A station area protection method based on comprehensive multiple judgment of fault discriminator

Abstract

The present invention provides a station-domain protection method based on comprehensive multiple determinations by a fault discriminator. The method includes determining a collaborative protection domain, which includes multiple protection domains, each of which is configured with at least one fault discriminator. When a fault discriminator determines that a fault has occurred in its protection domain, a first fault discriminator and a second fault discriminator are determined. Based on the fault determination results of the first fault discriminator and the second fault discriminator, a collaborative determination is made as to whether the fault occurred by the first fault discriminator is a misjudgment. When the fault occurred by the first fault discriminator is not a misjudgment, the method collaboratively determines the fault type and location of the fault occurred by the first fault discriminator based on the fault information determined by the first fault discriminator and the fault information determined by the second fault discriminator. The method also performs fault isolation on the fault type. Faster and more accurate fault location through collaborative determination can accelerate backup protection action and improve the overall protection performance of the substation.

Description

Technical Field

[0001] The present invention relates to the field of protection technology of intelligent substations, and in particular to a station-area protection method based on comprehensive multiple determinations of a fault discriminator. Background Art

[0002] With the integration of new energy sources and the emergence of increasingly complex power grid structures, traditional power system relay protection faces limited interactive information, increasingly difficult configuration and setting of protection devices, and may find it difficult to adapt to rapidly changing network conditions.

[0003] As the amount of network data in power systems increases, the response time required becomes faster and faster. Traditional relay protection methods are unable to quickly and conveniently achieve protection goals. The network topology of each line makes it difficult to control the overall situation, generating a large amount of normal and fault data, and the massive data is difficult to distinguish and process.

[0004] Currently, some studies have applied artificial intelligence algorithms to fault identification of components such as transformers and busbars, but most still require the auxiliary setting of additional starting criteria. Artificial intelligence algorithms cannot automatically identify the entire fault process. In addition, most studies have not constructed protection schemes from the perspective of the "four properties" of protection, and it is difficult to adapt well to the complexity and dynamics of the power system. Summary of the Invention

[0005] The purpose of this application is to propose a station protection method based on comprehensive multiple judgments of a fault discriminator, which can independently complete fault identification and positioning without starting judgment criteria, thereby improving the overall performance of the system.

[0006] In a first aspect, an embodiment of the present application provides a site domain protection method for collaborative identification, including:

[0007] Determine a collaborative protection domain, where the collaborative protection domain includes multiple protection domains, and each of the multiple protection domains is configured with at least one fault discriminator;

[0008] In the case where the fault discriminator discriminates that a fault occurs in its protection domain, determining the fault discriminator as a first fault discriminator, and determining the fault discriminator corresponding to at least another protection domain in the collaborative protection domain as a second fault discriminator;

[0009] collaboratively determining whether a fault occurring in the protection domain corresponding to the first fault determinator is a misjudgment based on a fault determination result of the first fault determinator on its protection domain and a fault determination result of the second fault determinator on its protection domain;

[0010] The preliminary judgment result of the fault judgment module of the collaborative protection domain is recorded as 0 and 1 according to no fault and fault respectively, that is, the normal operation state is recorded as 0, and both the internal and external faults are recorded as 1;

[0011] During operation, if the judgment result of one of the fault discriminators in the collaborative protection domain changes from 0 to 1, while the result of another fault discriminator in the collaborative protection zone remains 0, then after waiting for the first fault discriminator to have passed a preset time, the two fault discriminators will continuously output the preliminary judgment results for a quarter of a cycle again. If the results continuously output by the two fault discriminators for a quarter of a cycle are inconsistent, it is considered that the first fault discriminator has made a wrong judgment;

[0012] After the first fault discriminator initially determines that a fault has occurred in its protection domain and a preset discrimination time has elapsed, based on the fault discrimination result of the first fault discriminator on its protection domain and the fault discrimination result of the second fault discriminator on its collaborative protection domain, collaboratively determining whether the fault occurring in the protection domain corresponding to the first fault discriminator is a misjudgment;

[0013] If the two fault discriminators output the same results for a quarter of a cycle, it is considered that a fault has indeed occurred within the collaborative protection domain. The fault discriminators then perform a collaborative discrimination operation. Instead of outputting 0 and 1, they now sequentially classify the twenty types of faults both inside and outside the domain, outputting results corresponding to 1 to 20. Each fault output corresponds to a corresponding result, which is then collaboratively discriminated by the two fault discriminators to determine the fault type and location. Fault isolation is then performed within the collaborative protection domain based on the fault type and location of the fault in the protection domain corresponding to the first fault discriminator.

