A power transmission line emergency disconnection safety protection system and disconnection protection device

Abstract

This invention relates to the field of emergency protection circuit technology, specifically to an emergency disconnection safety protection system and disconnection protection device for transmission lines. The system includes: a data acquisition module for acquiring the voltage signal of each phase of the transmission line connected to the switchgear within a preset time period before each moment, and recording it as the voltage signal of each phase at each moment; a circuit analysis module for constructing multi-dimensional feature factors based on harmonic variation trends, voltage deviations, etc.; calculating the anomaly score and feature weight of each feature factor using the isolated forest algorithm, and determining the total anomaly score by combining similarity analysis, thus constructing anomaly factors; and a safety protection module for disconnecting and protecting the transmission line based on the anomaly factors. This application solves the problem of misjudging the health status of transmission lines caused by traditional fixed thresholds, improving power supply reliability and user power stability.

Description

Technical Field

[0001] This invention relates to the field of emergency protection circuit technology, specifically to an emergency disconnection safety protection system and disconnection protection device for power transmission lines. Background Technology

[0002] The KYN28A-12 AC metal-enclosed switchgear, also known as a switch cabinet, is a complete set of indoor power distribution equipment for three-phase AC, single busbar, and single busbar segmented systems. It is widely used in indoor power supply systems of power plants, substations, airports, docks, factories, mines, hotels, financial institutions, high-rise buildings, and civil buildings to receive and distribute electrical energy and monitor and protect the power grid.

[0003] In power distribution networks with large-scale distributed power sources, the harmonics injected into the distribution network by these sources exhibit strong time-varying characteristics, resulting in significant voltage deviations and harmonic fluctuations. Switchgear, which relies solely on fixed thresholds to identify abnormal harmonics and voltage deviations, cannot effectively distinguish between short-term power fluctuations and transmission line faults. This leads to frequent misjudgments by protection devices, severely impacting power supply reliability and the stability of electricity consumption for users. Summary of the Invention

[0004] To address the aforementioned technical problems, the present invention aims to provide an emergency power transmission line disconnection safety protection system and disconnection protection device, the specific technical solution of which is as follows:

[0005] This invention proposes an emergency disconnection safety protection system for power transmission lines, the system comprising:

[0006] The data acquisition module is used to acquire the voltage signal of each phase of the transmission line connected to the switchgear within a preset time period before each moment, and record it as the voltage signal of each phase at each moment.

[0007] The circuit analysis module is used to determine the abnormal characteristic values ​​of each harmonic in each phase voltage signal at each time point based on the changing trend of the harmonic content rate of the same harmonic at all times within a preset time period before each time point, and the difference between the harmonic content rate of each harmonic and the preset harmonic content rate limit; based on the difference between the effective voltage value of each phase voltage signal at each time point and the preset rated voltage, the module determines the voltage deviation value of each phase voltage signal at each time point, and in combination with the abnormal characteristic values, determines the voltage characteristic value of each phase voltage signal at each time point, which, together with the abnormal characteristic value, is collectively referred to as the characteristic factor;

[0008] The isolated forest algorithm is used to obtain the anomaly scores of each feature factor in the voltage signal of each phase at each time point in all the isolated trees in which it belongs. Combined with the distribution of each feature factor in the isolated trees, the anomaly score vector and feature vector of each feature factor are constructed. By analyzing the similarity between the anomaly score vector and the feature vector, the feature weight of each feature factor is determined. Based on the anomaly score of each feature factor in any isolated tree in which it belongs and the average distribution of the feature weights of all feature factors in any isolated tree, the total anomaly score of each feature factor is determined, so as to determine the anomaly factors of each phase voltage signal at each time point.

[0009] The safety protection module is used to disconnect and protect the transmission line based on the abnormal factors.

[0010] Preferably, the expression for the abnormal characteristic value of each harmonic in each phase voltage signal at each time point is: In the formula, This represents the abnormal characteristic value of the kth harmonic in the j-th phase voltage signal at time i; This represents the slope of the fitted straight line obtained by fitting the harmonic content rate of the kth harmonic of the j-th phase voltage signal at all times within a preset time period before time i. This represents the harmonic content of the k-th harmonic in the j-th phase voltage signal at time n within a preset time period prior to time i. represents the preset harmonic content limit; N represents the number of all moments within the preset duration; norm() represents the normalization function; exp() represents the exponential function with the natural constant as the base.

[0011] Preferably, the method for determining the voltage deviation value of each phase voltage signal at each time point is as follows:

[0012] The exponentialized result of the difference between the effective voltage value of each phase voltage signal and the preset rated voltage at each time point is calculated, and the sum of the exponentialized results at all times within the preset time period before each time point is used as the voltage deviation value of each phase voltage signal at each time point.

