CN120657673B - Self-adaptive protection setting method and system for secondary fusion on-column circuit breaker - Google Patents
Self-adaptive protection setting method and system for secondary fusion on-column circuit breakerInfo
- Publication number
- CN120657673B CN120657673B CN202511158796.8A CN202511158796A CN120657673B CN 120657673 B CN120657673 B CN 120657673B CN 202511158796 A CN202511158796 A CN 202511158796A CN 120657673 B CN120657673 B CN 120657673B
- Authority
- CN
- China
- Prior art keywords
- circuit breaker
- short
- window
- recovery
- abnormal event
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H3/00—Emergency protective circuit arrangements for automatic disconnection directly responsive to an undesired change from normal electric working condition with or without subsequent reconnection ; integrated protection
- H02H3/006—Calibration or setting of parameters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H7/00—Emergency protective circuit arrangements specially adapted for specific types of electric machines or apparatus or for sectionalised protection of cable or line systems, and effecting automatic switching in the event of an undesired change from normal working conditions
- H02H7/26—Sectionalised protection of cable or line systems, e.g. for disconnecting a section on which a short-circuit, earth fault, or arc discharge has occured
- H02H7/28—Sectionalised protection of cable or line systems, e.g. for disconnecting a section on which a short-circuit, earth fault, or arc discharge has occured for meshed systems
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a self-adaptive protection setting method and a self-adaptive protection setting system for a secondary fusion on-column circuit breaker, which relate to the related field of emergency protection devices of power systems, and the method comprises the steps of obtaining a plurality of secondary fusion on-column circuit breakers; the method comprises the steps of identifying a branch circuit relationship, determining a breaker group comprising upper and lower levels, setting a short-time activation window, extracting abnormal operation monitoring parameters of a main circuit breaker, calculating a recovery time window for the abnormal operation monitoring parameters, judging whether a linkage protection instruction is sent to the branch circuit breaker or not by comparing the recovery time window with the short-time activation window, and activating the linkage protection instruction if the recovery time window is smaller than the short-time activation window and not. The technical problems of poor protection accuracy and economy existing in the protection setting of the existing primary and secondary fusion pole-mounted circuit breaker are solved, and the technical effects of improving the power grid protection accuracy and economy are achieved.
Description
Technical Field
The application relates to the field of emergency protection devices of power systems, in particular to a self-adaptive protection setting method and system for a secondary fusion on-pole circuit breaker.
Background
The protection setting of the circuit breaker on the secondary fusion column has important significance for guaranteeing the reliability and the power supply continuity of the power grid. At present, when the main circuit breaker is detected to be abnormal, protection instructions are usually sent to all branch circuit breakers immediately so as to isolate a fault area rapidly. However, this approach lacks consideration of the abnormal recovery time of the main circuit breaker, i.e. it is impossible to distinguish between transient faults and permanent faults, and once the main circuit breaker recovers in a very short time, the protection command sent before will cause unnecessary branch circuit breaker actions, which not only wastes protection resources, but also may cause a chain reaction such as power interruption.
In the related art at the present stage, the protection setting for the circuit breaker on the secondary fusion column has the technical problem of poor protection accuracy and economy.
Disclosure of Invention
The application provides a self-adaptive protection setting method and a self-adaptive protection setting system for a secondary fusion column circuit breaker, which are characterized in that a plurality of circuit breaker devices are acquired, branch relationships among the circuit breaker devices are identified and grouped, each group comprises a main circuit breaker and a plurality of branch circuit breakers, a short-time activation window time is set, when the main circuit breaker is detected to be abnormal, abnormal operation parameters are extracted, a time window required for recovery is calculated, the recovery time is compared with the preset short-time activation window, if the recovery time is shorter than the activation window, the system does not trigger linkage protection and keeps running, if the recovery time is longer than the activation window, a linkage protection instruction is immediately sent to the branch circuit breaker, the main circuit breaker and the branch circuit breaker are synchronously disconnected, and the like.
The application provides a self-adaptive protection setting method for a secondary fusion on-pole breaker, which comprises the steps of obtaining a plurality of secondary fusion on-pole breakers, identifying the branch relationships of the secondary fusion on-pole breakers, determining breaker groups comprising upper and lower relationships, wherein each breaker group comprises a main circuit breaker and at least one branch breaker, setting a short-time activation window, extracting abnormal operation monitoring parameters of the main circuit breaker, calculating a recovery time window for the abnormal operation monitoring parameters, and judging whether linkage protection instructions are sent to the branch breakers or not by comparing the recovery time window with the short-time activation window, wherein if the recovery time window is smaller than the short-time activation window, the linkage protection instructions are not activated, and if the recovery time window is larger than the short-time activation window, the linkage protection instructions are activated.
In a possible implementation mode, the method comprises the following steps that each secondary fusion on-pole breaker of the plurality of secondary fusion on-pole breakers comprises a primary opening layer and a secondary intelligent control layer, wherein the primary opening layer is used for executing opening protection of the branch circuit breaker according to an activated linkage protection instruction, and the secondary intelligent control layer is used for carrying out abnormal operation monitoring and receiving or sending of the linkage protection instruction.
In a possible implementation manner, the method comprises the following steps of setting a short-time activation window, wherein the short-time activation window is determined through self-adaptive analysis on historical abnormal event samples of the main circuit breaker, and the historical abnormal event samples comprise abnormal event operation monitoring parameter samples, abnormal event recovery frequency, abnormal event duration and abnormal event fluctuation trend of the main circuit breaker.
In a possible implementation manner, the short-time activation window is determined through self-adaptive analysis of historical abnormal event samples of the main circuit breaker, and the method comprises the steps of screening effective recovery event samples of the historical abnormal event samples, wherein the effective recovery event samples are abnormal events marked as recovery normal, extracting recovery time distribution of the effective recovery event samples, analyzing the recovery time distribution to obtain a basic activation threshold, calculating a threshold adjustment factor according to abnormal event recovery frequency, abnormal event duration and abnormal event fluctuation trend of the historical abnormal event samples, and updating the basic activation threshold according to the threshold adjustment factor to obtain the self-adaptive short-time activation window of the main circuit breaker.
In a possible implementation manner, extracting recovery time distribution of the effective recovery event sample, analyzing the recovery time distribution to obtain a basic activation threshold, performing density cluster analysis according to the recovery time distribution to obtain a plurality of cluster results, extracting a first cluster result according to the density value of each cluster result, and taking the quantile value of the first cluster result as the basic activation threshold.