[0014] Secondly, the present application proposes a fault discriminator trained with an artificial intelligence model. The fault discriminator is first trained using a data training set, and then configured using a transfer learning method. According to the different deep learning models configured according to the bus, line and transformer, the fault discriminator can adapt to various changing power grid operation scenarios; according to the configuration of the fault discriminator, the fault discriminator can eventually identify the fault types of single-phase ground short circuit, two-phase short circuit, two-phase ground short circuit, and three-phase ground short circuit.

[0015] In a third aspect, the present application proposes a method for optimizing the preset judgment time setting of a fault discriminator, characterized in that the preset judgment time of the fault discriminator is set after three eighths of a cycle to prevent misjudgment caused by frequent disturbances and bad data points in the first quarter of a cycle, while the quarter to three eighths of a cycle provide a margin for the judgment time. In addition, when the fault occurring in the protection domain corresponding to the first fault discriminator is not misjudged and after the preset judgment time, the fault information judged by the first fault discriminator and the fault information of any fault discriminator in the collaborative protection domain other than the first fault discriminator are again collaboratively judged to determine that the fault occurring in the protection domain corresponding to the first fault discriminator is not misjudged, the preset judgment time is reduced, and the adjusted preset judgment time is greater than or equal to one eighth of a cycle, thereby accelerating the exit from the judgment state.

[0016] The station-domain protection scheme proposed in this application can locate faults more quickly and accurately through collaborative protection, and when the main protection refuses to operate, it can accelerate the backup protection action, thereby improving the overall protection performance of the substation; in addition, it is also proposed to configure the artificial intelligence model through transfer learning. This method can realize fast, small-sample deep learning model training, and realize a station-domain protection method for fault identification and positioning. This method is an artificial intelligence model that does not require startup criteria, can independently complete the fault identification process and meet the relay protection scheme of the "four properties" requirements of protection. It is specifically used for on-site protection of transformers and busbars, as well as station-domain protection of smart substations, thereby improving the reliability of the system; in addition, this application proposes a method for setting the preset identification time of the optimized fault discriminator, which improves the accuracy of the data and accelerates the fault identification speed.

[0017] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory and do not limit the disclosure of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0019] Figure 1 This is a flowchart of a multi-determination station domain protection method provided in an embodiment of the application;

[0020] Figure 2 This is a schematic diagram of the station protection zoning of a 220kV substation;

[0021] Figure 3 It is a schematic diagram of the research case model of the busbar;

[0022] Figure 4 It is a schematic diagram of the changes in the indicator parameters of each model during the training process;

[0023] Figure 5 It is a schematic diagram of the discrimination performance of each model for faults under CT saturation;

[0024] Figure 6 It is a schematic diagram of the changes in the indicator parameters of each model during the training process;

[0025] Figure 7 This is a schematic diagram of the accuracy of the transfer learning model in distinguishing between faults within and outside the busbar area;

[0026] Figure 8 It is a schematic diagram of the changes in the indicator parameters of each model during the training process;

[0027] Figure 9 It is a schematic diagram of the discrimination results of the model in the collaborative protection areas A1, A2 and A3;

[0028] Figure 10 It is a schematic diagram of the discrimination accuracy of the model in the collaborative protection areas A1, A2 and A3;

[0029] Figure 11 It is a schematic diagram of the discrimination results of the model in the collaborative protection areas A1 and B1;

[0030] Figure 12 It is a schematic diagram of the discrimination accuracy of the model in the collaborative protection areas A1 and B1;

[0031] Figure 13 It is a schematic diagram of the online discrimination results of the model in the collaborative protection zone B1;

[0032] Figure 14 It is a schematic diagram of the online discrimination accuracy of the model in the collaborative protection area B1. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0034] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0035] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0036] See also Figure 1 , Figure 1 This is a flowchart of a multiple determination site domain protection method provided by an embodiment of the present application. The determination method includes the following steps:

[0037] Step S110: determining a coordinated protection domain, wherein the coordinated protection domain includes multiple protection domains. The protection domains are mainly divided into busbar protection domain, transformer protection domain and line protection domain according to protection objects.

[0038] For example, see Figure 2 The station-domain protection zoning scheme for a 220kV substation is demonstrated, with detailed information for each protection domain shown in Table 1. The station-domain protection area is divided based on the controllable circuit breakers, ensuring that each circuit breaker is included in at least one protection domain, and each protection domain contains two single-element protection domains for electrical components or lines. Based on the type of protected object, the coordinated protection domains of the station-domain protection are divided into busbar-transformer coordinated protection domains and busbar-line coordinated protection zones.

