Power transmission line emergency cut-off safety protection system and cut-off protection device

Abstract

The invention relates to the technical field of emergency protection circuits, in particular to a power transmission line emergency cut-off safety protection system and a cut-off protection device. The system comprises a data acquisition module used for acquiring a voltage signal of each phase of a power transmission line connected with a switch cabinet in a preset time period before each moment, and recording the voltage signal as a voltage signal of each phase at each moment; the circuit analysis module is used for constructing a multi-dimensional characteristic factor based on the harmonic change trend, the voltage deviation and the like; calculating an abnormal score and a feature weight of each feature factor through an isolated forest algorithm, determining a total abnormal score in combination with similarity analysis, and constructing an abnormal factor; and the safety protection module is used for carrying out cut-off protection on the power transmission line based on the abnormal factors. The problem of misjudgment of the health condition of the power transmission line caused by a traditional fixed threshold value is solved, and the power supply reliability and the power utilization stability of a user are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency protection circuits, and in particular to a power transmission line emergency cut-off safety protection system and a cut-off protection device. Background Art

[0002] KYN28A-12 AC metal-enclosed switchgear, also known as switchgear, is a complete indoor power distribution device for three-phase AC, single busbar and single busbar segmented systems. It is widely used in power supply systems in power plants, substations, airports, docks, factories, mines, enterprises, hotels, financial high-rise buildings and civil buildings, realizing the functions of receiving and distributing electric energy as well as monitoring and protecting the power grid.

[0003] In power distribution networks connected to large-scale distributed generation (DGs), the harmonics injected into the network by these DGs are highly time-varying, leading to significant fluctuations in voltage deviations and harmonics. However, switchgear, which only uses fixed thresholds to identify abnormal harmonics and voltage deviations, is unable to effectively distinguish between short-term power fluctuations and transmission line faults. This leads to frequent misjudgments by protective devices, severely impacting power supply reliability and the stability of consumer electricity consumption. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a power transmission line emergency cut-off safety protection system and a cut-off protection device, and the technical solutions adopted are as follows: The present invention provides a power transmission line emergency cut-off safety protection system, the system comprising: The data acquisition module is used to obtain the voltage signal of each phase of the transmission line connected to the switch cabinet within a preset 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 value of each harmonic in each phase voltage signal at each moment based on the change trend of the harmonic content rate of the same harmonic in each phase voltage signal at all moments within a preset time period before each moment, and the difference between the harmonic content rate of each harmonic and the preset harmonic content rate limit; determine the voltage deviation value of each phase voltage signal at each moment based on the difference between the voltage effective value of each phase voltage signal at each moment and the preset rated voltage, and determine the voltage characteristic value of each phase voltage signal at each moment in combination with the abnormal characteristic value, and the voltage characteristic value and the abnormal characteristic value are collectively referred to as the characteristic factor; The isolated forest algorithm is adopted to obtain an abnormal score of each feature factor in each phase voltage signal at each time in all isolated trees where the feature factor is located, and an abnormal score vector and a feature vector of each feature factor are constructed by combining the distribution of each feature factor in the isolated trees and by analyzing the similarity between the abnormal score vector and the feature vector to determine the feature weight of each feature factor; the total abnormal score of each feature factor is determined based on the abnormal score of each feature factor in any isolated tree where the feature factor is located and the average distribution of the feature weight of all feature factors in the any isolated tree, so as to determine the abnormal factor of each phase voltage signal at each time. The security protection module is configured to cut off the power transmission line based on the abnormal factor.

[0005] Preferably, the abnormal feature value of each harmonic in each phase voltage signal at each time is expressed as: ; in the formula, wherein, Vjk(i) represents the abnormal feature value of the kth harmonic in the jth phase voltage signal at the ith time; represents the slope of a fitting straight line obtained by fitting the harmonic content rate of the kth harmonic in the jth phase voltage signal at all times within a preset time length before the ith time; represents the harmonic content rate of the kth harmonic in the jth phase voltage signal at the nth time within the preset time length before the ith time; represents a preset harmonic content rate limit value; N represents the number of all times within the preset time length; norm() represents a normalization function; and exp() represents an exponential function with a natural constant as the base number.

[0006] Preferably, the determination method of the voltage deviation value of each phase voltage signal at each time is as follows: The exponential result of the difference between the voltage effective value of each phase voltage signal at each time and a preset rated voltage is calculated, and the cumulative sum of the exponential results at all times within a preset time length before each time is taken as the voltage deviation value of each phase voltage signal at each time.

[0007] Preferably, the determination method of the voltage feature value of each phase voltage signal at each time is as follows: The mean value of the abnormal feature values of all harmonics of each phase voltage signal at each time is calculated, the average value of the abnormal feature values greater than the mean value is calculated among all harmonics, and the result of the positive fusion of the average value and the corresponding voltage deviation value is taken as the voltage feature value of each phase voltage signal at each time.

