A method and device for integrated monitoring of transmission line fault hazards

Abstract

The present application provides an integrated monitoring method and device for transmission line fault hazards, which relates to the field of transmission line monitoring technology. The method includes: when a first monitoring cycle is met, collecting traveling wave related parameters and monitoring traveling wave signals; counting baseline traveling wave signals of fault-free line samples that meet the traveling wave related parameters, and calculating a deviation vector; counting the fault triggering probability of the transmission line that meets the deviation vector; when the fault triggering probability is greater than or equal to the fault probability threshold, retrieving the high-frequency fault detection duration of the transmission line that meets the deviation vector, shortening the high-frequency fault detection duration by at least 0.5 times to obtain a second monitoring cycle, and using the second monitoring cycle to replace the first monitoring cycle. The present application can solve the existing problem of difficult balanced configuration of sampling frequencies, achieve the goal of balanced configuration of sampling frequencies, and achieve the technical effect of improving the efficiency of transmission line monitoring.

Description

Technical Field

[0001] The present application relates to the technical field of power transmission line monitoring, and in particular to an integrated monitoring method and device for transmission line fault hazards. Background Art

[0002] In the field of transmission line fault monitoring, traditional monitoring methods primarily rely on traveling wave theory. This theory detects and analyzes the propagation characteristics of traveling waves in transmission lines to achieve rapid fault warning and precise location. In practical applications, the sampling frequency setting has a direct impact on the accuracy and computational complexity of fault detection. A higher sampling frequency captures more traveling wave details, thereby improving fault detection accuracy. However, a high sampling frequency also requires greater computational complexity, placing higher demands on both the hardware and software of the monitoring system. On the other hand, if the sampling frequency is too low, some fault conditions may be missed, compromising the reliability of the entire monitoring system. Therefore, how to optimally configure the sampling frequency to reduce computational complexity and avoid resource waste while ensuring fault detection accuracy has become a pressing issue in current transmission line fault monitoring technology.

[0003] At present, the existing traditional transmission line fault hidden danger monitoring technology has deficiencies in the sampling frequency configuration. High sampling frequency leads to excessive calculation, while low sampling frequency may miss fault conditions. There is a technical problem that it is difficult to achieve balanced configuration of sampling frequency. Summary of the Invention

[0004] The purpose of this application is to provide an integrated monitoring method for transmission line fault hidden dangers, so as to solve the shortcomings of the existing traditional transmission line fault hidden danger monitoring technology in sampling frequency configuration. High sampling frequency leads to excessive calculation, while low sampling frequency may miss fault conditions, and there is a technical problem that it is difficult to achieve balanced configuration of sampling frequency.

[0005] The present application provides an integrated monitoring method for transmission line fault hazards, wherein the integrated monitoring method for transmission line fault hazards includes: when a first monitoring cycle is met, collecting traveling wave related parameters and monitoring traveling wave signals; counting the baseline traveling wave signals of fault-free line samples that meet the traveling wave related parameters, and calculating the deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal; counting the fault triggering probability of the transmission line that meets the deviation vector; when the fault triggering probability is greater than or equal to the fault probability threshold, retrieving the high-frequency fault detection duration of the transmission line that meets the deviation vector, shortening the high-frequency fault detection duration by at least 0.5 times to obtain a second monitoring cycle, and replacing the first monitoring cycle with the second monitoring cycle.

[0006] The present application also provides an integrated monitoring device for transmission line fault hazards, wherein the integrated monitoring device for transmission line fault hazards includes: an acquisition and monitoring module, which is used to acquire traveling wave related parameters and monitor traveling wave signals when a first monitoring cycle is met; a deviation vector calculation module, which is used to count the baseline traveling wave signals of fault-free line samples that meet the traveling wave related parameters, and calculate the deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal; a statistical module, which is used to count the fault triggering probability of the transmission line that meets the deviation vector; an update module, which is used to retrieve the high-frequency fault detection time of the transmission line that meets the deviation vector when the fault triggering probability is greater than or equal to the fault probability threshold, shorten the high-frequency fault detection time by at least 0.5 times to obtain a second monitoring cycle, and use the second monitoring cycle to replace the first monitoring cycle.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] When the first monitoring cycle is met, traveling wave related parameters and monitoring traveling wave signals are collected; baseline traveling wave signals of fault-free line samples that meet the traveling wave related parameters are counted, and the deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal is calculated; the fault trigger probability of the transmission line that meets the deviation vector is counted; when the fault trigger probability is greater than or equal to the fault probability threshold, the high-frequency fault detection duration of the transmission line that meets the deviation vector is retrieved, and the high-frequency fault detection duration is shortened by at least 0.5 times to obtain a second monitoring cycle, and the first monitoring cycle is replaced by the second monitoring cycle. In other words, when the first monitoring cycle is met, traveling wave related parameters and monitoring traveling wave signals are collected, baseline traveling wave signals of fault-free line samples are counted and the deviation vector is calculated, and then the fault trigger probability is counted. When the fault trigger probability reaches the threshold, the first monitoring cycle is updated based on the second monitoring cycle obtained by shortening the high-frequency fault detection duration. By dynamically adjusting the monitoring cycle according to the actual operating status of the transmission line, a balanced configuration of the sampling frequency is achieved. While ensuring the accuracy of fault detection, the amount of calculation is effectively reduced, and resource waste is avoided. This achieves the technical effect of improving the efficiency of monitoring hidden dangers of transmission line faults, timely discovering potential faults, and ensuring the stable operation of the power system.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the description, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in this application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and a person of ordinary skill in the art can obtain other drawings based on the provided drawings without creative work.