In a possible implementation manner, a threshold adjustment factor is calculated according to the abnormal event recovery frequency, the abnormal event duration and the abnormal event fluctuation trend of the historical abnormal event sample, and the threshold adjustment factor is obtained comprehensively by defining a frequency adjustment factor, a continuous adjustment factor and a trend adjustment factor according to the abnormal event recovery frequency, the abnormal event duration and the abnormal event fluctuation trend, and performing accumulated calculation according to the frequency adjustment factor, the continuous adjustment factor and the trend adjustment factor.
In a possible implementation manner, the breaker groups comprising the upper and lower level relations are determined, and the following processing is further executed, wherein if each breaker group comprises a main circuit breaker, at least one primary branch circuit breaker and at least one secondary branch circuit breaker, a first short-time activation window and a second short-time activation window are set, whether the main circuit breaker sends a primary linkage protection instruction to the primary branch circuit breaker is judged according to the first short-time activation window, and whether the primary branch circuit breaker sends a secondary linkage protection instruction to the secondary branch circuit breaker is judged according to the second short-time activation window.
In a possible implementation mode, the method comprises the following steps that the first short-time activation window is determined through self-adaptive analysis on a historical abnormal event sample of the main circuit breaker, the second short-time activation window is determined through self-adaptive analysis on a historical abnormal event sample of the primary circuit breaker, and the multi-level linkage protection instructions formed by the primary linkage protection instructions and the secondary linkage protection instructions are sequentially sent according to a hierarchical sequence.
In a possible implementation manner, the abnormal operation monitoring parameters are subjected to recovery time window calculation, and the following processing is carried out, namely an abnormal recovery time prediction model is constructed, the abnormal recovery time prediction model is obtained through supervision training on historical abnormal event samples of the main circuit breaker, the abnormal operation monitoring parameters are input into the abnormal recovery time prediction model, and a predicted recovery time window is output.
The application further provides a self-adaptive protection setting system for the secondary fusion on-pole circuit breakers, which comprises an on-pole circuit breaker acquisition module, a circuit breaker group identification module and a protection instruction transmission judgment module, wherein the on-pole circuit breaker acquisition module is used for acquiring a plurality of secondary fusion on-pole circuit breakers, the circuit breaker group identification module is used for identifying the branch relations of the plurality of secondary fusion on-pole circuit breakers and determining circuit breaker groups comprising upper and lower relations, each circuit breaker group comprises a main circuit breaker and at least one branch circuit breaker, the recovery time window calculation module is used for setting a short-time activation window, extracting abnormal operation monitoring parameters of the main circuit breaker, carrying out recovery time window calculation on the abnormal operation monitoring parameters, judging whether linkage protection instructions are transmitted to the branch circuit breakers or not by comparing the recovery time window with the short-time activation window, and the protection instruction transmission judgment module is used for activating the linkage protection instructions if the recovery time window is smaller than the short-time activation window and activating the linkage protection instructions if the recovery time window is larger than the short-time activation window.
The application discloses a self-adaptive protection setting method and a self-adaptive protection setting system for a secondary fusion on-column circuit breaker, which are proposed by the application, firstly acquire a plurality of secondary fusion on-column circuit breakers, then identify the branch circuit relationships of the plurality of secondary fusion on-column circuit breakers, determine circuit breaker groups comprising upper and lower relationships, each circuit breaker group comprises a main circuit breaker and at least one branch circuit breaker, then set a short-time activation window, extract abnormal operation monitoring parameters of the main circuit breaker, calculate a recovery time window of the abnormal operation monitoring parameters, judge whether to send linkage protection instructions to the branch circuit breakers by comparing the recovery time window with the short-time activation window, and activate the linkage protection instructions if the recovery time window is smaller than the short-time activation window and if the recovery time window is larger than the short-time activation window. The technical effect of improving the accuracy and economy of power grid protection is achieved.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present application, the following will briefly describe the drawings of the embodiments of the present application, in which flowcharts are used to illustrate operations performed by a system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Fig. 1 is a schematic flow chart of an adaptive protection setting method for a secondary fused on-column circuit breaker according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of an adaptive protection tuning system for a secondary fused on-column circuit breaker according to an embodiment of the present application.
Reference numerals indicate the on-pole breaker acquisition module 10, the breaker group identification module 20, the recovery time window calculation module 30, and the protection instruction transmission judgment module 40.
Detailed Description
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
The present application will be described in further detail below with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the present application more apparent, and the described embodiments should not be construed as limiting the present application, but all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, the term "first\second" being referred to merely as distinguishing between similar objects and not representing a particular ordering for the objects. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules that may not be expressly listed or inherent to such process, method, article, or apparatus, and 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 application pertains. The terminology used herein is for the purpose of describing embodiments of the application only.
The embodiment of the application provides a self-adaptive protection setting method for a secondary fusion on-column circuit breaker, which is shown in fig. 1 and comprises the following steps:
Step S100, a plurality of secondary fusion on-column circuit breakers are obtained, each secondary fusion on-column circuit breaker of the plurality of secondary fusion on-column circuit breakers comprises a primary opening fault and a secondary intelligent control layer, wherein the primary opening fault is used for executing opening protection of the branch circuit breaker according to an activated linkage protection instruction, and the secondary intelligent control layer is used for carrying out abnormal operation monitoring and receiving or sending of the linkage protection instruction.
Specifically, a plurality of secondary fused on-column circuit breakers are connected to a master station system by using a power system communication network (such as an optical fiber communication network, a wireless communication network and the like). Each pole-mounted circuit breaker is mounted on an electric pole of the power distribution network, and the position of each pole-mounted circuit breaker is determined according to the geographical distribution of the power distribution network and is identified in a master station system.
The primary opening layer comprises an operating mechanism, an arc extinguishing chamber and other components. The operating mechanism realizes the opening and closing action of the breaker through mechanical transmission, and the action power can come from spring energy storage or electromagnetic drive and the like. For example, the spring energy storage operating mechanism stores energy of a spring through a motor, and when opening and closing are needed, the spring energy is released to drive the circuit breaker to act. The arc extinguishing chamber is used for extinguishing an arc when the circuit breaker breaks a current, and the inside of the arc extinguishing chamber is filled with an arc extinguishing medium such as sulfur hexafluoride (SF 6) gas and the like.
The secondary intelligent control layer mainly comprises a microprocessor, a memory, a communication module and the like. A microprocessor such as an ARM chip is responsible for running various control algorithms and monitoring programs. The memory is used for storing information such as equipment parameters, historical operation data and the like. The communication module supports a plurality of communication protocols (such as DL/T634.5104, IEC61850 and the like) for data interaction with the master station system.