[0008] Preferably, the isolated forest algorithm is adopted to obtain the abnormal score of each feature factor in each phase voltage signal at each time in all isolated trees where the feature factor is located, and the abnormal score vector and the feature vector of each feature factor are constructed by combining the distribution of each feature factor in the isolated trees and by analyzing the similarity between the abnormal score vector and the feature vector to determine the feature weight of each feature factor, and the method comprises the following steps: All characteristic factors in each phase voltage signal at each moment are used as input to the isolation forest algorithm. A preset number of abnormal characteristic values ​​are randomly selected from all abnormal characteristic values ​​of all characteristic factors, and together with the voltage deviation value, a feature set is formed to construct an isolation tree. The abnormality score of each characteristic factor in all its isolated trees is output; The abnormal scores of each feature factor in all its isolated trees are combined into an abnormal score vector; Calculate the cumulative result of all other characteristic factors in any isolated tree where each characteristic factor is located, record it as the eigenvalue of each characteristic factor in any isolated tree where it is located, and combine the eigenvalues ​​of each characteristic factor in all isolated trees where it is located to form the eigenvector of each characteristic factor.

[0009] Preferably, the expression of the characteristic weight of each characteristic factor is: ; In the formula; Represents the feature weight of feature factor m; Represents the similarity between the anomaly score vector and the feature vector of feature factor m.

[0010] Preferably, the method for determining the total abnormality score of each characteristic factor is: Calculate the product of the abnormality score of each characteristic factor in any isolated tree in which it is located and the average of the characteristic weights of all characteristic factors in any isolated tree, and take the cumulative sum of the multiplication results of each characteristic factor in all isolated trees in which it is located as the total abnormality score of each characteristic factor.

[0011] Preferably, the method for determining the abnormal factor of each phase voltage signal at each moment is: The total abnormality score of all characteristic factors corresponding to each phase voltage signal at each moment is used as the input of the threshold segmentation algorithm, and the segmentation threshold is output. The sum of all total abnormality scores greater than the segmentation threshold is calculated, and the sum is divided by the cumulative sum of the total abnormality scores of all characteristic factors as the abnormal factor of each phase voltage signal at each moment.

[0012] Preferably, the protection of the power transmission line by cutting off the power transmission line includes: According to the abnormal factor acquisition method, the abnormal factors of each phase voltage signal at a preset number of moments during the normal operation of the transmission line are acquired, 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 transmission line connected to the switch cabinet will be cut off; otherwise, the transmission line connected to the switch cabinet will not be cut off.

[0013] The present application also proposes a power transmission line emergency cut-off protection device, including the power transmission line emergency cut-off safety protection system.

[0014] The present invention has the following beneficial effects: This application constructs a multidimensional characteristic factor by integrating the dynamic change trend of harmonics and the static over-limit degree, as well as the deviation of the effective value of voltage. It effectively overcomes the defect of the traditional fixed threshold method that is prone to misjudgment in the context of distributed power supply access, and helps to improve the accuracy of the dynamic assessment of abnormal risks of transmission lines. Furthermore, this application introduces the isolation forest algorithm, integrates the abnormal score of the characteristic factor and the dynamic weight allocation mechanism based on information uniqueness, and constructs an abnormal factor, thereby accurately reflecting the overall risk level of the transmission line, improving the accuracy and reliability of the emergency shutdown safety protection system in complex power grid environments, and effectively avoiding misjudgment and missed judgments. In summary, this application addresses the problem that harmonics in distribution networks containing distributed power sources are highly time-varying and traditional fixed threshold protection is prone to misjudgment. By dynamically extracting multidimensional features such as the harmonic change trend and voltage deviation of the voltage signal, and using the isolation forest algorithm to perform abnormal scoring and weight allocation on each feature, the abnormal factor is comprehensively generated to accurately identify the actual fault state of the line, thereby effectively avoiding false disconnections caused by normal fluctuations of distributed power sources, and significantly improving power supply reliability and user power stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A block diagram of a power transmission line emergency shutoff safety protection system provided by one embodiment of the present invention; Figure 2 A flowchart of the abnormal factor acquisition process provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a power transmission line emergency shutoff safety protection system and shutoff protection device proposed in accordance with the present invention. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0018] Unless defined otherwise, 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 belongs.

[0019] The following describes in detail a specific scheme of a power transmission line emergency cutoff safety protection system provided by the present invention with reference to the accompanying drawings.

[0020] See also Figure 1 , which shows a block diagram of a power transmission line emergency shutoff safety protection system provided by 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.