[0011] Figure 1 This is a flow chart of an integrated monitoring method for transmission line fault hazards in this application;

[0012] Figure 2 This is a flow chart of collecting traveling wave related parameters and monitoring traveling wave signals in an integrated monitoring method for transmission line fault hazards in this application. DETAILED DESCRIPTION

[0013] This application provides an integrated monitoring method for transmission line fault hazards, addressing the shortcomings of existing traditional transmission line fault hazard monitoring technologies in sampling frequency configuration. High sampling frequencies lead to excessive computational effort, while low sampling frequencies may miss fault conditions, resulting in the difficulty in achieving a balanced sampling frequency configuration. By dynamically adjusting the monitoring cycle based on the actual operating status of the transmission line, a balanced sampling frequency configuration is achieved. This effectively reduces computational effort while ensuring fault detection accuracy, avoiding resource waste, and achieving the technical effect of improving the efficiency of transmission line fault hazard monitoring, promptly detecting potential faults, and ensuring the stable operation of the power system.

[0014] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0015] For example, see the attached Figure 1 The present application provides a method for integrated monitoring of transmission line fault hazards, wherein the method comprises the following steps:

[0016] Step P10: When the first monitoring period is met, collect traveling wave related parameters and monitor traveling wave signals;

[0017] Specifically, the sampling frequency configuration is optimized by dynamically adjusting the monitoring cycle. Traveling wave parameters and monitoring traveling wave signals are collected during the first monitoring cycle. The comprehensive consideration of these multi-dimensional parameters enables more comprehensive and accurate fault monitoring. Specifically, traveling wave parameters and monitoring traveling wave signals are first collected during the first monitoring cycle. These traveling wave parameters include conductor temperature, vibration, current, altitude, visible light images, infrared images, ambient temperature and humidity, and other parameters. These parameters reflect the operating status of the transmission line from various perspectives, providing comprehensive data support for subsequent fault monitoring. The baseline traveling wave signals of fault-free line samples that meet these traveling wave parameters are then statistically analyzed, and the deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal is calculated. The fault trigger probability of the transmission line meeting this deviation vector is then calculated. If the fault trigger probability is greater than or equal to the fault probability threshold, the high-frequency fault detection duration of the transmission line meeting the deviation vector is retrieved and shortened by at least 0.5 times, thereby obtaining the second monitoring cycle to update the first monitoring cycle. In a specific example, assuming the first monitoring period is 10 minutes, the system collects traveling wave-related parameters and monitors traveling wave signals within this period. Statistical analysis reveals that certain transmission lines have a high probability of fault triggering under specific traveling wave parameters, reaching or exceeding the set fault probability threshold. The high-frequency fault detection duration of these lines is retrieved, assuming it is 5 minutes. This duration is shortened by at least 0.5 times, or adjusted to 2.5 minutes, to obtain a new second monitoring period, and the original 10-minute monitoring period is updated. This allows the monitoring period to be dynamically adjusted based on the actual operating status, achieving a reasonable configuration of the sampling frequency.

[0018] In summary, by dynamically adjusting the monitoring cycle, we optimize transmission line fault monitoring. This ensures fault detection accuracy while reducing computational complexity and resource waste, improving monitoring efficiency, and enabling timely detection of potential faults, thereby ensuring stable operation of the power system.

[0019] Step P20: Counting baseline traveling wave signals of fault-free line samples that meet the traveling wave related parameters, and calculating a deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal;

[0020] Specifically, statistics on baseline traveling wave signals and calculation of deviation vectors from the monitoring traveling wave signals provide a foundation for subsequent fault trigger probability statistics and monitoring cycle updates. The core of this approach is to use the baseline traveling wave signals of fault-free line samples as a reference to accurately identify abnormal changes in the current monitoring traveling wave signals, thereby achieving early warning and effective monitoring of potential transmission line faults, improving the accuracy and reliability of fault monitoring. Specifically, statistics are first collected for baseline traveling wave signals of fault-free line samples that meet the relevant traveling wave parameters. This process involves collecting and analyzing a large amount of data from fault-free line samples to ensure that the baseline traveling wave signals accurately reflect the traveling wave characteristics under normal operating conditions. The deviation vectors are then calculated between the baseline traveling wave signals and the monitoring traveling wave signals. This deviation vector is calculated by comparing the differences between the baseline traveling wave signals and the monitoring traveling wave signals in various dimensions, including key characteristics such as amplitude, frequency, and phase. The magnitude and direction of the deviation vectors intuitively reflect the degree of deviation of the monitoring traveling wave signals from their normal state, providing a quantitative basis for subsequent fault diagnosis.

[0021] In a specific example, suppose the average amplitude of the baseline traveling wave signal in a certain dimension is 100 units, while the amplitude of the monitoring traveling wave signal in that dimension is 120 units. Therefore, the deviation value in that dimension is 20 units. By calculating and integrating the deviations in all relevant dimensions, an overall deviation vector is obtained. If the deviation vector exceeds a preset threshold, it indicates that there is a significant difference between the monitoring traveling wave signal and the baseline traveling wave signal, which may indicate a potential fault and requires further analysis and treatment.

[0022] In summary, by statistically analyzing baseline traveling wave signals and calculating deviation vectors, accurate monitoring and anomaly identification of transmission line traveling wave signals are achieved.

[0023] Step P30: Counting the fault triggering probability of the transmission line that satisfies the deviation vector;

[0024] Specifically, by statistically analyzing the fault trigger probability of the transmission line that meets the deviation vector, data support is provided for the subsequent update of the monitoring cycle. First, the fault trigger probability of the transmission line that meets the deviation vector is statistically analyzed. This process involves the collection, organization and analysis of a large amount of historical fault data and real-time monitoring data. Through data mining and statistical modeling methods, a mapping relationship between the deviation vector and the fault trigger probability is established. Then, based on the statistically obtained fault trigger probability, it is determined whether the monitoring cycle needs to be updated. If the fault trigger probability is greater than or equal to the fault probability threshold, the high-frequency fault detection duration of the transmission line that meets the deviation vector will be retrieved and shortened by at least 0.5 times to obtain a new monitoring cycle.

[0025] In a specific example, suppose statistical analysis reveals that when the deviation vector exceeds 20 units in a certain dimension, the probability of a transmission line fault triggering increases significantly, reaching 15%. If the fault probability threshold is set at 10%, the current monitoring cycle is deemed insufficient to address the potential fault risk and needs to be updated. The high-frequency fault detection time for these transmission lines is retrieved, assuming it is 5 minutes. This time is shortened by at least 0.5 times, to 2.5 minutes. This new monitoring cycle is then determined to improve fault response speed and monitoring efficiency.