[0013] Preferably, the method for determining the voltage characteristic value of each phase voltage signal at each time point is as follows:

[0014] Calculate the mean value of the abnormal characteristic values ​​of all harmonics of each phase voltage signal at each time point. Among all harmonics, calculate the average value of the abnormal characteristic values ​​that are greater than the mean value. The result of positively fusing the average value with the corresponding voltage deviation value is taken as the voltage characteristic value of each phase voltage signal at each time point.

[0015] Preferably, the method of using the isolated forest algorithm to obtain the anomaly scores of each feature factor in the voltage signal of each phase at each time point in all the isolated trees in which it resides, and combining the distribution of each feature factor in the isolated trees to construct the anomaly score vector and feature vector of each feature factor, includes:

[0016] All feature factors in each phase voltage signal at each time point are used as input to the isolated forest algorithm. A preset number of abnormal feature values ​​are randomly selected from all abnormal feature values ​​of all feature factors and combined with the voltage deviation value to form a feature set for constructing an isolated tree. The abnormal score of each feature factor in all its isolated trees is output.

[0017] The abnormal scores of each feature factor in all its isolated trees are combined to form an abnormal score vector;

[0018] Calculate the sum of all other feature factors in any isolated tree for each feature factor, and record it as the feature value of each feature factor in any isolated tree. Combine the feature values ​​of each feature factor in all isolated trees to form the feature vector of each feature factor.

[0019] Preferably, the expression for the feature weights of each feature factor is: In the formula; This represents the feature weight of feature factor m; This represents the similarity between the outlier score vector of feature factor m and the feature vector.

[0020] Preferably, the method for determining the total anomaly score of each feature factor is as follows:

[0021] Calculate the product of the anomaly score of each feature factor in any isolated tree it belongs to and the mean of the feature weights of all feature factors in that isolated tree. The sum of the product of the product of each feature factor in all isolated trees it belongs to is taken as the total anomaly score of each feature factor.

[0022] Preferably, the method for determining the anomaly factor of each phase voltage signal at each time point is as follows:

[0023] The total anomaly score of all feature factors corresponding to each phase voltage signal at each time step is used as the input of the threshold segmentation algorithm. The output is the segmentation threshold. The sum of all total anomaly scores greater than the segmentation threshold is calculated. The sum of this sum and the sum of the total anomaly scores of all feature factors are used as the anomaly factor of each phase voltage signal at each time step.

[0024] Preferably, the method of disconnecting and protecting the transmission line includes:

[0025] According to the method for obtaining abnormal factors, the abnormal factors of the voltage signal of each phase at a preset number of time points during the normal operation of the transmission line are obtained, and the maximum abnormal factor is used as the abnormal threshold.

[0026] If the abnormal factor of any voltage signal at the current moment is greater than the corresponding abnormal threshold, the power transmission line connected to the switchgear will be disconnected; otherwise, the power transmission line connected to the switchgear will not be disconnected.

[0027] This application also proposes an emergency disconnection protection device for power transmission lines, including the aforementioned emergency disconnection safety protection system for power transmission lines.

[0028] The present invention has the following beneficial effects:

[0029] This application constructs a multi-dimensional feature factor by integrating the dynamic trend of harmonic changes and the static degree of exceeding limits, as well as the deviation of the effective voltage value. This effectively overcomes the shortcomings of the traditional fixed threshold method, which is prone to misjudgment in the context of distributed power source access, and helps to improve the accuracy of dynamic assessment of abnormal risks of transmission lines. Furthermore, this application constructs anomaly factors by introducing the isolated forest algorithm, combining the anomaly scores of feature factors with a dynamic weight allocation mechanism based on information uniqueness. This accurately reflects the overall risk level of the transmission line, improves the accuracy and reliability of emergency disconnection safety protection system judgment in complex power grid environments, and effectively avoids misjudgment and missed judgment. In summary, this application addresses the problem of strong time-varying harmonics and the susceptibility to misjudgment of traditional fixed threshold protection in distribution networks containing distributed power sources. By dynamically extracting multi-dimensional features such as the harmonic change trend and voltage deviation of voltage signals, and using the isolated forest algorithm to perform anomaly scoring and weight allocation on each feature, anomaly factors are generated to accurately identify the true fault state of the line. This effectively avoids false disconnection caused by normal fluctuations of distributed power sources, and significantly improves the reliability of power supply and the stability of user power consumption. Attached Figure Description

[0030] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. 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 effort.

[0031] Figure 1 A block diagram of an emergency disconnection safety protection system for power transmission lines provided in one embodiment of the present invention;

[0032] Figure 2 The flowchart illustrates the process of obtaining abnormal factors according to an embodiment of the present invention. Detailed Implementation

[0033] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a power transmission line emergency disconnection safety protection system and disconnection protection device proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0035] The following description, in conjunction with the accompanying drawings, details a specific scheme for an emergency power transmission line disconnection safety protection system provided by the present invention.