[0021] The data acquisition module 101 is used to obtain the voltage signal of each phase of the transmission line connected to the switch cabinet within a preset period before each moment, and record it as the voltage signal of each phase at each moment.

[0022] In the transmission line, the voltage signal of each phase of the transmission line connected to the switch cabinet within a preset time period before each moment is obtained, and recorded as the voltage signal of each phase at each moment, and recorded as the voltage signal of each phase at each moment, wherein the data acquisition frequency is set to f. In this embodiment, the value of the data acquisition frequency f is manually set. 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 by himself according to the specific situation. This embodiment does not impose any special restrictions.

[0023] The circuit analysis module 102 is used to construct multi-dimensional characteristic factors based on harmonic change trends, voltage deviations, etc.; the abnormality score and feature weight of each characteristic factor are calculated using the isolation forest algorithm, and the total abnormality score is determined in combination with similarity analysis, thereby identifying the abnormal factors of each phase voltage signal at each moment.

[0024] S1: Based on the change trend of the harmonic content rate of the same harmonic of each phase voltage signal at all moments within the preset time period before each moment, and the difference between the harmonic content rate of each harmonic and the preset harmonic content rate limit, determine the abnormal characteristic value of each harmonic in each phase voltage signal at each moment; based on the difference between the voltage effective value of each phase voltage signal at each moment and the preset rated voltage, determine the voltage deviation value of each phase voltage signal at each moment, and combine the abnormal characteristic value to determine the voltage characteristic value of each phase voltage signal at each moment, and collectively refer to them as characteristic factors together with the abnormal characteristic value.

[0025] In power systems with widespread access to distributed power sources, 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 unable to adapt to complex and changing operating environments and are prone to misjudging normal fluctuations as faults, thereby triggering unnecessary protection actions and affecting power supply reliability. Therefore, to address this issue, this embodiment analyzes the dynamic variation trend of the harmonic content rate of the voltage signal to capture its dynamic evolution law. At the same time, it uses the deviation between the effective voltage value and the rated voltage to distinguish between normal harmonic fluctuations and potential faults, thereby reducing the risk of misjudgment. The specific process is as follows: In this embodiment, first, the voltage signal of each phase at each moment is used as the input of the Fourier transform algorithm, and the fundamental wave and all subharmonics of the voltage signal of each phase at each moment are output. The harmonic content of all subharmonics is calculated based on the amplitudes of the fundamental wave and all subharmonics. Among them, 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 repeated here.

[0026] Furthermore, this embodiment determines the abnormal characteristic value of each harmonic in each phase voltage signal at each moment based on the change trend of the harmonic content rate of the same harmonic in each phase voltage signal at all moments within a preset time period before each moment, as well as the difference between the harmonic content rate of each harmonic and the preset harmonic content rate limit, so as to quantify the degree of change and the degree of exceeding the limit of the harmonic content rate, thereby avoiding misjudging the normal fluctuation of the operating state of the distributed power supply as a transmission line abnormality. Specifically: As an implementation method, in this embodiment, the abnormal characteristic value of the kth harmonic in the jth phase voltage signal at time i is The expression is: Where, represents the slope of the fitted straight line obtained by fitting the harmonic content rate of the kth harmonic of the jth phase voltage signal at all moments within a preset time period before moment i; Indicates the harmonic content rate of the kth harmonic in the jth phase voltage signal at time n within a preset time period before time i; Represents the preset harmonic content rate limit; N represents the number of all moments within the preset time length; norm() represents the normalization function; exp() represents the exponential function with a natural constant as the base.

[0027] It should be noted that the value of the preset harmonic content rate limit is artificially set. In this embodiment, the value of the preset harmonic content rate limit is 0.032. In actual application, as other implementation methods, the implementer needs to set it by himself according to the specific situation.

[0028] It should be noted that there are many commonly used fitting algorithms, and in the present embodiment, the least square method is used to fit the harmonic content rate. In actual application, as an alternative, the implementer can also use other fitting methods such as polynomial function fitting method according to the specific circumstances. The present embodiment does not make special limitations on the selection of the fitting algorithm.

[0029] Among them, the least square method is a known technology, and the specific process of fitting the blood content rate by using the least square method will not be repeated here.