[0026] In summary, by calculating the fault triggering probability of transmission lines, early warning and accurate monitoring of transmission line fault hazards can be achieved.

[0027] Step P40: When the fault trigger probability is greater than or equal to the fault probability threshold, retrieve the high-frequency fault detection duration of the transmission line that meets the deviation vector, shorten the high-frequency fault detection duration by at least 0.5 times to obtain a second monitoring period, and use the second monitoring period to replace the first monitoring period.

[0028] Specifically, when the fault trigger probability reaches or exceeds a preset threshold, the system updates the existing monitoring cycle by retrieving the high-frequency fault detection duration and shortening it to obtain a new monitoring period. First, it determines whether the fault trigger probability is greater than or equal to the fault probability threshold. If this condition is met, the transmission line is at a high fault risk and requires enhanced monitoring. The system then retrieves the high-frequency fault detection duration for transmission lines that meet the deviation vector. The high-frequency fault detection duration refers to the time required to quickly detect a fault at a high sampling frequency. The retrieved high-frequency fault detection duration is then shortened by at least 0.5 times to obtain a new second monitoring period, thereby updating the first monitoring period. In a specific example, assume the first monitoring period is 10 minutes. During monitoring, the fault trigger probability reaches 15%, while the set fault probability threshold is 10%. The system then retrieves the high-frequency fault detection duration for transmission lines that meet the deviation vector, assuming it is 5 minutes. As required by the solution, this duration is shortened by at least 0.5 times, to 2.5 minutes, to obtain a new second monitoring period. This will enable more frequent monitoring of transmission lines, timely capture of potential fault information, and improve the timeliness and accuracy of fault detection.

[0029] In summary, dynamically adjusting the monitoring frequency based on fault risk ensures timely fault detection while optimizing the utilization efficiency of monitoring resources, avoiding unnecessary resource waste, and improving the operational efficiency of the entire monitoring system. In other words, when the fault risk is high, the monitoring cycle is automatically shortened to strengthen monitoring efforts and ensure timely detection of potential fault hazards. When the fault risk is low, the monitoring cycle is maintained or appropriately extended to avoid resource waste caused by excessive monitoring. This flexible monitoring cycle adjustment mechanism not only improves the efficiency and reliability of fault monitoring, but also effectively reduces overall monitoring costs, ensuring the stable operation of the power system.

[0030] Further, as attached Figure 2 As shown, when the first monitoring period is met, the traveling wave related parameters are collected and the traveling wave signal is monitored, including:

[0031] Obtaining a monitoring attribute set and a traveling wave signal attribute set;

[0032] performing a correlation analysis on the first traveling wave signal attribute of the traveling wave signal attribute set and the monitoring attribute set to obtain a first monitoring attribute correlation set;

[0033] Until an Nth traveling wave signal attribute of the traveling wave signal attribute set is subjected to correlation analysis with the monitoring attribute set to obtain an Nth monitoring attribute correlation set;

[0034] The first monitoring attribute correlation set is extracted until the monitoring attributes in the Nth monitoring attribute correlation set are greater than or equal to a correlation threshold, and are added into the traveling wave related parameters.

[0035] Specifically, by analyzing the correlation between the monitoring attribute set and the traveling wave signal attribute set, monitoring attributes that are highly correlated with the traveling wave signal attributes are selected and added to the traveling wave-related parameters. The core of this approach is to utilize correlation analysis to quantitatively assess the correlation between different attributes, thereby enabling the precise construction of traveling wave-related parameters and improving the accuracy and reliability of fault monitoring.

[0036] First, a monitoring attribute set and a traveling wave signal attribute set are obtained. The monitoring attribute set covers a variety of attributes that may affect transmission line fault monitoring, such as conductor temperature, vibration, current, altitude, visible light images, infrared images, and ambient temperature and humidity. The traveling wave signal attribute set contains characteristic attributes of the traveling wave signal in different dimensions, such as signal amplitude, frequency, and phase. Then, a correlation analysis is performed between the first traveling wave signal attribute in the traveling wave signal attribute set and the monitoring attribute set to obtain the first monitoring attribute correlation set. This process quantitatively assesses the degree of correlation between the two attributes by calculating metrics such as the correlation coefficient or similarity between the two attributes. This process is repeated until the correlation analysis is completed for the Nth traveling wave signal attribute in the traveling wave signal attribute set, obtaining the Nth monitoring attribute correlation set. During the correlation analysis, monitoring attributes with a correlation threshold greater than or equal to the selected correlation threshold are selected and added to the traveling wave correlation parameters. The correlation threshold is set to ensure that only monitoring attributes highly correlated with traveling wave signal attributes are selected, thereby ensuring the quality and validity of the traveling wave correlation parameters.

[0037] In a specific example, assume that the monitoring attribute set contains 10 attributes and the traveling wave signal attribute set contains 5 attributes. The system first performs a correlation analysis on the first traveling wave signal attribute and the monitoring attribute set, and calculates the first monitoring attribute correlation set, of which there may be 3 monitoring attributes whose correlation is greater than or equal to the set threshold value of 0.6. Then, the same analysis is performed on the second traveling wave signal attribute, and there may be 2 new monitoring attributes that meet the conditions. And so on, until all 5 traveling wave signal attributes are analyzed. Finally, the system adds these monitoring attributes that meet the conditions to the traveling wave related parameters, so that the traveling wave related parameters can more comprehensively and accurately reflect the operating status of the transmission line.

[0038] In summary, by analyzing the correlation between the monitoring attribute set and the traveling wave signal attribute set, we have achieved the optimization of traveling wave-related parameters. This can effectively improve the accuracy and reliability of fault monitoring, ensure that the traveling wave-related parameters can accurately capture the fault characteristics of the transmission line, and provide high-quality data support for subsequent fault detection and diagnosis, thereby ensuring the stable operation of the power system and reducing the probability of faults and losses.