[0039]

[0040]

[0041] Table 1

[0042] Step S120: Configure at least one fault discriminator for each protection domain, and train each fault discriminator using an artificial intelligence model. Using the training strategy employed in this application and optimizing it with a transfer learning algorithm enables the SECapsNet model to perform online discrimination of transformer faults and magnetizing inrush currents without requiring additional startup criteria.

[0043] For example, for Figure 3 The busbar shown in the figure is analyzed, with the busbar flow direction as the positive direction. First, the three-phase current signals, current fault components, busbar voltage signals and voltage fault components of all branches connected to the busbar are selected as the basic electrical characteristics. The current of any line connected to the busbar is selected as i sI The sum of the currents in the remaining circuits is i sII, the currents flowing through lines L1, L2, L3 and L4 are i1, i2, i3 and i4 respectively, take i sI =i1, then i sII =i2+i3+i4. When the busbar is operating normally or an out-of-area fault occurs, i sI and i sII are equal in magnitude and 180° in phase; when a busbar fault occurs within the area, i sI and i sII The phase difference is 0°.

[0044] For the busbar, when a fault occurs outside the zone, the CT at the branch end where the fault point is located may face serious saturation problems. For example, when a fault occurs in line L2, the current flowing from the busbar to the other branches will all flow to the fault point. At this time, the current i2 flowing through line L2 will increase rapidly, and the CT of line L2 will face saturation problems. Therefore, i sI and i sII The fault characteristics are retained by the current polarity ratio characteristic quantity composed of the phase A current. sIa 、i sIIa I sI 、i sII Phase A current.

[0045] (1) The polarity ratio of the sum of the currents on both sides of the busbar, phase A, p a The calculation formula is as follows:

[0046]

[0047] (2) The difference dp between the polarity ratio of the sum of the currents on both sides of the busbar and the phase A a , is the current moment p a Subtract p corresponding to the fault-free time a .

[0048] (3) The polarity ratio of the current on both sides of the busbar and the phase A and p sa , is the sum of the current moment and the historical moment p, and the formula is as follows:

[0049]

[0050] Using busbar three-phase voltage and three-phase voltage fault components, all branches three-phase current signals and three-phase current fault components, i sI with i sII The three-phase current polarity ratio p, the three-phase current polarity ratio difference dp and the three-phase current polarity ratio and p s , combined to form the data feature model of the bus, the time window lengths are 1 / 4 cycle and 1 / 2 cycle respectively.

[0051] Model 1: busbar three-phase voltage signal, three-phase current signals of all branches connected to the busbar, and the summed three-phase current signal i of all branches x A combination of, where each phase i x is the sum of all branch currents of the corresponding phase. The model includes u a -u b -u c -i 1a -i 1b -i 1c -i 2a -i 2b -i 2c -i 3a -i 3b -i 3c -i 4a -i 4b -i 4c -i xa -i xb -i xc .

[0052] Model 2: busbar three-phase voltage fault component, combination of three-phase current fault components of all branches connected to the busbar, and fault component di of the sum of the three-phase currents of all branches x Combinations of a -du b -du c -di 1a -di 1b -di 1c

[0053] -di 2a -di 2b -di 2c -di 3a -di 3b -di 3c -di 4a -di 4b -di 4c -di xa -di xb -di xc .

[0054] Model 3: Based on Model 2, the current i is increased sI with i sII The three-phase current polarity ratio p combination includes:

[0055] p a -p b -p c .

[0056] Model 4: Based on Model 2, the current i is increased sI with isII The three-phase current polarity ratio difference dp combination, including dp a -dp b -dp c .

[0057] Model 5: Based on Model 2, the current i is increased sI with i sII The three-phase current polarity ratio and p s Combination, including p sa -p sb -p sc .

[0058] Exemplarily, the fault discriminator is firstly trained by deep learning using a data training set to establish a fault discriminator capable of realizing busbar fault discrimination.

[0059] See Table 2 for the SECapsNet model parameters used for busbar fault identification, and Table 3 for the SECapsNet model training parameters. This example uses a capsule neural network model to extract features from electrical quantities and stack them into slices for training. SECapsNet is used to classify busbar faults. Busbar states can be categorized into three categories: normal operation, out-of-zone faults, and in-zone faults. Out-of-zone faults and in-zone faults each include 10 fault types, resulting in a total of 21 busbar states.