[0030] According to the abnormal characteristic value of each harmonic in each phase voltage signal at each time, it can be understood that the abnormal characteristic value is used to reflect the abnormal degree of the harmonic component; if the slope of the fitting straight line obtained by fitting the harmonic content rate of the kth harmonic of the jth phase voltage signal at all times within the preset time length before time i is positive and larger, it means that the harmonic content rate of the kth harmonic is in a rapid rising trend, and the abnormal degree of the kth harmonic is higher, so the corresponding abnormal degree is larger, which means that the power transmission line is more likely to have a fault; at the same time, if the difference between the harmonic content rate of the kth harmonic in the jth phase voltage signal at time n and the harmonic content rate limit value within the preset time length before time i is larger, i.e. larger, it means that the harmonic content rate of the kth harmonic exceeds the harmonic content rate limit value more, and the abnormality of the kth harmonic component is more serious, so the abnormal characteristic value of the kth harmonic is larger, which means that the power transmission line has a higher risk of abnormality; On the contrary, if the slope of the fitting straight line obtained by fitting the harmonic content rate of the kth harmonic of the jth phase voltage signal at all times within the preset time length before time i is negative or 0, or a very small positive value, it means that the harmonic content rate of the kth harmonic is in a downward trend or remains stable, and the abnormal degree of the kth harmonic is low or improving, so the corresponding abnormal degree is smaller, which means that the power transmission line has a lower risk of fault due to the kth harmonic; at the same time, if the difference between the harmonic content rate of the kth harmonic in the jth phase voltage signal at time n and the harmonic content rate limit value within the preset time length before time i is smaller, i.e. smaller, it means that the harmonic content rate of the kth harmonic exceeds the harmonic content rate limit value less or completely within the normal range, and the abnormality of the kth harmonic component is less or does not exist, so the abnormal characteristic value of the kth harmonic is smaller, which means that the power transmission line has a smaller risk of abnormality.

[0031] Furthermore, in a power system containing distributed power sources, harmonic anomalies are the cause of voltage anomalies, and changes in the power flow of distributed power sources can also cause voltage deviations. The phenomenon of severe voltage imbalance indirectly indicates that there is an abnormality in the transmission line. Therefore, this embodiment determines the voltage deviation value of each phase voltage signal at each moment based on the difference between the voltage effective value of each phase voltage signal at each moment and the preset rated voltage, so as to quantify the amplitude and frequency of the voltage deviation, determine the degree of voltage deviation, and thus determine whether the transmission line is abnormal, thereby avoiding the misjudgment of normal fluctuations in the working state of the distributed power source as a transmission line abnormality. Specifically: In this embodiment, the exponential result of the difference between the effective voltage value of each phase voltage signal at each moment and the preset rated voltage is calculated, and the cumulative sum of the exponential results at all moments within a preset time period before each moment is used as the voltage deviation value of each phase voltage signal at each moment.

[0032] According to the voltage deviation value of each phase voltage signal at each moment, it can be understood that the voltage deviation value is used to reflect the degree to which the voltage effective value of the voltage signal at each moment deviates from the rated voltage. If the voltage deviation value of the voltage signal at the current moment is larger, it means that the voltage effective value of the voltage signal exceeds the rated voltage more times and the deviation amplitude is larger within the preset time period before the current moment. Therefore, the corresponding voltage deviation value is larger, indicating that the voltage deviation degree is greater, which means that the possibility of abnormality of the transmission line is greater; On the contrary, if the voltage deviation value of the voltage signal at the current moment is smaller, it means that the number of times the effective voltage value of the voltage signal exceeds the rated voltage within the preset time period before the current moment is small or even no, and even if there is an over-limit, the deviation amplitude is small. Therefore, the corresponding voltage deviation value is smaller, indicating that the voltage deviation degree is lower, the overall voltage level is stable and close to the rated value, which means that the transmission line is operating in a normal and healthy state, and the possibility of abnormality caused by voltage deviation is smaller.

[0033] It should be noted that, in this embodiment, a natural constant is used as the base, and an exponential function value of the difference between the effective voltage value of each phase voltage signal at each moment and the preset rated voltage is used as the independent variable, as the exponential result of the difference between the effective voltage value of each phase voltage signal at each moment and the preset rated voltage. In actual application, the implementer may also adopt other exponential functions based on the specific circumstances, and this embodiment does not impose any special restrictions.

[0034] It should be noted that the preset rated voltage value is artificially set. In this embodiment, the preferred rated voltage value is 0.7 kV. In actual application, as other implementation methods, the implementer needs to set it by himself based on the specific situation.

[0035] The effective value of voltage is a well-known technology, and its specific acquisition process will not be described in detail.

[0036] According to the voltage deviation value of each phase voltage signal at each time, it can be understood that further, the embodiment determines the voltage characteristic value of each phase voltage signal at each time based on the voltage deviation value of each phase voltage signal at each time and in combination with the abnormal characteristic value, to evaluate the abnormal risk situation of the power transmission line, specifically: In the embodiment, the mean value of the abnormal characteristic values of all harmonics of each phase voltage signal at each time is calculated, and among all the harmonics, the average value of the abnormal characteristic values greater than the mean value is calculated, and the result of the positive fusion of the average value and the corresponding voltage deviation value is taken as the voltage characteristic value of each phase voltage signal at each time.