[0039] Further, performing correlation analysis on the first traveling wave signal attribute of the traveling wave signal attribute set and the monitoring attribute set to obtain a first monitoring attribute correlation set includes:

[0040] Collecting a plurality of first traveling wave signal attribute abnormality logs in which the first traveling wave signal attribute is abnormal, wherein any one of the plurality of first traveling wave signal attribute abnormality logs includes an abnormal monitoring attribute set;

[0041] Traversing the monitoring attribute set, counting the proportion of trigger frequencies in the plurality of first traveling wave signal attribute abnormality logs, and setting the proportion as a frequency correlation set;

[0042] Extracting a frequency correlation attribute set whose frequency correlation is greater than or equal to a frequency correlation threshold value from the monitoring attribute set;

[0043] The fluctuation value of the first traveling wave signal attribute is used as a reference data sequence, the fluctuation value of the frequency-related attribute set is used as a comparison data sequence, a grey correlation matrix is configured to perform correlation analysis, and the first monitoring attribute correlation set is obtained.

[0044] Specifically, by collecting and analyzing the abnormal logs of the first line wave signal attributes, the monitoring attributes that are highly correlated with the fault trigger are screened out and constructed into a first monitoring attribute correlation set. First, several logs of the abnormal attributes of the first line wave signal are collected, and each log contains an abnormal monitoring attribute set. Then, the monitoring attribute set is traversed, and the proportion of the triggering frequency of these attributes in the abnormal logs is counted to form a frequency correlation set. Then, the attributes in the frequency correlation set that are greater than or equal to the frequency correlation threshold are extracted from the monitoring attribute set to form a frequency correlation attribute set. Finally, the fluctuation value of the first line wave signal attribute is used as the benchmark data sequence, and the fluctuation value of the frequency correlation attribute set is used as the comparison data sequence. The gray correlation matrix is configured to perform correlation analysis to obtain the first monitoring attribute correlation set.

[0045] In a specific example, assume that 100 first-wave signal attribute anomaly logs are collected, each containing 10 monitoring attributes. The monitoring attribute set is traversed and the trigger frequency percentage of each attribute in the anomaly log is counted. It is found that five attributes have a trigger frequency percentage exceeding 10%, forming a frequency-correlated attribute set. Then, using the fluctuation value of the first-wave signal attribute as a benchmark and the fluctuation values of these five attributes as a comparison sequence, a gray correlation matrix is constructed, and the correlation degree set of the first monitoring attribute is calculated. Attributes with higher correlation values are selected as key monitoring parameters.

[0046] In summary, through abnormal log analysis and correlation evaluation using methods such as frequency correlation and grey correlation matrix, the correlation degree between monitoring attributes and traveling wave signal attributes can be quantitatively evaluated, thereby achieving accurate construction of traveling wave related parameters. Furthermore, it can effectively screen out monitoring attributes that are highly correlated with fault triggering, improve the accuracy and reliability of fault monitoring, reduce false alarms and missed alarms, and provide a solid guarantee for the stable operation of the power system.

[0047] Furthermore, the baseline traveling wave signals of the fault-free line samples that meet the traveling wave related parameters are statistically collected, and the deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal is calculated, including:

[0048] Retrieving a plurality of recorded traveling wave signals of a plurality of fault-free line samples, wherein the first recorded line topology is the same as the transmission line topology and the first recorded traveling wave related parameters are consistent with the traveling wave related parameters;

[0049] performing same-attribute concentrated value sorting on the plurality of recorded traveling wave signals to obtain a concentrated interval of each attribute, and setting the concentrated interval as the baseline traveling wave signal;

[0050] Calculate the deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal.

[0051] Specifically, by searching and centralizing the value sorting of the recorded traveling wave signals of fault-free line samples, a baseline traveling wave signal that can reflect the normal operating status is constructed, and compared with the monitoring traveling wave signal, the abnormal status of the transmission line can be accurately identified, providing a scientific basis for subsequent fault diagnosis and monitoring cycle adjustment.

[0052] First, multiple recorded traveling wave signals of multiple fault-free line samples are retrieved, where the first recorded line topology is the same as the transmission line topology and the first recorded traveling wave-related parameters are consistent with the traveling wave-related parameters. Then, the multiple recorded traveling wave signals are sorted by the same attribute concentration value to obtain the concentration interval of each attribute, which is set as the baseline traveling wave signal. Next, the deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal is calculated. In a specific example, it is assumed that 100 recorded traveling wave signals of fault-free line samples that meet the conditions are retrieved, and each signal contains 5 key attributes. The same attribute concentration value is sorted for each attribute. For example, for the amplitude attribute, it is found that the amplitudes of most samples are concentrated within the range of 100±5 units. This range is set as the amplitude concentration interval of the baseline traveling wave signal. After completing the concentration value sorting of all attributes, a complete baseline traveling wave signal is obtained. Then, each attribute value of the monitoring traveling wave signal is compared with the corresponding concentration interval of the baseline traveling wave signal to calculate the deviation vector. For example, the amplitude of the monitored traveling wave signal is 120 units, which has a deviation of 15 units compared with the baseline concentration interval of 100±5 units, exceeding the allowable range. This indicates a significant deviation in the amplitude attribute, which may indicate an abnormal state of the transmission line.

[0053] In summary, by generating baseline traveling wave signals and calculating deviation vectors, we achieve precise monitoring of the operating status of transmission lines. This effectively identifies abnormal changes in transmission lines, providing strong support for early warning and diagnosis of faults. This improves the accuracy and reliability of fault monitoring, reduces the probability of faults and losses, and ensures the stable operation of the power system.

[0054] Further, calculating the deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal includes:

[0055] Extracting a first type of traveling wave signal attribute and a second type of traveling wave signal attribute of the traveling wave signal, wherein the first type of traveling wave signal attribute represents an attribute set having a correlation coefficient with the fault greater than or equal to a correlation coefficient threshold, and the second type of traveling wave signal attribute represents an attribute set having a correlation coefficient with the fault less than the correlation coefficient threshold;

[0056] Performing same-attribute deviation calculation on the attributes of the type of traveling wave signal to obtain a type of traveling wave signal deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal;

[0057] Counting the number of attributes of the second type of traveling wave signal that deviate from the baseline, and obtaining a second type of traveling wave signal deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal;

[0058] The first type of traveling wave signal deviation vector and the second type of traveling wave signal deviation vector are added to the deviation vector.