[0060] Furthermore, due to the large number of lines connected to the bus, the number of signals required to fuse the bus data feature model also increases. Therefore, a 5×5 convolution kernel replaces the original 3×3 convolution kernel in the convolution layer C2 and the main capsule layer. At the same time, the output of the digital capsule layer becomes 21×16, corresponding to the 20 fault types and 1 non-fault type of the bus.

[0061]

[0062] Table 2

[0063]

[0064] Table 3

[0065] This application is for Figure 3The busbar simulation case shown in the figure is studied. The specific system parameters are: source G1 = 330∠25°, source G2 = 330∠0°, source G3 = 330∠10°, and source G4 = 330∠5°. Line L1 is 10 km long, line L2 is 45 km long, line L3 is 50 km long, and line L4 is 15 km long. The line parameters are R1 = 0.027 Ω / km, X1 = 0.282 Ω / km, R0 = 0.195 Ω / km, and X0 = 0.693 Ω / km. The pre-fault power angle is the difference between the phase angles of sources G1 and G2 and is adjusted by changing the phase angle of source G1. S1 to S4 are protection units, and the fault distance is the distance from the fault point to the protection unit on the faulty line.

[0066] Simulation samples with various fault parameters were collected from protection units S1–S4. Each fault sample contained data for one cycle before and after the fault. The specific simulation parameters for the training and test sets are shown in Tables 4 and 5. The faults within the bus and the faults outside the bus on lines L1–L4 included single-phase ground faults, two-phase ground faults, two-phase ground faults, and three-phase ground faults, for a total of 10 fault types. Furthermore, the samples included cases where CT saturation occurred due to both internal and external bus faults. The CT saturation samples included all 10 internal and external fault types, with the number of samples being two-fifths of the number of non-saturated samples. The samples were preprocessed using a data feature model and randomly selected in a ratio of 7:2:1 to form the training, validation, and test subsets of the training set.

[0067]

[0068] Table 4

[0069]

[0070] Table 5

[0071] After data preprocessing using data feature models 1 to 5, the accuracy and loss changes of the trained SECapsNet models BM1 to BM5 during the training process are as follows: Figure 4 As shown in the figure, the accuracy of models BM1 to BM5 increases with the number of iterations, while the loss value gradually decreases. The accuracy of models BM1 to BM5 on the test subset of the training set is above 99%.

[0072] Internal and external faults are accompanied by CT saturation. Based on the bus test set, it is set that after an external fault occurs, the CT at the branch end where the fault point is located reaches a saturated state. For internal bus faults, the CT at the S1 side is set to be saturated. Figure 5The test results for models BM2 through BM5 are shown. When using saturated training samples, the duration of the fuzzy region for models BM2 through BM5 does not exceed the length of the used time window. However, within the stable region, only models BM4 and BM5 maintain 100% accuracy, while models BM2 and BM3 risk misjudgment.

[0073] When saturated training samples are not used, the accuracy of models BM2 through BM5 shows a trend of first decreasing, then increasing, then decreasing again, and then increasing again after a fault. The region corresponding to the time window after the fault is selected as the stable region, and the average accuracy of each model's stable region is calculated. Model BM5 has the highest average accuracy in the stable region, but at only 95%, there is still a significant risk of false tripping. Therefore, a small amount of CT saturation samples should be included in training to assist in the process.

[0074] For example, a model-based transfer learning method is used to achieve fast, small-sample SECapsNet model optimization to improve the robustness and versatility of the model, so that it can achieve accurate fault identification in new scenarios.

[0075] The SECapsNet models obtained through transfer learning using training sets TB1 to TB3 are denoted as models TBM1 to TBM3 respectively. The accuracy and loss changes of each model during the training process are shown in the following table. Figure 6 shown.

[0076] After 20 cycles of iteration, the training accuracy of each model increased rapidly, and the loss value continued to decrease. During training, the time required for each model to complete a training round was recorded. The specific data is as follows: model TBM1 took 27 seconds, model TBM2 took 76 seconds, model TBM3 took 133 seconds, and the pre-trained model BM5 took 181 seconds. As the number of training set samples doubled, the training time also showed a trend of increasing exponentially, once again confirming the significant advantages of transfer learning methods in saving time and data costs. During the testing phase, the time required for each model to test a single sample was recorded. The test times for models TBM1, TBM2, TBM3, and BM5 were 105us, 107us, 107us, and 104us, respectively, with minimal differences in test time between the models.