[0037] It should be understood that positive fusion refers to combining two or more indicators together through addition or multiplication, so as to obtain a comprehensive indicator, so as to more comprehensively and accurately evaluate a phenomenon or problem. Such fusion method is not limited to simple arithmetic operation, but can also include more complex statistical model and analysis method, and the implementer can select it according to the specific situation, and the embodiment does not make special limitation.

[0038] Preferably, as an implementation manner, the embodiment takes 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, and in actual application process, as other implementation manners, the implementer can also adopt other positive fusion methods such as sum value according to the specific situation, and the embodiment does not make special limitation.

[0039] According to the voltage characteristic value of each phase voltage signal at each time, it can be understood that the voltage characteristic value comprehensively considers the harmonic abnormality and voltage deviation characteristics of the voltage signal, and jointly evaluates the abnormal risk situation of the power transmission line; the more harmonics of all harmonics of the voltage signal exceeding the mean value of the abnormal characteristic value within the preset time length before the current time, the higher the harmonic abnormality degree of the voltage signal within a period of time before the current time, which means that the possibility of abnormal risk of the power transmission line is greater, therefore, the corresponding voltage characteristic value is greater; at the same time, the greater the voltage deviation value of the voltage signal within the preset time length before the current time, the greater the voltage deviation degree, which means that the possibility of abnormal risk of the power transmission line is greater, therefore, the corresponding voltage characteristic value is greater; On the contrary, if there are few or no harmonics in the voltage signal that exceed the mean value of the abnormal characteristic value within the preset time period before the current moment, it means that the degree of harmonic abnormality of the voltage signal in the period before the current moment is low, which means that the operation state of the transmission line is relatively stable and the possibility of faults caused by harmonic abnormalities is small. Therefore, the corresponding voltage characteristic value is smaller. At the same time, if the voltage deviation value of the voltage signal within the 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 abnormalities caused by voltage deviation is also low. Therefore, the corresponding voltage characteristic value is smaller.

[0040] Finally, for the convenience of expression, the abnormal characteristic values ​​and voltage deviation values ​​of all subharmonics of each phase voltage signal at each moment are collectively referred to as characteristic factors.

[0041] Thus, this embodiment has constructed a multidimensional characteristic factor by integrating the dynamic change trend of harmonics with the static over-limit degree and the deviation of the effective value of voltage. It effectively overcomes the defect of the traditional fixed threshold method that is prone to misjudgment in the context of distributed power supply access, and helps to improve the accuracy of the dynamic assessment of abnormal risks of transmission lines.

[0042] S2: The isolation forest algorithm is used to obtain the abnormal scores of each characteristic factor in each phase voltage signal in all its isolated trees at each moment, and the distribution of each characteristic factor in the isolated tree is combined to construct the abnormal score vector and characteristic vector of each characteristic factor. The characteristic weight of each characteristic factor is determined by analyzing the similarity between the abnormal score vector and the characteristic vector; based on the abnormal score of each characteristic factor in any isolated tree and the average distribution of the characteristic weights of all characteristic factors in any isolated tree, the total abnormal score of each characteristic factor is determined to determine the abnormal factor of each phase voltage signal at each moment.

[0043] In a complex and changeable power grid operation environment, a single feature is often susceptible to noise interference and is difficult to accurately reflect the true operating status of the transmission line, thereby increasing the risk of misjudgment or missed judgment. Therefore, in order to solve this problem, this embodiment introduces an isolation forest algorithm to achieve efficient anomaly detection of multi-dimensional feature data. That is, this embodiment uses the isolation forest algorithm to obtain the anomaly score of each characteristic factor in each phase voltage signal at each moment in all its isolated trees, and combines the distribution of each characteristic factor in the isolated tree to construct an anomaly score vector and a characteristic vector of each characteristic factor. By analyzing the similarity between the anomaly score vector and the characteristic vector, the characteristic weight of each characteristic factor is determined; based on the anomaly score of each characteristic factor in any isolated tree and the average distribution of the characteristic weights of all characteristic factors in any isolated tree, the total anomaly score of each characteristic factor is determined to determine the anomaly factor of each phase voltage signal at each moment to evaluate the abnormal situation of the transmission line. The specific process is as follows: In this embodiment, first, the isolation forest algorithm is used to obtain the abnormality score of each characteristic factor in each phase voltage signal at each moment in all its isolated trees. The abnormality score vector and characteristic vector of each characteristic factor are constructed by combining the distribution of each characteristic factor in the isolated trees. Specifically, In this embodiment, all characteristic factors of each phase electrical signal at each moment are used as inputs of the isolation 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 characteristic values ​​are randomly selected from all abnormal characteristic values ​​of all characteristic factors, and a feature set is formed with the voltage deviation value to construct an isolated tree. Finally, the abnormal score of each characteristic factor in all its isolated trees is output.