[0059] Specifically, by classifying and analyzing traveling wave signal attributes, we accurately capture abnormal changes in traveling wave signals, providing a scientific basis for subsequent fault diagnosis and monitoring cycle adjustments. First, we extract the first-class and second-class traveling wave signal attributes of the traveling wave signal. The first-class traveling wave signal attributes represent the set of attributes whose correlation coefficient with the fault is greater than or equal to the correlation coefficient threshold. These attributes are strongly associated with the occurrence of the fault and can directly reflect the fault characteristics. The second-class traveling wave signal attributes represent the set of attributes whose correlation coefficient with the fault is less than the correlation coefficient threshold. These attributes are less closely associated with the fault, but still have certain reference value in comprehensive assessment. Then, we calculate the same-attribute deviation of the first-class traveling wave signal attributes to obtain the first-class traveling wave signal deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal. Next, we count the number of attributes of the second-class traveling wave signal attributes that deviate from the baseline to obtain the second-class traveling wave signal deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal. Finally, we integrate the first-class and second-class traveling wave signal deviation vectors and add them to the total deviation vector.

[0060] In a specific example, assuming the correlation coefficient threshold is set to 0.6, five Class I traveling wave signal attributes and ten Class II traveling wave signal attributes are extracted. For the Class I traveling wave signal attributes, the attribute values of the baseline traveling wave signal are [100, 200, 150, 50, 80], and the attribute values of the monitoring traveling wave signal are [120, 210, 160, 45, 90]. By calculating the deviation of the same attributes, the Class I traveling wave signal deviation vector is [20, 10, 10, 5, 10]. For the Class II traveling wave signal attributes, statistics show that four attributes deviate from the baseline, resulting in a Class II traveling wave signal deviation vector of 4. Finally, these two deviation vectors are integrated and added to the total deviation vector to form a complete deviation assessment system.

[0061] In summary, this classification and integrated deviation calculation method enables comprehensive monitoring of the transmission line operating status. It effectively captures changes in attributes that are highly correlated with faults, while also accounting for abnormalities in other attributes. This improves the accuracy and reliability of fault monitoring and reduces false positives and missed alarms.

[0062] Furthermore, calculating the fault trigger probability of the transmission line satisfying the deviation vector includes:

[0063] Obtaining a fault trigger probability prediction network, wherein the fault trigger probability prediction network is generated by training multiple sets of data based on machine learning, wherein any set of the multiple sets of data includes: deviation vector record data of historical transmission lines with the same topology as the transmission line and a label identifying a true value of the fault trigger probability;

[0064] Obtaining a set of training deviation vectors for a preset time zone of the fault trigger probability prediction network;

[0065] Calculate the mean Euclidean distance between the deviation vector and the set of training deviation vectors, and according to the rule that the larger the mean Euclidean distance, the more integrated models, perform output mean integration of multiple fault trigger probability prediction networks to obtain a temporary prediction model of fault trigger probability, process the deviation vector, output the fault trigger probability, and delete the temporary prediction model of fault trigger probability.

[0066] Specifically, a fault trigger probability prediction network is constructed through machine learning methods, and the Euclidean distance mean and integrated model rules are used to improve the accuracy and reliability of the prediction. First, a fault trigger probability prediction network generated by machine learning training using multiple sets of data is obtained. These data include deviation vector record data of historical transmission lines with the same transmission line topology as the transmission line and labels that identify the true value of the fault trigger probability. Then, a set of training deviation vectors for the preset time zone of the prediction network is obtained. Then, the Euclidean distance mean of the current deviation vector and the training deviation vector set is calculated. According to the rule that the larger the Euclidean distance mean, the more integrated models there are, the output mean is integrated into multiple fault trigger probability prediction networks to obtain a temporary prediction model for the fault trigger probability. Finally, the temporary prediction model is used to process the deviation vector, output the fault trigger probability, and delete the temporary prediction model after the prediction is completed.

[0067] In a specific example, assume that the fault trigger probability prediction network is trained based on historical data from the past five years, containing thousands of different sets of deviation vector records and corresponding fault trigger probability labels. A set of deviation vectors trained on the network for the past month is obtained, containing 1,000 deviation vector samples. The mean Euclidean distance between the current deviation vector and these 1,000 samples is calculated, and it is found that the mean is large, indicating that more models need to be integrated according to the rules. Therefore, five different fault trigger probability prediction networks are integrated, and a temporary prediction model is generated by outputting the mean. This model is used to process the current deviation vector, resulting in a fault trigger probability of 15%. Based on this result, a decision is made as to whether the monitoring period needs to be adjusted. After the prediction is completed, the temporary prediction model is automatically deleted to save computing resources and avoid model overfitting.

[0068] In summary, by combining historical data with training to generate a prediction model and dynamically adjusting and optimizing the model structure, we can accurately predict the probability of transmission line fault triggering, providing a scientific basis for subsequent monitoring cycle adjustments and fault warnings. Furthermore, by dynamically adjusting the number of integrated models and promptly deleting temporary models, we optimize computing resource utilization and improve system operational efficiency.

[0069] Furthermore, according to the rule that the larger the mean value of the Euclidean distance is, the more integrated models there are, the output mean is integrated with multiple fault trigger probability prediction networks to obtain a temporary prediction model of the fault trigger probability, including:

[0070] Calculate the square value of the mean of the Euclidean distance and set it as the number of predicted network integration;

[0071] A plurality of the fault trigger probability prediction networks are integrated according to the number of prediction network integrations to obtain the temporary prediction model for the fault trigger probability.

[0072] Specifically, the number of prediction network integrations is determined by calculating the square value of the mean Euclidean distance, and multiple fault trigger probability prediction networks are integrated accordingly to obtain a temporary prediction model for the fault trigger probability. First, the square value of the mean Euclidean distance is calculated and set as the number of prediction network integrations. The number of prediction networks that need to be integrated is determined by quantitatively evaluating the difference between the current deviation vector and the training deviation vector set. Then, based on the number of prediction network integrations, multiple fault trigger probability prediction networks are integrated to obtain the temporary prediction model for the fault trigger probability. During the integration process, multiple prediction networks with high similarity to the current deviation waveform signal are selected, and a comprehensive temporary prediction model is constructed through certain fusion strategies, such as output mean, weighted average, etc. Finally, the temporary prediction model is used to process the current deviation vector, output the fault trigger probability, and delete the temporary prediction model after completing the prediction task to release computing resources and avoid model overfitting.

[0073] In a specific example, assume that the mean Euclidean distance between the current deviation vector and the set of training deviation vectors is 3, and the square of the distance is 9, meaning the number of prediction networks in the ensemble is 9. From multiple pre-trained fault trigger probability prediction networks, nine networks with high similarity to the current deviation vector are selected for ensemble. These networks may be trained based on different historical data segments, algorithms, or parameters, each with unique prediction characteristics. The prediction results of these nine networks are fused by outputting their mean values to obtain a final temporary prediction model for fault trigger probability. This model is used to process the current deviation vector, yielding a fault trigger probability of 18%. Based on this result, it is determined whether the monitoring period needs to be adjusted or other early warning measures should be implemented. After the prediction is complete, the temporary prediction model is automatically deleted so that the most appropriate prediction model can be rebuilt for the next prediction based on the new deviation vector. In summary, by dynamically determining the number of prediction networks to ensemble and constructing the temporary prediction model, accurate prediction of transmission line fault trigger probability is achieved.

[0074] Further, retrieving the high-frequency fault detection duration of the transmission line that satisfies the deviation vector includes:

[0075] Retrieving multiple fault detection durations of multiple fault line samples whose second recorded line topology is the same as the transmission line topology and whose recorded deviation vector is consistent with the deviation vector, wherein the fault detection duration represents the interval length of the fault occurrence after the recorded deviation vector appears;

[0076] Performing a centralized trend analysis on the multiple fault detection time periods to obtain a minimum value of the centralized fault detection time period, which is set as the high-frequency fault detection time period.

[0077] Specifically, by retrieving historical fault data consistent with the current transmission line topology and deviation vectors and performing centralized trend analysis, the detection duration of high-frequency faults can be accurately determined. Statistical analysis of historical data provides a scientific basis for subsequent adjustments to monitoring cycles, thereby ensuring timely fault detection while optimizing the utilization of monitoring resources and improving the operational efficiency of the entire monitoring system.

[0078] First, multiple fault detection durations of multiple fault line samples are retrieved, in which the second recorded line topology is the same as the transmission line topology and the recorded deviation vector is consistent with the deviation vector. The fault detection duration refers to the interval time after the occurrence of the fault after the recorded deviation vector appears. This data can reflect the speed and possibility of fault development under specific operating conditions. Then, a central trend analysis is performed on the multiple fault detection durations to obtain the minimum value of the centralized fault detection duration, which is set as the high-frequency fault detection duration. Central trend analysis usually includes calculating statistical indicators such as the mean, median, and mode. These indicators can determine the central trend of the fault detection duration in most cases, and the minimum value is selected as the high-frequency fault detection duration in order to adopt a more conservative and timely strategy in the adjustment of the monitoring cycle to ensure that potential faults can be discovered as early as possible.

[0079] In a specific example, suppose the system retrieves 50 samples of faulty lines that meet the criteria, with fault detection times varying from 2 minutes, 3 minutes, 3 minutes, 4 minutes, and 5 minutes. Central trend analysis of this data reveals an average of 3.2 minutes, a median of 3 minutes, and a mode of 3 minutes. Based on the solution requirements, the minimum value of 2 minutes is selected as the high-frequency fault detection duration. This high-frequency fault detection duration will be used as a basis for subsequent monitoring cycle adjustments, combined with other factors to determine a new monitoring cycle to improve fault response speed and monitoring efficiency.

[0080] In summary, by retrieving historical fault data and analyzing its central trend, we can accurately determine the duration of high-frequency fault detection. This effectively improves the timeliness and accuracy of fault monitoring, providing a scientific basis for subsequent adjustments to monitoring cycles, thereby ensuring stable power system operation and reducing the probability of faults and losses. Furthermore, through data-driven analysis, we optimize the utilization of monitoring resources, improve the system's operational efficiency and adaptability, and enable it to better respond to changes in the operating status of transmission lines.

[0081] In summary, the integrated monitoring method for transmission line fault hazards provided by this application has the following technical effects:

[0082] When the first monitoring cycle is met, traveling wave related parameters and monitoring traveling wave signals are collected; baseline traveling wave signals of fault-free line samples that meet the traveling wave related parameters are counted, and the deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal is calculated; the fault trigger probability of the transmission line that meets the deviation vector is counted; when the fault trigger probability is greater than or equal to the fault probability threshold, the high-frequency fault detection duration of the transmission line that meets the deviation vector is retrieved, and the high-frequency fault detection duration is shortened by at least 0.5 times to obtain a second monitoring cycle, and the first monitoring cycle is replaced by the second monitoring cycle. In other words, when the first monitoring cycle is met, traveling wave related parameters and monitoring traveling wave signals are collected, baseline traveling wave signals of fault-free line samples are counted and the deviation vector is calculated, and then the fault trigger probability is counted. When the fault trigger probability reaches the threshold, the first monitoring cycle is updated based on the second monitoring cycle obtained by shortening the high-frequency fault detection duration. By dynamically adjusting the monitoring cycle according to the actual operating status of the transmission line, a balanced configuration of the sampling frequency is achieved. While ensuring the accuracy of fault detection, the amount of calculation is effectively reduced, and resource waste is avoided. This achieves the technical effect of improving the efficiency of monitoring hidden dangers of transmission line faults, timely discovering potential faults, and ensuring the stable operation of the power system.

[0083] In a second embodiment, based on the same inventive concept as the integrated monitoring method for transmission line fault hazards in the aforementioned embodiment, the present application further provides an integrated monitoring device for transmission line fault hazards, the integrated monitoring device for transmission line fault hazards comprising:

[0084] An acquisition and monitoring module 11 is configured to acquire traveling wave related parameters and monitor traveling wave signals when a first monitoring period is satisfied;

[0085] a deviation vector calculation module 12, configured to collect statistics on baseline traveling wave signals of fault-free line samples that meet the traveling wave related parameters, and calculate a deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal;

[0086] A statistical module 13, which is used to calculate the fault triggering probability of the transmission line that meets the deviation vector;

[0087] An updating module 14 is configured to retrieve a high-frequency fault detection duration of a transmission line that satisfies the deviation vector when the fault trigger probability is greater than or equal to a fault probability threshold, shorten the high-frequency fault detection duration by at least 0.5 times, obtain a second monitoring period, and replace the first monitoring period with the second monitoring period.

[0088] Furthermore, the acquisition and monitoring module 11 is further configured to:

[0089] Obtaining a monitoring attribute set and a traveling wave signal attribute set;

[0090] performing a correlation analysis on the first traveling wave signal attribute of the traveling wave signal attribute set and the monitoring attribute set to obtain a first monitoring attribute correlation set;

[0091] Until an Nth traveling wave signal attribute of the traveling wave signal attribute set is subjected to correlation analysis with the monitoring attribute set to obtain an Nth monitoring attribute correlation set;

[0092] The first monitoring attribute correlation set is extracted until the monitoring attributes in the Nth monitoring attribute correlation set are greater than or equal to a correlation threshold, and are added into the traveling wave related parameters.

[0093] Furthermore, the acquisition and monitoring module 11 is further configured to:

[0094] Collecting a plurality of first traveling wave signal attribute abnormality logs in which the first traveling wave signal attribute is abnormal, wherein any one of the plurality of first traveling wave signal attribute abnormality logs includes an abnormal monitoring attribute set;

[0095] Traversing the monitoring attribute set, counting the proportion of trigger frequencies in the plurality of first traveling wave signal attribute abnormality logs, and setting the proportion as a frequency correlation set;

[0096] Extracting a frequency correlation attribute set whose frequency correlation is greater than or equal to a frequency correlation threshold value from the monitoring attribute set;

[0097] The fluctuation value of the first traveling wave signal attribute is used as a reference data sequence, the fluctuation value of the frequency-related attribute set is used as a comparison data sequence, a grey correlation matrix is configured to perform correlation analysis, and the first monitoring attribute correlation set is obtained.

[0098] Furthermore, the deviation vector calculation module 12 is further configured to:

[0099] Retrieving a plurality of recorded traveling wave signals of a plurality of fault-free line samples, wherein the first recorded line topology is the same as the transmission line topology and the first recorded traveling wave related parameters are consistent with the traveling wave related parameters;

[0100] performing same-attribute concentrated value sorting on the plurality of recorded traveling wave signals to obtain a concentrated interval of each attribute, and setting the concentrated interval as the baseline traveling wave signal;

[0101] Calculate the deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal.

[0102] Furthermore, the deviation vector calculation module 12 is further configured to:

[0103] Extracting a first type of traveling wave signal attribute and a second type of traveling wave signal attribute of the traveling wave signal, wherein the first type of traveling wave signal attribute represents an attribute set having a correlation coefficient with the fault greater than or equal to a correlation coefficient threshold, and the second type of traveling wave signal attribute represents an attribute set having a correlation coefficient with the fault less than the correlation coefficient threshold;

[0104] Performing same-attribute deviation calculation on the attributes of the type of traveling wave signal to obtain a type of traveling wave signal deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal;

[0105] Counting the number of attributes of the second type of traveling wave signal that deviate from the baseline, and obtaining a second type of traveling wave signal deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal;

[0106] The first type of traveling wave signal deviation vector and the second type of traveling wave signal deviation vector are added to the deviation vector.

[0107] Furthermore, the statistics module 13 is further configured to:

[0108] Obtaining a fault trigger probability prediction network, wherein the fault trigger probability prediction network is generated by training multiple sets of data based on machine learning, wherein any set of the multiple sets of data includes: deviation vector record data of historical transmission lines with the same topology as the transmission line and a label identifying a true value of the fault trigger probability;

[0109] Obtaining a set of training deviation vectors for a preset time zone of the fault trigger probability prediction network;

[0110] Calculate the mean Euclidean distance between the deviation vector and the set of training deviation vectors, and according to the rule that the larger the mean Euclidean distance, the more integrated models, perform output mean integration of multiple fault trigger probability prediction networks to obtain a temporary prediction model of fault trigger probability, process the deviation vector, output the fault trigger probability, and delete the temporary prediction model of fault trigger probability.

[0111] Furthermore, the statistics module 13 is further configured to:

[0112] Calculate the square value of the mean of the Euclidean distance and set it as the number of predicted network integration;

[0113] A plurality of the fault trigger probability prediction networks are integrated according to the number of prediction network integrations to obtain the temporary prediction model for the fault trigger probability.

[0114] Furthermore, the updating module 14 is further configured to:

[0115] Retrieving multiple fault detection durations of multiple fault line samples whose second recorded line topology is the same as the transmission line topology and whose recorded deviation vector is consistent with the deviation vector, wherein the fault detection duration represents the interval length of the fault occurrence after the recorded deviation vector appears;

[0116] Performing a centralized trend analysis on the multiple fault detection time periods to obtain a minimum value of the centralized fault detection time period, which is set as the high-frequency fault detection time period.