[0077] Next, the performance of models TBM1 to TBM3 was tested. Ten types of external faults were set on lines L1 to L4, and ten types of internal faults were set on the busbar. Test samples of CT saturation and single-phase high-resistance grounding faults caused by internal and external faults were simulated. The test results are shown in the figure below. Figure 7 shown.

[0078] exist Figure 7Among them, model TBM3, which uses the most training samples, performs best under various test conditions. Its fuzzy zone duration is the shortest among the three, and its accuracy remains at 100% in the stable zone. Model TBM1, which uses the fewest training samples, although its fuzzy zone duration is similar to model TBM3, fluctuates in accuracy in the stable zone, resulting in poor overall performance. Model TBM2 is not much different from model TBM3 in terms of fuzzy zone duration and maintains 100% accuracy in the stable zone. Considering that the training time and number of samples required for model TBM2 and model TBM3 are twice as different, model TBM2 is the best choice to strike a balance between training cost and model performance.

[0079] The SECapsNet models obtained through transfer learning using training sets TB4 and TB5 are denoted as models TBM4 and TBM5 respectively. The accuracy and loss changes of each model during the training process are shown in the following table. Figure 8 As shown in the figure, after 20 iterations, the training accuracy of each model increased rapidly, and the loss continued to decrease. Models TBM4 and TBM5 required 76 seconds and 78 seconds, respectively, to complete a training epoch, with no significant difference in training time between the two models. During testing, the time required for the two models to test a single sample was essentially the same, 103 and 105 microseconds, respectively.

[0080] Next, models TBM4 and TBM5 were tested. Ten in-zone faults were set on bus B2, and ten out-of-zone faults were set on line L5 and power source G6. Test samples of fault-induced CT saturation and single-phase high-resistance grounding faults were simulated. The performance of models TBM4 and TBM5 on the test set was statistically analyzed according to three performance zones. The test results are shown in Table 6.

[0081]

[0082] Table 6

[0083] Depend on Figure 8 It can be seen that the performance of model TBM4 is significantly better than that of model TBM5. The effect of using zero padding to complete missing data is much better than using the same-side current data to complete the missing data. Model TBM4 maintains 100% accuracy in the stable area, and the maximum duration of the fuzzy area does not exceed 1 / 4 cycle. After transfer learning, it shows good performance in the new target domain.

[0084] By using training sets of varying sizes for transfer learning, we verified that using a training set that is one-quarter the size of the original dataset effectively balances sample size, training time, and model performance. Furthermore, for missing data, zero-padding is more suitable for optimizing the busbar transfer learning model. In simulation case tests, both models TBM2 and TBM5 recovered their accuracy within one-quarter of a cycle after a fault, demonstrating superior performance in this novel scenario.

[0085] Therefore, the safety margin is set to 1 / 8 cycle, and the corresponding set durations for models BM5, TBM2, and TBM5 are all 3 / 8 cycles. Selecting s = 10, integrating the SECapsNet-based bus fault discrimination model, and using a larger data set to train the SECapsNet-based bus fault discrimination model. Next, analyzing the possible operating scenarios of the bus and using transfer learning methods to optimize the SECapsNet model can produce an excellent fault discriminator model.

[0086] Step S130: The fault discriminator performs preliminary discrimination and performs collaborative discrimination verification.

[0087] The collaboratively determining whether a fault occurring in the protection domain corresponding to the first fault determinator is a misjudgment based on the fault determination result of the first fault determinator on its protection domain and the fault determination result of the second fault determinator on its protection domain comprises:

[0088] After the first fault discriminator initially determines that a fault has occurred in its protection domain and after a preset determination time has passed, based on the fault determination result of the first fault discriminator on its protection domain and the fault determination result of the second fault discriminator on its protection domain, it is collaboratively determined whether the fault occurring in the protection domain corresponding to the first fault discriminator is a misjudgment.

[0089] The preliminary judgment result of the fault judgment module of the collaborative protection domain is recorded as 0 and 1 according to no fault and fault respectively, that is, the normal operation state is recorded as 0, and both the internal and external faults are recorded as 1;

[0090] During operation, if the judgment result of one of the fault discriminators in the collaborative protection domain changes from 0 to 1, while the result of the other fault discriminator in the collaborative protection zone is still 0, then after waiting for the first fault discriminator to pass a preset time, the two fault discriminators will re-output the preliminary judgment results of a quarter of a cycle continuously. If the results of a quarter of a cycle continuously output by the two fault discriminators are inconsistent, it is considered that the first fault discriminator has made a misjudgment, and the collaborative judgment verification state is jumped out; if the results of a quarter of a cycle continuously output by the two fault discriminators are consistent, the next collaborative judgment state is entered to confirm the fault location and fault type.