In the master station system, a device profile is established for each secondary fused on-column circuit breaker, including device model, manufacturer, delivery date, installation location, rated parameter (e.g., rated voltage, rated current, etc.) information. And initializing the software of the secondary intelligent control layer and loading a basic monitoring and control program. For example, the sampling rate of current, voltage monitoring is set, typically hundreds to thousands of samples per second, to ensure that the abnormal operating signal can be accurately captured.
Step 200, identifying the branch circuit relationships of the plurality of secondary fusion on-pole circuit breakers, and determining circuit breaker groups comprising upper and lower relationships, wherein each circuit breaker group comprises a main circuit breaker and at least one branch circuit breaker.
Specifically, the branch relationship refers to a connection relationship between a main circuit breaker and a branch circuit breaker in a power distribution network. The main-path pole-mounted circuit breaker is close to the outgoing line of the transformer substation, and provides power for the branch-path pole-mounted circuit breaker, and the branch-path pole-mounted circuit breaker supplies power to the respective load area.
And identifying upper and lower circuit breaker groups by utilizing network topology analysis software in the master station system and combining a primary wiring diagram of the power distribution network and the connection relation of the pole-mounted circuit breakers. For example, in a radial distribution network, substation outlets are first connected to a secondary fused on-pole circuit breaker as the main circuit breaker, which in turn is connected to a plurality of on-pole branch circuit breakers.
In a practical scenario, by assigning each pole-mounted breaker a unique identification code (e.g., a device code based on a power industry standard), the primary station system can construct a hierarchical relationship of breaker groups based on these identification codes and the wiring information of the distribution network.
The master station system acquires state information (such as opening and closing states, current sizes and the like) of the circuit breakers through communication with secondary intelligent control layers of the circuit breakers on each column to verify the accuracy of the topological relation. For example, when the master station system sends an instruction to a certain branch circuit breaker, the response condition and the influence on other related circuit breakers are observed, so that whether the branch relation is correct or not is verified.
And step S300, setting a short-time activation window, extracting abnormal operation monitoring parameters of the main circuit breaker, carrying out recovery time window calculation on the abnormal operation monitoring parameters, and judging whether to send a linkage protection instruction to the branch circuit breaker or not by comparing the recovery time window with the short-time activation window.
Specifically, the secondary intelligent control layer collects the operation parameters of the main circuit breaker in real time through built-in current and voltage sensors. These sensors may be electromagnetic or electronic transformers that convert high voltage, high current signals into small voltage signals suitable for processing by a microprocessor. For example, an electromagnetic current transformer converts a large current of a primary side into a small current signal of a secondary side in a certain proportion based on an electromagnetic induction principle. The collected abnormal operation monitoring parameters are preprocessed, and the operations comprise filtering (such as removing high-frequency interference signals by adopting a low-pass filter), data normalization (converting data of different dimensions into the same dimension range, such as converting current and voltage data into per unit value relative to rated values) and the like. The abnormal operation monitoring parameters are parameters capable of reflecting whether the operation state of the circuit breaker is normal or not, such as the amplitude value, the change rate and the like of current and voltage, and when the parameters exceed or fall below the normal range, the abnormal operation conditions such as short circuit, overcurrent and the like of the circuit breaker are indicated.
Setting a short-time activation window, wherein the short-time activation window is a preset time interval and is used for judging whether the abnormality of the main circuit breaker is an instantaneous disturbance or a continuous fault. In a power distribution network protection strategy, whether to link the branch circuit breaker is determined by comparing the relationship between the abnormal recovery time and the short-time activation window. The time length of the short-time activation window can be set according to specific conditions (such as power supply reliability requirements, common fault duration and the like) of the power distribution network. For example, in an urban core distribution network with high power reliability requirements, the short-time activation window may be set to 100-300 milliseconds. And calculating a recovery time window by monitoring the recovery process of the main circuit breaker after the occurrence of the abnormality. For example, when a short-circuit fault occurs, the time interval from the occurrence of an abnormality to the restoration to the normal range of the short-circuit current is monitored, and this time interval is the restoration time window. The recovery time window may reflect the duration of the anomaly and is used to determine whether the ganged branch circuit breaker is required to be protected.
And comparing the recovery time window with the short-time activation window by adopting a comparison algorithm. And a comparison program is run in the microprocessor, when the recovery time window is smaller than the short-time activation window, the linkage protection instruction is judged to be not required to be activated, otherwise, when the recovery time window is larger than the short-time activation window, the linkage protection instruction is judged to be required to be activated. This decision logic is implemented, for example, by writing a conditional decision statement (e.g., an "if resume time window > short activation window, then activate the coordinated protection instruction").
In one possible implementation manner, setting a short-time activation window, wherein the short-time activation window is further determined by adaptively analyzing a historical abnormal event sample of the main circuit breaker, and the historical abnormal event sample comprises an abnormal event operation monitoring parameter sample, an abnormal event recovery frequency, an abnormal event duration and an abnormal event fluctuation trend of the main circuit breaker.
Specifically, the historical abnormal event sample refers to records of various abnormal conditions of the main circuit breaker in the past operation process, and the records comprise information such as abnormal occurrence time, normal recovery time, operation monitoring parameters and the like. The abnormal event operation monitoring parameter sample is a record of various operation parameters monitored by the main circuit breaker when a historical abnormal event occurs, such as specific numerical values of parameters such as voltage, current, temperature and the like, when the main circuit breaker is abnormal, and the parameters can directly reflect the operation state of the main circuit breaker when the main circuit breaker is abnormal. The abnormal event recovery frequency refers to the frequency of the main circuit breaker recovering from an abnormal state to a normal state in a history of abnormal events. For example, in a certain period of time, how many anomalies the circuit breaker has occurred and how many times to recover after each anomaly, this frequency reflects the regularity of the recovery of the circuit breaker anomalies. The duration of the abnormal event refers to the duration of each occurrence of the abnormal event of the main circuit breaker, and the duration of the abnormal event may be different in different types and degrees, and reflects the severity and the development trend of the abnormal event. The fluctuation trend of the abnormal event describes the fluctuation change condition of various operation parameters of the main circuit breaker in the occurrence process of the abnormal event. For example, whether the voltage is gradually increased or decreased, whether the current is severely fluctuated, etc., reflect the development dynamics of the abnormal event.
By carrying out self-adaptive analysis on the historical abnormal event samples, a proper short-time activation window can be intelligently determined according to the historical operation characteristics and abnormal rules of the main circuit breaker. The window is more attached to the actual condition of the main circuit breaker, and provides more accurate and reasonable basis for the follow-up judgment of whether to send the linkage protection instruction.