[0044] Among them, the value of the preset number is set manually. In this embodiment, the value of the preset number is 5. In actual application, as other implementation methods, the implementer can also set it by himself based on the specific situation. This embodiment does not impose any special restrictions.

[0045] Among them, the isolation forest algorithm is a well-known technology, and the specific process of using it to construct an isolation tree and obtain anomaly scores will not be repeated here.

[0046] Furthermore, this embodiment forms an anomaly score vector by combining the anomaly scores of each feature factor in all isolated trees in which it is located; Calculate the cumulative result of all other characteristic factors in any isolated tree where each characteristic factor is located, record it as the eigenvalue of each characteristic factor in any isolated tree where it is located, and combine the eigenvalues ​​of each characteristic factor in all isolated trees where it is located to form the eigenvector of each characteristic factor.

[0047] Furthermore, this embodiment determines the characteristic weight of each characteristic factor by analyzing the similarity between the abnormality score vector and the characteristic vector, so as to quantify the contribution of the characteristic factor to the voltage signal abnormality assessment, specifically: In this embodiment, the feature weight of the feature factor m is The expression is: ; In the formula; Represents the similarity between the anomaly score vector and the feature vector of feature factor m.

[0048] It should be noted that there are many methods for measuring the similarity between vectors. In this embodiment, the cosine similarity between the abnormal score vector of the characteristic factor m and the characteristic vector is used as the similarity between the abnormal score vector of the characteristic factor m and the characteristic vector. In actual application, as other implementation methods, the implementer may also adopt other methods for measuring the similarity between vectors, such as the reciprocal of the Euclidean distance, based on specific circumstances. This embodiment does not impose any special restrictions on the selection of methods for measuring the similarity between vectors.

[0049] The calculation formula and method of cosine similarity are well-known technologies, and the specific calculation process will not be described in detail.

[0050] According to the feature weights of each feature factor, it can be understood that the feature weight quantifies the contribution of the feature factor to the voltage signal anomaly assessment; if the similarity between the anomaly score vector of the current feature factor and the feature vector is greater, that is, the similarity is closer to 1, then it means that the contribution of the current feature factor is redundant and does not provide new and independent information. 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 anomaly score vector of the current feature factor and the feature vector is smaller, that is, the similarity is closer to -1, then it means that the contribution of the current feature factor is unique and critical. It provides new information that other features do not have, and its behavior cannot be explained and predicted by other features. Therefore, the feature weight of the current feature factor is also greater.

[0051] Furthermore, this embodiment determines the total abnormality score of each characteristic factor based on the abnormality score of each characteristic factor in any isolated tree in which it is located and the average distribution of the characteristic weights of all characteristic factors in any isolated tree, so as to determine the abnormality factor of each phase voltage signal at each moment and evaluate the abnormality degree of the voltage signal. Specifically, In this embodiment, the product of the abnormality score of each characteristic factor in any isolated tree in which it is located and the average of the characteristic weights of all characteristic factors in any isolated tree is calculated, and the cumulative sum of the multiplication results of each characteristic factor in all isolated trees in which it is located is taken as the total abnormality score of each characteristic factor.

[0052] According to the total anomaly score of each characteristic factor, it can be understood that the total anomaly score is used to evaluate the degree of abnormality of the voltage signal. If the weight of the current characteristic factor among all the characteristic factors in its isolated tree is greater, and the anomaly score of the current characteristic factor in its isolated tree is greater, it means that from the perspective of the isolated tree where the current characteristic factor is located, the possibility of abnormal voltage signal is greater, which means that the possibility of abnormal transmission line is greater. On the contrary, if the current characteristic factor has a smaller weight than all the characteristic factors in the isolated tree where it is located, or its anomaly score is smaller, it means that in the specific fault mode or data subspace represented by the isolated tree, the current characteristic factor has a lower contribution to the judgment of voltage signal anomaly, or it itself does not show an obvious abnormal state. This shows that from the perspective of the isolated tree, the possibility of voltage signal anomaly is small, and accordingly, its contribution to the judgment of the overall abnormal risk of the transmission line is reduced, which indirectly reflects that the isolated tree tends to believe that the current transmission line is operating normally and does not have the conditions to trigger the protection action.

[0053] Furthermore, this embodiment uses the total abnormality score of all characteristic factors corresponding to each phase voltage signal at each moment as the input of the threshold segmentation algorithm, outputs the segmentation threshold, calculates the sum of all total abnormality scores greater than the segmentation threshold, and divides the sum by the cumulative sum of the total abnormality scores of all characteristic factors as the abnormal factor of each phase voltage signal at each moment.