[0091] Step S141: After the collaborative judgment confirms that the fault is misjudged, the fault judgement device exits the collaborative judgment waiting state.

[0092] The first fault discriminator initially discriminates that a fault occurs in its protection domain, and after a preset discrimination time has elapsed, collaboratively discriminating whether the fault occurring in the protection domain corresponding to the first fault discriminator is misjudged based on the fault discrimination result of the first fault discriminator on its protection domain and the fault discrimination result of the second fault discriminator on its collaborative protection domain, includes:

[0093] When the first fault determinator initially determines that a fault has occurred in its protection domain, if the current fault determination result of the second fault determinator on its coordinated protection domain indicates that no fault has occurred in the coordinated protection domain of the second fault determinator, then after a preset determination time has elapsed, obtaining the fault determination result of the first fault determinator on its protection domain and obtaining the fault determination result of the second fault determinator on its coordinated protection domain again;

[0094] If the fault determination result of the first fault determiner obtained again indicates that a fault occurs in its protection domain and the fault determination result of the second fault determiner obtained again indicates that no fault occurs in its collaborative protection domain, it is determined that a fault misjudgment occurs in the protection domain corresponding to the first fault determiner, and the fault determiner exits the collaborative determination waiting state.

[0095] Step S142: After collaborative identification confirms that the fault has occurred correctly, collaborative identification is performed again to confirm the fault location and fault type, and a trip signal is sent to achieve fault isolation.

[0096] The first fault discriminator initially discriminates that a fault occurs in its protection domain, and after a preset discrimination time has elapsed, collaboratively discriminating whether the fault occurring in the protection domain corresponding to the first fault discriminator is misjudged based on the fault discrimination result of the first fault discriminator on its protection domain and the fault discrimination result of the second fault discriminator on its collaborative protection domain, includes:

[0097] When the first fault determinator initially determines that a fault has occurred in its protection domain, if the current fault determination result of the second fault determinator on its coordinated protection domain indicates that no fault has occurred in the coordinated protection domain of the second fault determinator, then after a preset determination time has elapsed, obtaining the fault determination result of the first fault determinator on its protection domain and obtaining the fault determination result of the second fault determinator on its coordinated protection domain again;

[0098] If, during the collaborative determination again, the fault determination result obtained by the first fault determiner indicates that a fault has occurred in its protection domain and the fault determination result obtained by the second fault determiner again indicates that a fault has occurred in its collaborative protection domain, it is determined that the fault occurring in the protection domain corresponding to the first fault determiner is not misjudged.

[0099] After confirming the occurrence of a fault, the fault discriminator performs collaborative discrimination again. The fault discriminator no longer outputs 0 and 1. The fault discriminator now classifies the twenty types of faults inside and outside the zone in sequence, and the output results correspond to 1 to 20 one by one. The corresponding result of each fault output is then collaboratively discriminated by the multiple fault discriminators. At this time, the fault type and location can be determined, and then a trip signal is sent to isolate the fault.

[0100] For example, in response to the problem of long action time of existing backup protection, a specific implementation method of a station domain protection scheme with comprehensive multiple judgments is proposed, and a preset judgment time setting method for optimizing the fault discriminator is used to improve data accuracy and accelerate the fault judgment speed.

[0101] Models such as Figure 2 As shown in Figure 7, fault simulations were performed on the high-voltage, medium-voltage, and low-voltage sides of transformer T1, high-voltage bus Bus1, medium-voltage bus Bus2, and low-voltage bus Bus3, and high-voltage line L1, medium-voltage line L2, and low-voltage line L3. The specific simulation parameter settings are shown in Table 7. The station-area protection method with comprehensive multiple judgments proposed in this chapter was used to test the samples in the test set. The fault judgment process of line L1, bus Bus1, and the high-voltage side of transformer T1 was used as an example to elaborate on the fault collaborative judgment process between the various models.

[0102]

[0103] Table 7

[0104] A phase A ground fault is set on the high voltage side of transformer T1. The judgment results of the models in the coordinated protection zones A1, A2 and A3 are as follows: Figure 9As shown in Figure 1 , the output of the transformer T1 model, 11, corresponds to a phase A ground fault within the zone, while the output of the busbar Bus1, Bus2, and Bus3 models, 1, corresponds to a phase A ground fault outside the zone. At the moment of the fault, the output of the transformer T1 model changes from 0 to 11, and the output of the busbar Bus1, Bus2, and Bus3 models in the busbar-transformer coordinated protection zones A1, A2, and A3 are then detected. The busbar Bus1, Bus2, and Bus3 models determine the fault type after 1, 3, and 2 sampling points after the fault, respectively, and then enter a set waiting time. In the continuous segment interval [94,103], the output of the transformer T1 model is always 11, and the output of the busbar Bus1, Bus2, and Bus3 models is always 1. The judgment results of the four models match each other, and it is determined that the fault occurred on transformer T1 and was a phase A ground fault.