In a possible implementation manner, the short-time activation window is determined by carrying out self-adaptive analysis on a historical abnormal event sample of the main circuit breaker, and the method further comprises the steps of screening an effective recovery event sample of the historical abnormal event sample, wherein the effective recovery event sample is an abnormal event marked as normal recovery, extracting recovery time distribution of the effective recovery event sample, analyzing the recovery time distribution to obtain a basic activation threshold, calculating a threshold adjustment factor according to abnormal event recovery frequency, abnormal event duration and abnormal event fluctuation trend of the historical abnormal event sample, and updating the basic activation threshold according to the threshold adjustment factor to obtain the self-adaptive short-time activation window of the main circuit breaker.
Specifically, from a stored master circuit breaker history abnormal event sample library, each abnormal event is subjected to traversal checking. And screening out abnormal events marked as normal recovery through a preset mark recognition rule, wherein the events form an effective recovery event sample set. The marking recognition rule is based on the comprehensive judgment of various conditions such as the normal range of the circuit breaker operation monitoring parameter recovery and the related protection device reset signal. For example, if the current parameter of the circuit breaker gradually falls within ±5% of the rated current after an abnormality and the protection device issues a reset signal, the abnormality event is marked as restoration to normal.
And extracting the recovery time of each event, namely the time interval from the abnormal occurrence time to the marked normal recovery time, for the screened effective recovery event samples. These recovery time data are collated to form a recovery time distribution. Statistical analysis methods, such as calculating statistics of mean, median, etc. of recovery time are employed to determine the base activation threshold. For example, the average value of the recovery time of all the valid recovery event samples is calculated, and the average value is used as the initial value of the basic activation threshold. Meanwhile, the basic activation threshold value can be adjusted to a certain extent by combining factors such as standard deviation of recovery time and the like, so that the rationality and stability of the basic activation threshold value are improved.
The threshold adjustment factor is a coefficient calculated according to the recovery frequency of the abnormal event, the duration of the abnormal event and the fluctuation trend of the abnormal event, and is used for adjusting the basic activation threshold so as to obtain an adaptive short-time activation window which is more in line with the actual situation. In particular, for the abnormal event recovery frequency, the total number of abnormal events occurring to the main circuit breaker over a period of time, and the number of effective recovery event samples therein, may be counted. And calculating the recovery frequency of the abnormal events, namely the proportion of the number of effective recovery events to the total number of the abnormal events. If the recovery frequency of the abnormal event is high, the circuit breaker can recover automatically under most abnormal conditions, the short-time activation window can be longer at the moment, and more self-recovery time is given to the circuit breaker, otherwise, if the recovery frequency is low, the circuit breaker is more complex, the circuit breaker is difficult to recover automatically, and the circuit breaker needs to be protected in a linkage way in a more timely manner.
In the aspect of the duration of the abnormal event, the effective recovery event samples can be grouped from short to long according to the duration of the abnormal event, the number of the effective recovery event samples in each interval is counted, the proportion of the number of the samples in each interval to the total number of the effective recovery event samples is calculated, and the event duty ratio of each interval is obtained. And on the contrary, if the duty ratio distribution is more dispersed, the duty ratio is not obviously increased along with the increase of the duration, and even the duty ratio is reduced along with the increase of the duration, the abnormal duration of the self-recovery is shown to be mostly shorter, and the abnormality is not stable.
For each valid recovery event sample, the rate of change of an operating parameter (e.g., voltage, current, etc.) during the occurrence of an abnormal event may be analyzed. If the change rate is large, the abnormal condition is unstable, the waiting judging time is required to be increased so as to more accurately observe the development trend of the abnormality, otherwise, if the change rate is small, the abnormal condition is relatively stable.
And combining the three factors, and calculating a final threshold adjustment factor by adopting methods such as weighted average and the like. And multiplying or adding the calculated threshold adjustment factor with a basic activation threshold (determined according to a specific calculation model) to obtain an updated main circuit breaker self-adaptive short-time activation window.
In one possible implementation, extracting the recovery time distribution of the effective recovery event sample, analyzing the recovery time distribution to obtain a basic activation threshold, and further comprising performing density cluster analysis according to the recovery time distribution to obtain a plurality of cluster results, extracting a first cluster result according to the density value of each cluster result, and taking the quantile value of the first cluster result as the basic activation threshold.
Specifically, the recovery time of all the effective recovery event samples is summarized to form a recovery time distribution data set. For example, 100 valid recovery event samples are collected with recovery times of 50ms, 80 ms, 120 ms.
The recovery time distribution dataset is analyzed using a density clustering algorithm, such as a DBSCAN algorithm. The algorithm clusters based on the density of data points, classifying the density-connected data points into the same class. In the recovery time distribution, density clustering can classify events with similar recovery times. For example, after dense cluster analysis, three cluster results may be obtained, cluster A comprising events with recovery times between 0 and 100 milliseconds, cluster B comprising events with recovery times between 100 and 200 milliseconds, and cluster C comprising events with recovery times between 200 and 300 milliseconds. And calculating a density value of each clustering result, wherein the density value can be measured by the ratio of the number of data points in the clusters to the space occupied by the clusters. And selecting the clustering result with the largest density value as a first clustering result. Because the clusters with large density values represent a class of recovery time situations which are concentrated and have high occurrence frequency in the recovery time distribution, the characteristics of most effective recovery events can be reflected.
The recovery time data in the first cluster result is ordered and then 90% quantiles thereof are calculated. A 90% quantile indicates that in the first clustering result, 90% of the recovery time is less than this value. This 90% quantile is taken as the base activation threshold, i.e., most (90%) of the active recovery events can be restored to normal within the threshold time.
According to the implementation method, through density cluster analysis, the events with similar characteristics in the recovery time distribution can be gathered together, and the clustering result with the largest density is selected as the first clustering result, so that the actual situation of most effective recovery events can be represented. The 90% quantile is used as the basic activation threshold, so that the threshold can cover most effective recovery events, the influence of individual extreme values (such as events with extremely long or short recovery time) on the threshold is avoided, and the accuracy of the basic activation threshold is improved.
In one possible implementation, the method comprises the steps of calculating a threshold adjustment factor according to the abnormal event recovery frequency, the abnormal event duration and the abnormal event fluctuation trend of the historical abnormal event sample, defining a frequency adjustment factor, a continuous adjustment factor and a trend adjustment factor according to the abnormal event recovery frequency, the abnormal event duration and the abnormal event fluctuation trend, and carrying out accumulated calculation according to the frequency adjustment factor, the continuous adjustment factor and the trend adjustment factor to comprehensively obtain the threshold adjustment factor.
