event data set W=[W1, W2, ..., W m ], where 1~m are the data numbers, the time range covered by the data includes the time range covered by the discharge waveform data, and the waveform corresponds to the known hidden danger events during the time: W1 is the accumulation of dirt on the insulator, which starts to cause discharge; W2 is the burning of hanging objects, which causes more intense discharge and high vegetation, which causes discharge; W3 is the failure of the insulator to deteriorate and cause a fault trip; W4 is the line patrol personnel clearing the fault and restoring power supply; The hidden danger severity level sequence data includes setting a hidden danger severity level quantization value E in the range of 0-4 for each known hidden danger event according to the actual line operation and maintenance requirements, and setting the level range to the range of 0, 1, 2, and 3: E=0 means there is no hidden danger discharge phenomenon; E = 1 means slight discharge to maintain monitoring; E=2 means the discharge level is moderate, which will cause flashover tripping and local detection is required during line inspection; E = 3 means it is very serious and has caused a fault trip, and active maintenance must be carried out immediately; W1 is the accumulation of dirt on the insulator that begins to cause discharge, which is an early hidden danger with a light degree, E1 = 1; W2 is the burning of hanging objects, which causes more intense discharge. Excessively high vegetation causes discharge, which causes failure in the long term. E2 = 2; W3 is a fault trip caused by insulator deterioration and failure. It is considered to have tripped and must be repaired immediately. E3 = 3; W4 means the line patrol personnel cleared the fault and restored the power supply, which means the hidden danger was cleared and there was no event, E4 = 0; The resulting hidden danger level sequence is E = [1, 2, 3, 0].

4. A method for identifying potential discharge hazards in power transmission lines as claimed in claim 3, characterized in that: The acquisition and processing of transmission line hidden danger discharge event data includes evaluating the activity of hidden danger events through the discharge interval time according to the system identification model: Where n is the number of discharge events that occurred during the evaluation period, E is the severity level of the hidden danger event, and λ j is the decay rate of the jth discharge event, t1 and t2 are the start and end times of the evaluation period, respectively, and t j is the time when the jth discharge event occurs, Φ represents the normalization of the difference in discharge interval time, Δ(t′) represents the discharge interval time at time t′, represents the average value of the discharge interval, σ Δ represents the standard deviation of the discharge interval; When the Φ value is stable between 0.45 and 0.55, it means that the frequency and severity of discharge events match the average level, and monitoring should be maintained. When the Φ value is greater than 0.55, it means that the discharge interval is longer than the average time, and the green light flashes to indicate that the activity of the hidden danger event is weakened; When the Φ value is less than 0.45, it means that the discharge interval is shorter than the average time, and the A-level alarm indicates that the activity of the current hidden danger event is increasing; When the F(t) value decreases, the discharge event occurs but the frequency decreases, indicating that the long-term accumulation of current hidden danger events will cause transmission line failures. A Class B alarm is issued to identify hidden dangers and notify staff to carry out maintenance and inspection work. When the F(t) value increases, the frequent occurrence of discharge events indicates that the short-term development of the current hidden danger event will cause a transmission line failure and issue a D-level alarm. The hidden danger of the current hidden danger event needs to be identified and maintenance work should be carried out immediately.

5. A method for identifying potential discharge hazards in power transmission lines according to claim 4, characterized in that: The hidden danger identification requirement table is established, including the rule of the hidden danger identification requirement table: a total of a rows and b columns, a is the number of characteristic intervals obtained from the hidden danger discharge waveform data, b is the number of discharge severity levels obtained from the hidden danger discharge event data, the initial value of all elements is the level value E corresponding to the column, indicating that when a certain feature of the waveform belongs to the characteristic interval represented by a, the discharge severity level at the current moment is the operation and maintenance requirement of b, the column represented by the maximum value of the current row is the operation and maintenance action most needed to be taken in the current characteristic interval, when F>1, the same waveform has multiple features, then the maximum values ​​of each row are compared together, and the maximum value is taken as the operation and maintenance requirement of the current waveform; According to the characteristic interval matrix C, the shortest waveform u with the earliest acquisition time and the waveform v of the next adjacent time are obtained. Combined with the hidden danger identification requirement table, the characteristic interval value S of the i-th feature of the u-th waveform i (u) represents the row, and the Eu value corresponding to the waveform represents the column. i The element in the row (u) and column (Eu) represents the operation and maintenance requirement of the waveform feature i corresponding to the discharge level Eu. The table element is T(S i (u),Eu); For each feature i, update the table element T′(S i (u),Eu): T′(S i (u),I)=0.9×T(S i (u),I)+0.8×(Ev-T(S i (u),I)) Among them, 0.9 indicates the guiding role of the same hidden danger discharge characteristics in history in marking the severity of the hidden danger of new discharges, and 0.8 indicates the predictive significance of the hidden danger discharge that will occur in the future in the same discharge waveform for marking the current severity; In the order of acquisition time, update table elements for each waveform and the next waveform at adjacent time in turn until all waveforms are processed and the filling of table content is completed.