[0105] The test was conducted using 10 fault samples set on the high voltage side of transformer T1. The discrimination accuracy of transformer T1 model, bus Bus1 model, Bus2 model and Bus3 model is as follows: Figure 10 As shown, within 7.5ms after the fault, all four models achieved 100% accuracy, meeting the identification requirement and entering a delayed waiting period. During this waiting period, each model maintained 100% accuracy. Although there are three collaborative protection zones associated with the transformer, and a maximum of four models can participate in collaborative identification, three models actually provide information and functional redundancy. Therefore, the first three models to enter the set time period can be used as the basis for identification, reducing waiting time and the amount of data synchronization.

[0106] Set a phase A ground fault on Bus1. The judgment results of Bus1 model, line L1 model and transformer T1 model are as follows: Figure 11 As shown in the figure, the output result 11 of the busbar Bus1 model corresponds to a phase A ground fault within the zone, while the output results 1 of the line L1 model and the transformer T1 model correspond to a phase A ground fault outside the zone. One sampling moment after the fault occurs, the output of the busbar Bus1 model changes from 0 to 11, identifying the type of fault. The judgment results of the other models within the related busbar-transformer coordinated protection zone A1 and the busbar-line coordinated protection zone Bus1 are then checked. Both the line L1 model and the transformer T1 model are judged as faulty, and all three models enter a waiting state for the set duration [61,90]. Subsequently, in the continuous segment interval [91,100], the output results of the busbar Bus1 model are all 11, and the output results of the line L1 model and the transformer T1 model are all 1. The judgment results of the three models match each other, and it is determined that the fault occurred on busbar Bus1 and was a phase A ground fault.

[0107] Next, we use the 10 fault samples set at bus Bus1 in the test set to conduct the test. The discrimination accuracy of bus Bus1 model, line L1 model and transformer T1 model is as follows: Figure 12 As shown in Figure 3, within 7.5 ms after the fault, the accuracy of the three models all reached 100%, meeting the discrimination requirements.

[0108] Set a phase A ground fault on line L1. The discrimination results of line L1 model and bus Bus1 model are as follows: Figure 13 As shown. The output result 11 of the line L1 model corresponds to a phase A ground fault within the zone, and the output result 1 of the bus1 model corresponds to a phase A ground fault outside the zone. After one sampling moment after the fault occurs, the output result of the line L1 model is 17, which is judged as a fault type. The system enters the set waiting time [61,90] and then checks the judgment result of the bus1 model in the same coordinated protection zone as the line L1 model. After two sampling moments, the bus1 model is judged as a fault type and then enters the set time [62,91]. In the continuous segment [92,101], the judgment results of the line L1 model are all 11, and the judgment results of the bus1 model are all 1. The judgment results of the two models match each other, and it is judged that the fault occurs on line L1 and is a phase A ground fault.

[0109] The test is conducted using 10 fault samples set on line L1 in the test set. The discrimination accuracy of the line L1 and bus Bus1 models in the collaborative protection zone B1 is as follows: Figure 14 When a fault occurs in the L1 line, both the Bus1 model and the L1 line model wait for a set period of time. After the set 3 / 8 cycle period, the identification accuracy of both models reaches 100%, achieving accurate fault identification.

[0110] Table 4h shows the model accuracy and duration of the fuzzy zone for other components or lines that experienced faults. The duration of the fuzzy zone for each model was less than the set duration of 7.5 ms, and all models achieved 100% accuracy in the stable zone. During the delay waiting period, each model maintained 100% accuracy and activated promptly after the delay. Therefore, the proposed integrated multi-determination station-area protection method enables the coordinated coordination of multiple component fault discrimination models, achieving rapid and accurate fault identification and accelerating backup protection operation when the primary protection fails to operate.