One possible way to calculate the frequency adjustment factor is to periodically read historical abnormal event sample data from the database for a predetermined period of time and count the total number of times the abnormal event is recovered during the predetermined period of time. Meanwhile, a reference recovery frequency is preset, and the reference value can be determined according to past long-term stable operation data or industry experience. A frequency adjustment factor is calculated, the frequency adjustment factor being related to the difference between the actual recovery frequency and the reference recovery frequency and being multiplied by an adjustment factor. The value range of the adjusting coefficient is between 0 and 1, and the specific numerical value of the adjusting coefficient can be adjusted according to the sensitivity degree of the system and the actual requirement. For example, if the system is more sensitive to changes in the recovery frequency of an abnormal event, it is desirable that the frequency adjustment factor reflect such changes more significantly, a larger value may be taken, and if the system is relatively stable, the threshold may be taken without too frequent adjustment. The calculation thinking of the frequency adjustment factor is that the difference between the actual recovery frequency and the reference recovery frequency is calculated, then divided by the reference recovery frequency to obtain the relative change rate, and finally the adjustment coefficient is multiplied.
One possible way to calculate the persistence adjustment factor is to record the persistence duration of each historical anomaly event sample as it is read, and calculate an average of these persistence durations. At the same time, a reference duration is set, which can be determined according to the normal operating parameters of the system or the industry specifications. The calculation of the duration adjustment factor is also related to the difference between the actual average duration and the reference duration and is multiplied by an adjustment factor. The adjustment coefficient is also in the range of 0 to 1, and the value depends on the sensitivity of the system to the duration of the abnormal event. If the system is more sensitive to the change of duration, a larger value can be taken, and if not, a smaller value can be taken. The continuous adjustment factor is calculated by calculating the difference between the actual average duration and the reference duration, dividing the difference by the reference duration to obtain the relative change rate, and multiplying the relative change rate by the adjustment coefficient.
One possible way to calculate the trend adjustment factor is to analyze the trend of the abnormal event fluctuation by using a time series analysis method. After the historical abnormal event sample data is read, the change rate of the duration of the abnormal event of the adjacent samples is calculated. The rates of change of all adjacent samples are calculated in turn, and then the average of these rates of change is calculated. The trend adjustment factor is related to this average rate of change and is multiplied by an adjustment factor. The value range of the regulating coefficient is between 0 and 1, and the value depends on the sensitivity of the system to the fluctuation trend of the abnormal event. If the system hopes that the trend adjustment factor will reflect the change in the fluctuating trend more timely, a larger value may be taken, and if the system is relatively stable, less sensitive to trend changes, a smaller value may be taken.
After the frequency adjustment factor, the continuous adjustment factor and the trend adjustment factor are calculated respectively, the three adjustment factors are accumulated to obtain the final threshold adjustment factor. The accurate threshold adjustment factor can enable the main circuit breaker to be more accurate when judging whether to send linkage protection instructions to the branch circuit breaker. If the threshold adjustment factor is not calculated accurately enough, the short-time activation window may be set unreasonably, so that the system may malfunction (linkage instruction is sent when protection is not needed) or miss (linkage instruction is not sent when protection is needed). According to the implementation mode, the threshold adjustment factors are calculated by comprehensively considering a plurality of factors, so that the occurrence of false actions and missed actions can be effectively reduced, and the stability and reliability of the system are enhanced.
In one possible implementation manner, the recovery time window calculation is performed on the abnormal operation monitoring parameter, and step S300 further includes step S310 of constructing an abnormal recovery time prediction model, where the abnormal recovery time prediction model is obtained by performing supervision training on a historical abnormal event sample of the main circuit breaker. Specifically, a large number of historical abnormal event samples of the main circuit breaker are collected, and the samples comprise various abnormal conditions of the main circuit breaker under different working conditions, including but not limited to short circuit faults, overload faults, electric leakage faults and the like. For each abnormal event, information such as the occurrence time, the type of the abnormality, various operation parameters (such as current, voltage, power and the like) when the abnormality occurs, fault handling measures, and final recovery time and the like are recorded in detail.
Because the collected historical data may have problems such as noise, missing values or outliers, preprocessing is required to improve the data quality. Removing noise data by adopting a smoothing filtering method and the like, filling missing values by adopting an interpolation method (such as linear interpolation, mean interpolation and the like) according to the distribution characteristics and the correlation of the data, and identifying and correcting abnormal values by adopting a statistical analysis method (such as a standard deviation-based method). The preprocessed data is more accurate and reliable, and a good data basis is provided for model training.
And selecting a proper machine learning or deep learning algorithm to construct an abnormal recovery time prediction model, and dividing the preprocessed historical abnormal event sample into a training set and a testing set according to a certain proportion (such as 7:3 or 8:2). Based on the training set data, each operation parameter when abnormality occurs is used as an input characteristic, the corresponding recovery time is used as an output label, and the model is supervised and trained. In the training process, parameters of the model are continuously adjusted, so that the model can learn the mapping relation between the input features and the output labels, and the prediction capability of the model on the recovery time is improved. After training, the model is evaluated by using the test set data, and the performance of the model is measured by calculating error indexes (such as mean square error, average absolute error and the like) between the predicted recovery time and the actual recovery time. If the model performance does not meet the requirements, the model structure or parameters may be adjusted, re-trained and evaluated until a satisfactory model is obtained.
Step S320, inputting the abnormal operation monitoring parameter into the abnormal recovery time prediction model, and outputting a predicted recovery time window. Specifically, when the main circuit breaker is in abnormal operation, current abnormal operation monitoring parameters are collected in real time, and the parameters correspond to input characteristics used in model training and comprise operation data such as current, voltage and power. The collected parameters are subjected to necessary pretreatment (such as normalization treatment, so that the data are in the same order of magnitude, and model treatment is convenient), then the collected parameters are input into a trained abnormal recovery time prediction model, and the model rapidly calculates a predicted recovery time window according to the input abnormal operation monitoring parameters by utilizing the mapping relation learned in the training process.
According to the implementation mode, the abnormal recovery time prediction model is constructed through supervision training, and the comprehensive influence of various factors can be considered more accurately, so that the accuracy of recovery time prediction is improved.
In some possible embodiments, the anomaly recovery time prediction model is based on historical anomaly event sample supervision training, but there may be a problem that static models trained by historical samples are difficult to cope with running states of power grid real-time changes, such as load fluctuation caused by distributed energy access, topology adjustment or environmental mutation. When the main circuit breaker detects a novel abnormal mode (such as high-frequency oscillation fault), the model lacks a real-time learning mechanism, and the predicted recovery time window is seriously deviated from an actual value. This may lead to two risks, namely, if the predicted recovery time is too short, the transient fault may be misjudged to delay the linkage protection, the fault range is enlarged, and if the predicted recovery time is too long, the action of the branch circuit breaker may be triggered too early, and unnecessary power failure is caused.