[0036] Please see Figure 1 The diagram illustrates a block diagram of an emergency disconnection safety protection system for power transmission lines according to an embodiment of the present invention. The system includes: a data acquisition module 101, a circuit analysis module 102, and a safety protection module 103.

[0037] The data acquisition module 101 is used to acquire the voltage signal of each phase of the transmission line connected to the switch cabinet within a preset time period before each time, and record it as the voltage signal of each phase at each time.

[0038] In the transmission line, the voltage signal of each phase of the transmission line connected to the switchgear is acquired within a preset time period before each moment, and recorded as the voltage signal of each phase at each moment. The data acquisition frequency is set to f. In this embodiment, the value of the data acquisition frequency f is set manually. In this embodiment, the value of the data acquisition frequency f is 10kHz. In actual application, as other implementation methods, the implementer can also set it according to the specific situation. This embodiment does not impose any special restrictions.

[0039] The circuit analysis module 102 is used to construct multi-dimensional feature factors based on harmonic variation trends, voltage deviations, etc.; calculate the anomaly score and feature weight of each feature factor through the isolated forest algorithm, and determine the total anomaly score by combining similarity analysis, thereby identifying the anomaly factors of each phase voltage signal at each time.

[0040] S1: Based on the changing trend of the harmonic content rate of the same harmonic in each phase voltage signal at all times within a preset time period before each time, and the difference between the harmonic content rate of each harmonic and the preset harmonic content rate limit, the abnormal characteristic value of each harmonic in each phase voltage signal at each time is determined; based on the difference between the effective voltage value of each phase voltage signal at each time and the preset rated voltage, the voltage deviation value of each phase voltage signal at each time is determined, and combined with the abnormal characteristic value, the voltage characteristic value of each phase voltage signal at each time is determined, and together with the abnormal characteristic value, they are collectively referred to as characteristic factors.

[0041] In power systems with widespread distributed generation, the time-varying and dynamic fluctuations of harmonic signals are becoming increasingly significant. Traditional fixed threshold methods, relying solely on instantaneous values ​​for judgment, are ill-suited to complex and ever-changing operating environments, easily misinterpreting normal fluctuations as faults, thus triggering unnecessary protection actions and impacting power supply reliability. Therefore, to address this issue, this embodiment analyzes the dynamic trends of harmonic content in voltage signals to capture their dynamic evolution. Simultaneously, by combining the deviation between the effective voltage value and the rated voltage, it distinguishes between normal harmonic fluctuations and potential faults, thereby reducing the risk of misjudgment. The specific process is as follows:

[0042] In this embodiment, firstly, the voltage signal of each phase at each time moment is used as the input of the Fourier transform algorithm, and the fundamental wave and all harmonics of the voltage signal of each phase at each time moment are output. Based on the amplitude of the fundamental wave and all harmonics, the harmonic content of each harmonic is calculated. The Fourier transform algorithm and the specific calculation formula and method of the harmonic content are well known technologies. The specific process of obtaining the fundamental wave and harmonics of the voltage signal using the Fourier transform algorithm and the specific calculation process of the harmonic content are not described in detail.

[0043] Furthermore, this embodiment determines the abnormal characteristic values ​​of each harmonic in the voltage signal of each phase at each time point based on the changing trend of the harmonic content rate of the same harmonic at all times within a preset time period before each time point, and the difference between the harmonic content rate of each harmonic and the preset harmonic content rate limit. This is to quantify the degree of change and exceedance of the harmonic content rate, and to avoid misjudging the normal fluctuations of the distributed power source's operating state as transmission line abnormalities. Specifically:

[0044] As one implementation method, in this embodiment, the abnormal characteristic value of the kth harmonic in the j-th phase voltage signal at time i is... The expression is: In the formula, This represents the slope of the fitted straight line obtained by fitting the harmonic content rate of the kth harmonic of the j-th phase voltage signal at all times within a preset time period before time i. This represents the harmonic content of the k-th harmonic in the j-th phase voltage signal at time n within a preset time period prior to time i. represents the preset harmonic content limit; N represents the number of all moments within the preset duration; norm() represents the normalization function; exp() represents the exponential function with the natural constant as the base.

[0045] It should be noted that the preset harmonic content rate limit is set manually. In this embodiment, the preset harmonic content rate limit is 0.032. In actual applications, as other implementation methods, implementers need to set it according to specific circumstances.

[0046] It should be noted that there are many commonly used fitting algorithms. In this embodiment, the least squares method is used to fit the harmonic content rate. In practical applications, as other implementation methods, implementers may also use other fitting methods such as polynomial function fitting method according to specific circumstances. This embodiment does not impose any special restrictions on the selection of fitting algorithms.

[0047] The least squares method is a well-known technique, and the specific process of fitting the blood inclusion rate using the least squares method will not be elaborated here.