6. A method for identifying potential discharge hazards in power transmission lines according to claim 5, characterized in that: The comprehensive judgment and early warning of the hidden danger status of the line includes calculating the current hidden danger value Hd: The larger the Hd value, the more serious the hidden danger is, and the smaller the Hd value, the less serious the hidden danger is. Among them, B represents the discharge amplitude, d m Indicates the shape of the discharge waveform, M indicates the number of waveform parameters, α and β are parameters adjusted according to actual conditions, used to control the intensity of exponential decay and information filtering, Norm indicates normalizing the summation result, and Filter is used to filter the waveform shape parameters; Predict that accumulation under long-term conditions will cause transmission line failures, and make comprehensive judgments on the status of transmission lines: When the P value is larger, it means that the hidden danger state of the transmission line is more serious, where P is the comprehensive judgment value of the hidden danger state of the transmission line at time t, t3 is the initial time of the prediction cycle, t4 is the end time of the prediction cycle, and λ Hd is the attenuation coefficient of the speed at which the hidden danger decays over time, K is the number of hidden danger characteristic values, Hd k is the eigenvalue of the i-th hidden danger, σ k is the standard deviation of the eigenvalue of the i-th hidden danger, μ k is the mean of the ith hidden danger characteristic value.

7. A method for identifying potential discharge hazards in power transmission lines according to claim 6, characterized in that: The comprehensive state judgment includes: when the system collects a new high-frequency discharge waveform, obtains a new hidden danger discharge waveform y, extracts F features, and converts them into F feature interval values ​​S1(y), S2(y), ..., S F (y), according to the rules of the hidden danger identification demand table, look up the table to get the maximum value in the row where the characteristic interval is located and compare it, find the maximum value, the column where the maximum value is located corresponds to the discharge severity level E value, which is the severity level represented by the new hidden danger discharge waveform, and judge it in combination with the comprehensive status of the transmission line: When the new quantitative value E is less than 1 and the P value decreases, it means that the current hidden danger is light and has a long-term decreasing trend. In this case, monitoring should be maintained and regular maintenance should be performed. When the new quantitative value E is less than 1 and the P value increases, it means that the current hidden danger is light, but it is increasing in the long term. It is believed that no failure will occur in the predicted period, and the failure period will be delayed. A Class B alarm is used for local detection and local repair; When the new quantitative value E is greater than 1 and the P value decreases, it means that the current hidden danger is serious, but it is decreasing in the long term. It is considered that the transmission line will fail within the forecast period. The D-level alarm is used, and maintenance is immediately carried out and the long-term trend is re-forecasted until the hidden danger event shows a decreasing trend. When the new quantitative value E is greater than 1 and the P value increases, it means that the current hidden danger is serious and has a long-term increasing trend. It is believed that the transmission line will fail before the predicted period. A G-level alarm is used, and work is stopped immediately to take maintenance measures.

8. A system using a method for identifying potential discharge hazards in a power transmission line according to any one of claims 1 to 7, characterized in that: It includes data collection and processing module, hidden danger identification demand table module and early warning and status assessment module; The data acquisition and processing module is responsible for obtaining the measured data of hidden danger discharge of the transmission line, including hidden danger high-frequency discharge waveform data and hidden danger discharge event data, processing the hidden danger high-frequency discharge waveform data, extracting key features, and establishing a feature interval matrix, processing the hidden danger discharge event data, and establishing a hidden danger severity level sequence; The hidden danger identification demand table module establishes a hidden danger identification demand table according to the characteristic interval matrix and the hidden danger severity level sequence, and updates all elements in the table in chronological order, obtains the operation and maintenance demand level corresponding to the discharge waveform, and performs comprehensive judgment and early warning of the hidden danger status of the line; The early warning and status assessment module, based on the system identification model, assesses the activity of hidden danger events through the discharge interval time, and calculates the current hidden danger value and the comprehensive status judgment value of the transmission line. According to the assessment results, different levels of early warnings are issued, and corresponding maintenance and repair measures are taken.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images