Therefore, as an implementation manner, in order to solve the defect, in this embodiment, an edge training module and a real-time data pipeline are added to the secondary intelligent control layer, and the module is driven by an FPGA chip built in the main circuit breaker. When the main circuit breaker is abnormal, real-time operation parameters acquired by the current sensor and the voltage sensor are synchronously input into an abnormal recovery time prediction model and an edge training module. The edge training module dynamically updates the model weights by comparing the deviation of the predicted recovery time and the actual recovery time. For example, if the actual recovery time is 20% longer than the predicted value, the module automatically triggers the incremental learning algorithm to fine tune the model parameters using the new samples within the sliding time window. Meanwhile, the communication module exchanges model update parameters with the adjacent circuit breakers to form a collaborative learning network. The embodiment ensures that the prediction model has the environment self-adaption capability, solves the problem of failure of the static model in the dynamic power grid, and does not need to change the primary fault structure of the original device.
Further, self-verification is achieved through a closed loop of data between the devices. When the linkage protection instruction is activated, the primary fault action result (such as breaking time and fault isolation state) of the branch circuit breaker is returned to the main circuit breaker through the communication module. And the secondary intelligent control layer carries out cross verification on the result and the output of the prediction model, and if the significant deviation (such as error of 15%) appears continuously for 3 times, the model reconstruction mode is automatically started, namely the latest data of a historical abnormal event sample library is called, and full-quantity retraining is carried out in the edge training module. And after simulation verification, the reconstructed model is switched to an on-line state, so that the prediction precision is ensured to be continuously optimized. According to the technical scheme, the historical experience is fused with real-time learning, so that the scene adaptability of the model is remarkably improved.
Step S400, if the recovery time window is smaller than the short time activation window, the linkage protection instruction is not activated, and if the recovery time window is larger than the short time activation window, the linkage protection instruction is activated.
Specifically, the linkage protection instruction is a control instruction sent to the branch circuit breaker when the main circuit breaker detects an abnormality and determines that the branch circuit breaker needs to be protected in cooperation. The instruction can enable the branch circuit breaker to execute operations such as opening and closing so as to realize the protection function of the power distribution network.
When the linkage protection instruction is judged to be required to be activated, the secondary intelligent control layer generates the linkage protection instruction according to a preset protection strategy. The instruction content comprises an action object (such as a specific branch circuit breaker number) and an action type (such as opening and closing, etc.). For example, an instruction is generated to "branch circuit breaker 001 open", and encoded in accordance with the communication protocol. And transmitting the linkage protection instruction to the corresponding branch circuit breaker through the communication module. During transmission, a data check mechanism (e.g., cyclic redundancy check, CRC) is employed to ensure the accuracy and integrity of the instructions. For example, when the command is transmitted through optical fiber communication, a CRC check code is added at the transmitting end, and the received command is checked at the receiving end, and if a check error is found, retransmission is required. The primary opening layer of the branch circuit breaker realizes opening and closing operation through an electromagnetic mechanism or a spring mechanism according to the received instruction.
In one possible implementation, the method further comprises the steps of setting a first short-time activation window and a second short-time activation window, judging whether the main circuit breaker sends a primary linkage protection instruction to the primary circuit breaker according to the first short-time activation window, and judging whether the primary circuit breaker sends a secondary linkage protection instruction to the secondary circuit breaker according to the second short-time activation window if each circuit breaker comprises a main circuit breaker, at least one primary circuit breaker and at least one secondary circuit breaker.
Specifically, in this scenario, the main circuit breaker is at the uppermost layer, and when a major circuit has serious faults, such as a short circuit, overload, and the like, and the fault current exceeds the setting value of the main circuit breaker, the main circuit breaker needs to rapidly act to cut off the power supply so as to protect the entire power distribution system from being damaged more. The primary branch circuit breaker is responsible for monitoring and managing the electrical parameters of the primary branch where the primary branch circuit breaker is located, and acts in time when the branch is abnormal, so that the fault is prevented from expanding to a main road or other branches. The secondary branch circuit breaker also protects a smaller range of circuits, ensuring safe operation of a single device or small area. For example, in a power distribution system of a large commercial building, a main circuit breaker controls power supply of the whole building, a primary branch circuit breaker controls power supply of different floors respectively, and a secondary branch circuit breaker controls power supply of different merchants or functional areas in each floor.
The first short activation window is a time interval set for coordinated protection between the main circuit breaker and the primary branch circuit breaker. During the operation of the system, the electric parameters of the main circuit breaker and the primary branch circuit breaker, such as current, voltage and the like, are monitored in real time. When the main circuit breaker detects a fault signal (such as an overcurrent signal), a primary linkage protection instruction is not immediately sent to the primary branch circuit breaker, but a first short-time activation window is started first. During this window time, the system continuously monitors the fault condition of the main circuit breaker and the electrical state of the branch circuit where the primary branch circuit breaker is located. If the first short-time activation window is finished, the fault of the main circuit breaker still exists, and the primary circuit breaker is judged to be matched with the power-off power supply according to the preset linkage protection logic so as to prevent the fault from expanding, the main circuit breaker can send a primary linkage protection instruction to the primary circuit breaker, and the primary circuit breaker rapidly acts after receiving the instruction to cut off the power supply of the branch circuit where the primary circuit breaker is positioned.
The second short-time activation window is a time interval for linkage protection between the primary branch circuit breaker and the secondary branch circuit breaker. When the primary branch circuit breaker detects a fault signal or receives a primary linkage protection instruction sent by the main circuit breaker, the secondary linkage protection instruction is not immediately sent to the secondary branch circuit breaker, and a second short-time activation window is started. And in the window time, the system monitors the fault condition of the primary branch circuit breaker and the electrical state of the branch circuit where the secondary branch circuit breaker is positioned. If the second short-time activation window is finished, the second-stage branch circuit breaker is judged to be required to act according to preset logic to further isolate faults, the first-stage branch circuit breaker sends a second-stage linkage protection instruction to the second-stage branch circuit breaker, and the second-stage branch circuit breaker executes power-off operation.
The clear division of upper and lower circuit breaker groups and the accurate judgment of linkage protection instructions in the implementation mode enable faults to be rapidly located and isolated within a minimum range. The accurate fault isolation mode can effectively reduce the power failure range, improve the power supply reliability of the power system and ensure the power consumption requirement of important users.