[0111]

[0112] Table 8

[0113] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A site protection method based on comprehensive multiple determination of fault discriminators, characterized in that: include: Determine a collaborative protection domain, where the collaborative protection domain includes multiple protection domains, and each of the multiple protection domains is configured with at least one fault discriminator; In the case where the fault discriminator discriminates that a fault occurs in its protection domain, determining the fault discriminator as a first fault discriminator, and determining the fault discriminator corresponding to at least another protection domain in the collaborative protection domain as a second fault discriminator; collaboratively determining whether a fault occurring in the protection domain corresponding to the first fault determinator is a misjudgment based on the fault determination result of the first fault determinator on its protection domain and the fault determination result of the second fault determinator on its collaborative protection domain; After the first fault discriminator initially determines that a fault has occurred in its protection domain and a preset discrimination time has elapsed, based on the fault discrimination result of the first fault discriminator on its protection domain and the fault discrimination result of the second fault discriminator on its collaborative protection domain, collaboratively determining whether the fault occurring in the protection domain corresponding to the first fault discriminator is a misjudgment; After the first fault discriminator initially determines that a fault has occurred in its protection domain and a preset determination time has elapsed, collaboratively determining whether the fault occurring in the protection domain corresponding to the first fault discriminator is a misjudgment based on the fault determination result of the first fault discriminator for its protection domain and the fault determination result of the second fault discriminator for its collaborative protection domain; When the first fault determinator initially determines that a fault has occurred in its protection domain, if the current fault determination result of the second fault determinator on its coordinated protection domain indicates that no fault has occurred in the coordinated protection domain of the second fault determinator, then after a preset determination time has elapsed, obtaining the fault determination result of the first fault determinator on its protection domain and obtaining the fault determination result of the second fault determinator on its coordinated protection domain again; If the fault determination result of the first fault determinator obtained again indicates that a fault has occurred in its protection domain and the fault determination result of the second fault determinator obtained again indicates that a fault has occurred in its collaborative protection domain, it is determined that the fault occurring in the protection domain corresponding to the first fault determinator is not misjudged; If the fault determination result of the first fault determinator obtained again indicates that a fault occurs in its protection domain and the fault determination result of the second fault determinator obtained again indicates that no fault occurs in its collaborative protection domain, determining that a fault misjudgment occurs in the protection domain corresponding to the first fault determinator; If the fault determination result of the first fault determinator obtained again indicates that no fault has occurred in its protection domain and the fault determination result of the second fault determinator obtained again indicates that a fault has occurred in its collaborative protection domain, determining that a fault misjudgment has occurred in the protection domain corresponding to the first fault determinator; When the fault occurring in the protection domain corresponding to the first fault discriminator is not misjudged, collaboratively determining the fault type and location of the fault occurring in the protection domain corresponding to the first fault discriminator based on the fault information discriminated by the first fault discriminator and the fault information discriminated by the second fault discriminator; Fault isolation is performed on the fault type according to the fault type and location of the fault occurring in the protection domain corresponding to the first fault discriminator.

2. The station domain protection method according to claim 1, characterized in that: The protection domains are divided into line protection domains, transformer protection domains, busbar protection domains and circuit breaker protection domains according to the protection objects.

3. The station domain protection method according to claim 1, characterized in that: The fault discriminator is trained using an artificial intelligence model, and the artificial intelligence model is configured according to the line, transformer, busbar and circuit breaker; the fault discriminator can determine the fault types of single-phase ground short circuit, two-phase short circuit, two-phase ground short circuit and three-phase ground short circuit.

4. The station domain protection method according to claim 1, characterized in that: The method further comprises: In the case of a fault misjudgment occurring in the protection domain corresponding to the first fault discriminator, fault isolation is not performed on the fault type and location of the fault occurring in the protection domain corresponding to the first fault discriminator.

5. The station domain protection method according to claim 1, characterized in that: The method further comprises: When the fault occurring in the protection domain corresponding to the first fault discriminator is not misjudged, after a preset judgment time has passed, the fault type and location of the fault occurring in the protection domain corresponding to the first fault discriminator are again determined collaboratively based on the fault information judged by the first fault discriminator and the fault information judged by the second fault discriminator.

6. The station domain protection method according to claim 1, characterized in that: The preset determination time period includes three eighths of a cycle.

7. The station domain protection method according to claim 5, characterized in that: The method further comprises: When the fault occurring in the protection domain corresponding to the first fault discriminator is not misjudged and after the preset judgment time has passed, the fault occurring in the protection domain corresponding to the first fault discriminator is again collaboratively judged based on the fault information judged by the first fault discriminator and the fault information of any fault discriminator other than the first fault discriminator in the collaborative protection domain and is not misjudged, the preset judgment time is reduced, and the adjusted preset judgment time is greater than or equal to one eighth of a cycle, so as to accelerate the exit from the judgment state.

Images