[0054] According to the abnormal factors of each phase voltage signal at each moment, it can be understood that the abnormal factors are used to represent the overall risk level of the transmission line status. If the abnormal factor of the voltage signal at the current moment is larger, it means that the voltage data of the transmission line continues to show abnormalities frequently and the degree of abnormality is more serious. It is no longer a random fluctuation, but a moving trend fault sign. Therefore, it is judged that there is an abnormality in the transmission line and preparations are made to cut off. On the contrary, if the abnormal factor of the voltage signal at the current moment is smaller, it means that even if there are individual instantaneous fluctuations or slight abnormalities in the voltage data of the transmission line, their occurrence frequency is low and the degree is slight, and no continuous deterioration trend has been formed. These fluctuations are still accidental disturbances within the allowable range of normal operation of the power grid. Therefore, it is judged that the operating status of the transmission line is stable and there is no substantial failure risk. There is no need to take protective measures such as disconnection. The power system will continue to maintain normal operation, thereby ensuring the continuity and reliability of power supply.

[0055] 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 actual application, as other implementation methods, implementers can also use other threshold segmentation algorithms based on specific circumstances. This embodiment does not impose any special restrictions.

[0056] Wherein, the Otsu threshold segmentation algorithm is a known technology, and the specific process of dividing the total anomaly score will not be repeated.

[0057] Preferably, the anomaly factor acquisition process flowchart provided by the embodiment is as shown in Figure 2

[0058] So far, the embodiment introduces the isolation forest algorithm, integrates the anomaly score of the feature factor and the dynamic weight distribution mechanism based on the information uniqueness, constructs the anomaly factor, accurately reflects the overall risk level of the transmission line, improves the accuracy and reliability of the emergency shutdown safety protection system judgment in the complex power grid environment, and effectively avoids misjudgment and missed judgment.

[0059] The safety protection module 103 is configured to cut off the transmission line based on the anomaly factor.

[0060] According to the anomaly factor acquisition method in S2, the anomaly factors of each phase voltage signal at a preset number of time points during the normal operation state of the transmission line are acquired, and the maximum anomaly factor is taken as the anomaly threshold.

[0061] It should be noted that the value of the preset number is artificially set, and in the embodiment, the value of the preset number is 10000. In actual application, as other implementation manners, the implementer can also set it by himself according to the specific situation, and the embodiment does not make special limitation.

[0062] If the anomaly factor of any voltage signal at the current time is greater than the corresponding anomaly threshold, it indicates that the transmission circuit connected with the switch cabinet is abnormal, and then the transmission line connected with the switch cabinet is cut off. On the contrary, if the anomaly factor of any voltage signal at the current time is less than or equal to the corresponding anomaly threshold, it indicates that the transmission line connected with the switch cabinet is normal, and then the transmission line connected with the switch cabinet is not cut off.

[0063] So far, the embodiment aims at the problem that the harmonic time-varying property of the distribution network with distributed power supply is strong, and the traditional fixed threshold protection is easy to misjudge. The multi-dimensional features such as the harmonic change trend of the voltage signal and the voltage deviation are dynamically extracted, the isolation forest algorithm is used to score and weight the features, the anomaly factor is generated to accurately identify the real fault state of the line, and the misjudgment caused by the normal fluctuation of the distributed power supply is effectively avoided, so that the power supply reliability and the stability of user power consumption are significantly improved.

[0064] Based on the same inventive concept as the above method, the embodiment of the present application also provides a transmission line emergency shutdown protection device, which comprises the transmission line emergency shutdown safety protection system.

[0065] ​It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0067] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A power transmission line emergency shut-off safety protection system, characterized in that: The system comprises: The data acquisition module is used to obtain the voltage signal of each phase of the transmission line connected to the switch cabinet within a preset 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 value of each harmonic in each phase voltage signal at each moment based on the change trend of the harmonic content rate of the same harmonic in each phase voltage signal at all moments within a preset time period before each moment, and the difference between the harmonic content rate of each harmonic and the preset harmonic content rate limit; determine the voltage deviation value of each phase voltage signal at each moment based on the difference between the voltage effective value of each phase voltage signal at each moment and the preset rated voltage, and determine the voltage characteristic value of each phase voltage signal at each moment in combination with the abnormal characteristic value, and the voltage characteristic value and the abnormal characteristic value are collectively referred to as the characteristic factor; The isolation forest algorithm is used to obtain the abnormal score of each characteristic factor in each phase voltage signal at each moment in all its isolated trees, and the distribution of each characteristic factor in the isolated tree is combined to construct the abnormal score vector and characteristic vector of each characteristic factor. The characteristic weight of each characteristic factor is determined by analyzing the similarity between the abnormal score vector and the characteristic vector. Based on the abnormal score of each characteristic factor in any isolated tree and the average distribution of the characteristic weights of all characteristic factors in any isolated tree, the total abnormal score of each characteristic factor is determined to determine the abnormal factor of each phase voltage signal at each moment. The safety protection module is used to cut off the transmission line for protection based on the abnormal factors.

2. A power transmission line emergency shutoff safety protection system according to claim 1, characterized in that: The expression of the abnormal characteristic value of each harmonic in each phase voltage signal at each moment is: Where, represents the abnormal characteristic value of the kth harmonic in the jth phase voltage signal at time i; represents the slope of the fitted straight line obtained by fitting the harmonic content rate of the kth harmonic of the jth phase voltage signal at all moments within a preset time period before moment i; Indicates the harmonic content rate of the kth harmonic in the jth phase voltage signal at time n within a preset time period before time i; Represents the preset harmonic content rate limit; N represents the number of all moments within the preset time length; norm() represents the normalization function; exp() represents the exponential function with a natural constant as the base.

3. A power transmission line emergency shutoff safety protection system according to claim 1, characterized in that: The method for determining the voltage deviation value of each phase voltage signal at each moment is as follows: The exponential result of the difference between the effective voltage value of each phase voltage signal at each moment and the preset rated voltage is calculated, and the cumulative sum of the exponential results at all moments within a preset time length before each moment is used as the voltage deviation value of each phase voltage signal at each moment.

4. A power transmission line emergency shutoff safety protection system according to claim 1, characterized in that: The method for determining the voltage characteristic value of each phase voltage signal at each moment is: Calculate the mean of the abnormal characteristic values ​​of all subharmonics of each phase voltage signal at each moment. Among all subharmonics, calculate the average of the abnormal characteristic values ​​greater than the mean. The result of forward fusion of the mean and the corresponding voltage deviation value is used as the voltage characteristic value of each phase voltage signal at each moment.

5. A power transmission line emergency shutoff safety protection system according to claim 1, characterized in that: The isolation forest algorithm is used to obtain the abnormal score of each characteristic factor in each phase voltage signal at each moment in all its isolated trees, and the distribution of each characteristic factor in the isolated tree is combined to construct the abnormal score vector and characteristic vector of each characteristic factor, including: All characteristic factors in each phase voltage signal at each moment are used as input to the isolation forest algorithm. A preset number of abnormal characteristic values ​​are randomly selected from all abnormal characteristic values ​​of all characteristic factors, and together with the voltage deviation value, a feature set is formed to construct an isolation tree. The abnormality score of each characteristic factor in all its isolated trees is output; The abnormal scores of each feature factor in all its isolated trees are combined into an abnormal score vector; Calculate the cumulative result of all other characteristic factors in any isolated tree where each characteristic factor is located, record it as the eigenvalue of each characteristic factor in any isolated tree where it is located, and combine the eigenvalues ​​of each characteristic factor in all isolated trees where it is located to form the eigenvector of each characteristic factor.

6. A power transmission line emergency shutoff safety protection system according to claim 1, characterized in that: The expression of the characteristic weight of each characteristic factor is: ; In the formula; Represents the feature weight of feature factor m; Represents the similarity between the anomaly score vector and the feature vector of feature factor m.

7. A power transmission line emergency shutoff safety protection system according to claim 1, characterized in that: The method for determining the total abnormality score of each characteristic factor is as follows: Calculate the product of the abnormality score of each characteristic factor in any isolated tree in which it is located and the average of the characteristic weights of all characteristic factors in any isolated tree, and take the cumulative sum of the multiplication results of each characteristic factor in all isolated trees in which it is located as the total abnormality score of each characteristic factor.

8. A power transmission line emergency shutoff safety protection system according to claim 1, characterized in that: The method for determining the abnormal factor of each phase voltage signal at each moment is as follows: The total abnormality score of all characteristic factors corresponding to each phase voltage signal at each moment is used as the input of the threshold segmentation algorithm, and the segmentation threshold is output. The sum of all total abnormality scores greater than the segmentation threshold is calculated, and the sum is divided by the cumulative sum of the total abnormality scores of all characteristic factors as the abnormal factor of each phase voltage signal at each moment.

9. A power transmission line emergency shutoff safety protection system according to claim 1, characterized in that: The said cutting off protection of the transmission line comprises: According to the abnormal factor acquisition method, the abnormal factors of each phase voltage signal at a preset number of moments during the normal operation of the transmission line are acquired, 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 transmission line connected to the switch cabinet will be cut off; otherwise, the transmission line connected to the switch cabinet will not be cut off.

10. A power transmission line emergency cut-off protection device, characterized in that: It comprises a power transmission line emergency shutoff safety protection system as described in any one of claims 1 to 9.

Images