In a possible implementation manner, the method further comprises the steps that the first short-time activation window is determined through self-adaptive analysis on historical abnormal event samples of the main circuit breaker, the second short-time activation window is determined through self-adaptive analysis on historical abnormal event samples of the primary branch circuit breaker, and the multi-level linkage protection instructions formed by the primary linkage protection instructions and the secondary linkage protection instructions are sequentially sent according to a hierarchical sequence.
Specifically, the first short-time activation window and the second short-time activation window are consistent with the principle of determining the short-time activation window through the foregoing adaptive analysis, and will not be described herein. The multi-stage linkage protection instruction consists of a primary linkage protection instruction and a secondary linkage protection instruction, and the primary linkage protection instruction and the secondary linkage protection instruction are sequentially sent according to a hierarchical order. That is, after the main circuit breaker detects the fault signal, a first short-time activation window is started, within which the fault condition is continuously monitored. If the fault still exists and meets the primary linkage protection condition when the window is finished, the main circuit breaker sends a primary linkage protection instruction to the primary branch circuit breaker. After receiving the instruction, the primary branch circuit breaker does not immediately send the instruction to the secondary branch circuit breaker, but starts a second short-time activation window, and further judges the fault condition in the monitoring range of the primary branch circuit breaker. Only when the second short-time activation window is finished and the second-stage branch circuit breaker is determined to be required to act according to preset logic, the first-stage branch circuit breaker sends a second-stage linkage protection instruction to the second-stage branch circuit breaker. The mode of sequentially sending the instructions in the hierarchical sequence ensures that all levels of circuit breakers can participate in fault protection according to reasonable sequence and time, avoids confusion and conflict of the instructions, ensures that faults are gradually isolated according to a preset strategy, controls the influence range to be minimum, improves the stability and reliability of the whole power distribution system, and reduces the power failure time and range.
The embodiment of the application adopts the technical means of acquiring a plurality of circuit breaker devices, identifying branch relationships among the circuit breaker devices and grouping the circuit breaker devices, wherein each group comprises a main circuit breaker and a plurality of branch circuit breakers, setting a short-time activation window time, extracting abnormal operation parameters and calculating a time window required for recovering the main circuit breaker when detecting the occurrence of the abnormality of the main circuit breaker, comparing the recovery time with a preset short-time activation window, if the recovery time is shorter than the activation window, the system does not trigger linkage protection and keeps running continuously, and if the recovery time is longer than the activation window, immediately sending linkage protection instructions to the branch circuit breakers, synchronously disconnecting the main circuit and the branch circuit breakers and the like, thereby solving the technical problems of poor protection precision and economy existing in the protection setting of the circuit breakers on a secondary fusion column in the prior art and achieving the technical effect of improving the precision and economy of power grid protection.
In the above, the adaptive protection setting method for a secondary fused on-pole circuit breaker according to the embodiment of the present invention is described in detail with reference to fig. 1. Next, an adaptive protection tuning system for a secondary fused on-pole circuit breaker according to an embodiment of the present invention will be described with reference to fig. 2.
The self-adaptive protection setting system for the secondary fusion on-column circuit breaker is used for solving the technical problem that the protection setting of the existing secondary fusion on-column circuit breaker is poor in protection accuracy and economy, and achieves the technical effect of improving the power grid protection accuracy and economy. The self-adaptive protection setting system for the secondary fusion on-pole circuit breaker comprises an on-pole circuit breaker acquisition module 10, a circuit breaker group identification module 20, a recovery time window calculation module 30 and a protection instruction sending judgment module 40.
The circuit breaker on-column acquisition module 10 is used for acquiring a plurality of secondary fusion on-column circuit breakers, the circuit breaker group identification module 20 is used for identifying the branch circuit relationships of the plurality of secondary fusion on-column circuit breakers, determining circuit breaker groups comprising upper and lower relationships, each circuit breaker group comprises a main circuit breaker and at least one branch circuit breaker, the recovery time window calculation module 30 is used for setting a short-time activation window, extracting abnormal operation monitoring parameters of the main circuit breaker, carrying out recovery time window calculation on the abnormal operation monitoring parameters, judging whether to send linkage protection instructions to the branch circuit breakers by comparing the recovery time window with the short-time activation window, and the protection instruction sending judgment module 40 is used for activating the linkage protection instructions if the recovery time window is smaller than the short-time activation window and if the recovery time window is larger than the short-time activation window.
Next, the specific configuration of the on-pole breaker acquisition module 10 will be described in detail. As described above, the on-column breaker acquisition module 10 may further include that each of the plurality of secondary fused on-column breakers includes a primary open layer for performing open protection of the branch breaker according to the activated linkage protection instruction and a secondary intelligent control layer for performing abnormal operation monitoring and reception or transmission of the linkage protection instruction.
Next, the specific configuration of the recovery time window calculation module 30 will be described in detail. As described above, the recovery time window calculation module 30 may further include setting a short-time activation window, where the short-time activation window is determined by adaptively analyzing a historical abnormal event sample of the main circuit breaker, where the historical abnormal event sample includes an abnormal event operation monitoring parameter sample, an abnormal event recovery frequency, an abnormal event duration, and an abnormal event fluctuation trend of the main circuit breaker.
The short-time activation window is determined by adaptively analyzing a historical abnormal event sample of the main circuit breaker, the recovery time window calculation module 30 may further include an effective recovery event sample screening unit for screening an effective recovery event sample of the historical abnormal event sample, wherein the effective recovery event sample is an abnormal event marked as normal recovery, a recovery time distribution extraction unit for extracting a recovery time distribution of the effective recovery event sample, analyzing the recovery time distribution to obtain a basic activation threshold, a threshold adjustment factor calculation unit for calculating a threshold adjustment factor according to an abnormal event recovery frequency, an abnormal event duration and an abnormal event fluctuation trend of the historical abnormal event sample, and an update unit for updating the basic activation threshold according to the threshold adjustment factor to obtain the adaptive short-time activation window of the main circuit breaker.
The recovery time distribution extraction unit may further include a density cluster analysis subunit configured to perform density cluster analysis according to the recovery time distribution to obtain a plurality of cluster results, and the base activation threshold determination subunit is configured to extract a first cluster result according to a density value of each cluster result, and use a quantile value of the first cluster result as a base activation threshold.
The threshold adjustment factor calculating unit may further include an adjustment factor defining subunit configured to define a frequency adjustment factor, a continuous adjustment factor, and a trend adjustment factor according to the abnormal event recovery frequency, the abnormal event duration, and the abnormal event fluctuation trend of the historical abnormal event sample, and an accumulation calculating subunit configured to perform accumulation calculation according to the frequency adjustment factor, the continuous adjustment factor, and the trend adjustment factor, and obtain the threshold adjustment factor in a comprehensive manner.