[0117] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0118] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A method for integrated monitoring of transmission line fault hazards, characterized in that: An integrated monitoring terminal deployed on the target transmission line, including: When the first monitoring period is met, the traveling wave related parameters are collected and the traveling wave signal is monitored, including: Obtaining a monitoring attribute set and a traveling wave signal attribute set; Performing a correlation analysis between a first traveling wave signal attribute of the traveling wave signal attribute set and the monitoring attribute set includes: Collecting a plurality of first traveling wave signal attribute abnormality logs indicating that the first traveling wave signal attribute is abnormal; Counting the proportion of trigger frequencies in the plurality of first traveling wave signal attribute abnormality logs, and setting the proportion as a frequency correlation set; Extracting a frequency correlation attribute set greater than or equal to a frequency correlation threshold value from the frequency correlation set, performing correlation analysis, and obtaining a first monitoring attribute correlation set; Extracting monitoring attributes of the first monitoring attribute correlation set that are greater than or equal to a correlation threshold, and adding them to the traveling wave related parameters; Counting baseline traveling wave signals of fault-free line samples that meet the traveling wave related parameters, and calculating a deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal; Counting the fault triggering probability of the transmission line that satisfies the deviation vector; When the fault trigger probability is greater than or equal to the fault probability threshold, the high-frequency fault detection time of the transmission line that meets the deviation vector is retrieved, and the second monitoring period is obtained after shortening the high-frequency fault detection time by at least 0.5 times. The first monitoring period is replaced by the second monitoring period, wherein the fault detection time represents the interval length of the fault after the deviation vector appears; a centralized trend analysis is performed on multiple fault detection times to obtain the minimum value of the centralized fault detection time, which is set as the high-frequency fault detection time.

2. The method according to claim 1, wherein When the first monitoring period is met, the traveling wave related parameters are collected and the traveling wave signal is monitored, which also includes: Until an Nth traveling wave signal attribute of the traveling wave signal attribute set is subjected to correlation analysis with the monitoring attribute set to obtain an Nth monitoring attribute correlation set; The first monitoring attribute correlation set is extracted until the monitoring attributes in the Nth monitoring attribute correlation set are greater than or equal to a correlation threshold, and are added into the traveling wave related parameters.

3. The method according to claim 1, wherein Extracting a frequency correlation attribute set greater than or equal to a frequency correlation threshold from the frequency correlation set and performing correlation analysis to obtain a first monitoring attribute correlation set includes: The fluctuation value of the first traveling wave signal attribute is used as a reference data sequence, the fluctuation value of the frequency-related attribute set is used as a comparison data sequence, a grey correlation matrix is configured to perform correlation analysis, and a first monitoring attribute correlation set is obtained.

4. The method according to claim 1, wherein Counting baseline traveling wave signals of fault-free line samples that meet the traveling wave related parameters, and calculating a deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal, including: Retrieving a plurality of recorded traveling wave signals of a plurality of fault-free line samples, wherein the first recorded line topology is the same as the transmission line topology and the first recorded traveling wave related parameters are consistent with the traveling wave related parameters; performing same-attribute concentrated value sorting on the plurality of recorded traveling wave signals to obtain a concentrated interval of each attribute, and setting the concentrated interval as the baseline traveling wave signal; Calculate the deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal.

5. The method according to claim 4, wherein Calculating a deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal includes: Extracting a first-class traveling wave signal attribute and a second-class traveling wave signal attribute of the traveling wave signal, wherein the first-class traveling wave signal attribute represents an attribute set having a correlation coefficient with the fault greater than or equal to a correlation coefficient threshold, and the second-class traveling wave signal attribute represents an attribute set having a correlation coefficient with the fault less than the correlation coefficient threshold; Performing same-attribute deviation calculation on the attributes of the type of traveling wave signal to obtain a type of traveling wave signal deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal; Counting the number of attributes of the second type of traveling wave signal that deviate from the baseline, and obtaining a second type of traveling wave signal deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal; The first type of traveling wave signal deviation vector and the second type of traveling wave signal deviation vector are added to the deviation vector.

6. The method according to claim 1, wherein Counting the fault triggering probability of the transmission line satisfying the deviation vector includes: Obtaining a fault trigger probability prediction network, wherein the fault trigger probability prediction network is generated by training multiple sets of data based on machine learning, wherein any set of the multiple sets of data includes: deviation vector record data of historical transmission lines with the same topology as the transmission line and a label identifying a true value of the fault trigger probability; Obtaining a set of training deviation vectors for a preset time zone of the fault trigger probability prediction network; Calculate the mean Euclidean distance between the deviation vector and the set of training deviation vectors, and according to the rule that the larger the mean Euclidean distance, the more integrated models, perform output mean integration of multiple fault trigger probability prediction networks to obtain a temporary prediction model of fault trigger probability, process the deviation vector, output the fault trigger probability, and delete the temporary prediction model of fault trigger probability.

7. The method according to claim 6, wherein According to the rule that the larger the mean value of the Euclidean distance is, the more integrated models there are, the output mean integration of multiple fault trigger probability prediction networks is performed to obtain a temporary prediction model of the fault trigger probability, including: Calculate the square value of the mean of the Euclidean distance and set it as the number of predicted network integration; A plurality of the fault trigger probability prediction networks are integrated according to the number of prediction network integrations to obtain the temporary prediction model for the fault trigger probability.

8. The method according to claim 1, wherein The steps for obtaining multiple fault detection durations include: A plurality of fault detection durations of a plurality of fault line samples having a second recorded line topology that is the same as the transmission line topology and a recorded deviation vector that is consistent with the deviation vector are retrieved.

9. An integrated monitoring device for transmission line fault hazards, characterized in that: The device is communicatively connected to the integrated monitoring terminal, and is used to execute the method according to any one of claims 1 to 8, and the device includes: An acquisition and monitoring module, configured to acquire traveling wave related parameters and monitor traveling wave signals when a first monitoring period is satisfied; a deviation vector calculation module, configured to collect statistics on baseline traveling wave signals of fault-free line samples that meet the traveling wave related parameters, and calculate a deviation vector between the baseline traveling wave signal and the monitoring traveling wave signal; a statistical module, configured to calculate a fault trigger probability of a transmission line satisfying the deviation vector; An updating module is configured to, when the fault trigger probability is greater than or equal to a fault probability threshold, retrieve the high-frequency fault detection duration of the transmission line that satisfies the deviation vector, shorten the high-frequency fault detection duration by at least 0.5 times, obtain a second monitoring period, and replace the first monitoring period with the second monitoring period.

Images