[0048] Based on the abnormal characteristic values ​​of each harmonic in the voltage signal of each phase at each time point, it can be understood that the abnormal characteristic values ​​are used to reflect the degree of abnormality of the harmonic components. If the slope of the fitted line obtained by fitting the harmonic content rate of the kth harmonic of the phase j voltage signal at all times within the preset time period before time i is positive and larger, it indicates that the harmonic content rate of the kth harmonic is showing a rapid upward trend, indicating that the degree of abnormality of the kth harmonic is higher. Therefore, the greater the corresponding degree of abnormality, the more likely the transmission line is to experience a fault. At the same time, if the difference between the harmonic content rate of the kth harmonic in the phase j voltage signal at time n within the preset time period before time i and the harmonic content rate limit is larger, that is... The larger the value, the more the harmonic content of the kth harmonic exceeds the harmonic content limit, indicating that the anomalous component of the kth harmonic is more severe. Therefore, the anomalous characteristic value of the kth harmonic is correspondingly larger, which means that the transmission line is more likely to have an abnormal risk.

[0049] Conversely, if the slope of the fitted line obtained by fitting the harmonic content rate of the kth harmonic of the j-th phase voltage signal at all times within the preset time period before time i is negative or 0, or a very small positive value, it indicates that the harmonic content rate of the kth harmonic is decreasing or remaining stable, indicating that the degree of anomaly of the kth harmonic is low or improving. Therefore, the smaller the corresponding degree of anomaly, the lower the risk of transmission line failure due to this harmonic. At the same time, the smaller the difference between the harmonic content rate of the kth harmonic in the j-th phase voltage signal at time n within the preset time period before time i, i.e. The smaller the value, the less the harmonic content of the kth harmonic exceeds the harmonic content limit or is completely within the normal range. This indicates that the abnormality of the kth harmonic component is more slight or non-existent. Therefore, the abnormal characteristic value of the kth harmonic is correspondingly smaller, which means that the transmission line is less likely to have abnormal risks.

[0050] Furthermore, since harmonic anomalies are a cause of voltage anomalies in power systems containing distributed generation, and power flow changes in distributed generation can also cause voltage deviations, and severe voltage imbalance indirectly indicates anomalies in transmission lines, this embodiment determines the voltage deviation value of each phase voltage signal at each time point based on the difference between the effective voltage value of each phase voltage signal and the preset rated voltage. This quantifies the amplitude and frequency of the voltage deviation, judges the degree of voltage deviation, and thus determines whether the transmission line is abnormal, avoiding misjudging normal fluctuations in the operating state of distributed generation as transmission line anomalies. Specifically:

[0051] In this embodiment, the exponentialized result of the difference between the effective voltage value of each phase voltage signal and the preset rated voltage at each time moment is calculated, and the sum of the exponentialized results at all times within a preset time period before each time moment is used as the voltage deviation value of each phase voltage signal at each time moment.

[0052] Based on the voltage deviation value of each phase voltage signal at each time point, it can be understood that the voltage deviation value is used to reflect the degree to which the effective voltage value of the voltage signal deviates from the rated voltage at each time point. If the voltage deviation value of the voltage signal at the current time point is larger, it means that the effective voltage value of the voltage signal has exceeded the rated voltage more times and the deviation amplitude is larger within the preset time period before the current time point. Therefore, the larger the corresponding voltage deviation value, the greater the degree of voltage deviation, which means that the transmission line is more likely to have an anomaly.

[0053] Conversely, if the voltage deviation of the voltage signal at the current moment is smaller, it means that the effective voltage value of the voltage signal has exceeded the rated voltage fewer times or even none within the preset time period before the current moment. Even if there is an over-limit, the deviation amplitude is also small. Therefore, the corresponding voltage deviation value is small, indicating that the degree of voltage deviation is lower, the overall voltage level is stable and close to the rated value. This means that the transmission line is operating in a normal and healthy state, and the possibility of abnormalities caused by voltage deviation is also smaller.

[0054] It should be noted that in this embodiment, the exponential function value of the effective voltage value of each phase voltage signal at each time point and the preset rated voltage at each time point will be used as the base of the natural constant and the value of the exponential function ...

[0055] It should be noted that the preset rated voltage is set manually. In this embodiment, the preferred rated voltage is 0.7kV. In actual applications, as in other implementation methods, the implementer needs to set it according to the specific circumstances.

[0056] The effective value of voltage is a well-known technique, and its specific acquisition process will not be elaborated here.

[0057] Based on the voltage deviation value of each phase voltage signal at each time point, it can be understood that, further, this embodiment determines the voltage characteristic value of each phase voltage signal at each time point based on the voltage deviation value of each phase voltage signal at each time point and in combination with the aforementioned abnormal characteristic value, in order to assess the abnormal risk situation of the transmission line, specifically as follows:

[0058] In this embodiment, the mean value of the abnormal characteristic values ​​of all subharmonics of the voltage signal of each phase at each time is calculated. Among all subharmonics, the average value of the abnormal characteristic values ​​that are greater than the mean value is calculated. The result of positively fusing the average value with the corresponding voltage deviation value is used as the voltage characteristic value of the voltage signal of each phase at each time.

[0059] It should be understood that positive fusion refers to combining two or more indicators through addition or multiplication to obtain a comprehensive indicator, thereby more comprehensively and accurately assessing a phenomenon or problem. This fusion method is not limited to simple arithmetic operations, but can also include more complex statistical models and analytical methods. Implementers can choose according to specific circumstances, and this embodiment does not impose any special restrictions.

[0060] Preferably, as one implementation method, this embodiment uses the product of the average value and the corresponding voltage deviation value as the voltage characteristic value of each phase voltage signal at each time. In practical applications, as other implementation methods, implementers may also adopt other positive fusion methods such as sum values ​​according to specific circumstances. This embodiment does not impose any special restrictions.

[0061] Based on the voltage characteristic values ​​of each phase voltage signal at each time point, it can be understood that the voltage characteristic values ​​integrate the harmonic anomalies and voltage deviation characteristics of the voltage signal, jointly assessing the abnormal risk of the transmission line. If the number of harmonics in the voltage signal that exceed the average value of the abnormal characteristic values ​​within a preset time period before the current time point indicates a higher degree of harmonic anomaly in the voltage signal within that time period, it means that the transmission line is more likely to have an abnormal risk, and therefore, the corresponding voltage characteristic value is larger. At the same time, if the voltage deviation value of the voltage signal within a preset time period before the current time point is larger, it indicates a greater degree of voltage deviation, which means that the transmission line is more likely to have an anomaly, and therefore, the corresponding voltage characteristic value is larger.

[0062] Conversely, if the harmonic number exceeding the average abnormal characteristic value in the voltage signal within a preset time period before the current moment is very small or nonexistent, it indicates that the degree of harmonic anomaly in the voltage signal was low in the period before the current moment. This means that the transmission line is operating relatively smoothly, and the possibility of a fault caused by harmonic anomaly is small. Therefore, the corresponding voltage characteristic value is smaller. At the same time, if the voltage deviation value of the voltage signal within a preset time period before the current moment is smaller, it indicates that the voltage is closer to its rated value and the voltage fluctuation is within the normal allowable range. This means that the voltage quality of the transmission line is good, and the possibility of anomalies caused by voltage deviation is also low. Therefore, the corresponding voltage characteristic value is smaller.

[0063] Finally, for ease of description, the abnormal characteristic values ​​and voltage deviation values ​​of all harmonics of each phase voltage signal at each time point are collectively referred to as characteristic factors.

[0064] Thus, this embodiment constructs a multidimensional feature factor by integrating the dynamic change trend of harmonics with the static degree of exceeding limits, as well as the deviation of the effective voltage value. This effectively overcomes the shortcomings of the traditional fixed threshold method in the context of distributed power source access, and helps to improve the accuracy of dynamic assessment of abnormal risks of transmission lines.

[0065] S2: The isolated forest algorithm is used to obtain the anomaly scores of each feature factor in the voltage signal of each phase at each time point in all the isolated trees in which it belongs. Combined with the distribution of each feature factor in the isolated trees, the anomaly score vector and feature vector of each feature factor are constructed. By analyzing the similarity between the anomaly score vector and the feature vector, the feature weight of each feature factor is determined. Based on the anomaly score of each feature factor in any isolated tree in which it belongs and the average distribution of the feature weights of all feature factors in the isolated tree, the total anomaly score of each feature factor is determined, so as to determine the anomaly factor of each phase voltage signal at each time point.

[0066] In the complex and ever-changing power grid operating environment, single features are often susceptible to noise interference, making it difficult to accurately reflect the true operating status of transmission lines, thus increasing the risk of misjudgment or omission. Therefore, to solve this problem, this embodiment introduces the isolated forest algorithm to achieve efficient anomaly detection of multi-dimensional feature data. Specifically, this embodiment uses the isolated forest algorithm to obtain the anomaly scores of each feature factor in each phase voltage signal at each time point in all its isolated trees, and combines the distribution of each feature factor in the isolated trees to construct the anomaly score vector and feature vector of each feature factor. By analyzing the similarity between the anomaly score vector and the feature vector, the feature weight of each feature factor is determined. Based on the anomaly score of each feature factor in any isolated tree and the average distribution of the feature weights of all feature factors in any isolated tree, the total anomaly score of each feature factor is determined to identify the anomaly factors of each phase voltage signal at each time point, so as to assess the anomaly situation of the transmission line. The specific process is as follows:

[0067] In this embodiment, firstly, the isolated forest algorithm is used to obtain the anomaly scores of each feature factor in the voltage signal of each phase at each time point in all the isolated trees in which it resides. Then, the distribution of each feature factor in the isolated trees is combined to construct the anomaly score vector and feature vector of each feature factor. Specifically:

[0068] In this embodiment, all feature factors of each phase of the electrical signal at each time point are used as input to the isolated forest algorithm. In this embodiment, the number of isolated trees is set to 100, and the number of subsamples extracted each time is 256. Each time an isolated tree is constructed, a preset number of abnormal feature values ​​are randomly selected from all abnormal feature values ​​of all feature factors, and these abnormal feature values ​​are combined with the voltage deviation value to form a feature set for constructing the isolated tree. Finally, the abnormal score of each feature factor in all its isolated trees is output.

[0069] The preset quantity is set manually. In this embodiment, the preset quantity is 5. In actual application, as other implementation methods, the implementer can also set it according to the specific situation. This embodiment does not impose any special restrictions.

[0070] The isolated forest algorithm is a well-known technique, and the specific process of using it to construct isolated trees and obtain anomaly scores will not be elaborated here.

[0071] Furthermore, in this embodiment, the abnormal scores of each feature factor in all the isolated trees in which it resides are combined into an abnormal score vector;

[0072] Calculate the sum of all other feature factors in any isolated tree for each feature factor, and record it as the feature value of each feature factor in any isolated tree. Combine the feature values ​​of each feature factor in all isolated trees to form the feature vector of each feature factor.

[0073] Furthermore, this embodiment determines the feature weights of each feature factor by analyzing the similarity between the anomaly score vector and the feature vector, thereby quantifying the contribution of the feature factors to the voltage signal anomaly assessment. Specifically:

[0074] In this embodiment, the feature weights of feature factor m The expression is: In the formula; This represents the similarity between the outlier score vector of feature factor m and the feature vector.

[0075] It should be noted that there are many methods to measure the similarity between vectors. In this embodiment, the cosine similarity between the abnormal score vector of feature factor m and the feature vector is used as the similarity between the abnormal score vector of feature factor m and the feature vector. In practical applications, as other implementation methods, implementers may also use other methods to measure the similarity between vectors, such as the reciprocal of Euclidean distance, depending on the specific circumstances. This embodiment does not impose any special restrictions on the selection of methods to measure the similarity between vectors.

[0076] The formula and method for calculating cosine similarity are well-known techniques, and the specific calculation process will not be elaborated here.

[0077] Based on the feature weights of each feature factor, it can be understood that the feature weights quantify the contribution of the feature factor to the assessment of voltage signal anomalies. If the similarity between the current feature factor's anomaly score vector and the feature vector is greater, i.e., the similarity is closer to 1, it indicates that the contribution of the current feature factor is redundant, does not provide new and independent information, and its behavior can be explained and predicted by other features. Therefore, the feature weight of the current feature factor is also smaller. Conversely, if the similarity between the current feature factor's anomaly score vector and the feature vector is smaller, i.e., the similarity is closer to -1, it indicates that the contribution of the current feature factor is unique and crucial. It provides entirely new information that other features do not possess, and its behavior cannot be explained and predicted by other features. Therefore, the feature weight of the current feature factor is also greater.

[0078] Furthermore, this embodiment determines the total anomaly score of each feature factor based on the anomaly score of each feature factor in any isolated tree and the average distribution of the feature weights of all feature factors in that isolated tree, in order to determine the anomaly factor of each phase voltage signal at each time point and to assess the degree of anomaly of the voltage signal, specifically as follows:

[0079] In this embodiment, the anomaly score of each feature factor in any isolated tree is calculated by multiplying it by the mean of the feature weights of all feature factors in that isolated tree. The sum of the multiplication results of each feature factor in all isolated trees is then used as the total anomaly score of each feature factor.

[0080] Based on the total anomaly score of each feature factor, it can be understood that the total anomaly score is used to assess the degree of anomaly of the voltage signal. If the current feature factor has a larger weight among all feature factors in its isolated tree and a larger anomaly score in its isolated tree, it means that from the perspective of the isolated tree where the current feature factor is located, the voltage signal is more likely to be abnormal, which means that the transmission line is more likely to be abnormal.

[0081] Conversely, if the weight of the current feature factor among all feature factors in its isolated tree is smaller, or its anomaly score is smaller, it means that in the specific fault mode or data subspace represented by the isolated tree, the current feature factor contributes less to judging the voltage signal anomaly, or it does not show any obvious abnormal state. This indicates that from the perspective of the isolated tree, the possibility of voltage signal anomaly is small, and correspondingly, its contribution to judging the overall risk of anomaly in the transmission line is reduced. This indirectly reflects that the isolated tree tends to believe that the current transmission line is operating normally and does not meet the conditions for triggering protection action.

[0082] Furthermore, in this embodiment, the total anomaly score of all feature factors corresponding to each phase voltage signal at each time step is used as the input of the threshold segmentation algorithm, the segmentation threshold is output, the sum of all total anomaly scores greater than the segmentation threshold is calculated, and the sum of the sum of all feature factor total anomaly scores is used as the anomaly factor of each phase voltage signal at each time step.

[0083] Based on the anomaly factor of the voltage signal of each phase at each time, it can be understood that the anomaly factor is used to characterize the overall risk level of the transmission line status. If the anomaly factor of the voltage signal at the current time is larger, it indicates that the voltage data of the transmission line is continuously and frequently abnormal, and the degree of abnormality is relatively serious. It is no longer an occasional fluctuation, but a fault symptom with a moving trend. Therefore, it is judged that there is an anomaly in the transmission line and preparations are made to disconnect it.

[0084] Conversely, if the abnormal factor of the voltage signal is smaller at the current moment, it indicates that even if there are individual instantaneous fluctuations or slight anomalies in the voltage data of the transmission line, their frequency is low and their degree is slight, and they have not formed a continuous deterioration trend. These fluctuations are still within the range of random disturbances allowed by the normal operation of the power grid. Therefore, it can be judged that the operation of the transmission line is stable, there is no substantial risk of failure, and there is no need to take protective measures such as disconnection. The power system will continue to operate normally, thereby ensuring the continuity and reliability of power supply.

[0085] It should be noted that there are many commonly used threshold segmentation algorithms. In this embodiment, the Otsu threshold segmentation algorithm is used to divide the total anomaly score. In practical applications, as other implementation methods, implementers may also use other threshold segmentation algorithms according to specific circumstances. This embodiment does not impose any special restrictions.

[0086] Among them, the Otsu threshold segmentation algorithm is a well-known technique, and the specific process of using it to divide the total anomaly score will not be described in detail.

[0087] Preferably, the flowchart of the abnormal factor acquisition process provided in this embodiment is as follows: Figure 2 As shown.

[0088] Thus, this embodiment, by introducing the isolated forest algorithm and combining the anomaly scores of feature factors with a dynamic weight allocation mechanism based on information uniqueness, constructs anomaly factors, thereby accurately reflecting the overall risk level of transmission lines, improving the accuracy and reliability of emergency disconnection safety protection system judgment in complex power grid environments, and effectively avoiding misjudgments and omissions.

[0089] The safety protection module 103 is used to disconnect and protect the transmission line based on the abnormal factors.

[0090] According to the method for obtaining abnormal factors described in S2, the abnormal factors of each phase voltage signal at a preset number of time points during the normal operation of the transmission line are obtained, and the maximum abnormal factor is used as the abnormal threshold.

[0091] It should be noted that the preset number is set manually. In this embodiment, the preset number is 10000. In actual application, as other implementation methods, implementers can also set it according to specific circumstances. This embodiment does not impose any special restrictions.

[0092] If the abnormal factor of any voltage signal at the current moment is greater than the corresponding abnormal threshold, it indicates that there is an abnormality in the power transmission circuit connected to the switchgear, and the power transmission line connected to the switchgear is immediately disconnected. Conversely, if the abnormal factor of any voltage signal at the current moment is less than or equal to the corresponding abnormal threshold, it indicates that the power transmission line connected to the switchgear is normal, and the power transmission line connected to the switchgear is not disconnected.

[0093] Thus, this embodiment addresses the problem of strong harmonic time-varying characteristics and easy misjudgment by traditional fixed threshold protection in distribution networks containing distributed power sources. By dynamically extracting multi-dimensional features such as voltage signal harmonic variation trends and voltage deviations, and using the isolated forest algorithm to perform anomaly scoring and weight allocation on each feature, anomaly factors are comprehensively generated to accurately identify the true fault state of the line. This effectively avoids false disconnections caused by normal fluctuations of distributed power sources, and significantly improves power supply reliability and user power stability.

[0094] Based on the same inventive concept as the above method, this application also proposes an emergency disconnection protection device for power transmission lines, including the aforementioned emergency disconnection safety protection system for power transmission lines.

[0095] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0096] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0097] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A power transmission line emergency disconnection safety protection system, characterized in that, The system includes: The data acquisition module is used to acquire the voltage signal of each phase of the transmission line connected to the switchgear within a preset time period before each moment, and record it as the voltage signal of each phase at each moment. The circuit analysis module is used to determine the abnormal characteristic values ​​of each harmonic in each phase voltage signal at each time point based on the changing trend of the harmonic content rate of the same harmonic at all times within a preset time period before each time point, and the difference between the harmonic content rate of each harmonic and the preset harmonic content rate limit; based on the difference between the effective voltage value of each phase voltage signal at each time point and the preset rated voltage, the module determines the voltage deviation value of each phase voltage signal at each time point, and in combination with the abnormal characteristic values, determines the voltage characteristic value of each phase voltage signal at each time point, which, together with the abnormal characteristic value, is collectively referred to as the characteristic factor; The isolated forest algorithm is used to obtain the anomaly scores of each feature factor in the voltage signal of each phase at each time point in all the isolated trees in which it belongs. Combined with the distribution of each feature factor in the isolated trees, the anomaly score vector and feature vector of each feature factor are constructed. By analyzing the similarity between the anomaly score vector and the feature vector, the feature weight of each feature factor is determined. Based on the anomaly score of each feature factor in any isolated tree in which it belongs and the average distribution of the feature weights of all feature factors in any isolated tree, the total anomaly score of each feature factor is determined, so as to determine the anomaly factors of each phase voltage signal at each time point. The safety protection module is used to disconnect and protect the transmission line based on the abnormal factors.

2. The emergency disconnection safety protection system for power transmission lines according to claim 1, characterized in that, The expression for the abnormal characteristic value of each harmonic in each phase voltage signal at each time point is: In the formula, This represents the abnormal characteristic value of the kth harmonic in the j-th phase voltage signal at time i; This represents the slope of the fitted straight line obtained by fitting the harmonic content rate of the kth harmonic of the j-th phase voltage signal at all times within a preset time period before time i. This represents the harmonic content of the k-th harmonic in the j-th phase voltage signal at time n within a preset time period prior to time i. represents the preset harmonic content limit; N represents the number of all moments within the preset duration; norm() represents the normalization function; exp() represents the exponential function with the natural constant as the base.

3. The emergency disconnection safety protection system for power transmission lines according to claim 1, characterized in that, The method for determining the voltage deviation value of each phase voltage signal at each time point is as follows: The exponentialized result of the difference between the effective voltage value of each phase voltage signal and the preset rated voltage at each time point is calculated, and the sum of the exponentialized results at all times within the preset time period before each time point is used as the voltage deviation value of each phase voltage signal at each time point.

4. The emergency disconnection safety protection system for power transmission lines according to claim 1, characterized in that, The method for determining the voltage characteristic value of each phase voltage signal at each time point is as follows: Calculate the mean value of the abnormal characteristic values ​​of all harmonics of each phase voltage signal at each time point. Among all harmonics, calculate the average value of the abnormal characteristic values ​​that are greater than the mean value. The result of positively fusing the average value with the corresponding voltage deviation value is taken as the voltage characteristic value of each phase voltage signal at each time point.

5. The emergency disconnection safety protection system for power transmission lines according to claim 1, characterized in that, The isolated forest algorithm is used to obtain the anomaly scores of each feature factor in the phase voltage signal at each time step within all the isolated trees in which it resides. Combined with the distribution of each feature factor within the isolated trees, anomaly score vectors and feature vectors for each feature factor are constructed, including: All feature factors in each phase voltage signal at each time point are used as input to the isolated forest algorithm. A preset number of abnormal feature values ​​are randomly selected from all abnormal feature values ​​of all feature factors and combined with the voltage deviation value to form a feature set for constructing an isolated tree. The abnormal score of each feature factor in all its isolated trees is output. The abnormal scores of each feature factor in all its isolated trees are combined to form an abnormal score vector; Calculate the sum of all other feature factors in any isolated tree for each feature factor, and record it as the feature value of each feature factor in any isolated tree. Combine the feature values ​​of each feature factor in all isolated trees to form the feature vector of each feature factor.

6. The emergency disconnection safety protection system for power transmission lines according to claim 1, characterized in that, The expression for the feature weights of each feature factor is as follows: In the formula; This represents the feature weight of feature factor m; This represents the similarity between the outlier score vector of feature factor m and the feature vector.

7. The emergency disconnection safety protection system for power transmission lines according to claim 1, characterized in that, The method for determining the total anomaly score of each feature factor is as follows: Calculate the product of the anomaly score of each feature factor in any isolated tree it belongs to and the mean of the feature weights of all feature factors in that isolated tree. The sum of the product of the product of each feature factor in all isolated trees it belongs to is taken as the total anomaly score of each feature factor.

8. The emergency disconnection safety protection system for power transmission lines according to claim 1, characterized in that, The method for determining the anomaly factor of each phase voltage signal at each time point is as follows: The total anomaly score of all feature factors corresponding to each phase voltage signal at each time step is used as the input of the threshold segmentation algorithm. The output is the segmentation threshold. The sum of all total anomaly scores greater than the segmentation threshold is calculated. The sum of this sum and the sum of the total anomaly scores of all feature factors are used as the anomaly factor of each phase voltage signal at each time step.

9. The emergency disconnection safety protection system for power transmission lines according to claim 1, characterized in that, The aforementioned protection against power transmission line disconnection includes: According to the method for obtaining abnormal factors, the abnormal factors of the voltage signal of each phase at a preset number of time points during the normal operation of the transmission line are obtained, and the maximum abnormal factor is used as the abnormal threshold. If the abnormal factor of any voltage signal at the current moment is greater than the corresponding abnormal threshold, the power transmission line connected to the switchgear will be disconnected; otherwise, the power transmission line connected to the switchgear will not be disconnected.

10. An emergency disconnection protection device for power transmission lines, characterized in that, Including a power transmission line emergency disconnection safety protection system as described in any one of claims 1-9.

Images