If each breaker group comprises a main circuit breaker, at least one primary branch circuit breaker and at least one secondary branch circuit breaker, a first short-time activation window and a second short-time activation window are set, whether the main circuit breaker sends a primary linkage protection instruction to the primary branch circuit breaker is judged according to the first short-time activation window, and whether the primary branch circuit breaker sends a secondary linkage protection instruction to the secondary branch circuit breaker is judged according to the second short-time activation window.
The system can further comprise the steps that the first short-time activation window is determined through self-adaptive analysis of historical abnormal event samples of the main circuit breaker, the second short-time activation window is determined through self-adaptive analysis of historical abnormal event samples of the primary branch circuit breaker, and the multi-level linkage protection instructions composed of the primary linkage protection instructions and the secondary linkage protection instructions are sequentially sent according to a hierarchical sequence.
The recovery time window calculation module 30 may further include an abnormal recovery time prediction model construction unit configured to construct an abnormal recovery time prediction model, where the abnormal recovery time prediction model is obtained by performing supervised training on a historical abnormal event sample of the main circuit breaker, and the abnormal recovery time prediction unit is configured to input the abnormal operation monitoring parameter into the abnormal recovery time prediction model and output a predicted recovery time window.
The self-adaptive protection setting system for the secondary fusion on-column circuit breaker provided by the embodiment of the invention can execute the self-adaptive protection setting method for the secondary fusion on-column circuit breaker provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Although the present application makes various references to certain modules in a system according to an embodiment of the present application, any number of different modules may be used and run on a user terminal and/or a server, and each unit and module included are merely divided according to functional logic, but are not limited to the above-described division, so long as the corresponding functions can be implemented, and in addition, specific names of each functional unit are only for convenience of distinguishing from each other, and are not intended to limit the scope of protection of the present application.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application. In some cases, the acts or steps recited in the present application may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511158796.8A CN120657673B (en) | 2025-08-19 | 2025-08-19 | Self-adaptive protection setting method and system for secondary fusion on-column circuit breaker |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202511158796.8A CN120657673B (en) | 2025-08-19 | 2025-08-19 | Self-adaptive protection setting method and system for secondary fusion on-column circuit breaker |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120657673A CN120657673A (en) | 2025-09-16 |
| CN120657673B true CN120657673B (en) | 2025-10-14 |
Family
ID=96999922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202511158796.8A Active CN120657673B (en) | 2025-08-19 | 2025-08-19 | Self-adaptive protection setting method and system for secondary fusion on-column circuit breaker |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120657673B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120831927B (en) * | 2025-09-18 | 2025-11-18 | 石家庄西屋电气设备有限公司 | Low-delay control method and system for secondary fusion on-column circuit breaker |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2408080A2 (en) * | 2010-07-16 | 2012-01-18 | General Electric Company | Protection system having reduced energy let-through mode and zone selectivity |
| CN106688155A (en) * | 2014-09-04 | 2017-05-17 | 伊顿公司 | System and method for switching an electrical system to backup power during a utility power outage |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111130058A (en) * | 2020-01-17 | 2020-05-08 | 中国电力科学研究院有限公司 | Method and device for breaking large short-circuit current of power system by using graded operation |
| CN119340933A (en) * | 2024-10-30 | 2025-01-21 | 常熟开关制造有限公司(原常熟开关厂） | A power distribution protection device |
| CN119834182A (en) * | 2025-01-17 | 2025-04-15 | 深圳职业技术大学 | Power supply and distribution system based on upper-level circuit breaker actively indicating action of lower-level circuit breaker |
-
2025
- 2025-08-19 CN CN202511158796.8A patent/CN120657673B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2408080A2 (en) * | 2010-07-16 | 2012-01-18 | General Electric Company | Protection system having reduced energy let-through mode and zone selectivity |
| CN106688155A (en) * | 2014-09-04 | 2017-05-17 | 伊顿公司 | System and method for switching an electrical system to backup power during a utility power outage |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120657673A (en) | 2025-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118884129B (en) | Power distribution network fault positioning method based on artificial intelligence and storage medium | |
| CN120657673B (en) | Self-adaptive protection setting method and system for secondary fusion on-column circuit breaker | |
| CN119667370A (en) | Real-time fault detection and automatic repair system for power grid | |
| CN120524842B (en) | Power flow calculation and simulation control method and system for digital twin power grid | |
| CN119165297B (en) | Fault judgment method of oilfield distribution network based on line voltage amplitude variation | |
| CN120454323B (en) | Railway traction substation status monitoring method, system, equipment, and medium | |
| CN118508381A (en) | Comprehensive relay protection and management system based on intelligent algorithm | |
| CN114781476A (en) | Fault analysis system and method for measuring equipment | |
| CN119651611A (en) | A method and system for intelligent switching between bypass shelter and main power line | |
| CN120011715A (en) | Distribution system fault prediction system and prediction method based on big data analysis | |
| CN120873372B (en) | Current transformer error dynamic monitoring method and system | |
| Campos et al. | ML-assistant for human operators using alarm data to solve and classify faults in electrical grids | |
| CN119168170B (en) | Method and system for generating typical operation ticket of substation | |
| CN120498133A (en) | Remote monitoring and fault early warning method for substation power system based on Internet of things | |
| CN120745417A (en) | Data processing method and system for monitoring state of explosion-proof equipment | |
| CN120414911A (en) | Abnormal current warning method for distribution cabinet based on big data | |
| CN116593883B (en) | A method, device, equipment, and storage medium for fault diagnosis of the circuit breaker body of an intelligent high-voltage switch. | |
| CN120630093B (en) | Electric energy meter precision degradation evaluation system and equipment based on sampling unit fault characteristics | |
| CN120511860B (en) | Direct current screen switching method and system based on reinforcement learning | |
| CN120338088B (en) | Method and system for constructing automatic generation rule base of equipment safety measures | |
| CN118971381B (en) | Method and device for sensing power grid situation and managing faults based on generated AI | |
| CN120123899A (en) | A high-risk circuit fault identification method, system, medium, device and program | |
| CN121440900A (en) | Transformer substation tripping and closing loop and pressing plate state sensing and visualizing method, system, equipment and medium | |
| CN121097955A (en) | High-low voltage power distribution cabinet operation monitoring management method based on big data analysis | |
| Napier et al. | An automated fault analysis system for SP energy networks: Requirements, design and implementation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |